Method for predicting producing area style of tobacco product, and method and device for determining target combination formula

Abstract

The invention relates to a tobacco product producing area style prediction method and a method and device for determining a target combination formula, and relates to the technical field of tobacco production. The method comprises the following steps: acquiring first thermogravimetric analysis data and first chemical component data of each tobacco product raw material in a plurality of tobacco product raw materials of the tobacco product; based on the first thermogravimetric analysis data and the combination formula, determining second thermogravimetric analysis data of the tobacco product, wherein the second thermogravimetric analysis data comprises a plurality of second pyrolysis temperatures and a second mass change rate corresponding to each second pyrolysis temperature in the plurality of second pyrolysis temperatures; based on the first chemical component data and the combination formula, determining second chemical component data of the tobacco product, wherein the second chemical component data comprises the content of each chemical component in multiple chemical components; and based on the second thermogravimetric analysis data and the second chemical component data of the tobacco product, predicting the production place style of the tobacco product by using the trained prediction model. According to the technical scheme, the prediction accuracy of the producing area style of the tobacco product can be improved.

Description

Technical Field

[0001] The present disclosure relates to the technical field of tobacco production, and particularly relates to a method for predicting the origin style of a tobacco product, a method for determining a target combined formula of a tobacco product, an electronic device, a device, a computer-readable storage medium, and a computer program product. Background Art

[0002] A tobacco product is formed by combining various tobacco product raw materials according to a specific combined formula. Taking tobacco product raw materials as tobacco leaves and the tobacco product as cigarettes as an example, different combined formulas of tobacco leaves will result in different flavors and tastes of the formed cigarettes. The origin style is an index characterizing the flavor and taste of cigarettes. As raw materials, tobacco leaves can have a definite origin. Although cigarettes formed by combining tobacco leaves do not have an origin, if their characteristics such as flavor and taste are similar to those of tobacco leaves from a specific origin, their origin style can be said to be that specific origin. For example, a cigarette formed by combining three kinds of tobacco leaves produced in Yunnan, Guizhou, and Hunan may finally have a flavor and taste close to those of Yunnan tobacco leaves under a specific combined formula, and its origin style is determined to be Yunnan.

[0003] Determining the origin style of a tobacco product is an important basis for combined formula design. Due to differences in ecological environment, soil conditions, climate and other factors, different tobacco product raw materials have formed their own unique flavors and tastes. However, after combining different tobacco product raw materials based on the combined formula, the origin style of the finally formed tobacco product may undergo uncertain changes. When conducting combined formula design, it is necessary to judge the origin style of the tobacco product obtained under this combined formula to determine whether this combined formula meets the design requirements. Summary of the Invention

[0004] To solve the above problems, the embodiments of the present disclosure provide the following solutions.

[0005] According to some embodiments of the present disclosure, a method for predicting the origin style of a tobacco product is provided. The tobacco product includes a combination of multiple tobacco product raw materials. The method for predicting the origin style includes: obtaining first thermogravimetric analysis data and first chemical composition data for each tobacco product raw material among the multiple tobacco product raw materials. The first thermogravimetric analysis data includes multiple first pyrolysis temperatures of the pyrolysis process of each tobacco product raw material and a first mass change rate of each tobacco product raw material corresponding to each of the multiple first pyrolysis temperatures. The first chemical composition data includes the content of each chemical component among the multiple chemical components of each tobacco product raw material; determining second thermogravimetric analysis data of the tobacco product based on the first thermogravimetric analysis data and the combination formula of the multiple tobacco product raw materials in the tobacco product. The second thermogravimetric analysis data includes multiple second pyrolysis temperatures and a second mass change rate corresponding to each of the multiple second pyrolysis temperatures; determining second chemical composition data of the tobacco product based on the first chemical composition data and the combination formula. The second chemical composition data includes the content of each chemical component among the multiple chemical components; and predicting the origin style of the tobacco product using a trained prediction model based on the second thermogravimetric analysis data and the second chemical composition data of the tobacco product.

[0006] In some embodiments, the determining the second thermogravimetric analysis data of the tobacco product based on the first thermogravimetric analysis data and the combination formula of the tobacco product includes: taking the mass percentage of each tobacco product raw material in the tobacco product in the combination formula as the weight value of the first thermogravimetric analysis data, and calculating a first weighted sum of the first thermogravimetric analysis data; and determining the first weighted sum as the second thermogravimetric analysis data.

[0007] In some embodiments, the determining the second chemical composition data of the tobacco product based on the first chemical composition data and the combination formula includes: taking the mass percentage of each tobacco product raw material in the tobacco product in the combination formula as the weight value of the first chemical composition data, and calculating a second weighted sum of the first chemical composition data; and determining the second weighted sum as the second chemical composition data.

[0008] In some embodiments, predicting the origin style of the tobacco product by using the trained prediction model based on the second thermogravimetric data and the second chemical composition data of the tobacco product includes: determining characteristic data from the second thermogravimetric analysis data, where the characteristic data includes characteristic temperatures determined from the plurality of second pyrolysis temperatures and mass change rates corresponding to the characteristic temperatures; predicting the origin style of the tobacco product by using the trained prediction model based on at least one parameter among the characteristic temperatures and the mass change rates corresponding to the characteristic temperatures and the second chemical composition data.

[0009] In some embodiments, the plurality of second pyrolysis temperatures form a temperature range, and the mass change rate corresponding to the characteristic temperature includes an extreme value of the second mass change rate within the temperature range.

[0010] In some embodiments, the plurality of second pyrolysis temperatures form adjacent first and second temperature ranges, the mass change rate corresponding to the characteristic temperature includes a median value between a first extreme value of the second mass change rate within the first temperature range and a second extreme value of the second mass change rate within the second temperature range, the characteristic temperature includes a first temperature corresponding to the median value in the second thermogravimetric analysis data, the temperature corresponding to the first extreme value is less than the temperature corresponding to the second extreme value, and the first temperature is greater than the temperature corresponding to the first extreme value and less than the temperature corresponding to the second extreme value.

[0011] In some embodiments, the characteristic temperature includes a second temperature corresponding to the median value in the second thermogravimetric analysis data, and the second temperature is less than the temperature corresponding to the first extreme value or greater than the temperature corresponding to the second extreme value.

[0012] In some embodiments, the characteristic temperature includes a starting temperature or an ending temperature among the plurality of second pyrolysis temperatures.

[0013] In some embodiments, the first chemical composition data includes a ratio of the contents of different chemical components among the plurality of chemical components of each tobacco product raw material, and the second chemical composition data further includes a comprehensive ratio determined based on the ratio and the mass proportion of each tobacco product raw material in the combination formula in the tobacco product.

[0014] In some embodiments, the prediction model is trained as follows: Obtain the thermogravimetric analysis data and chemical composition data of each tobacco product raw material sample from multiple tobacco product raw material samples from multiple different origins. The thermogravimetric analysis data of each tobacco product raw material sample includes multiple sample pyrolysis temperatures of the pyrolysis process of each tobacco product raw material sample and the mass change rate corresponding to each sample pyrolysis temperature among the multiple sample pyrolysis temperatures. The chemical composition data of each tobacco product raw material sample includes the content of each chemical component among the multiple chemical components of each tobacco product raw material sample; Determine the characteristic data of each tobacco product raw material sample from the thermogravimetric analysis data of each tobacco product raw material sample. The characteristic data of each tobacco product raw material sample includes the sample characteristic temperature among the multiple sample pyrolysis temperatures and the mass change rate corresponding to the sample characteristic temperature; And use at least one parameter among the sample characteristic temperature and the mass change rate corresponding to the sample characteristic temperature and the chemical composition data of each tobacco product raw material sample as the input, and the predicted origin of each tobacco product raw material sample as the output, and train the prediction model until the training end condition is met.

[0015] In some embodiments, the prediction model includes a random forest model.

[0016] In some embodiments, the multiple chemical components include at least one of total nitrogen, nicotine, total sugar, reducing sugar, potassium, and chlorine.

[0017] According to some other embodiments of the present disclosure, a method for determining a target combined formula of a tobacco product is provided. The tobacco product includes a combination of multiple tobacco product raw materials. The method includes: obtaining first thermogravimetric analysis data and first chemical composition data of each tobacco product raw material among the multiple tobacco product raw materials. The first thermogravimetric analysis data includes multiple first pyrolysis temperatures of the pyrolysis process of each tobacco product raw material and the first mass change rate of each tobacco product raw material corresponding to each of the multiple first pyrolysis temperatures. The first chemical composition data includes the content of each chemical component among the multiple chemical components of each tobacco product raw material; for each of the multiple candidate combined formulas based on the multiple tobacco product raw materials, perform the following steps to construct a combined formula - origin style database: based on the first thermogravimetric analysis data and the candidate combined formula, determine second thermogravimetric analysis data corresponding to the candidate combined formula. The second thermogravimetric analysis data includes multiple second pyrolysis temperatures and the second mass change rate corresponding to each of the multiple second pyrolysis temperatures; based on the first chemical composition data and the candidate combined formula, determine second chemical composition data corresponding to the candidate combined formula. The second chemical composition data includes the content of each chemical component among the multiple chemical components; based on the second thermogravimetric analysis data and the second chemical composition data, use a trained prediction model to predict the origin style corresponding to the candidate combined formula; and store the candidate combined formula and the corresponding origin style into the combined formula - origin style database; retrieve the combined formula corresponding to the target origin style from the combined formula - origin style database to determine the target combined formula.

[0018] In some embodiments, the method further includes: determining the combined formula that meets the first criterion among the retrieved combined formulas as the target combined formula.

[0019] According to some further embodiments of the present disclosure, there is provided an apparatus for predicting the origin style of a tobacco product, where the tobacco product includes a combination of a plurality of tobacco product raw materials, and the apparatus includes: an acquisition module configured to acquire first thermogravimetric analysis data and first chemical composition data of each of the plurality of tobacco product raw materials, where the first thermogravimetric analysis data includes a plurality of first pyrolysis temperatures of the pyrolysis process of each of the tobacco product raw materials and a first mass change rate of each of the tobacco product raw materials corresponding to each of the plurality of first pyrolysis temperatures, and the first chemical composition data includes the content of each chemical component among a plurality of chemical components of each of the tobacco product raw materials; a determination module configured to determine second thermogravimetric analysis data of the tobacco product based on the first thermogravimetric analysis data and the combination formula of the plurality of tobacco product raw materials in the tobacco product, where the second thermogravimetric analysis data includes a plurality of second pyrolysis temperatures and a second mass change rate corresponding to each of the plurality of second pyrolysis temperatures; and determine second chemical composition data of the tobacco product based on the first chemical composition data and the combination formula, where the second chemical composition data includes the content of each chemical component among the plurality of chemical components; a prediction module configured to predict the origin style of the tobacco product based on the second thermogravimetric analysis data and the second chemical composition data of the tobacco product by using a trained prediction model.

[0020] According to some further embodiments of the present disclosure, there is provided an apparatus for determining a target combined formula of a tobacco product, the tobacco product including a combination of a plurality of tobacco product raw materials, the apparatus including: an acquisition module configured to acquire first thermogravimetric analysis data and first chemical composition data of each of the plurality of tobacco product raw materials, the first thermogravimetric analysis data including a plurality of first pyrolysis temperatures of the pyrolysis process of each of the tobacco product raw materials and a first mass change rate of each of the tobacco product raw materials corresponding to each of the plurality of first pyrolysis temperatures, the first chemical composition data including the content of each of the various chemical components in each of the tobacco product raw materials; a database construction module configured to, for each of a plurality of candidate combined formulas based on the plurality of tobacco product raw materials, perform the following steps to construct a combined formula - origin style database: based on the first thermogravimetric analysis data and the candidate combined formula, determine second thermogravimetric analysis data corresponding to the candidate combined formula, the second thermogravimetric analysis data including a plurality of second pyrolysis temperatures and a second mass change rate corresponding to each of the plurality of second pyrolysis temperatures; based on the first chemical composition data and the candidate combined formula, determine second chemical composition data corresponding to the candidate combined formula, the second chemical composition data including the content of each of the various chemical components; based on the second thermogravimetric analysis data and the second chemical composition data, use a trained prediction model to predict the origin style corresponding to the candidate combined formula; and store the candidate combined formula and the corresponding origin style into the combined formula - origin style database; a determination module configured to retrieve the combined formula corresponding to the target origin style from the combined formula - origin style database to determine the target combined formula.

[0021] According to some further embodiments of the present disclosure, there is provided an electronic device including: a memory; and a processor coupled to the memory, the processor being configured to execute the method for predicting the origin style of a tobacco product or the method for determining the target combined formula of a tobacco product in any one of the above embodiments based on instructions stored in the memory device.

[0022] According to some still further embodiments of the present disclosure, there is provided a computer - readable storage medium having stored thereon computer instructions, which when executed by a processor, implement the method for predicting the origin style of a tobacco product or the method for determining the target combined formula of a tobacco product in any one of the above embodiments.

