A method of processing a tea leaf sample

Abstract

The present application relates to the technical field of electric digital data processing, and particularly relates to a tea sample processing method. The method comprises the following steps: acquiring a meteorological parameter list R of tea samples, R=(r1, r2, …, r i ,…,r u ), r i is a record of the meteorological parameter of the i-th tea sample; acquiring a standard priority sequence Z of the tea samples; traversing R, and adding r j i,m to a preset j-th original sequence H m,j of the m-th meteorological parameter; acquiring a Pearson correlation coefficient original list P; traversing P, and if p m,j ≥p0, then adding the key information (m, j) corresponding to p m,j to a preset target parameter sequence G; acquiring a target weight sequence A; acquiring data E of a target tea; traversing E, and according to e n , acquiring the grade b n of the target tea; and acquiring the priority z' of the target tea. The present application can automatically judge the priority of tea.

Description

Technical Field

[0001] This invention relates to the field of electronic digital data processing technology, and in particular to a method for processing tea samples. Background Technology

[0002] Current technologies for evaluating tea priority primarily rely on human experience and sensory assessment. Different tea priorities correspond to different tea qualities, with higher priorities indicating better quality. However, this method of manually determining tea priority is highly subjective. Meteorological factors during tea growth significantly influence tea priority, and how to automatically determine tea priority based on these factors is a pressing issue that needs to be addressed. Summary of the Invention

[0003] The purpose of this invention is to provide a method for processing tea samples, which is used to automatically determine the priority of tea based on meteorological factors during the tea growth process.

[0004] According to the present invention, a method for processing tea samples includes the following steps:

[0005] S100, Obtain the meteorological parameter list R for the tea sample, R = (r1, r2, ..., r i ,…,r u ), r i For the meteorological parameters of the i-th tea sample, r i =(r i,1 ,r i,2 ,…,r i,m ,…,r i,M ), r i,m Let r be the sequence of the m-th meteorological parameter of the i-th tea sample. i,m =(r 1 i,m ,r 2 i,m ,…,r j i,m ,…,r v i,m ), r j i,m Let j be the value of the m-th meteorological parameter corresponding to the i-th tea sample at the j-th preset time point, where j ranges from 1 to v, v is the number of preset time points, m ranges from 1 to M, M is the number of meteorological parameters, and i ranges from 1 to u, where u is the number of tea samples.

[0006] S200, Obtain the standard priority sequence Z of the tea samples, Z = (z1, z2, ..., z...). i ,…,z u ), z iThe standard priority is the i-th tea sample.

[0007] S300, iterate through R, and r j i,m Added to the j-th original sequence H of the m-th meteorological parameter in the preset sequence. m,j H m,j =(r j 1,m ,r j 2,m ,…,r j i,m ,…,r j u,m ), H m,j It is initialized to a null value.

[0008] S400, obtain the original list P of Pearson correlation coefficients, P = (p 1,1 ,p 1,2 ,…,p 1,j ,…,p 1,v ,p 2,1 ,p 2,2 ,…,p 2,j ,…,p 2,v ,…,p m,1 ,p m,2 ,…,p m,j ,…,p m,v ,…,p M,1 ,p M,2 ,…,p M,j ,…,p M,v ), p m,j For H m,j Pearson correlation coefficient with Z.

[0009] S500, iterate through P, if p m,j If p ≥ p0, then p m,j The corresponding key information (m,j) is appended to the preset target parameter sequence G, resulting in G = (g1,g2,…,g n ,…,g N ), g n For the nth key piece of information added to G, g n =(c n ,t n ), c n For g n The included meteorological parameter numbers, t n For g n The preset time point number is included, where n ranges from 1 to N, N is the number of key information points appended to G, and G is initialized to null; p0 is the preset Pearson correlation coefficient threshold.

[0010] S600, Obtain the target weight sequence A, A = (a1, a2, ..., a... n ,…,a N ), a n For the cth n The t-th meteorological parameter n Weights at preset time points.

[0011] S700, Obtain the target tea data E, E = (e1, e2, ..., e n ,…,e N ), e n For the target tea, the cth n The t-th meteorological parameter n The value of a preset time point;

[0012] S800, iterate through E, based on e n Obtain the target tea grade b n ;

[0013] S900, obtain the priority z' of the target tea leaves, z' = ∑ N n＝1 (a n ×b n ), 0 n <1,∑ N n＝1 a n =1.

