CN111383722B

CN111383722B - Data-driven model analysis method and device for solving grape wine raw material index range

Info

Publication number: CN111383722B
Application number: CN202010118187.0A
Authority: CN
Inventors: 尚雪纯; 杨华; 周康; 刘朔; 刘江蓉; 高婧; 周坚; 镇依婷
Original assignee: Wuhan Polytechnic University
Current assignee: Wuhan Polytechnic University
Priority date: 2020-02-25
Filing date: 2020-02-25
Publication date: 2023-04-25
Anticipated expiration: 2040-02-25
Also published as: CN111383722A

Abstract

The invention relates to the technical field of wine processing, and discloses a data-driven model analysis method and a data-driven model analysis device for solving the range of raw material indexes of wine, wherein the method comprises the steps of obtaining a sample database constructed according to the raw material indexes of wine grapes and the indexes of wine products; the method comprises the steps of extracting a wine brewing grape raw material sample set and a wine product sample set from the wine brewing grape raw material sample set, preprocessing data in a sample database based on the wine brewing grape raw material sample set and the wine product sample set, predicting the quality index of the wine product based on processed target data, constructing a wine brewing grape raw material quality standard optimization model according to calculation data in a prediction process and a preset optimization target, and determining the range of the wine brewing grape raw material quality index by constructing the wine brewing grape raw material quality standard optimization model, so that the problem of how to quickly and scientifically determine the optimal range of the wine brewing grape raw material quality index under given production process conditions is solved, and the wine brewing grape raw material can produce qualified wine products.

Description

Data-driven model analysis method and device for solving grape wine raw material index range

Technical Field

The invention relates to the technical field of wine processing, in particular to a data-driven model analysis method and device for solving the range of raw material indexes of wine.

Background

In the field of wine processing, for brewing wine, as various wine products have different physicochemical properties, the requirements on the quality of wine brewing grape raw materials are different, and wine products conforming to national standards, provinces standards, row standards and enterprise standards are required to be manufactured, the optimal quality range of the wine brewing grape raw materials is predicted according to the quality of the wine products, thus providing basis for enterprises to collect and handle proper wine brewing grape raw materials, brewing qualified wine products under given production process conditions, improving the qualification rate of the wine products, reducing the waste of the wine brewing grape raw materials, reducing loss for enterprises and improving profit of enterprises.

At present, enterprises have a plurality of methods for determining which brewing grape raw materials are used for brewing and producing, and generally, by comparing wine products brewed from various brewing grape raw materials according to the sensory feeling of a grape brewing expert, what brewing grape raw materials are put into brewing can be roughly judged to obtain what grape wine products. However, this method of deciding on the process of wine brewing solely through the organoleptic sensations of the wine brewing specialist presents a certain risk in terms of efficiency and effectiveness, while also presenting a certain space for improvement. For the production planning of enterprises, how to scientifically find the quality range of wine brewing grape raw materials which are most suitable for brewing grape wine is an urgent problem to be solved.

The foregoing is provided merely for the purpose of facilitating understanding of the technical solutions of the present invention and is not intended to represent an admission that the foregoing is prior art.

Disclosure of Invention

The invention mainly aims to provide a data-driven model analysis method and a data-driven model analysis device for solving the range of wine raw material indexes, and aims to solve the technical problem of how to quickly and scientifically determine the optimal range of wine raw material quality indexes under given production process conditions, so that the wine raw materials can produce qualified wine products.

In order to achieve the above object, the present invention provides a data-driven model analysis method for solving a range of raw material indexes of wine, the method comprising the steps of:

acquiring a sample database constructed according to wine grape raw material indexes and wine product indexes;

extracting a wine grape raw material sample set and a wine product sample set from the sample database, setting indexes in the wine grape raw material sample set as prediction variables, and setting indexes in the wine product sample set as response variables;

preprocessing the data in the sample database based on the predicted variable and the response variable to obtain processed target data;

Predicting the quality index of the wine product based on the target data, and acquiring calculation data in the prediction process;

constructing a brewing grape raw material quality standard optimization model according to the calculated data and a preset optimization target;

and determining the quality index range of the brewing grape raw material according to the brewing grape raw material quality standard optimization model.

Preferably, the step of preprocessing the data in the sample database based on the predicted variable and the response variable to obtain processed target data specifically includes:

performing standardization processing on a sample set in the sample database based on the prediction variable and the response variable to obtain a standardized wine raw material sample set and a standardized wine product sample set;

performing main component dimension reduction on the standardized brewing grape raw material sample data in the standardized brewing grape raw material sample set to obtain target brewing grape raw material sample data and a main component factor load matrix;

extracting target wine grape raw material indexes from the target wine grape raw material sample data;

mapping the target brewing grape raw material index into a brewing grape raw material quality index according to the main component factor load matrix;

And taking the target wine grape raw material sample data, the standardized grape product sample set and the wine grape raw material quality index as target data.

Preferably, the step of predicting the quality index of the wine product based on the target data and obtaining the calculation data in the prediction process specifically includes:

generating a training set of a multiple linear regression model according to the target brewing grape raw material sample data and the standardized grape product sample set;

training the multiple linear regression model according to the training set to obtain a prediction model corresponding to the quality index of the wine product;

extracting target wine product indexes from the standardized wine product sample set, and determining regression functions corresponding to the target wine product indexes based on a preset coefficient matrix;

determining a goodness of fit according to the regression function;

and taking the prediction model and the goodness of fit as calculation data in the prediction process.

Preferably, the step of constructing the optimization model of the wine grape raw material quality standard according to the calculated data and the preset optimization target specifically includes:

searching physical and chemical property data of the quality of the brewing grape raw material corresponding to the quality index of the brewing grape raw material, and determining limitation constraint of the brewing grape raw material based on the physical and chemical property data;

Determining wine product limitation constraint based on the prediction model and a preset target food quality requirement;

correcting the wine product limit constraint according to the fitting goodness to obtain a target wine product limit constraint;

constructing a high-dimensional target space according to a plurality of target brewing grape raw material indexes, and setting diffusion factors in the high-dimensional target space;

determining a diffusion factor constraint according to the diffusion factor and a preset target area requirement;

taking the wine grape raw material limit constraint, the wine product limit constraint and the diffusion factor constraint as constraint conditions;

and constructing a brewing grape raw material quality standard optimization model according to the constraint conditions and a preset optimization target.