[0023] According to some still further embodiments of the present disclosure, there is also provided a computer program product including instructions, which when executed by a processor, cause the processor to execute the method for predicting the origin style of a tobacco product or the method for determining the target combined formula of a tobacco product in any one of the above embodiments.

[0024] In the above embodiments, in the process of predicting the origin style of tobacco products, on the one hand, the second thermogravimetric analysis data and the second chemical composition data of the tobacco products can be obtained as the objective analysis basis, reducing the subjective error; on the other hand, the obtained second thermogravimetric analysis data and the second chemical composition data can reflect two different types of indicators, namely the pyrolysis characteristics and the chemical composition of the tobacco products, avoiding the one-sidedness caused by predicting only using a single dimension of indicators of the same type. Thus, the prediction accuracy of the origin style of tobacco products is improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] The drawings constituting a part of the specification depict embodiments of the present disclosure and, together with the specification, are used to explain the principles of the present disclosure.

[0026] With reference to the drawings, the present disclosure can be more clearly understood from the following detailed description, wherein:

[0027] Figure 1 A flowchart showing a method for predicting the origin style of tobacco products according to some embodiments of the present disclosure;

[0028] Figure 2 A schematic diagram showing thermogravimetric analysis data according to some embodiments of the present disclosure;

[0029] Figure 3 Showing Figure 1 A schematic flowchart of some embodiments of step 140 in

[0030] Figure 4 A schematic diagram showing thermogravimetric analysis data according to some other embodiments of the present disclosure;

[0031] Figure 5 A flowchart showing a method for training a prediction model according to some embodiments of the present disclosure;

[0032] Figure 6 A flowchart showing a specific example of a method for training a prediction model according to some embodiments of the present disclosure;

[0033] Figure 7 A schematic flowchart showing a method for determining a target combined formula of a tobacco product according to some embodiments of the present disclosure;

[0034] Figure 8 A schematic diagram showing the probability distribution of each origin style corresponding to the target combined formula according to some embodiments of the present disclosure;

[0035] Figures 9A to 9C A schematic diagram showing the normalized root mean square error between the target tobacco leaves and other tobacco leaves of the origin and the tobacco products according to some embodiments of the present disclosure;

[0036] Figure 10 Block diagram of a device for predicting the origin style of a tobacco product showing some embodiments of the present disclosure;

[0037] Figure 11 Block diagram of a device for determining the target combination formula of a tobacco product showing some embodiments of the present disclosure;

[0038] Figure 12 Block diagram of an electronic device showing some embodiments of the present disclosure;

[0039] Figure 13 Block diagram of an electronic device showing some other embodiments of the present disclosure. Detailed implementation manners

[0040] Various exemplary embodiments of the present disclosure will now be described in detail with reference to the accompanying drawings. It should be noted that: Unless otherwise specifically stated, the relative arrangements of components and steps, numerical expressions and values set forth in these embodiments do not limit the scope of the present disclosure.

[0041] The following description of at least one exemplary embodiment is merely illustrative in nature and is in no way a limitation on the present disclosure, its application, or use.

[0042] Techniques, methods, and devices known to those of ordinary skill in the relevant art may not be discussed in detail, but where appropriate, the techniques, methods, and devices should be regarded as part of the specification.

[0043] In all the examples shown and discussed herein, any specific values should be construed as merely exemplary and not as a limitation. Thus, other examples of the exemplary embodiments may have different values.

[0044] It should be noted that: Similar reference numerals and letters denote similar items in the following drawings, and thus, once an item is defined in one drawing, it need not be further discussed in subsequent drawings.

[0045] In the related art, the origin style of a tobacco product is mainly judged by professional smokers subjectively evaluating aspects such as the fragrance and taste of the tobacco product (i.e., sensory evaluation). However, this method has strong subjectivity, resulting in low accuracy in determining the origin style of the tobacco product.

[0046] The inventors of the present disclosure have found through research that the characteristics of the smoke formed by tobacco products are affected by the chemical composition content and pyrolysis characteristics of the tobacco product raw materials, and are also affected by the combined formula of the tobacco product raw materials. Due to differences in factors such as soil composition, climate conditions, and planting techniques, tobacco product raw materials from different origins will have differences in their chemical composition content and pyrolysis characteristics. For example, the tobacco leaves produced in Zimbabwe have a relatively high nicotine content, and the smoke generated during their pyrolysis is relatively strong and has a complex aroma, while the tobacco leaves produced in Yunnan have a moderate nicotine content, and the smoke generated during their pyrolysis is relatively mild and has a long-lasting aroma. The internal correlation between the chemical composition content and pyrolysis characteristics of tobacco product raw materials and their origins can be analyzed, and the origin style of tobacco products can be determined by combining the combined formula of tobacco product raw materials in tobacco products.

[0047] In terms of the origin analysis of tobacco product raw materials, if only the chemical composition content of tobacco product raw materials is analyzed, it can provide a certain basis for origin prediction. However, due to the large variety of chemical components in tobacco product raw materials, it is difficult to accurately measure the content of some chemical components, and tobacco product raw materials from different origins may also have similar chemical composition contents, resulting in inaccurate prediction results of the origin obtained solely based on the chemical composition content. Pyrolysis reaction is one of the main chemical reactions that occur when tobacco product raw materials (such as tobacco leaves) are continuously heated in a temperature range above the pyrolysis threshold temperature. The pyrolysis reaction can occur in the heat-not-burn stage or in the combustion stage, and the temperature in the former stage is generally lower than that in the latter stage. Pyrolysis characteristics can reflect the behavioral characteristics of tobacco product raw materials in the pyrolysis reaction. Although analyzing only the pyrolysis characteristics of tobacco product raw materials can also provide a certain basis for origin prediction, however, the pyrolysis reaction is affected by various factors such as heating rate and heating temperature, and these factors may cause tobacco product raw materials from the same origin to exhibit different pyrolysis characteristics. In addition, the pyrolysis characteristics of tobacco product raw materials are often characterized by collecting data such as temperature and mass change rate during the reaction process, and the selection of characteristic points during the collection process will affect the accuracy of the characterization. These make it equally inaccurate to predict the origin solely based on pyrolysis characteristics.

[0048] Therefore, neither pyrolysis characteristics nor chemical composition content alone is sufficient to accurately predict the origin of tobacco product raw materials. To improve the accuracy of origin prediction of tobacco product raw materials, in the differentiation of the origin of tobacco product raw materials, multiple dimensions of indicators including chemical composition content and pyrolysis characteristics can be used in combination. By combining data from multiple different dimensions, their complementary advantages can be utilized to reduce the deviation caused by a single data source, so as to more comprehensively capture the origin characteristics of tobacco product raw materials and make the prediction results more reliable.

[0049] On the basis of improving the accuracy of predicting the origin of tobacco product raw materials, combined with the combined formula of tobacco products, the accuracy of predicting the origin style of tobacco products can be further improved. Specifically, the embodiments of the present disclosure propose a technical solution for predicting the origin style of tobacco products. First, obtain the first thermogravimetric analysis data and the first chemical composition data of each tobacco product raw material among multiple tobacco product raw materials in the tobacco product, and combine the combined formula of the tobacco product raw materials as the second thermogravimetric analysis data and the second chemical composition data for objectively supporting the prediction of the origin style of the tobacco product. Then, use the trained prediction model to perform fusion processing on the second thermogravimetric analysis data and the second chemical composition data of the tobacco product to achieve accurate prediction of the origin style of the tobacco product.

[0050] Figure 1 The flowchart showing the method for predicting the origin style of tobacco products according to some embodiments of the present disclosure is as follows. Figure 1 As shown, for example, the method for predicting the origin style of tobacco products may include steps 110 to 140.

[0051] In step 110, obtain the first thermogravimetric analysis data and the first chemical composition data of each tobacco product raw material among multiple tobacco product raw materials of the tobacco product.

[0052] In the present disclosure, a tobacco product is a product made entirely or partially from tobacco leaves as raw materials and is used for smoking, chewing, nasal inhalation, or other uses. Tobacco products may include, but are not limited to, cigarettes, cigars, pipe tobacco, or hookah, etc. From the perspective of tobacco leaf formula and processing technology, cigarettes may include, but are not limited to, flue-cured tobacco, burley tobacco, oriental tobacco, or sun-cured tobacco, etc. Tobacco products release chemical substances such as nicotine (commonly known as "tobacco alkaloid") through heating (such as heat-not-burn tobacco products) and / or combustion (such as cigarettes, cigars, etc.). Tobacco products may or may not have a cigarette paper wrapper and may or may not have a filter tip. In the present disclosure, for the convenience of description, in some cases, cigarettes are used as examples of tobacco products for illustration. However, it should be recognized that the various features or limitations described here regarding cigarettes also apply to other types of tobacco products.

[0053] Tobacco product raw materials may include tobacco leaves in various forms. For example, they may be tobacco leaves or cut tobacco, tobacco flakes, tobacco powder, or tobacco blocks formed by processing tobacco leaves. In some embodiments, the tobacco product raw materials are tobacco leaves from a specific origin. Here, the multiple tobacco product raw materials may be tobacco leaves from different origins, or tobacco leaves from different growth parts of the same origin (for example, divided into "upper", "middle", and "lower" according to the growth part of the tobacco leaf on the tobacco plant), or tobacco leaves from different batches of the same growth part of the same origin.

[0054] The first chemical composition data of each tobacco product raw material includes the content of each chemical composition among various chemical compositions in each tobacco product raw material. For example, the content of each chemical composition among various chemical compositions in each tobacco product raw material can be obtained by using a continuous flow method.

[0055] In some embodiments, the multiple tobacco product raw materials can include tobacco product raw materials from multiple different origins.

[0056] In some embodiments, the various chemical compositions can include at least one of total nitrogen, nicotine, total sugar, reducing sugar, potassium, and chlorine.

[0057] The first thermogravimetric analysis data of each tobacco product raw material includes a plurality of first pyrolysis temperatures of the pyrolysis process of each tobacco product raw material and the first mass change rate of each tobacco product raw material corresponding to each first pyrolysis temperature among the plurality of first pyrolysis temperatures.

[0058] For example, the thermogravimetric analysis data of a tobacco product raw material can be obtained by conducting a pyrolysis experiment on the tobacco product raw material and recording a plurality of pyrolysis temperatures during the pyrolysis process and the mass change rate of the tobacco product raw material corresponding to each pyrolysis temperature. The mass change rate can be determined by taking the derivative of the mass of the tobacco product raw material with respect to temperature during the pyrolysis process.

[0059] Taking a certain tobacco leaf as an example of the tobacco product raw material, the process of conducting a pyrolysis experiment on the tobacco product raw material will be exemplarily introduced below.

[0060] First, place a certain tobacco leaf in a constant temperature and humidity box (for example, at a temperature of (22 ± 1) °C and a relative humidity of (60 ± 2)%) and equilibrate for a period of time (for example, 48 h). Then, grind the tobacco leaf, filter and fully mix the ground tobacco powder through a sieve (for example, a sieve with a mesh number in the range of 80 to 100 or a sieve with a sieve hole diameter in the range of 150 micrometers (μm) to 180 micrometers). Weigh, for example, 20 mg of the tobacco powder as a sample. In a thermal analyzer, heat the sample in a nitrogen atmosphere (for example, the flow rate of nitrogen is 100 milliliters per minute (i.e., the carrier gas flow rate is 100 mL / min)) at a certain rate (for example, 10 Kelvin per minute (10 K / min)) to a certain temperature (for example, 373 Kelvin (K)), and keep it at a constant temperature for a period of time to remove the influence caused by different moisture contents of the tobacco leaf. Then, continue to heat the sample to a higher temperature (for example, 873 Kelvin (K)) at the same rate. Record the relationship between the mass and temperature of the sample during the heating process to obtain a weight loss (TG, Thermo-Gravimetry) curve. To make the pyrolysis behavior of the tobacco more obvious, take the derivative of the TG curve to obtain a derivative weight loss (DTG, Derivative Thermo-Gravimetry) curve, which reflects the relationship between the mass change rate and temperature, that is, the "thermal weight loss analysis data" described in this article. If the thermal weight loss analysis data is presented in the form of a curve graph (i.e., the DTG curve), the abscissa represents the temperature (i.e., the "pyrolysis temperature" described in this article), with the unit of Kelvin (K), and the ordinate represents the mass change rate of the tobacco leaf during pyrolysis, with the unit of percentage per Kelvin (% / K). This curve is also called a thermal analysis spectrum.

[0061] Figure 2 Schematic diagram showing the DTG curves of some embodiments of the present disclosure.

