Cigarette formula design method, device and storage medium based on main ingredients and style quality

Abstract

The present invention discloses a cigarette formula design method, device and storage medium based on main components and style quality, wherein the method includes: obtaining the flavor type, conventional chemical components, style value, quality value, price cost, inventory, production year, origin and grade data of single-grade tobacco leaves to be used; performing preliminary screening by setting cost, feed amount and tobacco production year constraints to form a candidate tobacco set; dividing the candidate tobacco set into four subsets according to the flavor type of tobacco leaves; setting grade quantity constraints; expressing the formula design target as a planning problem; based on the grade quantity constraints and the planning problem, selecting the grade quantity of tobacco leaves of each flavor type in the four subsets and combining them into a formula; optimizing the formula ratio to meet the preset formula cost and preset feed amount constraints to obtain the final tobacco leaf group formula. The tobacco leaf group formula design based on non-artificial experience is realized, and the efficiency of tobacco leaf group formula design is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of cigarette and cigarette product quality detection, and in particular to a cigarette formula design method, device and storage medium based on main components and style quality. Background Art

[0002] Cigarette formula is the foundation and core of tobacco production. Cigarette formula is made by mixing a variety of different single-grade tobacco leaves in a certain proportion. Usually, the finished cigarette formula is made by mixing 15 to 30 different single-material tobaccos in a certain proportion. In the process of cigarette production, cigarette formula is an important part of maintaining the stability of cigarette brand quality. Traditional cigarette formula maintenance is a complicated task, which requires sensory evaluation and measuring instruments to comprehensively evaluate whether the sensory and smoke indicators of the replaced cigarette formula meet the requirements. This usually requires the evaluation personnel to have rich experience in evaluation and long-term training and accumulation of practical experience. The health and mental state of the evaluation personnel also have a great impact on the evaluation results. This method of relying on expert evaluation and analysis and testing is inefficient, time-consuming and costly. Therefore, it is necessary and urgent to develop intelligent maintenance technology and means for cigarette formula.

[0003] Over the years, cigarette companies have accumulated a large amount of basic data and R&D data, which are very valuable, but they are scattered, poorly integrated, insufficiently correlated, and poorly consistent. In recent years, with the widespread application and development of machine learning, data mining, and artificial intelligence in various fields, using these methods to mine and process data can reveal the huge value it contains, thereby improving the understanding of the inherent regularity of tobacco production, providing support for the design of cigarette leaf group formulas, and realizing the digitalization and scientificization of cigarette product design. This has important practical significance for cigarette companies to scientifically and efficiently design and produce cigarette products, avoid duplication of labor, improve work efficiency, enhance the stability of cigarette production, thereby improving market competitiveness, and promoting the sustainable development of enterprises.

[0004] The present invention aims to restrict the conventional chemical components (total sugar, reducing sugar, total nitrogen, total alkali, chlorine, potassium) and style quality of the target formula, and recommend several leaf group formula lists that meet the constraints, so as to achieve tobacco leaf group formula design based on non-artificial experience and improve the efficiency of tobacco leaf group formula design. Summary of the invention

[0005] In view of the deficiencies in the prior art, the present invention provides a method, device and storage medium for designing cigarette formulas based on main ingredients and style quality, aiming to realize the design of cigarette leaf group formulas based on non-artificial experience and improve the efficiency of cigarette leaf group formula design.

[0006] In a first aspect, a method for designing a cigarette formula based on main ingredients and style quality is provided, comprising:

[0007] S1: Obtain the aroma, conventional chemical composition, style value, quality value, price cost, inventory, production year, origin and grade data of the single-grade tobacco leaves to be used;

[0008] S2: Preliminary screening is performed on all single-grade tobacco leaves to be used by setting constraints based on preset formula costs, preset feed amounts, and tobacco leaf production year data to form a candidate tobacco leaf set;

[0009] S3: Divide the candidate tobacco leaf set into four subsets according to the aroma type of tobacco leaves: C 清 , C 浓 , C 中 , C 进 Among them, C 清 represents the candidate set of light-fragrant tobacco leaves, C 浓 represents the candidate tobacco leaf set of Luzhou-flavor type, C 中 represents the candidate tobacco leaf set of intermediate aroma, C 进 represents the set of candidate tobacco leaves for import;