Preferably, the step of determining the range of the quality index of the raw material of the wine grape according to the optimization model of the quality standard of the raw material of the wine grape specifically includes:

converting the brewing grape raw material quality standard optimization model into a single-target brewing grape raw material quality standard optimization model based on a linear weighting method;

performing quartile calculation on the standardized brewing grape raw material sample data according to the single-target brewing grape raw material quality standard optimization model to obtain quartile calculation result data;

Determining a regulation and control model according to the quartile calculation result data and the brewing grape raw material quality standard optimization model;

and determining the quality index range of the brewing grape raw material according to the regulation model.

Preferably, the step of determining a regulation model according to the quartile calculation result data and the optimization model of the wine grape raw material quality standard specifically includes:

selecting lower quartile data and upper quartile data from the quartile calculation result data;

calculating a difference value according to the lower quartile data and the upper quartile data;

determining constraint weights according to the difference value and a preset standardization method;

optimizing the diffusion factor constraint according to the constraint weight and the diffusion factor to obtain a target diffusion factor constraint;

and regulating and controlling the brewing grape raw material quality standard optimization model according to the target diffusion factor constraint to obtain the regulation and control model.

Preferably, the step of determining the range of the quality index of the raw material of the wine grape according to the regulation model specifically includes:

calculating a lower limit value of the quality index of the raw material of the wine grapes and an upper limit value of the quality index of the raw material of the wine grapes according to the regulation model;

Performing inverse standardization processing on the lower limit value of the wine grape raw material quality index and the upper limit value of the wine grape raw material quality index;

and determining the quality index range of the wine grape raw material according to the processing result.

In addition, in order to achieve the above object, the present invention also provides a data-driven model analysis device for solving a raw material index range of wine, the data-driven model analysis device for solving a raw material index range of wine comprising:

the data acquisition module is used for acquiring a sample database constructed according to the wine grape raw material index and the wine product index;

the variable setting module is used for extracting a wine raw material sample set and a grape wine product sample set from the sample database, setting indexes in the wine raw material sample set as prediction variables and setting indexes in the grape wine product sample set as response variables;

the data processing module is used for preprocessing the data in the sample database based on the predicted variable and the response variable to obtain processed target data;

the index prediction module is used for predicting the quality index of the wine product based on the target data and acquiring calculation data in the prediction process;

The model construction module is used for constructing a brewing grape raw material quality standard optimization model according to the calculation data and a preset optimization target;

and the standard determining module is used for determining the quality index range of the brewing grape raw material according to the brewing grape raw material quality standard optimizing model.

Preferably, the data processing module is further configured to perform standardization processing on the sample set in the sample database based on the prediction variable and the response variable, so as to obtain a standardized wine raw material sample set and a standardized wine product sample set;

the data processing module is further used for carrying out main component dimension reduction on the standardized brewing grape raw material sample data in the standardized brewing grape raw material sample set to obtain target brewing grape raw material sample data and a main component factor load matrix;

the data processing module is also used for extracting target brewing grape raw material indexes from the target brewing grape raw material sample data;

the data processing module is further used for mapping the target wine brewing grape raw material index into a wine brewing grape raw material quality index according to the main component factor load matrix;

the data processing module is further used for taking the target wine grape raw material sample data, the standardized grape product sample set and the wine grape raw material quality index as target data.

Preferably, the index prediction module is further configured to generate a training set of a multiple linear regression model according to the target wine grape raw material sample data and the standardized grape product sample set;

the index prediction module is further used for training the multiple linear regression model according to the training set to obtain a prediction model corresponding to the quality index of the wine product;

the index prediction module is further used for extracting target wine product indexes from the standardized wine product sample set and determining regression functions corresponding to the target wine product indexes based on a preset coefficient matrix;

the index prediction module is further used for determining a goodness of fit according to the regression function;

the index prediction module is further used for taking the prediction model and the goodness of fit as calculation data in the prediction process.

According to the data-driven model analysis method for solving the range of the wine raw material index, a sample database constructed according to the wine raw material index and the wine product index is obtained; extracting a wine raw material sample set and a wine product sample set from the sample database, setting indexes in the wine raw material sample set as prediction variables, and setting indexes in the wine product sample set as response variables; preprocessing the data in the sample database based on the predicted variable and the response variable to obtain processed target data; predicting the quality index of the wine product based on the target data, and acquiring calculation data in the prediction process; constructing a brewing grape raw material quality standard optimization model according to the calculation data and a preset optimization target; and determining the range of the quality index of the brewing grape raw material according to the quality standard optimizing model of the brewing grape raw material. According to the method, the data in the sample database are preprocessed to obtain the target data, the calculation data in the process of predicting the quality index of the wine product based on the target data are obtained, the transfer of the color tone and the taste of the wine product to the raw material components and sweetness of the wine grape is completed, the quality standard optimization model of the wine grape raw material is constructed, the quality index range of the wine grape raw material is determined by constructing the quality standard optimization model of the wine grape raw material, the potential of the wine grape raw material input selection to improve the quality of the wine product is exerted, and the technical problem that how to quickly and scientifically determine the optimal range of the quality index of the wine grape raw material under given production process conditions is solved, so that the wine grape raw material can produce qualified wine products is solved.

Drawings

FIG. 1 is a schematic flow chart of a first embodiment of a data-driven model analysis method for solving a wine raw material index range according to the present invention;

FIG. 2 is a representation of a limitation constraint of wine products in a two-dimensional space in a first embodiment of a data-driven model analysis method for solving a range of wine raw material indicators in accordance with the present invention;

FIG. 3 is a schematic flow chart of a second embodiment of a data-driven model analysis method for solving a wine raw material index range according to the present invention;

FIG. 4 is a schematic flow chart of a third embodiment of a data-driven model analysis method for solving a wine raw material index range according to the present invention;

FIG. 5 is a schematic diagram of functional blocks of a first embodiment of a data-driven model analysis device for solving a range of wine raw material indicators according to the present invention.

The achievement of the objects, functional features and advantages of the present invention will be further described with reference to the accompanying drawings, in conjunction with the embodiments.

Detailed Description

It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention.

The embodiment of the invention provides a data-driven model analysis method for solving a raw material index range of a wine, and referring to fig. 1, fig. 1 is a flow diagram of a first embodiment of the data-driven model analysis method for solving the raw material index range of the wine.

In this embodiment, the data-driven model analysis method for solving the raw material index range of the wine includes the following steps:

and step S10, obtaining a sample database constructed according to the wine grape raw material index and the wine product index.

It should be noted that, the execution body of the embodiment may be a computing service device with data processing, program running and network communication functions, for example, a smart phone, a tablet computer, a personal computer, etc., and may also be other data-driven model analysis devices capable of implementing the same or similar functions for solving the range of raw materials of wine, which is not limited in this embodiment, and in this embodiment, a data-driven model analysis device for solving the range of raw materials of wine grape is taken as an example for description. And solving the raw material index range of the wine, namely solving the raw material index range of the wine brewing grape.