[0062] For example, in the above example, data points can be taken at a step size of 0.5 K, with a total of 801 data points between 401.138 K and 801.138 K as the thermal weight loss analysis data of the tobacco leaf, and presented in the form of a curve to obtain a DTG curve as shown by the black solid line. Figure 2 The DTG curve shown by the black solid line.

[0063] It can be understood here that the pyrolysis temperature in the thermal weight loss analysis data (i.e., the abscissa of the DTG curve) can reflect the temperature change range of the tobacco leaf during pyrolysis, and different pyrolysis temperatures may correspond to different pyrolysis stages in the pyrolysis reaction. The mass change rate in the thermal weight loss analysis data (i.e., the ordinate of the DTG curve) can reflect the intensity of the reaction during the pyrolysis of the tobacco leaf, thus revealing the kinetic characteristics of the pyrolysis reaction of the tobacco leaf. That is to say, the pyrolysis temperature and mass change rate in the thermal weight loss analysis data of the tobacco leaf can reflect the pyrolysis characteristics of the tobacco leaf from two different dimensions.

[0064] The multiple pyrolysis temperatures in the thermogravimetric analysis data can be evenly distributed or unevenly distributed. To more accurately characterize the pyrolysis characteristics of tobacco leaves, the temperature difference between adjacent pyrolysis temperatures among the multiple pyrolysis temperatures can be as small as possible, for example, it can be 10K, 5K, 1K, 0.5K or other values.

[0065] In step 120, based on the first thermogravimetric analysis data and the combined formula of multiple tobacco product raw materials in the tobacco product, the second thermogravimetric analysis data of the tobacco product is determined.

[0066] The second thermogravimetric analysis data of the tobacco product includes multiple second pyrolysis temperatures and the second mass change rate corresponding to each second pyrolysis temperature among the multiple second pyrolysis temperatures.

[0067] In some embodiments, the combined formula of multiple tobacco product raw materials in the tobacco product may include the mass percentage of the multiple tobacco product raw materials in the tobacco product. The mass percentage can be presented in the form of an absolute value or a relative value. In the form of an absolute value, the combined formula may include, for example, the mass of each tobacco product raw material (e.g., in grams, milligrams, micrograms, etc.), thereby indirectly reflecting the mass percentage. In the case of a relative value, the combined formula may include, for example, the ratio of the mass of each tobacco product raw material divided by the mass of the tobacco product (e.g., in percentage), thereby directly reflecting the mass percentage.

[0068] In some embodiments, the second thermogravimetric analysis data of the tobacco product can be obtained based on the first thermogravimetric analysis data of each tobacco product raw material and the mass percentage of the tobacco product raw material in the tobacco product.

[0069] In step 130, based on the first chemical composition data and the combined formula of multiple tobacco product raw materials in the tobacco product, the second chemical composition data of the tobacco product is determined.

[0070] The second chemical composition data of the tobacco product includes the content of each chemical component among multiple chemical components.

[0071] In some embodiments, the second chemical composition data of the tobacco product can be obtained based on the first chemical composition data of each tobacco product raw material and the mass percentage of the tobacco product raw material in the tobacco product.

[0072] In step 140, based on the second thermogravimetric analysis data and the second chemical composition data of the tobacco product, the origin style of the tobacco product is predicted using the trained prediction model.

[0073] As described above, the regional style of a tobacco product refers to the comprehensive sensory characteristics and style performance presented after blending different tobacco product raw materials. In other words, the regional style of a tobacco product reflects the overall style characteristics presented by the fragrance and taste characteristics of tobacco leaves from various origins in the tobacco product after blending. For example, if the regional style of a tobacco product is Fujian, it means that the tobacco product as a whole presents the style characteristics (such as fragrance type style, etc.) of tobacco leaves produced in Fujian.

[0074] In some embodiments, the second thermogravimetric analysis data and the second chemical composition data of the tobacco product can be input into a trained prediction model to obtain the regional style of the tobacco product output by the prediction model. As an exemplary implementation, different regional styles can correspond to different prediction labels. For example, the number 1 represents the regional style of Yunnan, and the number 2 represents the regional style of Fujian. In response to the prediction label output by the prediction model being 1, it can be determined that the regional style of the tobacco product is Yunnan.

[0075] In the above embodiments, the second thermogravimetric analysis data and the second chemical composition data for characterizing the pyrolysis characteristics and chemical composition of the tobacco product can be obtained as the objective analysis data of the tobacco product. The trained prediction model is used to process these objective analysis data to predict the regional style of the tobacco product.

[0076] In this way, in the process of predicting the regional style of a tobacco product, on the one hand, the objective analysis data of the tobacco product can be used as the analysis basis, reducing subjective errors; on the other hand, the obtained objective analysis data can reflect two different types of indicators, namely the pyrolysis characteristics and chemical composition of the tobacco product. Predicting based on such objective analysis data avoids the one-sidedness caused by predicting only using a single dimension of indicators of the same type. Thus, the prediction accuracy of the regional style of the tobacco product is improved.

[0077] First, the related implementations of steps 120 and 130 will be exemplarily described in combination with some embodiments below.

[0078] In some embodiments, the second thermogravimetric analysis data of the tobacco product can be determined in the following manner.

[0079] First, the mass ratio of each tobacco product raw material in the combined formula of multiple tobacco product raw materials in the tobacco product is used as the weight of the first thermogravimetric analysis data of each tobacco product raw material, and the first weighted sum of the first thermogravimetric analysis data of each tobacco product raw material is calculated.

[0080] Then, the first weighted sum is determined as the second thermogravimetric analysis data of the tobacco product.

[0081] For example, a tobacco product contains tobacco leaf A from Yunnan, tobacco leaf B from Fujian, and tobacco leaf C from Henan. And the mass proportion (such as percentage) of tobacco leaf A in the tobacco product is a, the mass proportion of tobacco leaf B in the tobacco product is b, and the mass proportion of tobacco leaf C in the tobacco product is c. Taking a as the weight of the first thermogravimetric analysis data S1 of tobacco leaf A, b as the weight of the first thermogravimetric analysis data S2 of tobacco leaf B, and c as the weight of the first thermogravimetric analysis data S3 of tobacco leaf C, the second thermogravimetric analysis data S of the tobacco product can be calculated as S = a×S1 + b×S2 + c×S3.

[0082] In this calculation method, each second pyrolysis temperature in the second thermogravimetric analysis data of the tobacco product is the weighted sum of the first pyrolysis temperatures in the first thermogravimetric analysis data of each tobacco product raw material. The second mass change rate corresponding to each second pyrolysis temperature in the second thermogravimetric analysis data of the tobacco product is the weighted sum of the first mass change rates corresponding to the first pyrolysis temperature in the first thermogravimetric analysis data of each tobacco product raw material.

[0083] For example, the first thermogravimetric analysis data S1 of tobacco leaf A includes the starting temperature T1 and the mass change rate W1 corresponding to T1. The first thermogravimetric analysis data S2 of tobacco leaf B includes the starting temperature T2 and the mass change rate W2 corresponding to T2. The first thermogravimetric analysis data S3 of tobacco leaf C includes the starting temperature T3 and the mass change rate W3 corresponding to T3. Thus, in the second thermogravimetric analysis data of the calculated tobacco product, the starting temperature T’ = a×T1 + b×T2 + c×T3, and the mass change rate W’ corresponding to the starting temperature T’ = a×W1 + b×W2 + c×W3.

[0084] In some embodiments, the data volume of the first thermogravimetric analysis data of each tobacco product raw material is equal. For example, if the first thermogravimetric analysis data of each tobacco product raw material is represented in the form of a curve, then for each tobacco product raw material, Figure 2 as shown in the example, a total of 801 data between 401.138K and 801.138K can be taken to form the corresponding DTG curve. Then, taking the mass proportion of each tobacco product raw material in the tobacco product as the weight of each data in the DTG curve of each tobacco product raw material, 801 weighted sum data are calculated accordingly to form the DTG curve of the tobacco product.

[0085] In the above embodiments, in the process of obtaining the second thermogravimetric analysis data of the tobacco product by using the first thermogravimetric analysis data of each tobacco product raw material in the tobacco product, by calculating the weighted sum with the mass percentage of each tobacco product raw material in the tobacco product in the combined formula as the weight, it can be ensured that the influence of the pyrolysis characteristics of each tobacco product raw material on the overall pyrolysis characteristics of the tobacco product is fully considered. In this way of quantitative calculation, the obtained second thermogravimetric analysis data can more accurately reflect the actual pyrolysis characteristics of the tobacco product, thereby improving the prediction accuracy of the origin style of the tobacco product.

[0086] In some embodiments, the number of each tobacco product raw material in the tobacco product can be multiple. For example, each tobacco product raw material can include multiple tobacco leaves from the same origin, and the first thermogravimetric analysis data of each tobacco product raw material can include the thermogravimetric analysis data of each tobacco leaf among these multiple tobacco leaves.

[0087] In this case, for example, the second thermogravimetric analysis data of the tobacco product can be determined in the following manner.

[0088] First, calculate the average value of the first thermogravimetric analysis data of each tobacco product raw material to obtain the average thermogravimetric analysis data of each tobacco product raw material.

[0089] Then, take the mass percentage of each tobacco product raw material in the combined formula of the tobacco product as the weight of the average thermogravimetric analysis data of each tobacco product raw material, and calculate the weighted sum of the average thermogravimetric analysis data of each tobacco product raw material as the first weighted sum.

[0090] After that, determine the first weighted sum as the second thermogravimetric analysis data of the tobacco product.

[0091] Continuing the above example, assume that tobacco leaf A from Yunnan includes multiple tobacco leaves (such as tobacco leaf A1, tobacco leaf A2, and tobacco leaf A3). The first thermogravimetric analysis data of tobacco leaf A includes the thermogravimetric analysis data x1 of tobacco leaf A1, the thermogravimetric analysis data x2 of tobacco leaf A2, and the thermogravimetric analysis data x3 of tobacco leaf A3. Calculate the average value of the three thermogravimetric analysis data x1, x2, and x3 in the first thermogravimetric analysis data of tobacco leaf A, and the average thermogravimetric analysis data P1 of tobacco leaf A can be obtained as P1 = (x1 + x2 + x3) / 3. Similarly, if the number of tobacco leaf B and the number of tobacco leaf C are multiple, the average thermogravimetric analysis data P2 of tobacco leaf B and the average thermogravimetric analysis data P3 of tobacco leaf C can be calculated. Thus, the second thermogravimetric analysis data S of the tobacco product is S = a×P1 + b×P2 + c×P3.

[0092] In the above embodiments, when each tobacco product raw material in a tobacco product includes a plurality of tobacco leaves, first calculate the average thermogravimetric analysis data of each tobacco product raw material, and then obtain the second thermogravimetric analysis data of the tobacco product based on the average thermogravimetric analysis data of each tobacco product raw material. In this way, when the multiple tobacco product raw materials of the tobacco product are distinguished by different production areas, the influence of the pyrolysis characteristics of each tobacco leaf in the same production area on the overall pyrolysis characteristics of the tobacco product is also fully considered, thereby improving the prediction accuracy of the production area style of the tobacco product.

[0093] In some embodiments, the temperature ranges formed by the multiple first pyrolysis temperatures in the first thermogravimetric analysis data of each tobacco product raw material of the tobacco product are the same. Specifically, the starting temperature and the ending temperature of the first thermogravimetric analysis data of each tobacco product raw material can be the same. In this case, when calculating the second thermogravimetric analysis data of the tobacco product based on the first thermogravimetric analysis data of multiple tobacco product raw materials, for the first thermogravimetric analysis data corresponding to each starting temperature and ending temperature, it is not necessary to weight each starting temperature and ending temperature, but directly use the starting temperature and the ending temperature, and only weight the mass change rate corresponding to each starting temperature and ending temperature. The temperature range formed by the multiple second pyrolysis temperatures in the second thermogravimetric analysis data of the obtained tobacco product is the same as the temperature range formed by the multiple first pyrolysis temperatures in the first thermogravimetric analysis data of each tobacco product raw material.

[0094] Continuing the above example, the tobacco product contains tobacco leaf A from Yunnan, tobacco leaf B from Fujian, and tobacco leaf C from Henan. The temperature ranges formed by the multiple first pyrolysis temperatures in the first thermogravimetric analysis data of tobacco leaf A, tobacco leaf B, and tobacco leaf C can all be from 401.138K to 801.138K. That is, the starting temperature T1 in the first thermogravimetric analysis data of tobacco leaf A, the starting temperature T2 in the first thermogravimetric analysis data of tobacco leaf B, and the starting temperature T3 in the first thermogravimetric analysis data of tobacco leaf C are the same, all being 401.138K, so the starting temperature T' in the second thermogravimetric analysis data of the tobacco product is T1 = T2 = T3 = 401.138K.

[0095] Similarly, the ending temperature in the second thermogravimetric analysis data of the tobacco product is the same as the ending temperatures in the first thermogravimetric analysis data of tobacco leaf A, tobacco leaf B, and tobacco leaf C, that is, all being 801.138K.