[0010] S4: Set the upper limit of the total number of tobacco leaves used in the recipe and the upper limit of the number of tobacco leaves of each flavor type used;

[0011] S5: Formulate the formulation design objective as a planning problem: min{f(t)}=α∑|t i -y i |+β∑|t k -z k |; where min{f(t)} represents the objective function, t i Indicates the preset design target of the conventional chemical composition content of the formula, t k Represents the preset formula style value and quality value design target; y i Indicates the conventional chemical composition content of the designed formula, z k represents the style value and quality value of the designed formula; a represents the weight of the conventional chemical component content, β represents the weight of the style value and quality value; i takes an integer in (0, N], N is the total number of conventional chemical components, and k takes 1 or 2, representing the style and quality respectively;

[0012] S6: Based on the constraints in step S4 and the planning problem in step S5, 清 , C 浓 , C 中 , C 进 In the four subsets, single-grade tobacco leaves of various flavors whose conventional chemical component contents, style values, and quality values ​​are close to the corresponding design targets are selected, respectively N 清 N浓 N 中 N 进 , combined into a formula P; where N 清 Indicates the number of grades of light-fragrant tobacco leaves used in the recipe, N 浓 Indicates the number of grades of strong-flavor tobacco leaves used in the recipe, N 中 Indicates the number of intermediate-flavor tobacco leaves used in the recipe, N 进 Indicates the quantity of imported tobacco grades used in the recipe;

[0013] S7: Based on the Monte Carlo method, the proportion of each tobacco leaf in the formula P is optimized to meet the preset formula cost and preset feed amount constraints, and the final tobacco leaf group formula is obtained.

[0014] Furthermore, the conventional chemical components of the single-grade tobacco leaves to be used in step S1 include the contents of total sugar, reducing sugar, total nitrogen, total alkali, chlorine and potassium.

[0015] Furthermore, the style value and quality value of the single-grade tobacco leaves to be used in step S1 are obtained through manual evaluation.

[0016] Furthermore, the flavor of the single-grade tobacco leaves to be used in step S1 is obtained by the following method:

[0017] The sensory evaluation of the single-grade tobacco leaves to be used mainly includes the scores of the four aroma notes of the single-grade tobacco leaves to be used, namely, fresh sweet aroma, honey sweet aroma, mellow sweet aroma and burnt sweet aroma. Combined with the regional information of tobacco production areas, the single-grade tobacco leaves to be used are classified as follows according to the evaluation results:

[0018] In the evaluation results, the tobacco leaves with the highest score for light sweet aroma are defined as light aroma tobacco leaves; in the evaluation results, the tobacco leaves with the highest score for burnt sweet aroma are defined as strong aroma tobacco leaves; in the evaluation results, the tobacco leaves with the highest score for honey sweet aroma or mellow sweet aroma are defined as medium aroma tobacco leaves; and tobacco leaves produced in foreign countries are defined as imported tobacco leaves.

[0019] Furthermore, in step S2, constraints are set for all single-grade tobacco leaves to be used by presetting the formula cost, tobacco leaf inventory, and tobacco leaf production year data. The constraints specifically include:

[0020] The production year of the required single-grade tobacco leaf x is manually set; the unit price of the required single-grade tobacco leaf x×a<the preset formula cost; the inventory of the required single-grade tobacco leaf x>the preset feed quantity×b; wherein a and b are both empirical parameters.

[0021] Furthermore, the value range of a is [10, 50], and the value range of b is [0.01, 0.2].

[0022] Furthermore, in step S4, the upper limit of the total grade of tobacco leaves used in the recipe and the upper limit of the grade of tobacco leaves of each flavor type are set, and the constraints specifically include:

[0023] N 清 +N 浓 +N 中 +N 进 ≤N;N 清 ≤ Artificially set the upper limit of the number of light-fragrant tobacco grades, N 浓 ≤ Artificially set the upper limit of the number of grades of strong-flavor tobacco leaves, N 中 ≤ Artificially set the upper limit of the number of intermediate-flavor tobacco leaves, N 进 ≤Manually set the upper limit of the number of imported tobacco leaf grades; where N is the preset upper limit of the total number of grades.