It is known that a sample database constructed from raw material indexes of wine grapes and indexes of wine products is a high-quality database including { x } ₁ ,x ₂ ,…x _m ，y ₁ ,y ₂ ,…y _n (x) ₁ ,x ₂ ,…x _m The } is a wine grape raw material index that can evaluate the wine grape raw material, { y ₁ ,y ₂ ,…y _n And is a wine product index that allows the assessment of wine products.

The sample database D is:

D _A is basic information data of wine grape raw material, D _M Is an index data set of the raw materials of the wine grapes, namely a sample set of the raw materials of the wine grapes, D _N The method is an index data set of a wine product, namely a wine product sample set, wherein t is t brewing grape raw materials, k is basic information data of the kth brewing grape raw materials, m is index data of the mth brewing grape raw materials, and n is index data of the nth wine product.

Specifically, A ₁ Is numbered A ₁₁ Is the 1 st basic attribute, x of the 1 st brewing grape raw material _tm Is the mth basic attribute of the t-th brewing grape raw material. Basic attributes of the wine grape raw material may include variety of wine grape, production place, etc., wherein the variety of wine grape raw material may include: cabernet Sauvignon, serpentis, pink, meile, sila, and indigo naturalis; the place of origin of the wine grape raw material may include: langerhans, french LongHegudi, french Bondy, crohn's, california, shandong Bondy Bay, tianjin coast, etc.

Further, wine product metrics (including but not all of the following) of the wine product are evaluated: sensory requirements = { clarity, hue, purity, concentration, quality, purity, concentration, persistence, quality }, physicochemical requirements = { alcoholic strength, total sugar, dry extract, volatile acid }, composition = { anthocyanin, tannin, total phenol, total flavonoids of wine, resveratrol, trans-resveratrol glycoside, cis-resveratrol glycoside, trans-resveratrol, cis-resveratrol, DPPH half-inhibitory volume }. The index data set of the wine preparation may consist of all or part of the wine preparation index as described above for evaluating the wine preparation.

The wine grape raw material index (including but not all of the following) of the wine grape raw material is evaluated: total amino acid, single amino acid content, protein, VC content, anthocyanin, fresh weight, tartaric acid, malic acid, citric acid, polyphenol oxidase activity, browning degree, DPPH free radical, total phenol, tannin, total grape flavone, resveratrol, trans-resveratrol glycoside, cis-resveratrol glycoside, trans-resveratrol, cis-resveratrol, flavonol, myricetin, quercetin, kaempferol, isorhamnetin, total sugar, reducing sugar, fructose, glucose, soluble solids, PH, titratable acid, solid acid ratio, dry matter content, ear mass, hundred grain mass, fruit stem ratio, juice yield, peel mass, peel color. The index data set of the wine grape raw material may be composed of all or part of the wine grape raw material index for evaluating the wine grape raw material.

It should be understood that the sample database may be obtained from a local memory, from a network, or from other manners, which is not limited in this embodiment.

And S20, extracting a wine grape raw material sample set and a wine product sample set from the sample database, setting indexes in the wine grape raw material sample set as prediction variables, and setting indexes in the wine product sample set as response variables.

The method comprises the steps of obtaining a wine raw material sample set and a wine product sample set in the sample database, setting indexes in the wine product sample set as response variables, and setting indexes in the wine raw material sample set as prediction variables, so that constraints on the wine product standards can be converted into constraints on the wine raw material standards.

And step S30, preprocessing the data in the sample database based on the predicted variable and the response variable to obtain processed target data.

It should be understood that, based on the predicted variable and the response variable, preprocessing the data in the sample database, and the step of obtaining the processed target data specifically includes:

firstly, carrying out standardization processing on a sample set in the sample database based on the prediction variable and the response variable to obtain a standardized wine raw material sample set and a standardized wine product sample set. Specifically, a wine raw material sample set and a wine product sample set are extracted from a sample database based on the prediction variable and the response variable, and then the wine raw material sample set and the wine product sample set are subjected to standardization processing respectively, so that a standardized wine raw material sample set and a standardized wine product sample set can be obtained, and the sample set is subjected to standardization processing firstly, because the data in the sample set after the standardization processing is more convenient for subsequent use.

And secondly, carrying out main component dimension reduction on the standardized brewing grape raw material sample data in the standardized brewing grape raw material sample set to obtain target brewing grape raw material sample data and a main component factor load matrix. Specifically, standardized brewing grape raw material sample data in a standardized brewing grape raw material sample set are obtained, main component dimension reduction is carried out on the standardized brewing grape raw material sample data, target brewing grape raw material sample data and a main component factor load matrix are obtained, and the purpose of main component dimension reduction is to eliminate unsuitable data, so that the dimension of the data is reduced, the dimension-reduced data meets training requirements of a follow-up relation model, and training difficulty is reduced.

And extracting a target wine grape raw material index from the target wine grape raw material sample data, mapping the target wine grape raw material index into a wine grape raw material quality index according to the main component factor load matrix, and taking the target wine grape raw material sample data, the standardized wine product sample set and the wine grape raw material quality index as target data for subsequent calculation and use, wherein the target data comprises the target wine grape raw material sample data, the standardized wine product sample set and the wine grape raw material quality index.

And S40, predicting the quality index of the wine product based on the target data, and acquiring calculation data in the predicting process.

The step of predicting the quality index of the wine product based on the target data is specifically:

firstly, generating a training set of a multiple linear regression model according to the target brewing grape raw material sample data and the standardized grape product sample set, training the multiple linear regression model according to the training set to obtain a prediction model corresponding to the grape product quality index, wherein the prediction model is used for predicting the grape product quality index according to the brewing grape raw material quality index, and in the follow-up step, the grape product limitation constraint is determined through the prediction model.

And secondly, extracting target wine product indexes from the standardized wine product sample set, determining a regression function corresponding to the target wine product indexes based on a preset coefficient matrix, and determining the fitting goodness according to the regression function.

And thirdly, taking the prediction model and the fitting goodness obtained in the prediction step process as calculation data in the prediction process for subsequent calculation and use, namely, the calculation data in the prediction process comprise the prediction model and the fitting goodness.

It should be understood that, in order to solve the precision problem, a correction factor based on regression prediction precision is introduced for the constraint of the wine grape raw material standard to reform the constraint condition, so that the optimized wine grape raw material can maximally ensure that a product conforming to the wine quality standard is obtained, and the reliability of the optimization decision is improved.

And S50, constructing a brewing grape raw material quality standard optimization model according to the calculated data and a preset optimization target.

The preset optimization target is to set optimization of the raw material quality index standard as a target.