[0014] The present invention has at least the following beneficial effects:

[0015] This invention obtains a list of meteorological parameters for tea samples, which stores the values ​​of each meteorological parameter for each tea sample at each preset time point. It also obtains a standard priority sequence for the tea samples, where each element corresponds to a standard priority for a tea sample. Furthermore, this invention obtains an original sequence composed of the values ​​of different tea samples corresponding to the same meteorological parameter at the same preset time point, and obtains the Pearson correlation coefficient between each original sequence and the standard priority sequence. If the Pearson correlation coefficient between an original sequence and the standard priority sequence is greater than or equal to a preset Pearson correlation coefficient threshold, the meteorological parameter number and preset time point number corresponding to that original sequence are appended to the target parameter sequence. Thus, this invention can obtain all meteorological parameter numbers and preset time point numbers that are relatively relevant to the tea priority. Based on the weights corresponding to each meteorological parameter number and preset time point number in the target parameter sequence, this invention can predict the priority of the target tea, achieving the purpose of automatically determining the tea priority. Attached Figure Description

[0016] ​To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0017] Figure 1 This is a flowchart of a tea sample processing method provided in an embodiment of the present invention. Detailed Implementation

[0018] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0019] According to the present invention, a method for processing tea samples is provided, such as... Figure 1 As shown, it includes:

[0020] S100, Obtain the meteorological parameter list R for the tea sample, R = (r1, r2, ..., r i ,…,r u ), r i For the meteorological parameters of the i-th tea sample, r i =(r i,1 ,r i,2 ,…,r i,m ,…,r i,M ), r i,m Let r be the sequence of the m-th meteorological parameter of the i-th tea sample. i,m =(r 1 i,m ,r 2 i,m ,…,r j i,m ,…,r v i,m ), r j i,m Let j be the value of the m-th meteorological parameter corresponding to the i-th tea sample at the j-th preset time point, where j ranges from 1 to v, v is the number of preset time points, m ranges from 1 to M, M is the number of meteorological parameters, and i ranges from 1 to u, where u is the number of tea samples.

[0021] Preferably, the processing method of the present invention further includes, before S100:

[0022] S010, Obtain the tea data L to be filtered, L = {l1, l2, ..., l s ,…,l η}, l s For the data of the s-th tea leaf to be filtered,

[0023] l s =(l 1 s,1 ,l 2 s,1 ,…,l j s,1 ,…,l v s,1 ,l 1 s,2 ,l 2 s,2 ,…,l j s,2 ,…,l v s,2 ,…,l 1 s,m ,l 2 s,m ,…,l j s,m ,…,l v s,m ,…,l 1 s,M ,l 2 s,M ,…,l j s,M ,…,l v s

[0024] ,M ), l j s,m Let be the value of the m-th meteorological parameter corresponding to the j-th preset time point of the s-th tea to be screened. The value of s ranges from 1 to η, and η is the number of teas to be screened.

[0025] S020, group the tea leaves to be screened according to the similarity between any two data points of tea leaves in L, and obtain the grouping result B, B={B1,B2,…,B2 ... γ ,…,B λ}, B γ Let γ be the γth group, where γ ranges from 1 to λ, and λ is the number of groups.

[0026] Those skilled in the art will understand that any method in the prior art for obtaining the similarity between two vectors falls within the protection scope of this invention. Optionally, the cosine similarity algorithm can be used to obtain the similarity between any two tea data to be screened in L.

[0027] Those skilled in the art know that any clustering method in the prior art falls within the protection scope of the present invention. Optionally, first obtain the similarity between the data of two teas to be screened in L, and then use the derivative of the sum of the similarity and 1 as the distance between the data of the two teas to be screened in L; after obtaining the distance between the data of any two teas to be screened in L, clustering can be performed according to the clustering algorithms disclosed in the prior art, and the clustering process will not be elaborated here. It should be understood that in this embodiment, the similarity between the data of the teas to be screened belonging to the same group is relatively large, and the similarity between the data of the teas to be screened belonging to different groups is relatively small.

[0028] S030, traverse B to obtain the average priority pi of B γ of B γ , pi γ =(∑ ξ σ＝1 pi γ,σ ) / ξ, where pi γ,σ is the standard priority of the σth tea to be screened in B γ , the value range of σ is from 1 to ξ, and ξ is the number of teas to be screened included in B γ .