[0024] Furthermore, the step S7 specifically includes:

[0025] Randomly generate n groups of ratio data and assign them to the formula P, where n is a preset value;

[0026] If each set of ratio data cannot make the formula P meet the preset formula cost and preset feed amount constraints, then the n sets of ratio data are discarded, and n sets of ratio data are randomly generated again, and it is determined whether each set of ratio data makes the formula P meet the preset formula cost and preset feed amount constraints; otherwise, for the ratio data that meet the preset formula cost and preset feed amount constraints, a group is averaged or randomly selected to assign the formula P to obtain the final cigarette leaf group formula.

[0027] In a second aspect, a device for designing cigarette formula based on main ingredients and style quality is provided, comprising:

[0028] A data acquisition module is used to obtain the flavor, conventional chemical composition, style value, quality value, price cost, inventory, production year, origin and grade data of the single-grade tobacco leaves to be used;

[0029] The initial screening module is used to perform preliminary screening on all the single-grade tobacco leaves to be used by setting constraints based on the preset formula cost, preset feed amount, and tobacco leaf production year data to form a candidate tobacco leaf set;

[0030] The candidate tobacco leaf set division module is used to divide the candidate tobacco leaf set into four subsets according to the flavor of the tobacco leaves: C 清 , C 浓 , C 中 , C 进 Among them, C 清 represents the candidate set of light-fragrant tobacco leaves, C 浓 represents the candidate tobacco leaf set of Luzhou-flavor type, C 中 represents the candidate tobacco leaf set of intermediate aroma, C进 represents the set of candidate tobacco leaves for import;

[0031] The grade quantity constraint module is used to set the upper limit of the total grade quantity of tobacco leaves used in the formula and the upper limit of the grade quantity of tobacco leaves of each flavor type;

[0032] Planning module, used to express the recipe design goal as a planning problem: min{f(t)}=α∑|t i -y i |+β∑|t k -z k |; where min{f(t)} represents the objective function, t i Indicates the preset design target of the conventional chemical composition content of the formula, t k Represents the preset formula style value and quality value design target; y i Indicates the conventional chemical composition content of the designed formula, z k represents the style value and quality value of the designed formula; α represents the weight of the conventional chemical component content, β represents the weight of the style value and quality value; i takes an integer in (0, N], N is the total number of conventional chemical components, and k takes 1 or 2, representing style and quality respectively;

[0033] The recipe generation module is used to generate the planning problem based on the constraints set by the level quantity constraint module and the planning module. 清 , C 浓 , C 中 , C 进 In the four subsets, single-grade tobacco leaves of various flavors whose conventional chemical component contents, style values, and quality values ​​are close to the corresponding design targets are selected, respectively N 清 N 浓 N 中 N 进 , combined into a formula P; where N 清 Indicates the number of grades of light-fragrant tobacco leaves used in the recipe, N 浓 Indicates the number of grades of strong-flavor tobacco leaves used in the recipe, N 中 Indicates the number of intermediate-flavor tobacco leaves used in the recipe, N 进 Indicates the quantity of imported tobacco grades used in the recipe;

[0034] The recipe optimization module is used to optimize the proportion of each tobacco leaf in the recipe P based on the Monte Carlo method to meet the preset recipe cost and preset feed amount constraints to obtain the final tobacco leaf group recipe.

[0035] In a third aspect, a computer-readable storage medium is provided, which stores a computer program, and when the computer program is executed by a processor, the method for designing a cigarette formula based on main ingredients and style quality as described above is implemented.

[0036] Beneficial Effects

[0037] The present invention proposes a cigarette formula design method, device and storage medium based on main ingredients and style quality. On the basis of constraining factors in tobacco leaf design such as tobacco leaf cost, batch feed quantity, proportion of light-flavor tobacco leaves, proportion of medium-flavor tobacco leaves, proportion of strong-flavor tobacco leaves, proportion of imported tobacco leaves, number of formula grades, and tobacco leaf years of a target formula, combined with constraining conventional chemical ingredients, style, and quality of the target formula, a leaf group formula list that meets the constraints is generated, thereby achieving tobacco leaf group formula design based on non-artificial experience and improving the efficiency of tobacco leaf group formula design. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0039] Figure 1 The present invention provides a flow chart of a method for designing a cigarette formula based on main ingredients and style quality. DETAILED DESCRIPTION

[0040] To make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be described in detail below. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other implementation methods obtained by ordinary technicians in this field without creative work belong to the scope of protection of the present invention.