It should be noted that, constraint conditions of the optimization model of the quality standard of the raw material of the wine grape are mainly divided into two types:

a first type of constraint: wine grape raw material limitation constraint. The constraint limits the solving range according to the theoretical reasonable range of index values of the wine grape raw materials.

The second type of constraint: wine preparation restriction constraints. The constraint is that the limitation of the wine product is transferred to the limitation of the wine raw material through the transfer of the relation model of the wine raw material and the wine product, wherein the problem of precision correction of the relation model is also considered. Taking two wine brewing grape raw material indexes and two wine product indexes as examples to research and construct the principle of wine product limitation constraint, the principle can be popularized to the situation of higher dimensional space.

Establishing wine product limitation constraint:

wherein x is ₁ 、x ₂ For two predicted variables (ingredient and sweetness of the wine grape raw material), y ₁ 、y ₂ For two response variables (hue and mouthfeel of wine products), a predictive model y is trained ₁ ＝f ₁ (x ₁ ，x ₂ )、y ₂ ＝f ₂ (x ₁ ，x ₂ ) The method comprises the steps of carrying out a first treatment on the surface of the Wherein, the liquid crystal display device comprises a liquid crystal display device,

indicating the lower boundary of the color and taste index standard of the wine product, < >, and->

The upper limit of the color and taste index standard of the wine product is shown.

The four solid oblique straight lines as in fig. 2 form the boundary of the wine product limitation constraint, and the area enclosed by the four oblique straight lines is the wine product limitation constraint area, namely a parallelogram area, and the coordinate points (x ₁ ，x ₂ ) The components and sweetness quality indexes of the expressed wine grape raw materials are mapped into wine product indexes through a relation model f under the condition that the first constraint of the wine grape raw materials is not considered, and the wine product indexes obtained after the mapping in theory all meet the wine product constraint.

The wine product constraint domain shown in fig. 2, if the first class constraint is considered, obtains the quality of the wine brewing grape raw material conforming to the quality standard of the wine brewing grape raw material, namely, the target area of the required wine quality range is selected inside the area, and the required target area is a rectangle in the quality range area of the wine brewing grape raw material. The target area should be a rectangular area containing as many varieties of the raw materials of the wine grapes as possible in the raw material quality area of the wine grapes formulated in conformity with the quality standards of the raw materials of the wine grapes.

The rectangular area can be determined by two points: the points of the rectangular area furthest from the origin and closest can be determined accordingly. The optimization model aims at enabling points farthest from the original point to reach the farthest and enabling the nearest points to reach the nearest point on the premise that all vertexes of the target area are in the area conforming to the quality standard of the wine grape raw material.

For example, two points A and B in FIG. 2 are shown, and the coordinate values of the two points are the upper and lower bounds of the quality index of the brewing grape raw material, which are the optimal modeling results. The rectangular area drawn by the points A and B is the dotted area in fig. 2, and the index value of the raw material of the wine grape indicated by the coordinate points contained in the area is theoretically preferable. The objective of the optimization model is to find the coordinates of the points A and B, and the coordinates of the two points are set as the optimization objective. The set requirements for the optimization objective are described in connection with the rectangle in fig. 2:

(1) The length of each side represents the value range of the wine quality index represented by the side, so that each side needs to be as long as possible.

(2) The sum of the rectangular side lengths should also be the largest sought in the feasible region.

(3) Therefore, when the multi-objective is subjected to weighted solution, the optimization weight importance of each index is set according to the discrete characteristic of the quality index, and each weight proportion is intuitively expressed as the ratio of the side length of the dotted rectangle.

And reducing the dimension of the solving space to the index number of the wine grape raw material index set, wherein the wine grape raw material restriction constraint and the wine product restriction constraint form a feasible region defined by a plurality of hyperplanes, and the modeling optimization solving target is to search a hypercube in the feasible region.

And step S60, determining the quality index range of the brewing grape raw material according to the brewing grape raw material quality standard optimization model.

It should be noted that, the optimization model of the quality standard of the raw material of the wine grape can be optimized to obtain a regulating and controlling model, and then the quality index range of the raw material of the wine grape is determined according to the regulating and controlling model, and it should be understood that the index range is the index standard, and in this embodiment, the index range represents the same meaning.

The main means of the optimization is to adjust the weight in the optimization function, so that the samples of the solution conclusion after the regulation are covered as much as possible, and the weight can be adjusted by adopting the methods of quartiles and the like in the discrete measurement index. Calculating the length of the quartile, obtaining the weight through normalization processing, and substituting the weight into a model of the modeling step to carry out secondary modeling solution. The ratio of each side length of the rectangle obtained by the secondary modeling is the ratio of the dispersion of each index, and then sensitivity analysis is carried out to search the sum of the ranges of each index (the sum of each side length) so as to observe whether the possibility of improvement exists or not, thereby obtaining the most suitable solution.

The secondary modeling is controlled as follows based on the primary modeling:

(1) Substituting the maximum side length in the primary modeling solution conclusion into constraint, and setting the optimization weight of each side length as the dispersion of each index of the sample data.

(2) And (3) setting a reduction step length for the maximum side length in the step (1), and carrying out multiple optimization solutions.

(1) And the step is to optimize parameters based on the primary modeling result and redefine the ratio constraint of each side length. (2) Setting a comparison experiment to analyze sensitivity, and analyzing the change condition of the solution range to obtain an optimal solution. The optimized solution regulated and controlled in the two steps can meet the setting requirement of the optimization target in the modeling step, and the optimized range of each index is obtained.

In the embodiment, a sample database constructed according to the wine grape raw material index and the wine product index is obtained; extracting a wine grape raw material sample set and a wine product sample set from the sample database, setting indexes in the wine grape raw material sample set as prediction variables, and setting indexes in the wine product sample set as response variables; preprocessing the data in the sample database based on the predicted variable and the response variable to obtain processed target data; predicting the quality index of the wine product based on the target data, and acquiring calculation data in the prediction process; constructing a brewing grape raw material quality standard optimization model according to the calculation data and a preset optimization target; and determining the range of the quality index of the raw material of the wine grapes according to the optimization model of the quality standard of the raw material of the wine grapes. According to the method, the data in the sample database are preprocessed to obtain the target data, the calculation data in the process of predicting the quality index of the wine product based on the target data is obtained, the transfer of the color tone and the taste of the wine product to the components and the sweetness of the wine raw material is completed, the wine raw material quality standard optimization model is built, the wine raw material quality index range is determined by building the wine raw material quality standard optimization model, the potential of wine raw material input selection to improve the quality of the wine product is exerted, and the technical problem that how to quickly and scientifically determine the optimal range of the wine raw material quality index under given production process conditions is solved, so that the wine raw material can produce qualified wine products is solved.