[0096] In the above embodiments, the starting temperature and the ending temperature in the second thermogravimetric analysis data of the tobacco product are the same as the starting temperature and the ending temperature in the first thermogravimetric analysis data of each tobacco product raw material. That is, at least there is no need to separately calculate the weighted sum of the starting temperature and the ending temperature in the first thermogravimetric analysis data of each tobacco product raw material, reducing the amount of calculation required to obtain the second thermogravimetric analysis data.

[0097] In some embodiments, each second pyrolysis temperature among the multiple second pyrolysis temperatures in the second thermogravimetric analysis data of the tobacco product is the same as each first pyrolysis temperature among the multiple first pyrolysis temperatures in the first thermogravimetric analysis data of each tobacco product raw material.

[0098] For example, if the first thermogravimetric analysis data of each tobacco product raw material and the second thermogravimetric analysis data of the tobacco product are both represented in the form of a DTG curve, the abscissa of the DTG curve of each tobacco product raw material is the same as the abscissa of the DTG curve of the tobacco product.

[0099] In this way, there is no need to calculate the weighted sum of the multiple first pyrolysis temperatures in the first thermogravimetric analysis data of each tobacco product raw material, reducing the amount of calculation required to obtain the second thermogravimetric analysis data.

[0100] In some embodiments, the second chemical composition data of the tobacco product can be determined in the following manner.

[0101] First, take the mass proportion of each tobacco product raw material in the combined formula of the tobacco product as the weight of the first chemical composition data of each tobacco product raw material, and calculate the second weighted sum of the first chemical composition data of each tobacco product raw material.

[0102] Then, determine the second weighted sum as the second chemical composition data of the tobacco product.

[0103] Continuing with the above example, taking the chemical composition including total nitrogen as an example, assume that the content of total nitrogen in the first chemical composition data of tobacco leaf A is Q1, the content of total nitrogen in the first chemical composition data of tobacco leaf B is Q2, and the content of total nitrogen in the first chemical composition data of tobacco leaf C is Q3. Taking a as the weight of the content Q1 of total nitrogen in tobacco leaf A, taking b as the weight of the content Q2 of total nitrogen in tobacco leaf B, and taking c as the weight of the content Q3 of total nitrogen in tobacco leaf C, the content Q of total nitrogen in the second chemical composition data of the tobacco product can be calculated as Q = a×Q1 + b×Q2 + c×Q3.

[0104] Similarly, the contents of other components in the second chemical composition data of the tobacco product can be calculated.

[0105] In the above embodiments, in the process of obtaining the second chemical component data of the tobacco product by using the first chemical component data of each tobacco product raw material in the tobacco product, by taking the mass percentage of each tobacco product raw material in the combined formula in the tobacco product as the weight for weighted sum calculation, it can ensure that the influence of the chemical components of each tobacco product raw material on the overall chemical components of the tobacco product is fully considered. This quantitative calculation method can make the obtained second chemical component data more accurately reflect the actual chemical components of the tobacco product, thereby improving the prediction accuracy of the origin style of the tobacco product.

[0106] In some embodiments, the number of each tobacco product raw material in the tobacco product can be multiple. For example, each tobacco product raw material can include multiple tobacco leaves from the same origin, and the first chemical component data of each tobacco product raw material can include the chemical component data of each tobacco leaf among these multiple tobacco leaves.

[0107] In this case, for example, the second chemical component data of the tobacco product can be determined in the following manner.

[0108] First, calculate the average value of the first chemical component data of each tobacco product raw material to obtain the average chemical component data of each tobacco product raw material.

[0109] Then, take the mass percentage of each tobacco product raw material in the combined formula of the tobacco product as the weight of the average chemical component data of each tobacco product raw material, and calculate the weighted sum of the average chemical component data of each tobacco product raw material as the second weighted sum.

[0110] After that, determine the second weighted sum as the second chemical component data of the tobacco product.

[0111] Continuing with the above example, still taking the total nitrogen as the chemical component, assume that tobacco leaf A from Yunnan includes multiple tobacco leaves (such as tobacco leaf A1, tobacco leaf A2, and tobacco leaf A3). The first chemical component data of tobacco leaf A includes the content y1 of total nitrogen in tobacco leaf A1, the content y2 of total nitrogen in tobacco leaf A2, and the content y3 of total nitrogen in tobacco leaf A3. Calculate the average value of the three total nitrogen contents y1, y2, and y3 in the first chemical component data of tobacco leaf A, and the average content R1 of total nitrogen in the average chemical component data of tobacco leaf A can be obtained as R1 = (y1 + y2 + y3) / 3. Similarly, if the number of tobacco leaf B and the number of tobacco leaf C are multiple, the average content R2 of total nitrogen in the average chemical component data of tobacco leaf B and the average content R3 of total nitrogen in the average chemical component data of tobacco leaf C can be calculated. Thus, the content Q of total nitrogen in the second chemical component data of the tobacco product is Q = a×R1 + b×R2 + c×R3.

[0112] Similarly, the contents of other components in the second chemical composition data of the tobacco product can be calculated and obtained.

[0113] In the above embodiments, when each tobacco product raw material in the tobacco product includes a plurality of tobacco leaves, the average chemical composition data of each tobacco product raw material is first calculated, and then the second chemical composition data of the tobacco product is obtained based on the average chemical composition data of each tobacco product raw material. In this way, when the multiple tobacco product raw materials of the tobacco product are distinguished by different production areas, the influence of the chemical compositions of the tobacco leaves in the same production area on the overall chemical composition of the tobacco product is also fully considered, thereby improving the prediction accuracy of the production area style of the tobacco product.

[0114] First, some embodiments will be combined below to exemplarily illustrate the related implementation of step 140.

[0115] In some embodiments, characteristic data can be determined from the first thermogravimetric analysis data of each tobacco product raw material. This characteristic data includes the characteristic temperature determined from multiple first pyrolysis temperatures and the mass change rate corresponding to the characteristic temperature. Then, the above-mentioned weighted sum quantization calculation method is used to calculate this characteristic data to obtain the second thermogravimetric analysis data. After that, based on the second thermogravimetric data and the second chemical composition data, the production area style of the tobacco product is predicted using the trained prediction model.

[0116] In some embodiments, the above-mentioned weighted sum quantization calculation method can be used to calculate the first thermogravimetric analysis data of each tobacco product raw material to obtain the second thermogravimetric analysis data. Then, characteristic data is determined from the second thermogravimetric analysis data. This characteristic data includes the characteristic temperature determined from multiple second pyrolysis temperatures and the mass change rate corresponding to the characteristic temperature. After that, based on this characteristic data and the second chemical composition data, the production area style of the tobacco product is predicted using the trained prediction model. The following combines Figure 3 to exemplarily illustrate this method.

[0117] Figure 3 A flowchart showing some embodiments of step 140 is shown. As Figure 3 shown, for example, step 140 may include step 141 and step 142.

[0118] In step 141, characteristic data is determined from the second thermogravimetric analysis data of the tobacco product. The characteristic data includes the characteristic temperature determined from multiple second pyrolysis temperatures and the mass change rate corresponding to the characteristic temperature.

[0119] In some embodiments, a part of characteristic points can be selected from the DTG curve corresponding to the second thermogravimetric analysis data of the tobacco product. The abscissa values of these characteristic points in the DTG curve are determined as the characteristic temperatures in the characteristic data, and the ordinate values of these characteristic points in the DTG curve are determined as the mass change rates corresponding to the characteristic temperatures in the characteristic data.

[0120] In step 142, based on at least one parameter of the characteristic temperature and the mass change rate corresponding to the characteristic temperature and the second chemical composition data, the origin style of the tobacco product is predicted using the trained prediction model.

[0121] In some embodiments, at least one parameter of the characteristic temperature and the mass change rate corresponding to the characteristic temperature and the chemical composition data can be jointly used as the input of the trained prediction model to obtain the origin style of the tobacco product output by the prediction model.

[0122] It can be understood here that the number of characteristic temperatures can be one or more. Correspondingly, the number of mass change rates corresponding to the characteristic temperatures can also be one or more. The characteristic temperature and the mass change rate corresponding to the characteristic temperature are two types of parameters in different dimensions. That is to say, in step 142, based on the second chemical composition data, any one type of parameter of the characteristic temperature and the mass change rate corresponding to the characteristic temperature or both types of parameters of the characteristic temperature and the mass change rate corresponding to the characteristic temperature can be combined, and the trained prediction model is used to predict the origin style of the tobacco product.

[0123] For example, the characteristic data can include multiple characteristic temperatures and the mass change rate corresponding to each characteristic temperature among the multiple characteristic temperatures.

[0124] For example, multiple characteristic temperatures and the chemical composition data can be jointly input into the trained prediction model to predict the origin style of the tobacco product; or the mass change rate corresponding to each characteristic temperature among the multiple characteristic temperatures and the chemical composition data can be jointly input into the trained prediction model to predict the origin style of the tobacco product; or multiple characteristic temperatures, the mass change rate corresponding to each characteristic temperature among the multiple characteristic temperatures, and the chemical composition data can be jointly input into the trained prediction model to predict the origin style of the tobacco product.

[0125] In the above embodiments, the characteristic data determined from the second thermogravimetric analysis data of the tobacco product includes two parameters, namely the characteristic temperature and the second mass change rate corresponding to the characteristic temperature, which can effectively characterize the overall pyrolysis characteristics of the tobacco product. The trained prediction model is used to perform fusion processing on at least one of these two parameters and the second chemical composition data of the tobacco product to predict the origin style of the tobacco product.

[0126] In this way, in the process of predicting the origin style of tobacco products, the overall pyrolysis characteristics of tobacco products and the contents of various chemical components in tobacco products can be effectively combined for consideration, thereby achieving accurate prediction of the origin style of tobacco products.

[0127] In some embodiments, in step 142, the origin style of the tobacco product can be predicted using the trained prediction model based on the characteristic temperature, the mass change rate corresponding to the characteristic temperature, and the second chemical component data. For example, the characteristic temperature, the mass change rate corresponding to the characteristic temperature, and the chemical component data can be jointly used as the input of the trained prediction model to obtain the prediction label output by the prediction model, and the origin style of the tobacco product can be determined based on this prediction label.

[0128] In this way, since the combination of the pyrolysis temperature and the mass change rate can more accurately reveal the overall pyrolysis characteristics of tobacco products, on the basis of the second chemical component data, further inputting the characteristic temperature included in the characteristic data and the second mass change rate corresponding to the characteristic temperature into the trained prediction model together can more accurately predict the origin style of tobacco products.

[0129] The following will exemplarily illustrate the characteristic data in step 141 in conjunction with some embodiments.

[0130] In some embodiments, the characteristic temperature may include the starting temperature and / or the ending temperature among multiple second pyrolysis temperatures.

[0131] That is to say, the characteristic data determined from the second thermogravimetric analysis data may include the starting temperature among multiple second pyrolysis temperatures and the mass change rate corresponding to the starting temperature, and / or the characteristic data determined from the second thermogravimetric analysis data may include the ending temperature among multiple second pyrolysis temperatures and the mass change rate corresponding to the ending temperature.

[0132] For the convenience of description, using the method described above, the mass proportion of each tobacco product raw material in the tobacco product is used as the weight of each data in the DTG curve of each tobacco product raw material, and accordingly, a plurality of weighted sum data are calculated to form the DTG curve of the tobacco product.

[0133] The following will take Figure 2 the curve shown representing the DTG curve of the tobacco product as an example for exemplary illustration.

[0134] See Figure 2, for example, in the DTG curve of a tobacco product, the starting point A1 and the ending point A2 are selected as characteristic points. The abscissa value of the starting point A1 is the starting temperature TA1, and the ordinate value of the starting point A1 is the mass change rate WA1 corresponding to the starting temperature. The abscissa value of the ending point A2 is the ending temperature TA2, and the ordinate value of the ending point A2 is the mass change rate WA2 corresponding to the ending temperature.

[0135] For example, any set of data among (TA1, TA2), (WA1, WA2), (TA1, TA2, WA1, WA2) and the chemical composition data of the tobacco leaves can be input into the trained prediction model to predict the origin style of the tobacco product.

[0136] In the above embodiments, since the starting temperature marks the beginning of thermal decomposition of the tobacco leaves, and the ending temperature marks the completion of thermal decomposition of the tobacco leaves, therefore, making the characteristic data include the starting temperature among multiple second pyrolysis temperatures, the mass change rate corresponding to the starting temperature, the ending temperature, and the mass change rate corresponding to the ending temperature can effectively utilize the thermal stability characteristics of each tobacco product raw material to predict the origin style of the tobacco product. Thus, the accuracy of predicting the origin style of the tobacco product can be further improved.