[0041] like Figure 1 As shown, an embodiment of the present invention provides a cigarette formula design method based on main ingredients and style quality, comprising:

[0042] S1: Obtain the aroma, conventional chemical composition, style value, quality value, price cost, inventory, production year, origin and grade data of the single-grade tobacco leaves to be used.

[0043] Among them, conventional chemical components include the content of total sugar, reducing sugar, total nitrogen, total alkali, chlorine, and potassium. During implementation, it can be obtained through a flow analyzer or an existing near-infrared prediction model. The style value and quality value of the single-grade tobacco leaves to be used are obtained through manual evaluation.

[0044] The aroma of the single-grade tobacco leaves to be used is obtained by the following method:

[0045] The sensory evaluation of the single-grade tobacco leaves to be used mainly includes the scores of the four aroma notes of the single-grade tobacco leaves to be used, namely, fresh sweet aroma, honey sweet aroma, mellow sweet aroma and burnt sweet aroma. Combined with the regional information of tobacco production areas, the single-grade tobacco leaves to be used are classified as follows according to the evaluation results:

[0046] ① In the evaluation results, the tobacco leaves with the highest score for light sweet aroma are defined as light aroma tobacco leaves; ② In the evaluation results, the tobacco leaves with the highest score for burnt sweet aroma are defined as strong aroma tobacco leaves; ③ In the evaluation results, the tobacco leaves with the highest score for honey sweet aroma or mellow sweet aroma are defined as medium aroma tobacco leaves; ④ Tobacco leaves produced in foreign countries are defined as imported tobacco leaves.

[0047] S2: Preliminary screening of all single-grade tobacco leaves to be used by setting constraints based on preset formula cost, preset feed amount, and tobacco leaf production year data to form a candidate tobacco leaf set. The specific process includes:

[0048] Set preset conditions: ① Manually set the production year of the required single-grade tobacco leaf x; ② The unit price of the required single-grade tobacco leaf x × a < the preset formula cost; ③ The inventory of the required single-grade tobacco leaf x > the preset feed amount × b; where a and b are both empirical parameters, a represents the empirical value of the grade quantity of the single-grade tobacco leaf in the formula, and its value range is [10, 50], and b represents the empirical value of the ratio of the least single-grade tobacco leaf used in the formula, and its value range is [0.01, 0.2]. In this embodiment, a = 33, b = 2%. The single-grade tobacco leaf x that meets the above constraints enters the candidate tobacco leaf set, which is recorded as C.

[0049] S3: Divide the candidate tobacco leaf set into four subsets according to the aroma type of tobacco leaves: C 清 , C 浓 , C 中 , C 进 Among them, C 清 represents the candidate set of light-fragrant tobacco leaves, C 浓 represents the candidate tobacco leaf set of Luzhou-flavor type, C 中 represents the candidate tobacco leaf set of intermediate aroma, C 进 represents the set of candidate tobacco leaves for import;

[0050] S4: Set the upper limit of the total number of tobacco leaves used in the recipe and the upper limit of the number of tobacco leaves used for each flavor. The constraints include:

[0051] ①N 清 +N 浓 +N 中 +N 进 ≤N, N is the upper limit of the total number of levels; ②N 清 ≤ Artificially set the upper limit of the number of light-fragrant tobacco grades, N 浓≤ Artificially set the upper limit of the number of grades of strong-flavor tobacco leaves, N 中 ≤ Artificially set the upper limit of the number of intermediate-flavor tobacco leaves, N 进 ≤ Artificially set the upper limit on the quantity of imported tobacco leaf grades.

[0052] S5: Formulate the formulation design objective as a planning problem: min{f(t)}=α∑|t i -y i |+β∑|t k -z k |; where min{f(t)} represents the objective function, t i Indicates the preset design target of the conventional chemical composition content of the formula, t k Represents the preset formula style value and quality value design target; y i Indicates the conventional chemical composition content of the designed formula, z k represents the style value and quality value of the designed formula; α represents the weight of the conventional chemical component content, β represents the weight of the style value and quality value, and both α and β are empirical parameters, which can be assigned in combination with manual experience and historical cigarette product characteristics; i is an integer in (0, N], N is the total number of conventional chemical components, and in this embodiment, N is 6; k is 1 or 2, representing style and quality respectively;