As shown in fig. 3, a second embodiment of the data-driven model analysis method for solving the range of raw material indexes of wine according to the present invention is proposed based on the first embodiment, and the step S30 specifically includes:

step S301, performing standardization processing on the sample set in the sample database based on the prediction variable and the response variable, to obtain a standardized wine raw material sample set and a standardized wine product sample set.

The brewing grape raw material sample sets D are respectively _M And wine product sample set D _N Carrying out standardization treatment to obtain a standardized wine raw material sample set and a standardized wine product sample set, wherein the calculation formula is as follows:

wherein x is _i ＝(x _1i ；x _2i ；…；x _ti ) (i=1, 2, …, m) is wine grapeA raw material sample set;

y _j ＝(y _1j ；y _2j ；…；y _tj ) (j=1, 2, …, n) is a sample set of wine preparations; t brewing grape raw materials;

mean value of

Standard deviation->

The normalized sample set is still denoted as D _M 、D _N 。

And step S302, performing main component dimension reduction on the standardized brewing grape raw material sample data in the standardized brewing grape raw material sample set to obtain target brewing grape raw material sample data and main component factor load moment.

The specific steps of dimension reduction of the specific main components are as follows:

(1) And carrying out Pearson correlation analysis according to the evaluation index of the wine product and the evaluation index of the wine brewing grape raw material. If strong correlation exists between indexes, the main component dimension reduction can be considered, and the quality of the wine product under a given production scene can be predicted by using a multi-element linear model.

The evaluation indexes of the wine products are (including but not all the following) as follows: sensory requirements = { clarity, hue, purity, concentration, quality, purity, concentration, persistence, quality }, physicochemical requirements = { alcoholic strength, total sugar, dry extract, volatile acid }, composition = { anthocyanin, tannin, total phenol, total flavonoids of wine, resveratrol, trans-resveratrol glycoside, cis-resveratrol glycoside, trans-resveratrol, cis-resveratrol, DPPH half-inhibitory volume }.

The evaluation indexes of the wine grape raw materials are (the following are included but not all indexes): total amino acid, single amino acid content, protein, VC content, anthocyanin, fresh weight, tartaric acid, malic acid, citric acid, polyphenol oxidase activity, browning degree, DPPH free radical, total phenol, tannin, total grape flavone, resveratrol, trans-resveratrol glycoside, cis-resveratrol glycoside, trans-resveratrol, cis-resveratrol, flavonol, myricetin, quercetin, kaempferol, isorhamnetin, total sugar, reducing sugar, fructose, glucose, soluble solids, PH, titratable acid, solid acid ratio, dry matter content, ear mass, hundred grain mass, stem ratio, juice yield, peel mass, peel color.

(2) The main component is used for reducing the dimension. In the principal component analysis PCA flow, m is the dimension of a brewing grape raw material sample set, d is the dimension of data after dimension reduction, d is specified by observing the total variance of the data after dimension reduction, and the total variance can be interpreted as the interpretation variable number of the second-stage regression model to be trained. After the PCA process of principal component analysis is finished, the eigenvectors with smaller corresponding eigenvalues are discarded, the discarding rule is that if the accumulated variance of the former eigenvalues exceeds 95%, the subsequent eigenvectors can be discarded, and the dimension of the principal component dimension reduction is m-d. The purpose of dimension reduction is to reduce the cost of training calculation and simultaneously make the input training data accord with one of basic assumptions of a multi-element linear model, namely, no correlation exists among interpretation variables.

Finally, reducing the dimension of the standardized brewing grape raw material sample data to target brewing grape raw material sample data D _d ：

Obtaining a principal component factor load matrix:

step S303, extracting target wine grape raw material indexes from the target wine grape raw material sample data.

And step S304, mapping the target brewing grape raw material index into a brewing grape raw material quality index according to the main component factor load matrix.

The main component factor load matrix is used for calculating s main component expressions, and the main component expressions are used for mapping the target wine grape raw material index into the wine grape raw material quality index. The expression of the main components is:

where i=1, 2, …, m,

represents the i-th raw material quality index, j=1, 2, …, d, coefficient of main component with respect to each raw material quality index ∈>

，λ＝(λ ₁ ，λ ₂ ，…，λ _j ) For the d eigenvalues selected.

And step S305, taking the target wine grape raw material sample data, the standardized grape product sample set and the wine grape raw material quality index as target data.

Further, the step S40 includes:

and S401, generating a training set of a multiple linear regression model according to the target wine grape raw material sample data and the standardized grape product sample set.

It should be understood that the target brewing grape raw material sample data D after dimension reduction _d Based on the quality index of the wine brewing grape raw material, the quality index of the grape wine product is predicted.

In training the multiple linear regression model of each quality index of the wine product, D is given as _d And standardized wine product sample set D _N Training set (D) constituting multiple linear regression model _d |D _N )。

And step S402, training the multiple linear regression model according to the training set to obtain a prediction model corresponding to the quality index of the wine product.

Step S403, extracting target wine product indexes from the standardized wine product sample set, and determining regression functions corresponding to the target wine product indexes based on a preset coefficient matrix.

And step S404, determining the goodness of fit according to the regression function.

It should be noted that, since each multiple linear regression model is used to predict a single variable, the sample set input in each solution using the least squares method is:

wherein D is _d Is the target brewing grape raw material sample data after dimension reduction, y _j ＝(y _1j ；y _2j ；…；y _tj ) (j=1, 2, …, n) is a wine product index set.

And (3) ending the algorithm flow, and obtaining a prediction model of the quality index of each wine product. According to the coefficient matrix (θ|ω) ^* ) _n*(m+1) Giving a regression function of the ith wine product index:

where i=1, 2, …, n, j=1, 2, …, m. θ is the principal component factor load matrix, multiple linear regression function f _i (x) Fitting goodness R of (2) _i ² The value is 0,1]。

And step S405, taking the prediction model and the goodness of fit as calculation data in the prediction process.

In this embodiment, the accuracy of the prediction model is ensured by performing data processing on the data in the sample database, and then the quality index of the wine product is predicted by the quality index of the wine raw material, so that the transfer of the quality index of the wine product to the quality index of the wine raw material is completed, and the direct, effective and reasonable model establishment is ensured.

As shown in fig. 4, a third embodiment of the data-driven model analysis method for solving the range of raw materials of wine according to the present invention is proposed based on the first embodiment or the second embodiment, in this embodiment, the step S50 is described based on the second embodiment, and includes:

step S501, physical and chemical property data of the quality of the brewing grape raw material corresponding to the brewing grape raw material quality index are searched, and the limiting constraint of the brewing grape raw material is determined based on the physical and chemical property data.