[0137] In some embodiments, multiple second pyrolysis temperatures form a temperature range. The mass change rate corresponding to the characteristic temperature includes one or more extreme values of the second mass change rate within the temperature range. That is to say, the characteristic data determined from the second thermogravimetric analysis data can include at least one extreme value of the second mass change rate and the temperature corresponding to this at least one extreme value. The at least one extreme value can include a maximum value and / or a minimum value. Here, if the mass change rate is differentiated with respect to temperature, the extreme value is the mass change rate corresponding to when the derivative is 0. Or, if the pyrolysis temperature and the mass change rate are plotted as a curve, the extreme value corresponds to the peak or valley on the curve.

[0138] For example, as Figure 2 shown, the lower limit of the temperature range formed by multiple second pyrolysis temperatures is 401.138K, and the upper limit is 801.138K. Multiple points (B1 - B5) with a slope of 0 are selected as characteristic points in the DTG curve. Among them, B1 and B4 are the trough points on the DTG curve, and B2, B3, and B5 are the peak points on the DTG curve.

[0139] The ordinate values (WB1 - WB5) of these characteristic points are the extreme values of the second mass change rate within the temperature range from 401.138K to 801.138K, and the abscissa values (TB1 - TB5) of these characteristic points are the temperatures corresponding to the extreme values (i.e., the characteristic temperatures).

[0140] For example, any set of data among (TB1 to TB5), (WB1 to WB5), ((TB1, WB1) to (TB5, WB5)) and the second chemical composition data of the tobacco product can be input into the trained prediction model to predict the origin style of the tobacco product.

[0141] In the above embodiments, since the peak points and trough points in the curve corresponding to the thermogravimetric analysis data can reflect the main thermal decomposition stages of the tobacco leaves, therefore, making the characteristic data include one or more extreme values of the second mass change rate within the temperature range and the corresponding characteristic temperatures can effectively utilize the characteristics of each tobacco product raw material in each thermal decomposition stage for predicting the origin style of the tobacco product. Thus, the accuracy of predicting the origin style of the tobacco product can be further improved.

[0142] In some embodiments, the characteristic data determined from the second thermogravimetric analysis data may include: the starting temperature among the multiple second pyrolysis temperatures and the mass change rate corresponding to the starting temperature, the ending temperature among the multiple second pyrolysis temperatures and the mass change rate corresponding to the ending temperature, at least one extreme value of the second mass change rate, and the temperature corresponding to this at least one extreme value.

[0143] For example, the starting point A1, the ending point A2, and the characteristic points B1 to B5 can be selected together from the DTG curve to obtain the characteristic data for predicting the origin style of the tobacco product.

[0144] Please continue to refer to Figure 2 , the curve obtained after curve fitting based on these 7 characteristic points A1, A2, and B1 to B5 is as Figure 2 shown by the dashed line in. It can be seen that the curve fitted according to these 7 characteristic points can more accurately reflect the trend of the actual DTG curve. This indicates that the characteristic data obtained using these 7 characteristic points can more accurately reflect the thermal decomposition characteristics of the tobacco leaves during the pyrolysis process. Therefore, using these characteristic data can help accurately predict the origin style of the tobacco product.

[0145] In some embodiments, the multiple second pyrolysis temperatures form adjacent first and second temperature ranges.

[0146] The mass change rate corresponding to the characteristic temperature includes the intermediate value of the first extreme value of the second mass change rate within the first temperature range and the second extreme value of the second mass change rate within the second temperature range. In other words, the mass change rate corresponding to the characteristic temperature can include the intermediate value of the two extreme values corresponding to the second mass change rate within two adjacent temperature ranges.

[0147] In some embodiments, the characteristic temperature corresponding to the median value may include a first temperature corresponding to the median value in the second thermogravimetric analysis data. For example, the temperature corresponding to the first extreme value is less than the temperature corresponding to the second extreme value, and the first temperature is greater than the temperature corresponding to the first extreme value and less than the temperature corresponding to the second extreme value. In other words, the characteristic temperature corresponding to the median value may include a first temperature between the temperature corresponding to the first extreme value and the temperature corresponding to the second extreme value.

[0148] Thus, further including the median value of the two extreme values corresponding to the second mass change rate in two adjacent temperature intervals and the first temperature corresponding to the median value in the characteristic data can further effectively utilize the characteristics of each tobacco product raw material in each thermal decomposition stage for predicting the origin style of the tobacco product. Therefore, the accuracy of predicting the origin style of the tobacco product can be further improved.

[0149] In some embodiments, the characteristic temperature corresponding to the median value may include a second temperature corresponding to the median value in the second thermogravimetric analysis data. For example, the second temperature is less than the temperature corresponding to the first extreme value or greater than the temperature corresponding to the second extreme value. In other words, the characteristic temperature corresponding to the median value may include a second temperature less than the temperature corresponding to the first extreme value or a second temperature greater than the temperature corresponding to the second extreme value.

[0150] Thus, considering that the median value may correspond to multiple different temperatures in the second thermogravimetric analysis data, further including the median value and the second temperature corresponding to the median value different from the first temperature in the characteristic data can further effectively utilize the characteristics of each tobacco product raw material in each thermal decomposition stage for predicting the origin style of the tobacco product. Therefore, the accuracy of predicting the origin style of the tobacco product can be further improved.

[0151] The following combines Figure 4 to further illustrate the case where the characteristic data includes the median value of the two extreme values corresponding to the second mass change rate in two adjacent temperature intervals and the temperature corresponding to the median value.

[0152] Figure 4 A schematic diagram showing the DTG curves of some other embodiments of the present disclosure.

[0153] Figure 4 Continuing Figure 2 the example shown, the DTG curve of the example shown above is also shown as a solid black line. As Figure 4 shown, A1 and A2 are respectively the starting point and the ending point on the DTG curve. B1 and B4 are the trough points on the DTG curve, and B2, B3, and B5 are the peak points on the DTG curve.

[0154] For example, B1 and B2 are the extreme values within two adjacent temperature ranges. The ordinate value of feature point B1 can be taken as the first extreme value, and the ordinate value of feature point B2 can be taken as the second extreme value. The points C1 and D1 corresponding to the intermediate value between the ordinate value of feature point B1 and the ordinate value of feature point B2 on the DTG curve are selected as feature points. Among them, the abscissa value of feature point C1 is between the abscissa values corresponding to feature points B1 and B2, that is, the abscissa value of feature point C1 is the first temperature TC1 corresponding to the intermediate value WC1; the abscissa value of feature point D1 is less than the abscissa value corresponding to feature point B1, that is, the abscissa value of feature point D1 is the second temperature TD1 corresponding to the intermediate value WD1. And so on.

[0155] Here, it can be understood that the point D1' corresponding to the intermediate value between the ordinate value of feature point B1 and the ordinate value of feature point B2 on the DTG curve can also be selected as a feature point. The abscissa value of feature point D1' is greater than the abscissa value corresponding to feature point B2, that is, the abscissa value of feature point D1' is the second temperature TD1' corresponding to the intermediate value WD1'.

[0156] Figure 4 Eight feature points C1 to C4 and D1 to D4 (also known as "half-peak points") selected are schematically shown. Any combination of one or two types of data among the temperatures and mass change rates of these eight feature points can be used as the characteristic temperature and / or the corresponding mass change rate and input into the trained prediction model to predict the origin style of the tobacco product.

[0157] For example, any set of data among (TC1~TC4), (WC1~WC4), ((TC1,WC1)~(TC4,WC4)) and the second chemical composition data can be input into the trained prediction model to predict the origin style of the tobacco product.

[0158] For example, any set of data among (TD1~TD4), (WD1~WD4), ((TD1,WD1)~(TD4,WD4)) and the second chemical composition data can be input into the trained prediction model to predict the origin style of the tobacco product.

[0159] For example, any set of data among (TC1~TC4 and TD1~TD4), (WC1~WC4 and WD1~WD4), ((TC1,WC1)~(TC4,WC4), (TD1,WD1)~(TD4,WD4)) and the second chemical composition data can be input into the trained prediction model to predict the origin style of the tobacco product.

[0160] In some embodiments, the characteristic data determined from the second thermogravimetric analysis data may include: the starting temperature among multiple second pyrolysis temperatures and the mass change rate corresponding to the starting temperature, the ending temperature among multiple second pyrolysis temperatures and the mass change rate corresponding to the ending temperature, at least one extreme value of the second mass change rate and the temperature corresponding to the at least one extreme value, the intermediate value of two extreme values corresponding to the second mass change rate in two adjacent temperature intervals and the first temperature corresponding to the intermediate value, the intermediate value of two extreme values corresponding to the mass change rate of the second cigarette raw material in two adjacent temperature intervals and the second temperature corresponding to the intermediate value.

[0161] For example, the starting point A1, the ending point A2, the characteristic points B1 - B5 (also known as "inflection points"), the "half-peak points" C1 - C4, and D1 - D4 can be selected together from the DTG curve to obtain the characteristic data for predicting the origin style of tobacco products.

[0162] The following schematically shows the characteristic data (also known as "characteristic parameters") obtained based on these characteristic points in Table 1.

[0163] Table 1

[0164]

[0165] Please continue to refer to Figure 4 , the curve obtained after curve fitting based on the 15 characteristic points A1, A2, B1 - B5, C1 - C4, and D1 - D4 is as shown by the dashed line in Figure 4 . It can be seen that the trend of the curve fitted according to these 15 characteristic points is basically consistent with the actual DTG curve. This indicates that the 30 characteristic data obtained using these 15 characteristic points can quite accurately reflect the pyrolysis characteristics of tobacco leaves during the special decomposition process. Therefore, using these characteristic data can further help accurately predict the origin style of tobacco products.

[0166] In some embodiments, the first chemical composition data of each tobacco product raw material may further include the ratio of the contents of different chemical components among multiple chemical components in each tobacco product raw material. For example, the multiple chemical components may include total nitrogen, nicotine, total sugar, reducing sugar, potassium, and chlorine. The ratio of the contents of different chemical components among the multiple chemical components may include at least one of the potassium-chlorine ratio (i.e., the ratio of the contents of potassium and chlorine), the nitrogen-nicotine ratio (i.e., the ratio of the contents of total nitrogen and nicotine), the sugar-nicotine ratio (i.e., the ratio of the contents of total sugar and nicotine), and the two-sugar ratio (i.e., the ratio of the contents of reducing sugar and total sugar).

[0167] The second chemical composition data may further include a comprehensive ratio determined based on the ratio of the contents of different chemical components among multiple chemical components in each tobacco product raw material and the mass proportion of each tobacco product raw material in the tobacco product.

[0168] For example, a tobacco product contains tobacco leaf A from Yunnan, tobacco leaf B from Fujian, and tobacco leaf C from Henan. And the mass proportion of tobacco leaf A in the tobacco product is a, the mass proportion of tobacco leaf B in the tobacco product is b, and the mass proportion of tobacco leaf C in the tobacco product is c. Taking the potassium-chlorine ratio of the first chemical component data of each tobacco product raw material as an example, assuming that the potassium-chlorine ratio in the first chemical component data of tobacco leaf A is Y1, the potassium-chlorine ratio in the first chemical component data of tobacco leaf B is Y2, and the potassium-chlorine ratio in the first chemical component data of tobacco leaf C is Y3. Taking a as the weight of the potassium-chlorine ratio Y1, taking b as the weight of the potassium-chlorine ratio Y2, and taking c as the weight of the potassium-chlorine ratio Y3, the comprehensive ratio Y corresponding to the potassium-chlorine ratio in the second chemical component data of the tobacco product can be calculated as Y = a×Y1 + b×Y2 + c×Y3.

[0169] In some embodiments, the number of each tobacco product raw material in the tobacco product can be multiple. For example, each tobacco product raw material can include multiple tobacco leaves from the same origin, and the first chemical component data of each tobacco product raw material can include the ratios of the contents of different chemical components in each of these multiple tobacco leaves. In this case, for example, the comprehensive ratio in the second chemical component data can be obtained by referring to the method of obtaining the second chemical component data described above.

[0170] In the above embodiments, by analyzing the ratios of the contents of different chemical components in each tobacco product raw material, the influence of the chemical components of each tobacco product raw material on the overall chemical components of each tobacco product can be comprehensively judged. Thus, the origin of the tobacco product raw material can be predicted more accurately, and further the prediction accuracy of the origin style of the tobacco product can be improved.

[0171] The foregoing introduced the related implementation of predicting the origin style of a tobacco product using a trained prediction model. Next, a training method for a prediction model for predicting the origin style of a tobacco product is further introduced.

[0172] Figure 5 A flowchart showing a training method of a prediction model according to some embodiments of the present disclosure is shown. As Figure 5 shown, for example, the training method of the prediction model can include steps 510 to 530. Among them, the prediction model is used to predict the origin style of a tobacco product.