[0053] S6: Based on the constraints in step S4 and the planning problem in step S5, 清 , C 浓 , C 中 , C 进 In the four subsets, single-grade tobacco leaves of various flavors whose conventional chemical component contents, style values, and quality values ​​are close to the corresponding design targets are selected, respectively N 清 N 浓 N 中 N 进 , combined into a formula P; where N 清 Indicates the number of grades of light-fragrant tobacco leaves used in the recipe, N 浓 Indicates the number of grades of strong-flavor tobacco leaves used in the recipe, N 中 Indicates the number of intermediate-flavor tobacco leaves used in the recipe, N 进 Indicates the quantity of imported tobacco grades used in the recipe;

[0054] S7: Based on the Monte Carlo method, optimize the proportion of each tobacco leaf in the recipe P to meet the preset recipe cost and preset feed amount constraints, and obtain the final tobacco leaf group recipe. Specifically including:

[0055] Randomly generate n groups of ratio data and assign them to a formula P; wherein n is a preset value, preferably n>1000;

[0056] If each set of ratio data cannot make the formula P meet the preset formula cost and preset feed amount constraints, then the n sets of ratio data are discarded, and n sets of ratio data are randomly generated again, and it is determined whether each set of ratio data makes the formula P meet the preset formula cost and preset feed amount constraints; otherwise, for the ratio data that meet the preset formula cost and preset feed amount constraints, a group is averaged or randomly selected to assign the formula P to obtain the final cigarette leaf group formula.

[0057] The preset formula cost and preset feed quantity constraints here correspond to the preset formula cost and preset feed quantity in step S2, that is, the sum of the unit price of each single-grade tobacco leaf in the formula and the product of the ratio does not exceed the preset formula cost, and the inventory of each single-grade tobacco leaf is not less than the product of the preset feed quantity and its ratio.

[0058] Another embodiment of the present invention provides a device for designing cigarette formula based on main ingredients and style quality, comprising:

[0059] A data acquisition module is used to obtain the flavor, conventional chemical composition, style value, quality value, price cost, inventory, production year, origin and grade data of the single-grade tobacco leaves to be used;

[0060] The initial screening module is used to perform preliminary screening on all the single-grade tobacco leaves to be used by setting constraints based on the preset formula cost, preset feed amount, and tobacco leaf production year data to form a candidate tobacco leaf set;

[0061] The candidate tobacco leaf set division module is used to divide the candidate tobacco leaf set into four subsets according to the flavor of the tobacco leaves: C 清 , C 浓 , C 中 , C 进 Among them, C 清 represents the candidate set of light-fragrant tobacco leaves, C 浓 represents the candidate tobacco leaf set of Luzhou-flavor type, C 中 represents the candidate tobacco leaf set of intermediate aroma, C 进 represents the set of candidate tobacco leaves for import;

[0062] The grade quantity constraint module is used to set the upper limit of the total grade quantity of tobacco leaves used in the formula and the upper limit of the grade quantity of tobacco leaves of each flavor type;

[0063] Planning module, used to express the recipe design goal as a planning problem: min{f(t)}=α∑|t i -y i |+β∑|t k -z k |; where min{f(t)} represents the objective function, t i Indicates the preset design target of the conventional chemical composition content of the formula, tk Represents the preset formula style value and quality value design target; y i Indicates the conventional chemical composition content of the designed formula, z k represents the style value and quality value of the designed formula; α represents the weight of the conventional chemical component content, β represents the weight of the style value and quality value; i takes an integer in (0, N], N is the total number of conventional chemical components, and k takes 1 or 2, representing style and quality respectively;

[0064] The recipe generation module is used to generate the planning problem based on the constraints set by the level quantity constraint module and the planning module. 清 , C 浓 , C 中 , C 进 In the four subsets, single-grade tobacco leaves of various flavors whose conventional chemical component contents, style values, and quality values ​​are close to the corresponding design targets are selected, respectively N 清 N 浓 N 中 N 进 , combined into a formula P; where N 清 Indicates the number of grades of light-fragrant tobacco leaves used in the recipe, N 浓 Indicates the number of grades of strong-flavor tobacco leaves used in the recipe, N 中 Indicates the number of intermediate-flavor tobacco leaves used in the recipe, N 进 Indicates the quantity of imported tobacco grades used in the recipe;

[0065] The recipe optimization module is used to optimize the proportion of each tobacco leaf in the recipe P based on the Monte Carlo method to meet the preset recipe cost and preset feed amount constraints to obtain the final tobacco leaf group recipe.