It should be understood that the lower and upper limit values x of the criteria determining the various quality indicators of the raw material of the wine grape ^low ，x ^up A vector of decision variables;

wherein, the liquid crystal display device comprises a liquid crystal display device,

it should be noted that, based on the physicochemical properties of the raw material quality of the wine grapes, a first type of constraint is determined: wine grape raw material limitation constraint.

The wine grape raw material limiting constraint is a wine grape raw material index range meeting the requirements which is put into actual production, and the vector space represented by the index range is:

X _limit ＝{x|l _α ≤x _α ≤u _α ，α＝1，2，…，m)

wherein l _α And u _α Respectively the raw material index x of the wine grapes _α There are m such indices for the lower and upper bounds of (2).

Step S502, determining wine preparation limit constraints based on the prediction model and preset target food quality requirements.

And step S503, correcting the wine product limit constraint according to the fitting goodness to obtain a target wine product limit constraint.

It should be noted that, based on the prediction model and the preset target food quality requirement, determining a wine product limitation constraint, and correcting the wine product limitation constraint according to the fitness, the step of obtaining the target wine product limitation constraint specifically includes:

(1) Determination of quality standards for wine products

Assuming physicochemical properties and feel in quality index of wine productsThe feasible range of the official score or TPA index is l= (L ₁ ，L ₂ ，…，L _n )，U＝(U ₁ ，U ₂ ，…，U _n ) Representing the lower and upper bounds of the target wine product quality index, respectively.

(2) Determination of correction factors

To improve the accuracy of the limitation constraint of the wine products, the degree of fit R is used ² And correcting the constraint of the quality standard of the wine product. Goodness of fit obtained for the prediction stage

The specific correction method comprises the following steps:

a. calculating delta _k ＝L _k -U _k ，Δ _k Is the range initial value.

b. Calculating the goodness of fit R of each regression function _i ² "correction factor" of (3):

c. calculating the upper and lower bounds of the quality index of the wine product to reduce and increase the same size according to the correction amounts of the upper and lower bounds:

[L′ _j ，U′ _j ]＝[L _j +0、5*Δ _j *∈ _j ，U _j -0.5*Δ _j *∈ _j ]

where j=1, 2, …, n, represents the quality standard at which the kth product index is established, and 0.5 represents the upper and lower bound correction amounts are equally distributed between the upper and lower bounds.

(3) Wine product limitation constraint

The wine product limit constraint is set by the steps of (1) and (2):

wherein k=1, 2, …, n, X _process The feasible region limited by the "wine product limitation constraint",

is the regression function of the kth wine product index, L= (L) ₁ ，L ₂ ，…，L _n )，U＝(U ₁ ，U ₂ ，…，U _n ) Representing the lower and upper bounds of the target wine product quality index, respectively.

Step S504, a high-dimensional target space is constructed according to a plurality of target brewing grape raw material indexes, and diffusion factors are set in the high-dimensional target space.

And step S505, determining diffusion factor constraint according to the diffusion factor and the preset target area requirement.

The preset target area requirement is a requirement targeting maximization of the target area.

It should be noted that, based on the requirement that the target area is maximized as the target, a third type of constraint is determined: diffusion factor constraint, namely setting a diffusion factor 'in a high-dimensional target space formed by a plurality of target brewing grape raw material indexes, and substituting the diffusion factor' into a linear weighting method target to meet the following requirements:

(1) The range is reasonable, so that the range of the raw materials of the wine grape is ensured to be a high-credibility range solution given under the condition of comprehensively considering the prediction errors of various products.

(2) The range is the most widespread, and the final solution is pursued to cover as much as possible in the wine raw material limitation constraint and the wine product limitation constraint.

Let x be ^low ，x ^up For the lower and upper bounds of the final solution of each raw material, delta is the diffusion factor, and there are m such indices

And step S506, taking the wine grape raw material limit constraint, the wine product limit constraint and the diffusion factor constraint as constraint conditions.

And S507, constructing a wine grape raw material quality standard optimization model according to the constraint conditions and a preset optimization target.

The range of the quality index of the brewing grape raw material solved by the multi-objective optimization model needs to cover a wider range on the premise of meeting constraint conditions, and the maximization of delta needs to be met firstly, which is the primary objective:

max f ₁ ＝δ

And the final solution upper and lower bounds are to meet the maximum and minimum, respectively, with the following secondary objectives:

in summary, the optimization model of the quality standard of the wine grape raw material is a mathematical model of multi-objective optimization, and is specifically expressed as follows:

wherein x is ^low ，x ^up The lower and upper limit values of the standard of each quality index of the wine grape raw material are adopted, delta is a diffusion factor, f is an objective function, and L= (L) ₁ ，L ₂ ，…，L _n )，U＝(U ₁ ，U ₂ ，…，U _n ) Respectively representing the lower and upper bounds and X of the quality index of the target wine product _limit Vector space, y, expressed by raw material index range of wine grape meeting requirements _k Is a wine product index set.

Further, the step S60 includes:

and step S601, converting the brewing grape raw material quality standard optimization model into a single-target brewing grape raw material quality standard optimization model based on a linear weighting method.

It should be noted that, by using a linear weighting method, a weight value with an order difference is set according to the priority of the target and the importance of the target of the same level, and the optimization model of the quality standard of the wine grape raw material is converted into a optimization model of the quality standard of the single target wine grape raw material:

wherein beta is _α The weights of the indexes are equal

Beta' is the weight of the diffusion factor, and the general ratio beta is calculated when the proper solution is obtained _α One and two orders of magnitude greater. />

In a high-dimensional space constructed by all wine grape raw material index variables, X _limit Limiting the basic value range of the variable of each dimension of the space to form a hypercube space, and X _process A super-dimensional space with irregular shapes is constructed by linear functions of the dimensional variables and L, U. These two spaces have two cases of inclusion or partial overlap in the high-dimensional space. The objective of setting the objective function is to find a hypercube in the overlapping region of the two high-dimensional spaces, the hypercube having 2 ^m A plurality of vertexes, wherein the coordinates of two points are respectively

And->

The two coordinates already contain all vertex coordinate information of the hypercube, so that all the standard ranges of the brewing grape raw material quality can be determined only by determining the two coordinates.

And step S602, performing quartile calculation on the standardized brewing grape raw material sample data according to the single-target brewing grape raw material quality standard optimization model to obtain quartile calculation result data.