[0173] In step 510, obtain the thermogravimetric analysis data and chemical component data of each tobacco product raw material sample from multiple tobacco product raw material samples from multiple different origins.

[0174] The thermogravimetric analysis data of each tobacco product raw material sample includes the pyrolysis temperatures of multiple samples in the pyrolysis process of each tobacco product raw material sample and the mass change rate corresponding to each pyrolysis temperature among the multiple pyrolysis temperatures of the samples. The chemical composition data of each tobacco product raw material sample includes the content of each chemical component among multiple chemical components in each tobacco product raw material sample.

[0175] To improve the generalization ability of model training, when selecting training data, it is possible to consider selecting tobacco product raw material samples from multiple origins covering various different flavor styles. In some embodiments, the multiple origins can cover three flavor styles: light flavor, intermediate flavor, and strong flavor. For a similar purpose, when selecting training data, it is also possible to further consider selecting tobacco product raw material samples covering multiple growth parts for each origin. Here, the growth part to which the tobacco product raw material belongs is, for example, the growth part of the tobacco leaf on the tobacco plant, such as the upper part, the middle part, or the lower part. In some embodiments, the tobacco product raw material samples from one or more origins may include upper tobacco leaves, middle tobacco leaves, and lower tobacco leaves. For example, it is possible to select at least one tobacco product raw material sample from a corresponding origin for light flavor, intermediate flavor, and strong flavor respectively, and the selected tobacco product raw material samples for each origin cover upper tobacco leaves, middle tobacco leaves, and lower tobacco leaves, thereby constructing a training data set.

[0176] In this way, the constructed training data set can more comprehensively cover the characteristics of various types of tobacco product raw materials. Using such a training data set to train the prediction model can help the prediction model learn more extensive characteristics of different tobacco product raw materials, improve the generalization ability of the model, and thus contribute to improving the prediction performance of the model.

[0177] In step 520, the characteristic data of each tobacco product raw material sample is determined from the thermogravimetric analysis data of each tobacco product raw material sample.

[0178] The characteristic data of each tobacco product raw material sample includes the sample characteristic temperature among the multiple sample pyrolysis temperatures and the mass change rate corresponding to the sample characteristic temperature.

[0179] The selection method of the characteristic data of the tobacco product raw material sample during the training process of the prediction model is similar to the selection method of the characteristic data during the prediction process using the prediction model. For specific descriptions, reference can be made to the relevant embodiments above. Details are not repeated here.

[0180] In step 530, the prediction model is trained with at least one parameter of the sample characteristic temperature and the mass change rate corresponding to the sample characteristic temperature and the chemical composition data of each tobacco product raw material sample as inputs and the predicted origin of each tobacco product raw material sample as the output until the training end condition is met. The training end condition can be, for example, that the number of training times reaches a specified number and / or the difference between the predicted origin of each tobacco product raw material sample and the actual origin of each tobacco product raw material sample is less than a threshold. The difference between the predicted origin and the actual origin can be characterized by the loss function value of the prediction model.

[0181] It can be understood here that the types of data input into the prediction model during the training of the prediction model are the same as the types of data input into the prediction model during the process of applying the prediction model for prediction.

[0182] For example, if the prediction model is trained with the sample characteristic temperature and the chemical composition data of each tobacco product raw material sample as inputs and the predicted origin of each tobacco product raw material sample as the output, then during the process of using the trained prediction model for prediction, the characteristic temperature in the characteristic data and the second chemical composition data are jointly input into the prediction model to obtain the prediction result of the origin style of the tobacco product.

[0183] For example, if the prediction model is trained with the sample characteristic temperature, the mass change rate corresponding to the sample characteristic temperature, and the chemical composition data of each tobacco product raw material sample as inputs and the predicted origin of each tobacco product raw material sample as the output, then during the process of using the trained prediction model for prediction, the characteristic temperature in the characteristic data, the mass change rate corresponding to the characteristic temperature, and the second chemical composition data are jointly input into the prediction model to obtain the prediction result of the origin style of the tobacco product.

[0184] In some embodiments, the prediction model may include a random forest model. Since the random forest model has good interpretability and is more suitable for large-scale data sets and structured data, using the random forest model for predicting the origin style of tobacco products can obtain better prediction results.

[0185] Figure 6 A flowchart showing a specific example of the training method of the prediction model according to some embodiments of the present disclosure.

[0186] As Figure 6 shown, for example, the training method of the prediction model may include steps 610 to 680. This method can be executed as Figure 5 a specific implementation manner of the method in

[0187] In step 610, tobacco product raw material samples are selected. For example, tobacco product raw material samples (such as tobacco leaf samples) from 8 production areas are selected according to light aroma type, medium aroma type, and strong aroma type, each production area includes at least 30 different tobacco product raw material samples, and the selected tobacco product raw material samples include upper tobacco leaves, middle tobacco leaves, and lower tobacco leaves.

[0188] In step 620, chemical composition data for each tobacco product raw material sample is obtained.

[0189] For example, the chemical composition data of each tobacco product raw material sample is obtained by a continuous flow method. The chemical composition data of each tobacco product raw material sample may include total nitrogen, nicotine, total sugar, reducing sugar, potassium, chlorine, potassium-chlorine ratio, nitrogen-alkali ratio, sugar-alkali ratio and two sugar ratio.

[0190] In step 630, a pyrolysis experiment is performed on each tobacco product raw material sample.

[0191] For example, each tobacco product raw material sample is placed in a constant temperature and humidity chamber for a period of time (e.g., 48 hours). After being taken out and ground, it is sieved and fully mixed. For example, 20 mg of tobacco powder is weighed as a sample and placed in an alumina flat crucible. The sample is heated from room temperature to 873K in a nitrogen atmosphere in a thermal analyzer.

[0192] In step 640, thermogravimetric analysis data is obtained for each tobacco product raw material sample.

[0193] For example, for each tobacco product raw material sample, with a step length of 0.5 K, a total of 801 data between 401.138 K and 801.138 K are taken as the thermogravimetric analysis data of the tobacco product raw material sample.

[0194] In step 650, characteristic data of each tobacco product raw material sample is determined from the thermogravimetric analysis data of each tobacco product raw material sample. For example, 30 characteristic data are selected from the DTG curve to characterize the thermogravimetric analysis data of the tobacco product raw material sample.

[0195] For example, refer to the previous article Figures 2 to 4 In the relevant example, the 30 characteristic data of each tobacco product raw material sample can be determined by selecting the starting point A1, the ending point A2, the characteristic points B1~B5, the "half-peak points" C1~C4 and D1~D4 from the DTG curve of each tobacco product raw material sample, and then determining the horizontal and vertical coordinate values of these 15 characteristic points in the DTG curve.

[0196] In step 660, a training data set is constructed. For example, the training data set is constructed in the form of "feature data - chemical composition data - origin".

[0197] In step 670, a prediction model is trained based on a training data set to obtain a trained prediction model (also referred to as a "style prediction model").

[0198] For example, the prediction model is a random forest model. Using the sample characteristic temperature in the characteristic data of each tobacco product raw material sample, the mass change rate corresponding to the sample characteristic temperature, and the chemical composition data of each tobacco product raw material sample as inputs, and the predicted origin of each tobacco product raw material sample as the output, the random forest model is trained until the difference between the predicted origin of each tobacco product raw material sample and the actual origin of each tobacco product raw material sample is less than a threshold.

[0199] In some embodiments, the characteristic data of the tobacco product and the second chemical composition data used as test samples can be input into the trained prediction model to obtain the prediction result output by the prediction model. For example, the prediction result output by the prediction model can include the probabilities of the tobacco product presenting the styles of various origins.

[0200] For more embodiments of the training method of the prediction model provided in the embodiments of the present disclosure, reference can be made to the description of the method and its embodiments for predicting the origin style of tobacco products in the foregoing text.

[0201] It should be recognized that in Figure 2 , Figure 4 and Figure 5 the examples, the pyrolysis temperature and the number of characteristic points (characteristic temperature and the corresponding mass change rate) are only exemplary.

[0202] The following will exemplarily illustrate, in combination with some embodiments, the construction of a combined formula - origin style database by using the technical solution proposed in the present disclosure for predicting the origin style of tobacco products, so that the target combined formula can be quickly determined with the help of the constructed database when a combined formula design is required.

[0203] Figure 7 The flowchart of the method for determining the target combined formula according to some embodiments of the present disclosure is shown. As Figure 7 shown, for example, the method for determining the target combined formula may include step 710 to step 730.

[0204] In step 710, the first thermogravimetric analysis data and the first chemical composition data of each tobacco product raw material among a plurality of tobacco product raw materials are obtained.

[0205] The first thermogravimetric analysis data includes a plurality of first pyrolysis temperatures of the pyrolysis process of each tobacco product raw material and the first mass change rate of each tobacco product raw material corresponding to each of the plurality of first pyrolysis temperatures. The first chemical composition data includes the content of each chemical component among the various chemical components in each tobacco product raw material.

[0206] For the relevant descriptions of the first thermogravimetric analysis data and the first chemical composition data, reference can be made to the descriptions in the relevant embodiments above. For example Figure 1 the description of step 110 in

[0207] In step 720, for each of the multiple candidate combination formulas based on multiple tobacco product raw materials, steps 721 to 724 are executed to construct a combination formula - origin style database.

[0208] In step 721, based on the first thermogravimetric analysis data and the candidate combination formula, the second thermogravimetric analysis data corresponding to the candidate combination formula of the tobacco product is determined. For example, the second thermogravimetric analysis data includes multiple second pyrolysis temperatures and a second mass change rate corresponding to each of the multiple second pyrolysis temperatures.

[0209] In step 722, based on the first chemical composition data and the candidate combination formula, the second chemical composition data corresponding to the candidate combination formula of the tobacco product is determined. For example, the second chemical composition data includes the content of each chemical component in multiple chemical components.

[0210] In step 723, based on the second thermogravimetric analysis data and the second chemical composition data, the origin style corresponding to the candidate combination formula is predicted using the trained prediction model.

[0211] For the relevant descriptions of predicting the origin style using the trained prediction model, reference can be made to the descriptions in the relevant embodiments above. For example Figure 1 the description of steps 120 - 140 in

[0212] In step 724, the candidate combination formula and the corresponding predicted origin style are stored in the combination formula - origin style database.

[0213] For example, a certain candidate combination formula includes 90% of tobacco leaves from Yunnan and 10% of tobacco leaves from Fujian, and the predicted origin style corresponding to this candidate combination formula is Yunnan. This candidate combination formula and the corresponding predicted origin style are stored as a piece of data in the combination formula - origin style database.

[0214] In step 730, the combination formula corresponding to the target origin style is retrieved from the combination formula - origin style database to determine the target combination formula.

[0215] In some embodiments, the combination formula that meets the first criterion among the retrieved combination formulas is determined as the target combination formula.

[0216] For example, in the combined formula - origin style database, the probabilities of various origin styles presented by each candidate combined formula can be correspondingly stored. Taking the probability of the target origin style being greater than a threshold (e.g., 80%) as the first criterion, the combined formulas that meet this first criterion among the retrieved combined formulas are determined as the target combined formulas. Also for example, there may be multiple combined formulas retrieved according to the target origin style. Taking one or more of the mass ratio, inventory, or year of the tobacco product raw materials among the multiple candidate combined formulas meeting certain conditions as the first criterion, the target combined formula can also be determined.

[0217] In the above - mentioned embodiments, for each of the multiple candidate combined formulas based on multiple tobacco product raw materials, the origin style prediction technical solution of the tobacco product as described above can be used to predict the origin style, and a combined formula - origin style database can be constructed. In the case of needing to design a combined formula corresponding to the target origin style, it is only necessary to retrieve from the combined formula - origin style database to determine the target combined formula.

[0218] In this way, the origin style prediction technical solution of the tobacco product can accurately determine the origin style corresponding to each combined formula. The database constructed accordingly can provide strong data support for the combined formula design. Thus, the determined target combined formula can accurately meet the expected standards in practical applications, and the efficiency and flexibility of the combined formula design are also significantly improved.

[0219] Next, some embodiments are combined to exemplarily illustrate how to design a combined formula and the corresponding effects by using the technical solution for determining the target combined formula of the present disclosure.

[0220] First, construct a combined formula - origin style database according to the following steps 1 - 5.

[0221] Step 1: Select 434 tobacco product raw material samples from 8 origins, namely Origin A, Origin B, Origin C, Origin D, Origin E, Origin F, Origin G, and Origin H.

[0222] Step 2: Use the continuous - flow method to measure the 10 chemical composition data of each of the 434 tobacco product raw material samples. For example, these 10 chemical composition data include total nitrogen, nicotine, total sugar, reducing sugar, potassium, chlorine, potassium - to - chlorine ratio, nitrogen - to - base ratio, sugar - to - base ratio, and disaccharide ratio.