[0029] S040, traverse B to delete the teas to be screened in B γ whose absolute value of the difference from pi γ is greater than the preset difference threshold, and append the updated B γ to the set B' of screened teas, and the initial value of B' is an empty set.

[0030] In this embodiment, the teas to be screened in B γ whose standard priorities are quite different from those of other teas to be screened are excluded, and the standard priorities of the teas to be screened in the updated B γ are relatively consistent.

[0031] S050, determine the screened teas in B' as tea samples.

[0032] The S010 - S050 of this embodiment realizes the screening process of tea data, excludes the tea data with relatively large similarity between the tea data but relatively large differences in the corresponding tea standard priorities, and ensures the accuracy of the tea data corresponding to the finally obtained tea samples.

[0033] In this embodiment, M=8. The first meteorological parameter is the average temperature (the average temperature is obtained by summing up the daily temperature data and then dividing by the number of observation days). The second meteorological parameter is the accumulated temperature (the accumulated temperature is obtained by comparing the daily temperature with a preset benchmark temperature and summing the temperatures if the temperature is higher than the preset benchmark temperature). The third meteorological parameter is the effective accumulated temperature (the effective accumulated temperature is obtained by summing up the portion of the daily temperature that is higher than the preset benchmark temperature). The fourth meteorological parameter is the average daily temperature range (the average daily temperature range is obtained by summing up the difference between the daily highest and lowest temperatures and then dividing by the number of observation days). The meteorological parameters are as follows: the number of days of observation (to obtain the average daily temperature range), the fifth meteorological parameter is the number of days with suitable temperature (i.e., counting whether the temperature is within the suitable temperature range each day, and accumulating the number of days that meet the conditions, thus obtaining the number of days with suitable temperature), the sixth meteorological parameter is the number of rainy days (i.e., counting the number of days with precipitation greater than the preset precipitation threshold, thus obtaining the number of rainy days), the seventh meteorological parameter is the cumulative sunshine hours (i.e., accumulating the sunshine hours of each day, thus obtaining the cumulative sunshine hours), and the eighth meteorological parameter is the average humidity (i.e., accumulating the humidity data of each day, and then dividing by the number of observation days, thus obtaining the average humidity value).

[0034] In this embodiment, v=8, the first preset time point is 10 days before harvest, the second preset time point is 20 days before harvest, the third preset time point is 30 days before harvest, the fourth preset time point is 40 days before harvest, the fifth preset time point is 50 days before harvest, the sixth preset time point is 60 days before harvest, the seventh preset time point is 70 days before harvest, and the eighth preset time point is 80 days before harvest.

[0035] This embodiment selects a large number of meteorological parameters, which is comprehensive, and also considers a large number of preset time points, which is more comprehensive and helps to improve the accuracy of labeling the target tea.

[0036] S200, Obtain the standard priority sequence Z of the tea samples, Z = (z1, z2, ..., z...). i ,…,z u ), z i The standard priority is the i-th tea sample.

[0037] Optional, z i The methods for obtaining it include:

[0038] S210, Obtain the initial sequence D of the i-th tea sample. i D i =(d i,1 ,d i,2 ,d i,3 ), d i,1 Let d be the phenol-to-amino acid ratio of the i-th tea sample. i,2Let d be the water extract content of the i-th tea sample. i,3 Let be the caffeine content of the i-th tea sample.

[0039] Those skilled in the art will understand that any existing method for obtaining the phenol-to-amino acid ratio, water extract content, and caffeine content in tea falls within the protection scope of this invention.

[0040] S220, Obtain the normalized sequence D' of the i-th tea sample. i D' i =(d' i,1 ,d' i,2 ,d' i,3 ), d' i,1 For d i,1 The normalized value, d' i,2 For d i,2 The normalized value, d' i,3 For d i,3 The value after normalization.

[0041] Those skilled in the art will understand that any normalization method in the prior art falls within the protection scope of this invention. Optionally, a max-min normalization method may be used for normalization.

[0042] S230, obtain z i , z i =β1×d' i,1 +β2×d' i,2 +β3×d' i,3 β1 is the weight corresponding to the phenol-amino acid ratio, β2 is the weight corresponding to the water extract content, β3 is the weight corresponding to the caffeine content, and β1+β2+β3=1.