It should be understood that the third class constraint is optimized using the optimal solution calculated by the single-object orthographic normalization model, and the quartiles of the raw material normalization data are calculated first, that is, the quartiles are used to arrange all the values from small to large and divide them into four equal parts, and the values are located at the three division points.

And step S603, determining a regulation and control model according to the quartile calculation result data and the brewing grape raw material quality standard optimization model.

Further, in the step S603, the method specifically includes:

selecting lower quartile data and upper quartile data from the quartile calculation result data; calculating a difference value according to the lower quartile data and the upper quartile data; determining constraint weights according to the difference value and a preset standardization method; optimizing the diffusion factor constraint according to the constraint weight and the diffusion factor to obtain a target diffusion factor constraint; and regulating and controlling the brewing grape raw material quality standard optimization model according to the target diffusion factor constraint to obtain a regulation and control model.

From the calculation result data, a value at 25% (lower quartile data) and a value at 75% (upper quartile data) are selected, and a difference r= (R) is calculated from the lower quartile data and the upper quartile data ₁ ，r ₂ ，…，r _α )。

Calculating new solving weights and constraint weights of all decision variables by using a min-max standardization method:

β _α ＝r _α /∑ _α r _α

at this time, the weights still satisfy

But not equal. According to the diffusion factor delta ₀ Adjusting the third type of restriction

Modify it to +.>

Wherein ρ is a relaxation factor used to shrink the diffusion factorSmall such that the coordinates of the final solution space (hypercube) have delta ₀ * The relaxation space of ρ, each vertex can adjust for variations in this space. And gamma is a floating variable and is used for controlling the final solution of each index to float according to the discrete characteristics of each quality index of the actual brewing grape raw material so as to obtain different solution ranges.

The regulated multi-objective optimization model with priority is as follows:

/>

wherein x is ^low ，x ^up The lower and upper limit values of the standard of each quality index of the wine grape raw material are adopted, delta is a diffusion factor, f is an objective function, and L= (L) ₁ ，L ₂ ，…，L _n )，U＝(U ₁ ，U ₂ ，…，U _n ) Respectively representing the lower and upper bounds and X of the quality index of the target wine product _limit Vector space, y, expressed by raw material index range of wine grape meeting requirements _k Is a wine product index set, and gamma is a floating variable.

Wherein P1 is far greater than P2, the value range of the relaxation factor rho is [0,0.5], namely, the maximum half value of the maximum diffusion factor is used as the floating range of the hypercube coordinate, the step length of 0.05 rho is set, 10 times of solving is carried out, and the most reasonable solution range is obtained by comparing the result.

And step S604, determining the quality index range of the brewing grape raw material according to the regulation model.

Further, in the step S604, the method specifically includes:

calculating a lower limit value of the quality index of the raw material of the wine grapes and an upper limit value of the quality index of the raw material of the wine grapes according to the regulation model; performing inverse standardization treatment on the lower limit value of the quality index of the brewing grape raw material and the upper limit value of the quality index of the brewing grape raw material; and determining the quality index range of the wine grape raw material according to the processing result.

When solving by using a linear weighting method, new solving weights of all decision variables are substituted into the multi-objective single-objective method:

wherein γ is a "floating variable", x ^low ，x ^up A lower limit value (lower limit value of the quality index of the wine grape raw material) and an upper limit value (upper limit value of the quality index of the wine grape raw material) which are the standard of each quality index of the wine grape raw material, m indexes, beta _α For updated optimization weights, β' is an order of magnitude greater than β _α Is high.

It should be appreciated that the standard deviation sigma is normalized in terms of data _i Mean value of

i represents the number of raw material quality indexes, and the solution result x ^low 、x ^up Performing inverse standardization treatment to obtain the optimized range of each raw material index

The inverse normalization formula is:

in the embodiment, the standard of the quality index of the raw material of the wine grape is determined by constructing a standardized optimization model of the quality index of the raw material of the wine grape, and in order to contain as many raw material varieties as possible in the formulated variation range of the quality index of the raw material of the wine grape, the structure and parameters of the model of the quality index of the raw material are optimized and adjusted, the standardized optimization model of the raw material of the wine grape is improved to obtain a regulation and control model, and the shape of a hypercube is optimized, so that the most suitable range of the quality index of the raw material of the wine grape of a target product is obtained.

In addition, referring to fig. 5, the embodiment of the invention further provides a data-driven model analysis device for solving the raw material index range of the wine, where the data-driven model analysis device for solving the raw material index range of the wine includes:

the data acquisition module 10 is used for acquiring a sample database constructed according to the wine grape raw material index and the wine product index.

The variable setting module 20 is configured to extract a wine raw material sample set and a wine product sample set from the sample database, and set an index in the wine raw material sample set as a prediction variable, and set an index in the wine product sample set as a response variable.

And the data processing module 30 is configured to pre-process the data in the sample database based on the prediction variable and the response variable, and obtain processed target data.

The index prediction module 40 is configured to predict the quality index of the wine product based on the target data, and obtain the calculation data in the prediction process.

The model construction module 50 is configured to construct a wine grape raw material quality standard optimization model according to the calculation data and a preset optimization target.

The standard determining module 60 is configured to determine a range of quality indexes of the raw materials of the wine brewing grape according to the optimization model of the quality standard of the raw materials of the wine brewing grape.

In this embodiment, the data acquisition module 10 is configured to acquire a sample database constructed according to a wine raw material index and a grape wine product index; a variable setting module 20, configured to extract a wine grape raw material sample set and a wine product sample set from the sample database, and set an index in the wine grape raw material sample set as a prediction variable, and set an index in the wine product sample set as a response variable; a data processing module 30, configured to pre-process data in the sample database based on the prediction variable and the response variable, and obtain processed target data; an index prediction module 40, configured to predict a wine product quality index based on the target data, and obtain calculation data in a prediction process; the model construction module 50 is used for constructing a brewing grape raw material quality standard optimization model according to the calculation data and a preset optimization target; the standard determining module 60 is configured to determine a range of quality indexes of the raw materials of the wine grapes according to the optimization model of the quality standard of the raw materials of the wine grapes.

In an embodiment, the model building module 50 is further configured to find physicochemical property data of the quality of the wine grape raw material corresponding to the quality index of the wine grape raw material, and determine a limitation constraint of the wine grape raw material based on the physicochemical property data; determining wine product limitation constraint based on the prediction model and a preset target food quality requirement; correcting the wine product limit constraint according to the fitting goodness to obtain a target wine product limit constraint; constructing a high-dimensional target space according to a plurality of target wine grape raw material indexes, and setting diffusion factors in the high-dimensional target space; determining a diffusion factor constraint according to the diffusion factor and a preset target area requirement; taking the wine grape raw material limit constraint, the grape product limit constraint and the diffusion factor constraint as constraint conditions; and constructing a brewing grape raw material quality standard optimization model according to the constraint conditions and a preset optimization target.