[0066] For other specific implementations of this embodiment, please refer to the aforementioned embodiments and will not be described in detail here.

[0067] Another embodiment of the present invention provides a cigarette formula design device based on multiple constraints, comprising:

[0068] a memory storing a computer program;

[0069] The processor is used to execute the computer program to implement the cigarette formula design method based on main ingredients and style quality as described in the above embodiment.

[0070] Another embodiment of the present invention provides a computer-readable storage medium storing a computer program, wherein the computer program, when executed by a processor, implements the cigarette formulation design method based on main ingredients and style quality as described above.

[0071] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that include computer-usable program code.

[0072] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0073] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0074] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0075] It can be understood that the same or similar parts of the above embodiments can be referenced to each other, and the contents not described in detail in some embodiments can refer to the same or similar contents in other embodiments.

[0076] Any process or method description in a flowchart or otherwise described herein may be understood to represent a module, segment or portion of code that includes one or more executable instructions for implementing the steps of a specific logical function or process, and the scope of the preferred embodiments of the present invention includes alternative implementations in which functions may not be performed in the order shown or discussed, including performing functions in a substantially simultaneous manner or in the reverse order depending on the functions involved, which should be understood by those skilled in the art to which the embodiments of the present invention belong.

[0077] The technical solution of the present invention is further described below in conjunction with a specific example:

[0078] Examples

[0079] 1. Obtain data on 500 single-grade tobacco leaves from Hunan China Tobacco’s inventory covering major domestic and foreign tobacco producing areas, including price cost, inventory, production year, origin and grade;

[0080] 2. Performing sensory evaluation on the 500 single-grade tobacco leaves, obtaining the four aroma score data of fresh sweet aroma, honey sweet aroma, mellow sweet aroma and burnt sweet aroma of all single-grade tobacco leaves, and according to the aroma score and origin information of each tobacco leaf, classifying each grade of tobacco leaves into fresh aroma type, strong aroma type, medium aroma type and imported tobacco leaves according to the classification standard in S2 of the present invention;

[0081] 3. Obtain the content, style value and quality value of conventional chemical components (total sugar, reducing sugar, total nitrogen, total alkali, chlorine and potassium) of the above 500 single-grade tobacco leaves through flow analyzer and manual evaluation;

[0082] 4. Set the leaf group formula constraints as follows: the production years of the tobacco leaves used in the formula are 2016, 2017 and 2018, the preset cost of the formula is 4,000 yuan / box, the preset feed amount is 3,000 kg, the upper limit N of the number of grades of tobacco leaves used in the formula is 30, and the number of grades of light-fragrant tobacco leaves used in the formula is N. 清 is 12, the number of grades of strong-flavor tobacco leaves used in the recipe is N 浓 =6, the number of grades of intermediate-flavor tobacco leaves used in the recipe N 中 =9, the number of grades of imported tobacco leaves used in the recipe N 进 3; the design targets of conventional chemical composition indicators of leaf group formula are: total sugar content is 29.0%, reducing sugar content is 22.0%, total nitrogen content is 2.0%, total alkali content is 2.5%, chlorine content is 0.4%, potassium content is 2.4%, style value is 2.2, quality value is 22.0; the weight of conventional chemical composition content α is 0.7, and the weight of style value and quality value β is 0.3;

[0083] 5. Run the leaf group formula design scheme provided in the present invention, and finally obtain the following leaf group formula list:

[0084]

[0085]

[0086] The production year and inventory of tobacco leaves used in the formula sheet formed according to the scheme of the present invention, the grade quantity of tobacco leaves of various flavors, the actual formula cost, the overall formula structure, etc., all meet the requirements. The designed formula has a total sugar content of 29.8%, a reducing sugar content of 21.7%, a total nitrogen content of 2.1%, a total alkali content of 2.7%, a chlorine content of 0.6%, a potassium content of 2.7%, a style value of 2.3, and a quality value of 22.2, which basically meet the design requirements of the tobacco leaf group formula.

[0087] Although the embodiments of the present invention have been shown and described above, it is to be understood that the above embodiments are exemplary and are not to be construed as limitations of the present invention. A person skilled in the art may change, modify, replace and vary the above embodiments within the scope of the present invention.