[0043] Optional values ​​are β1 = 0.5, β2 = 0.3, and β3 = 0.2.

[0044] S300, iterate through R, and r j i,m Added to the j-th original sequence H of the m-th meteorological parameter in the preset sequence. m,j H m,j =(r j 1,m ,r j 2,m ,…,r j i,m ,…,r j u,m ), H m,j It is initialized to a null value.

[0045] In this embodiment, H m,jThis is a sequence consisting of the values ​​of the m-th meteorological parameter at the j-th preset time point corresponding to all tea samples.

[0046] S400, obtain the original list P of Pearson correlation coefficients, P = (p 1,1 ,p 1,2 ,…,p 1,j ,…,p 1,v ,p 2,1 ,p 2,2 ,…,p 2,j ,…,p 2,v ,…,p m,1 ,p m,2 ,…,p m,j ,…,p m,v ,…,p M,1 ,p M,2 ,…,p M,j ,…,p M,v ), p m,j For H m,j Pearson correlation coefficient with Z.

[0047] Those skilled in the art will recognize that the process of obtaining the Pearson correlation coefficient is prior art and will not be described in detail here.

[0048] S500, iterate through P, if |p m,j If |≥p0, then p m,j The corresponding key information (m,j) is appended to the preset target parameter sequence G, resulting in G = (g1,g2,…,g n ,…,g N ), g n For the nth key piece of information added to G, g n =(c n ,t n ), c n For g n The included meteorological parameter numbers, t n For g n The preset time point number is included, where n ranges from 1 to N, N is the number of key information points appended to G, and G is initialized to null; p0 is the preset Pearson correlation coefficient threshold.

[0049] Optionally, p0 is an empirical value.

[0050] Preferably, the process of obtaining p0 includes:

[0051] S510, randomly select Q tea samples from R to obtain the meteorological parameter records, resulting in a selection list R', R' = (r'1, r'2, ..., r'). q ,…,r' Q ), r' qLet r' be the record of meteorological parameters for the q-th tea sample randomly selected from R. q =(r' q,1 ,r' q,2 ,…,r' q,m ,…,r' q,M ), r' q,m Let r' be the sequence of the m-th meteorological parameter of the q-th tea sample randomly drawn from R. q,m =(r 1,1 q,m ,r 2,1 q,m ,…,r j,1 q,m ,…,r v,1 q,m ), r j,1 q,m Let be the value of the m-th meteorological parameter corresponding to the j-th preset time point of the q-th tea sample randomly selected from R; q ranges from 1 to Q, where Q is the preset number of samples. <M。

[0052] In this embodiment, the computational load of recording the meteorological parameters of Q tea samples randomly selected from R and performing subsequent S520-S590 is relatively small, which improves the efficiency of obtaining p0.

[0053] S520, Obtain the standard priority sequence Z' for extracting tea samples, Z' = (z'1, z'2, ..., z') q ,…,z' Q ), z' q The standard priority is the qth tea sample randomly drawn from R.

[0054] S530, iterate through R', and r j,1 q,m Added to the j-th extraction sequence H' of the preset m-th meteorological parameter m,j , thus obtaining H' m,j =(r j,1 1,m ,r j,1 2,m ,…,r j,1 q,m ,…,r j,1 Q,m ), H' m,j It is initialized to a null value.

[0055] S540, Obtain the Pearson correlation coefficient extraction list P', P' = (p' 1,1 ,p' 1,2 ,…,p' 1,j ,…,p' 1,v ,p' 2,1 ,p'2,2 ,…,p' 2,j ,…,p' 2,v ,…,p' m,1 ,p' m,2 ,…,p' m,j ,…,p' m,v ,…,p' M,1 ,p' M,2 ,…,p' M,j ,…,p' M,v ), p' m,j For H' m,j Pearson correlation coefficient with Z'; set the first variable k=1.

[0056] S550, iterate through P', if |p' m,j |≥p k Then p' m,j The corresponding key information (m,j) is appended to the preset k-th extraction parameter sequence G' k , to obtain G' k =(g' 1,k ,g' 2,k ,…,g' f(k),k ,…,g' F(k),k ), g' f(k) To be added to G' k The f(k)th key piece of information, g' f(k) =(c' f(k) ,t' f(k) ), c' f(k) for g' f(k) The included meteorological parameter number, t' f(k) for g' f(k) The preset time points are included, and the value of f(k) ranges from 1 to F(k), where F(k) is the value appended to G'. k The amount of key information, G' k p is initialized to a null value; k p is the preset threshold for the k-th Pearson correlation coefficient. k =p1-(k-1)×Δp, where Δp is the preset step size of the Pearson correlation coefficient.