In one embodiment, the standard determining module 60 is further configured to convert the wine brewing grape raw material quality standard optimization model into a single-objective wine brewing grape raw material quality standard optimization model based on a linear weighting method; performing quartile calculation on the standardized brewing grape raw material sample data according to the single-target brewing grape raw material quality standard optimization model to obtain quartile calculation result data; determining a regulation and control model according to the quartile calculation result data and the brewing grape raw material quality standard optimization model; and determining the quality index range of the brewing grape raw material according to the regulation model.

In one embodiment, the standard determining module 60 is further configured to select lower quartile data and upper quartile data from the quartile calculation result data; calculating a difference value according to the lower quartile data and the upper quartile data; determining constraint weights according to the difference value and a preset standardization method; optimizing the diffusion factor constraint according to the constraint weight and the diffusion factor to obtain a target diffusion factor constraint; and regulating and controlling the brewing grape raw material quality standard optimization model according to the target diffusion factor constraint to obtain the regulation and control model.

In one embodiment, the standard determining module 60 is further configured to calculate a lower limit value of a raw material quality index of the wine-making grape and an upper limit value of a raw material quality index of the wine-making grape according to the regulation model; performing inverse standardization treatment on the lower limit value of the wine grape raw material quality index and the upper limit value of the wine grape raw material quality index; and determining the quality index range of the wine grape raw material according to the processing result.

Other embodiments or specific implementation methods of the data-driven model analysis device for solving the wine raw material index range of the present invention may refer to the above method embodiments, and will not be described herein.

It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.

The foregoing embodiment numbers of the present invention are merely for the purpose of description, and do not represent the advantages or disadvantages of the embodiments.

From the above description of embodiments, it will be clear to a person skilled in the art that the above embodiment method may be implemented by means of software plus a necessary general hardware platform, but may of course also be implemented by means of hardware, but in many cases the former is a preferred embodiment. Based on this understanding, the technical solution of the present invention may be embodied essentially or in a part contributing to the prior art in the form of a software product stored in an estimator readable storage medium (e.g. ROM/RAM, magnetic disk, optical disk) as described above, comprising instructions for causing a smart device (which may be a cell phone, estimator, data driven model analysis device for solving a raw material index range of a wine, air conditioner, or data driven model analysis device for solving a raw material index range of a wine network, etc.) to perform the method described in the embodiments of the present invention.

The foregoing description is only of the preferred embodiments of the present invention, and is not intended to limit the scope of the invention, but rather is intended to cover any equivalents of the structures disclosed herein or equivalent processes shown in the accompanying drawings, or any application, directly or indirectly, in other related arts.

Claims

1. A data-driven model analysis method for solving a range of wine raw material indexes, the method comprising the steps of:

constructing a brewing grape raw material quality standard optimization model according to the calculation data and a preset optimization target;

determining the quality index range of the brewing grape raw material according to the brewing grape raw material quality standard optimization model;

the step of constructing the brewing grape raw material quality standard optimization model according to the calculated data and the preset optimization target specifically comprises the following steps:

searching physicochemical property data of the quality of the brewing grape raw material corresponding to the quality index of the brewing grape raw material, and determining the limitation constraint of the brewing grape raw material based on the physicochemical property data;

taking the wine grape raw material limit constraint, the grape product limit constraint and the diffusion factor constraint as constraint conditions;

2. The method for analyzing a data-driven model for solving a range of wine raw material indexes according to claim 1, wherein the step of preprocessing data in the sample database based on the predicted variable and the response variable to obtain processed target data specifically comprises the steps of:

carrying out standardization processing on a sample set in the sample database based on the prediction variable and the response variable to obtain a standardized wine raw material sample set and a standardized wine product sample set;

3. The method for analyzing a data-driven model for solving a range of wine raw material indexes according to claim 2, wherein the step of predicting the quality index of the wine product based on the target data and obtaining the calculation data in the prediction process specifically comprises the following steps:

determining a goodness of fit according to the regression function;

4. The method for analyzing a data-driven model for solving a wine raw material index range according to claim 1, wherein the step of determining a wine raw material quality index range according to the wine raw material quality standard optimization model specifically comprises:

5. The method for analyzing a data-driven model for solving a range of wine raw material indexes according to claim 4, wherein the step of determining a regulation model according to the quartile calculation result data and the optimization model of wine raw material quality standard specifically comprises the following steps:

6. The method for analyzing a data-driven model for solving a wine raw material index range according to claim 4, wherein the step of determining a wine raw material quality index range according to the regulation model specifically comprises:

calculating a lower limit value of the wine grape raw material quality index and an upper limit value of the wine grape raw material quality index according to the regulation model;

7. The data-driven model analysis device for solving the raw material index range of the wine is characterized by comprising the following components:

the variable setting module is used for extracting a wine grape raw material sample set and a wine product sample set from the sample database, setting indexes in the wine grape raw material sample set as prediction variables and setting indexes in the wine product sample set as response variables;

the standard determining module is used for determining the quality index range of the brewing grape raw material according to the brewing grape raw material quality standard optimizing model;

the model construction module is also used for searching physicochemical property data of the quality of the brewing grape raw materials corresponding to the quality index of the brewing grape raw materials and determining the limitation constraint of the brewing grape raw materials based on the physicochemical property data; determining wine product limitation constraint based on the prediction model and a preset target food quality requirement; correcting the wine product limit constraint according to the fitting goodness to obtain a target wine product limit constraint; constructing a high-dimensional target space according to a plurality of target brewing grape raw material indexes, and setting diffusion factors in the high-dimensional target space; determining a diffusion factor constraint according to the diffusion factor and a preset target area requirement; taking the wine grape raw material limit constraint, the grape product limit constraint and the diffusion factor constraint as constraint conditions; and constructing a brewing grape raw material quality standard optimization model according to the constraint conditions and a preset optimization target.

8. The data-driven model analysis device for solving a wine raw material index range according to claim 7, wherein the data processing module is further configured to perform normalization processing on a sample set in the sample database based on the prediction variable and the response variable to obtain a normalized wine raw material sample set and a normalized wine product sample set;

the data processing module is also used for extracting target wine grape raw material indexes from the target wine grape raw material sample data;

the data processing module is further used for mapping the target brewing grape raw material index into a brewing grape raw material quality index according to the main component factor load matrix;

9. The data-driven model analysis device for solving a wine raw material index range of claim 8, wherein the index prediction module is further configured to generate a training set of a multiple linear regression model from the target wine raw material sample data and the standardized wine product sample set;