Claims

1. A method for designing cigarette formula based on main ingredients and style quality, characterized in that: include: S1: Obtain the aroma, conventional chemical composition, style value, quality value, price cost, inventory, production year, origin and grade data of the single-grade tobacco leaves to be used; S2: Preliminary screening is performed on all single-grade tobacco leaves to be used by setting constraints based on preset formula costs, preset feed amounts, and tobacco leaf production year data to form a candidate tobacco leaf set; S3: Divide the candidate tobacco leaf set into four subsets according to the aroma type of tobacco leaves: C 清 , C 浓 , C 中 , C 进 ; Among them, C 清 represents the candidate set of light-fragrant tobacco leaves, C 浓 represents the candidate tobacco leaf set of Luzhou-flavor type, C 中 represents the candidate tobacco leaf set of intermediate aroma, C 进 represents the set of candidate tobacco leaves for import; S4: Set the upper limit of the total number of tobacco leaves used in the recipe and the upper limit of the number of tobacco leaves of each flavor type used; S5: Formulate the formulation design objective as a planning problem: min{f(t)}=α∑|t i -y i |+β∑|t k -z k |; where min{f(t)} represents the objective function, t i Indicates the preset design target of the conventional chemical composition content of the formula, t k Represents the preset formula style value and quality value design target; y i Indicates the conventional chemical composition content of the designed formula, z k represents the style value and quality value of the designed formula; α represents the weight of the conventional chemical component content, β represents the weight of the style value and quality value; i takes an integer in (0, N], N is the total number of conventional chemical components, and k takes 1 or 2, representing style and quality respectively; S6: Based on the constraints in step S4 and the planning problem in step S5, 清 , C 浓 , C 中 , C 进 In the four subsets, single-grade tobacco leaves of various flavors whose conventional chemical component contents, style values, and quality values ​​are close to the corresponding design targets are selected, respectively N 清 N 浓 N 中 N 进 , combined into a formula P; where N 清 Indicates the number of grades of light-fragrant tobacco leaves used in the recipe, N 浓 Indicates the number of grades of strong-flavor tobacco leaves used in the recipe, N 中 Indicates the number of intermediate-flavor tobacco leaves used in the recipe, N 进 Indicates the quantity of imported tobacco grades used in the recipe; S7: Based on the Monte Carlo method, the proportion of each tobacco leaf in the formula P is optimized to meet the preset formula cost and preset feed amount constraints, and the final tobacco leaf group formula is obtained.

2. The cigarette formula design method based on main ingredients and style quality according to claim 1, characterized in that: The conventional chemical components of the single-grade tobacco leaves to be used in step S1 include the contents of total sugar, reducing sugar, total nitrogen, total alkali, chlorine and potassium.

3. The method for designing cigarette formula based on main ingredients and style quality according to claim 1, characterized in that: The style value and quality value of the single-grade tobacco leaves to be used in step S1 are obtained through manual evaluation.

4. The method for designing cigarette formula based on main ingredients and style quality according to claim 1, characterized in that: The flavor of the single-grade tobacco leaves to be used in step S1 is obtained by the following method: The sensory evaluation of the single-grade tobacco leaves to be used mainly includes the scores of the four aroma notes of the single-grade tobacco leaves to be used, namely, fresh sweet aroma, honey sweet aroma, mellow sweet aroma and burnt sweet aroma. Combined with the regional information of tobacco production areas, the single-grade tobacco leaves to be used are classified as follows according to the evaluation results: In the evaluation results, the tobacco leaves with the highest score for light sweet aroma are defined as light aroma tobacco leaves; in the evaluation results, the tobacco leaves with the highest score for burnt sweet aroma are defined as strong aroma tobacco leaves; in the evaluation results, the tobacco leaves with the highest score for honey sweet aroma or mellow sweet aroma are defined as medium aroma tobacco leaves; and tobacco leaves produced in foreign countries are defined as imported tobacco leaves.

5. The method for designing cigarette formula based on main ingredients and style quality according to claim 1, characterized in that: In step S2, constraints are set for all single-grade tobacco leaves to be used by presetting formula cost, tobacco leaf inventory, and tobacco leaf production year data. The constraints specifically include: The production year of the required single-grade tobacco leaf x is manually set; the unit price of the required single-grade tobacco leaf x × a < the preset formula cost; the inventory of the required single-grade tobacco leaf x > the preset feed quantity × b; wherein a and b are both empirical parameters.