[0223] Step 3: For each of the 434 tobacco product raw material samples, select the corresponding tobacco powder sample for thermogravimetric testing. In a thermal analyzer, heat the tobacco powder sample from room temperature to 873 K at a certain heating rate (10 K / min) under a nitrogen atmosphere (carrier gas flow rate is 100 mL / min), and test the mass change of the tobacco powder sample during heating to obtain thermogravimetric data (i.e., the data corresponding to the TG curve). Derivative calculation is performed on the thermogravimetric data to obtain 801 thermogravimetric analysis data (i.e., the data corresponding to the DTG curve).

[0224] Construct a data set in the form of a sample pair of "characteristic data - chemical composition data - origin", and use, for example, the random forest algorithm for model training to obtain a trained prediction model (hereinafter also referred to as the "random forest model").

[0225] Step 4: Construct combined formulas in the ways of different quantities of tobacco product raw materials, different origins of tobacco product raw materials, and different ratios among tobacco product raw materials. Taking the construction of a combined formula using 2 tobacco product raw materials as an example, there are 9 proportion relationships such as 0.9:0.1, 0.8:0.2, 0.7:0.3, 0.6:0.4, 0.5:0.5, 0.4:0.6, 0.3:0.7, 0.2:0.8, 0.1:0.9, so that 252 combined formulas can be constructed. By analogy, a total of 19440 combined formulas can be constructed using 8 tobacco product raw materials.

[0226] Step 5: For each of the 19440 combined formulas, construct a combined formula - origin style database in the way described in, for example, step 720 above.

[0227] For example, use the trained prediction model to predict the origin style corresponding to each combined formula, and store each combined formula and the corresponding predicted origin style in the combined formula - origin style database.

[0228] In some embodiments, for each combined formula in the combined formula - origin style database, the probabilities of each origin style presented by this combined formula can be correspondingly stored.

[0229] In some embodiments, the combined formula - origin style database can also store tobacco leaf identification information such as the inventory quantity and year of each tobacco product raw material in each leaf group formula.

[0230] However, assume that it is required to design a combined formula presenting the style of origin D, wherein the mass proportion of the tobacco leaves of origin D in the tobacco product is between 20% and 30%; the mass proportion of the tobacco leaves of origin C is 10%; the mass proportion of the tobacco leaves of origin B with rich inventory is not less than 40%; and the tobacco leaves of origin A, origin E, origin G, and origin H with tight inventory are not used.

[0231] Based on the above requirements, among the 19,440 combined formulations stored in the combined formulation - origin style database, 7,573 combined formulations with a predicted origin style of "Origin D" can be screened out. Then, further screening is carried out under the condition that the proportion of tobacco leaves from Origin A, Origin E, Origin G, and Origin H in the leaf group is 0%. As a result, 111 combined formulations meet the requirements. Further, by restricting the proportion of tobacco leaves from Origin D to be between 20% and 30%, 30 combined formulations meet the requirements. After that, by restricting the proportion of tobacco leaves from Origin C to be 10% and the proportion of tobacco leaves from Origin B to be not less than 40%, finally, 1 combined formulation meets the requirements. The selected combined formulations are shown in Table 2.

[0232] Table 2

[0233]

[0234] Figure 8 It shows the probability distribution of each origin style corresponding to the combined formulation after inputting the characteristic data corresponding to the combined formulation shown in Table 2 into the random forest model.

[0235] From Figure 8 it can be seen that the probability of the combined formulation shown in Table 2 presenting the style of Origin D is the largest, indicating that the tobacco product obtained based on the combined formulation shown in Table 2 will present the style of Origin D.

[0236] Subsequently, a single - grade tobacco leaf D - 1 from Origin D with a medium - upper quality level and a relatively distinct origin style is selected as the target tobacco leaf, and its thermo - analysis spectrum is used as the target spectrum. Tobacco leaves from Origins B, C, and D are fitted according to the combined formulation shown in Table 2. From the tobacco product schemes obtained by fitting, the scheme with the smallest difference degree between the thermo - analysis spectrum and the target spectrum is selected for blending to obtain the tobacco product Z corresponding to the combined formulation shown in Table 2. After that, the tobacco product Z is compared with the tobacco leaf D - 1 from Origin D in terms of thermo - analysis spectrum, chemical composition, and sensory evaluation.

[0237] Figures 9A to 9C It shows the normalized root - mean - square error (NRMSE) between the target tobacco leaf D - 1 and other tobacco leaves D - 2, D - 3 from Origin D, as well as the tobacco product Z.

[0238] From Figures 9A to 9C it can be seen that among the other tobacco leaf samples from Origin D, the NRMSE value between tobacco leaf D - 2 and the target tobacco leaf D - 1 is the smallest, which is 2.5%; the NRMSE value between tobacco leaf D - 3 and the target tobacco leaf D - 1 is the largest, which is 4.9%. The NRMSE value between the tobacco product Z and the target tobacco leaf D - 1 is 2.6%, which is relatively close to the minimum NRMSE value of 2.5% and is far from the maximum NRMSE value of 4.9%.

[0239] This indicates that the combined formula corresponding to tobacco product Z can effectively simulate the characteristics of target tobacco leaf D-1, verifying the feasibility and effectiveness of the combined formula determined in accordance with the present disclosure.

[0240] Table 3 shows the comparison of the chemical component data of tobacco product Z, tobacco leaves D-1, D-2, and D-3.

[0241] Comparison of Chemical Component Data in Table 3

[0242]

[0243] It can be seen from Table 3 that each data in the chemical component data of tobacco product Z is within the range of the chemical component data of the tobacco leaves from origin D. This indicates that tobacco product Z has a high degree of consistency with the tobacco leaves from origin D in terms of chemical composition, thus verifying the rationality of the combined formula corresponding to tobacco product Z.

[0244] After inputting the characteristic data corresponding to tobacco product Z, tobacco leaves D-1, D-2, and D-3 into the random forest model, the obtained probability distribution is shown in Table 5.

[0245] Table 4 shows the probability distribution of the styles of each origin presented by tobacco product Z, tobacco leaves D-1, D-2, and D-3.

[0246] Probability Distribution of Styles of Each Origin in Table 4

[0247]

[0248]

[0249] It can be seen from Table 4 that the probability of tobacco product Z presenting the style of origin D is the largest. Combining with the combined formula shown in Table 2, although the proportion of the tobacco leaves from origin D in tobacco product Z is relatively low, it can finally present the style of origin D. This also verifies the feasibility of the combined formula determined in accordance with the present disclosure.

[0250] In addition, in the sensory evaluation, tobacco product Z also has relatively similar style characteristics to target tobacco leaf D-1. Moreover, some defects (such as off-flavors) existing in target tobacco leaf D-1 are effectively balanced in tobacco product Z, and tobacco product Z has better fragrance and taste characteristics, meeting the design requirements.

[0251] That is to say, for example, in the case of designing a combined formula with the style of origin D, compared with directly using a large amount of tobacco leaves from origin D for formula design to obtain the corresponding tobacco product, adopting the method of the present disclosure to determine the target combined formula presenting the style of origin D, and then using multiple different tobacco product raw materials to form the corresponding tobacco product based on the determined target combined formula can reduce the off-odor in the finally obtained tobacco product. In this way, the obtained tobacco product can not only present the style of origin D, but also reduce the off-odor unique to the tobacco leaves of origin D, that is, it has better sensory characteristics.

[0252] In summary, the combined formula determined by adopting the method of the present disclosure can effectively screen out a tobacco product that is highly consistent with the characteristics of origin D in terms of thermoanalysis spectrum, chemical composition and sensory characteristics, while significantly improving the adverse characteristics (such as off-odor) of the tobacco leaves of origin D, achieving better quality performance.

[0253] Figure 10 The block diagram showing some embodiments of the origin style prediction device for the tobacco product of the present disclosure.

[0254] As Figure 10 shown, the origin style prediction device 1000 of the tobacco product includes an acquisition module 1001, a determination module 1002 and a prediction module 1003.

[0255] The acquisition module 1001 is configured to acquire the first thermogravimetric analysis data and the first chemical composition data of each tobacco product raw material among multiple tobacco product raw materials of the tobacco product. The first thermogravimetric analysis data includes multiple first pyrolysis temperatures of the pyrolysis process of each tobacco product raw material and the first mass change rate of each tobacco product raw material corresponding to each first pyrolysis temperature among the multiple first pyrolysis temperatures. The first chemical composition data includes the content of each chemical component among multiple chemical components in each tobacco product raw material.

[0256] The determination module 1002 is configured to determine the second thermogravimetric analysis data of the tobacco product based on the first thermogravimetric analysis data and the combined formula of the tobacco product, where the second thermogravimetric analysis data includes multiple second pyrolysis temperatures and the second mass change rate corresponding to each second pyrolysis temperature among the multiple second pyrolysis temperatures; and determine the second chemical composition data of the tobacco product based on the first chemical composition data and the combined formula, where the second chemical composition data includes the content of each chemical component among multiple chemical components.

[0257] The prediction module 1003 is configured to predict the origin style of the tobacco product based on the second thermogravimetric analysis data and the second chemical composition data of the tobacco product by using the trained prediction model.

[0258] In some embodiments, the origin style prediction device 1000 of the tobacco product may further include other modules that perform other operations in the related embodiments of the method for predicting the origin style of the tobacco product described above.

[0259] Figure 11 The block diagram showing some embodiments of the device for determining the target combined formula of the present disclosure.

[0260] As Figure 11 As shown, the device 1100 for determining the target combined formula includes an acquisition module 1101, a database construction module 1102, and a determination module 1103.

[0261] The acquisition module 1101 is configured to acquire the first thermogravimetric analysis data and the first chemical composition data of each tobacco product raw material among a plurality of tobacco product raw materials. The first thermogravimetric analysis data includes a plurality of first pyrolysis temperatures of the pyrolysis process of each tobacco product raw material and the first mass change rate of each tobacco product raw material corresponding to each first pyrolysis temperature among the plurality of first pyrolysis temperatures. The first chemical composition data includes the content of each chemical component among the various chemical components in each tobacco product raw material.

[0262] The database construction module 1102 is configured to perform the following steps for each of the plurality of combined formulas based on the plurality of tobacco product raw materials to predict the origin style corresponding to the combined formula and construct a combined formula - origin style database. These steps include: determining the second thermogravimetric analysis data corresponding to the combined formula based on the first thermogravimetric analysis data and the combined formula. The second thermogravimetric analysis data includes a plurality of second pyrolysis temperatures and the second mass change rate corresponding to each second pyrolysis temperature among the plurality of second pyrolysis temperatures; determining the second chemical composition data corresponding to the combined formula based on the first chemical composition data and the combined formula. The second chemical composition data includes the content of each chemical component among the various chemical components; predicting the origin style using the trained prediction model based on the second thermogravimetric analysis data and the second chemical composition data; and storing the combined formula and the corresponding predicted origin style into the combined formula - origin style database.

[0263] The determination module 1103 is configured to retrieve the combined formula corresponding to the target origin style from the combined formula - origin style database to determine the target combined formula.

[0264] In some embodiments, the device 1100 for determining the target combined formula may further include other modules that perform other operations in the related embodiments of the method for determining the target combined formula described above.

[0265] Figure 12 The block diagram showing some embodiments of the electronic device of the present disclosure.

[0266] AsFigure 12 As shown, the electronic device 1200 of this embodiment includes: a memory 1201 and a processor 1202 coupled to the memory 1201. The processor 1202 is configured to execute the method in any one of the embodiments of the present disclosure based on the instructions stored in the memory 1201.

[0267] Among them, the memory 1201 may include, for example, a system memory, a fixed non-volatile storage medium, etc. The system memory stores, for example, an operating system, application programs, a boot loader, a database, and other programs.

[0268] In some embodiments, the electronic device 1200 may be used as a device for predicting the origin style of a tobacco product that executes the operations of any one of the above embodiments. In other embodiments, the electronic device 1200 may be used as a device for determining a target combined formula that executes the operations of any one of the above embodiments.

[0269] Figure 13 The block diagram of some other embodiments of the electronic device of the present disclosure is shown.

[0270] As Figure 13 shown, the electronic device 1300 of this embodiment includes: a memory 1301 and a processor 1302 coupled to the memory 1301. The processor 1302 is configured to execute the method in any one of the foregoing embodiments based on the instructions stored in the memory 1301.

[0271] The memory 1301 may include, for example, a system memory, a fixed non-volatile storage medium, etc. The system memory stores, for example, an operating system, application programs, a boot loader, and other programs.

[0272] The electronic device 1300 may further include an input / output interface 1303, a network interface 1304, a storage interface 1305, etc. These interfaces 1303, 1304, 1305 and the memory 1301 and the processor 1302 may be connected through a bus 1306, for example. Among them, the input / output interface 1303 provides a connection interface for input / output devices such as a display, a mouse, a keyboard, a touch screen, a microphone, and a speaker. The network interface 1304 provides a connection interface for various networking devices. The storage interface 1305 provides a connection interface for external storage devices such as an SD card and a USB flash drive.

[0273] In some embodiments, the electronic device 1300 may be used as a device for predicting the origin style of a tobacco product that executes the operations of any one of the above embodiments. In other embodiments, the electronic device 1300 may be used as a device for determining a target combined formula that executes the operations of any one of the above embodiments.

[0274] Embodiments of the present disclosure also provide a computer-readable storage medium, including computer program instructions, which, when executed by a processor, implement the method of any one of the above embodiments.

[0275] Embodiments of the present disclosure also provide a computer program product, including a computer program, which, when executed by a processor, implement the method of any one of the above embodiments.

[0276] Those skilled in the art should understand that the embodiments of the present disclosure can be provided as a method, a system, or a computer program product. Therefore, the present disclosure can take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present disclosure can take the form of a computer program product implemented on one or more computer-usable non-transitory storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0277] So far, the technical solutions for predicting the origin style of tobacco products and determining the target combination formula according to the present disclosure have been described in detail. To avoid obscuring the concept of the present disclosure, some details well known in the art are not described. Those skilled in the art can fully understand how to implement the technical solutions disclosed herein based on the above description.

[0278] The methods and systems of the present disclosure can be implemented in many ways. For example, the methods and systems of the present disclosure can be implemented by software, hardware, firmware, or any combination of software, hardware, and firmware. The above order of steps for the method is only for illustration, and the steps of the method of the present disclosure are not limited to the specific order described above, unless otherwise specifically stated. In addition, in some embodiments, the present disclosure can also be implemented as a program recorded in a recording medium, and these programs include machine-readable instructions for implementing the method according to the present disclosure. Therefore, the present disclosure also covers a recording medium storing a program for executing the method according to the present disclosure.

[0279] Although some specific embodiments of the present disclosure have been described in detail by way of examples, those skilled in the art should understand that the above examples are only for illustration and not for limiting the scope of the present disclosure. Those skilled in the art should understand that the above embodiments can be modified without departing from the scope and spirit of the present disclosure. The scope of the present disclosure is defined by the appended claims.

Claims

1. A method for predicting the origin style of a tobacco product, the tobacco product comprising a combination of a plurality of tobacco product raw materials, the origin style prediction method comprising: Obtaining first thermogravimetric analysis data and first chemical composition data for each tobacco product raw material among the plurality of tobacco product raw materials, the first thermogravimetric analysis data including a plurality of first pyrolysis temperatures of the pyrolysis process of each tobacco product raw material and a first mass change rate of each tobacco product raw material corresponding to each of the plurality of first pyrolysis temperatures, and the first chemical composition data including the content of each chemical component among the various chemical components of each tobacco product raw material; Determining second thermogravimetric analysis data of the tobacco product based on the first thermogravimetric analysis data and the combination formula of the plurality of tobacco product raw materials in the tobacco product, the second thermogravimetric analysis data including a plurality of second pyrolysis temperatures and a second mass change rate corresponding to each of the plurality of second pyrolysis temperatures; Determining second chemical composition data of the tobacco product based on the first chemical composition data and the combination formula, the second chemical composition data including the content of each chemical component among the various chemical components; And Predicting the origin style of the tobacco product using a trained prediction model based on the second thermogravimetric analysis data and the second chemical composition data of the tobacco product.

2. The origin style prediction method according to claim 1, wherein, The determining the second thermogravimetric analysis data of the tobacco product based on the first thermogravimetric analysis data and the combination formula of the tobacco product includes: Taking the mass proportion of each tobacco product raw material in the tobacco product in the combination formula as the weight of the first thermogravimetric analysis data, and calculating a first weighted sum of the first thermogravimetric analysis data; Determining the first weighted sum as the second thermogravimetric analysis data.

3. The origin style prediction method according to claim 1, wherein, The determining the second chemical composition data of the tobacco product based on the first chemical composition data and the combination formula includes: Taking the mass proportion of each tobacco product raw material in the tobacco product in the combination formula as the weight of the first chemical composition data, and calculating a second weighted sum of the first chemical composition data; Determining the second weighted sum as the second chemical composition data.

4. The origin style prediction method according to any one of claims 1-3, wherein, The predicting the origin style of the tobacco product using a trained prediction model based on the second thermogravimetric data and the second chemical composition data of the tobacco product includes: Determining characteristic data from the second thermogravimetric analysis data, the characteristic data including characteristic temperatures determined from the plurality of second pyrolysis temperatures and mass change rates corresponding to the characteristic temperatures; Predicting the origin style of the tobacco product using a trained prediction model based on at least one parameter among the characteristic temperature and the mass change rate corresponding to the characteristic temperature and the second chemical composition data.

5. The origin style prediction method according to claim 4, wherein, The plurality of second pyrolysis temperatures form a temperature range, and the mass change rate corresponding to the characteristic temperature includes an extreme value of the second mass change rate within the temperature range.

6. The origin style prediction method according to claim 4, wherein, The plurality of second pyrolysis temperatures form adjacent first temperature range and second temperature range, The mass change rate corresponding to the characteristic temperature includes the intermediate value between the first extreme value of the second mass change rate within the first temperature range and the second extreme value of the second mass change rate within the second temperature range. The characteristic temperature includes the first temperature corresponding to the intermediate value in the second thermogravimetric analysis data. The temperature corresponding to the first extreme value is less than the temperature corresponding to the second extreme value, and the first temperature is greater than the temperature corresponding to the first extreme value and less than the temperature corresponding to the second extreme value.

7. The origin style prediction method according to claim 6, wherein, The characteristic temperature includes the second temperature corresponding to the intermediate value in the second thermogravimetric analysis data. The second temperature is less than the temperature corresponding to the first extreme value or greater than the temperature corresponding to the second extreme value.

8. The origin style prediction method according to claim 4, wherein, The characteristic temperature includes the starting temperature or the ending temperature among the multiple second pyrolysis temperatures.

9. The origin style prediction method according to any one of claims 1-3, wherein, The first chemical composition data includes the ratio of the contents of different chemical components among the multiple chemical components of each tobacco product raw material, and the second chemical composition data further includes the comprehensive ratio determined based on the ratio and the mass proportion of each tobacco product raw material in the tobacco product in the combined formula.

10. The origin style prediction method according to any one of claims 1-3, wherein, The prediction model is trained in the following manner: Obtain the thermogravimetric analysis data and chemical composition data of each tobacco product raw material sample from multiple tobacco product raw material samples from multiple different origins. The thermogravimetric analysis data of each tobacco product raw material sample includes multiple sample pyrolysis temperatures of the pyrolysis process of each tobacco product raw material sample and the mass change rate corresponding to each sample pyrolysis temperature among the multiple sample pyrolysis temperatures. The chemical composition data of each tobacco product raw material sample includes the content of each chemical component among the multiple chemical components of each tobacco product raw material sample; Determine the characteristic data of each tobacco product raw material sample from the thermogravimetric analysis data of each tobacco product raw material sample. The characteristic data of each tobacco product raw material sample includes the sample characteristic temperature among the multiple sample pyrolysis temperatures and the mass change rate corresponding to the sample characteristic temperature; and Use at least one parameter of the sample characteristic temperature and the mass change rate corresponding to the sample characteristic temperature and the chemical composition data of each tobacco product raw material sample as the input, and the predicted origin of each tobacco product raw material sample as the output to train the prediction model until the training end condition is met.

11. The origin style prediction method according to claim 10, wherein, The prediction model includes a random forest model.

12. The origin style prediction method according to any one of claims 1-3, wherein, The multiple chemical components include at least one of total nitrogen, nicotine, total sugar, reducing sugar, potassium, and chlorine.

13. A method for determining the target combined formula of a tobacco product, the tobacco product comprising a combination of multiple tobacco product raw materials, the method comprising: Obtain the first thermogravimetric analysis data and the first chemical composition data of each tobacco product raw material among the multiple tobacco product raw materials. The first thermogravimetric analysis data includes multiple first pyrolysis temperatures of the pyrolysis process of each tobacco product raw material and the first mass change rate of each tobacco product raw material corresponding to each of the multiple first pyrolysis temperatures. The first chemical composition data includes the content of each chemical component among the multiple chemical components of each tobacco product raw material; For each of the multiple candidate combination formulas based on the multiple tobacco product raw materials, perform the following steps to construct a combination formula - origin style database: Based on the first thermogravimetric analysis data and the candidate combination formula, determine the second thermogravimetric analysis data corresponding to the candidate combination formula. The second thermogravimetric analysis data includes multiple second pyrolysis temperatures and the second mass change rate corresponding to each of the multiple second pyrolysis temperatures; Based on the first chemical composition data and the candidate combination formula, determine the second chemical composition data corresponding to the candidate combination formula. The second chemical composition data includes the content of each chemical component among the multiple chemical components; Based on the second thermogravimetric analysis data and the second chemical composition data, use the trained prediction model to predict the origin style corresponding to the candidate combination formula; and Store the candidate combination formula and the corresponding origin style into the combination formula - origin style database; Retrieve the combination formula corresponding to the target origin style from the combination formula - origin style database to determine the target combination formula.

14. The method according to claim 13, further comprising: Determine the combination formula that meets the first criterion among the retrieved combination formulas as the target combination formula.

15. An apparatus for predicting the origin style of a tobacco product, the tobacco product comprising a combination of multiple tobacco product raw materials, the apparatus comprising: An acquisition module configured to obtain the first thermogravimetric analysis data and the first chemical composition data of each tobacco product raw material among the multiple tobacco product raw materials. The first thermogravimetric analysis data includes multiple first pyrolysis temperatures of the pyrolysis process of each tobacco product raw material and the first mass change rate of each tobacco product raw material corresponding to each of the multiple first pyrolysis temperatures. The first chemical composition data includes the content of each chemical component among the multiple chemical components of each tobacco product raw material; A determination module configured to determine the second thermogravimetric analysis data of the tobacco product based on the first thermogravimetric analysis data and the combination formula of the multiple tobacco product raw materials in the tobacco product. The second thermogravimetric analysis data includes multiple second pyrolysis temperatures and the second mass change rate corresponding to each of the multiple second pyrolysis temperatures; and determine the second chemical composition data of the tobacco product based on the first chemical composition data and the combination formula. The second chemical composition data includes the content of each chemical component among the multiple chemical components; A prediction module, configured to predict the origin style of the tobacco product by using a trained prediction model based on the second thermogravimetric analysis data and the second chemical composition data of the tobacco product.

16. An apparatus for determining a target combined formula of a tobacco product, the tobacco product comprising a combination of a plurality of tobacco product raw materials, the apparatus comprising: An acquisition module, configured to acquire first thermogravimetric analysis data and first chemical composition data of each tobacco product raw material among the plurality of tobacco product raw materials, the first thermogravimetric analysis data including a plurality of first pyrolysis temperatures of the pyrolysis process of each tobacco product raw material and a first mass change rate of each tobacco product raw material corresponding to each of the plurality of first pyrolysis temperatures, and the first chemical composition data including the content of each chemical component among the plurality of chemical components of each tobacco product raw material; A database construction module, configured to perform the following steps for each of a plurality of candidate combined formulas based on the plurality of tobacco product raw materials to construct a combined formula - origin style database: Based on the first thermogravimetric analysis data and the candidate combined formula, determine second thermogravimetric analysis data corresponding to the candidate combined formula, the second thermogravimetric analysis data including a plurality of second pyrolysis temperatures and a second mass change rate corresponding to each of the plurality of second pyrolysis temperatures; Based on the first chemical composition data and the candidate combined formula, determine second chemical composition data corresponding to the candidate combined formula, the second chemical composition data including the content of each chemical component among the plurality of chemical components; Based on the second thermogravimetric analysis data and the second chemical composition data, use a trained prediction model to predict the origin style corresponding to the candidate combined formula; And Store the candidate combined formula and the corresponding origin style into the combined formula - origin style database; A determination module, configured to retrieve a combined formula corresponding to a target origin style from the combined formula - origin style database to determine a target combined formula.

17. An electronic device, comprising: A memory; And A processor coupled to the memory, the processor being configured to execute the method for predicting the origin style of a tobacco product according to any one of claims 1 - 12 or the method for determining a target combined formula of a tobacco product according to any one of claims 13 - 14 based on instructions stored in the memory.

18. A computer - readable storage medium, having computer instructions stored thereon, which when executed by a processor implement the method for predicting the origin style of a tobacco product according to any one of claims 1 - 12 or the method for determining a target combined formula of a tobacco product according to any one of claims 13 - 14.

19. A computer program product, comprising instructions, which when executed by a processor cause the processor to execute the method for predicting the origin style of a tobacco product according to any one of claims 1 - 12 or the method for determining a target combined formula of a tobacco product according to any one of claims 13 - 14.

Images