6. The method for designing cigarette formula based on main ingredients and style quality according to claim 5, characterized in that: The value range of a is [10, 50], and the value range of b is [0.01, 0.2].

7. The method for designing cigarette formula based on main ingredients and style quality according to claim 1, characterized in that: In step S4, the upper limit of the total grade of tobacco leaves used in the recipe and the upper limit of the grade of tobacco leaves of each flavor type are set. The ... constraints specifically include: N 清 +N 浓 +N 中 +N 进 ≤N;N 清 ≤ Artificially set the upper limit of the number of light-fragrant tobacco grades, N 浓 ≤ Artificially set the upper limit of the number of grades of strong-flavor tobacco leaves, N 中 ≤ Artificially set the upper limit of the number of intermediate-flavor tobacco leaves, N 进 ≤Manually set the upper limit of the number of imported tobacco leaf grades; where N is the preset upper limit of the total number of grades.

8. The method for designing cigarette formula based on main ingredients and style quality according to claim 1, characterized in that: The step S7 specifically includes: Randomly generate n groups of ratio data and assign them to the formula P, where n is a preset value; If each set of ratio data cannot make the formula P meet the preset formula cost and preset feed amount constraints, then the n sets of ratio data are discarded, and n sets of ratio data are randomly generated again, and it is determined whether each set of ratio data makes the formula P meet the preset formula cost and preset feed amount constraints; otherwise, for the ratio data that meet the preset formula cost and preset feed amount constraints, a group is averaged or randomly selected to assign the formula P to obtain the final cigarette leaf group formula.

9. A cigarette formula design device based on main ingredients and style quality, characterized in that: include: A data acquisition module is used to obtain the flavor, conventional chemical composition, style value, quality value, price cost, inventory, production year, origin and grade data of the single-grade tobacco leaves to be used; The initial screening module is used to perform preliminary screening on all the single-grade tobacco leaves to be used by setting constraints based on the preset formula cost, preset feed amount, and tobacco leaf production year data to form a candidate tobacco leaf set; The candidate tobacco leaf set division module is used to divide the candidate tobacco leaf set into four subsets according to the flavor of the tobacco leaves: C 清 , C 浓 , C 中 , C 进 ; Among them, C 清 represents the candidate set of light-fragrant tobacco leaves, C 浓 represents the candidate tobacco leaf set of Luzhou-flavor type, C 中 represents the candidate tobacco leaf set of intermediate aroma, C 进 represents the set of candidate tobacco leaves for import; The grade quantity constraint module is used to set the upper limit of the total grade quantity of tobacco leaves used in the formula and the upper limit of the grade quantity of tobacco leaves of each flavor type; Planning module, used to express the recipe design goal as a planning problem: min{f(t)}=α∑|t i -y i |+β∑|t k -z k |; where min{f(t)} represents the objective function, t i Indicates the preset design target of the conventional chemical composition content of the formula, t k Represents the preset formula style value and quality value design target; y i Indicates the conventional chemical composition content of the designed formula, z k represents the style value and quality value of the designed formula; α represents the weight of the conventional chemical component content, β represents the weight of the style value and quality value; i takes an integer in (0, N], N is the total number of conventional chemical components, and k takes 1 or 2, representing style and quality respectively; The recipe generation module is used to generate the planning problem based on the constraints set by the level quantity constraint module and the planning module. 清 , C 浓 , C 中 , C 进 In the four subsets, single-grade tobacco leaves of various flavors whose conventional chemical component contents, style values, and quality values ​​are close to the corresponding design targets are selected, respectively N 清 N 浓 N 中 N 进 , combined into a formula P; where N 清 Indicates the number of grades of light-fragrant tobacco leaves used in the recipe, N 浓 Indicates the number of grades of strong-flavor tobacco leaves used in the recipe, N 中 Indicates the number of intermediate-flavor tobacco leaves used in the recipe, N 进 Indicates the quantity of imported tobacco grades used in the recipe; The recipe optimization module is used to optimize the proportion of each tobacco leaf in the recipe P based on the Monte Carlo method to meet the preset recipe cost and preset feed amount constraints to obtain the final tobacco leaf group recipe.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the method for designing cigarette formula based on main ingredients and style quality as claimed in any one of claims 1 to 8 is implemented.

Images