[0057] Optionally, the absolute value of the Pearson correlation coefficient with the largest absolute value in P' can be determined as p1.

[0058] In this embodiment, Δp is an empirical value, and optionally, Δp is 0.1.

[0059] S560, traverse G' k The c'th tea leaf sample randomly drawn from R will be the qth tea leaf sample. f(k) The t'th meteorological parameter f(k)The values ​​at each preset time point are appended to the k-th data vector X of the q-th tea sample randomly drawn from R. k,q X k,q It is initialized to a null value.

[0060] S570, classify the randomly selected tea samples from R based on the similarity between the k-th data vectors of any two randomly selected tea samples from R, and obtain the classification result Y. k =(y 1,k ,y 2,k ,…,y x(k),k ,…,y φ(k),k ), y x(k),k Let x(k) be the set of tea samples included in the x(k)th category obtained by classification, where x(k) ranges from 1 to φ(k) and φ(k) is the number of categories.

[0061] Those skilled in the art will understand that any method in the prior art for obtaining the similarity between two vectors falls within the protection scope of this invention. Optionally, the cosine similarity algorithm can be used to obtain the similarity between the k-th data vector of any two tea samples randomly drawn from R.

[0062] Those skilled in the art will understand that any clustering method in the prior art falls within the protection scope of this invention. Optionally, the similarity between the k-th data vectors of two randomly selected tea samples from R is first obtained, and then the derivative of the sum of the similarity and 1 is used as the distance between the k-th data vectors of the two randomly selected tea samples from R. After obtaining the distance between the k-th data vectors of any two randomly selected tea samples from R, clustering can be performed according to the clustering algorithms disclosed in the prior art. The clustering process will not be described in detail here. It should be understood that in this embodiment, the similarity between the k-th data vectors of tea samples belonging to the same category is relatively high, and the similarity between the k-th data vectors of tea samples belonging to different categories is relatively low.

[0063] S580, traverse Y k , obtain Y k The mean variance δ k δ k =(∑ φ(k) x(k)＝1 δ k,x(k) ) / φ(k), δ k,x(k) For y x(k),k The variance of the standard priority of the Chinese tea sample.

[0064] Those skilled in the art will recognize that the method for obtaining variance is prior art and will not be described in detail here.

[0065] S590, if δ kIf the value is greater than δ0, then k = k + 1, and repeat S560-S580 until δ... k ≤δ0, p k Let p0 be the variance threshold and δ0 be the preset variance threshold.

[0066] In this embodiment, δ0 is an empirical value, when δ k When ≤δ0, determine y x(k),k The differences in standard priority among tea samples are relatively small; when δ k When y > δ0, determine y x(k),k The standards for tea samples vary considerably.

[0067] According to the p0 obtained by S510-S590 of the present invention, it can ensure that the meteorological parameters and preset time point information that have a greater impact on the priority of tea leaves are extracted in S500. This avoids the situation where the workload of predicting the priority of the target tea leaves is too large when p0 is set too small, and the situation where the priority prediction of the target tea leaves is inaccurate when p0 is set too large. It takes into account both the accuracy and efficiency of judging the priority of the target tea leaves.

[0068] S600, Obtain the target weight sequence A, A = (a1, a2, ..., a... n ,…,a N ), a n For the cth n The t-th meteorological parameter n Weights at preset time points.

[0069] Optionally, the analytic hierarchy process (AHP) can be used to obtain a. n To reflect the cth aspect of tea n The t-th meteorological parameter n The values ​​at preset time points indicate the importance of the tea leaves to their priority. Those skilled in the art will understand that the process of obtaining weights using the analytic hierarchy process (AHP) is prior art and will not be elaborated upon here. n The larger the value, the higher the c-th value of the tea. n The t-th meteorological parameter n The more important a preset time point value is to the priority of tea leaves.

[0070] S700, Obtain the target tea data E, E = (e1, e2, ..., e n ,…,e N ), e n For the target tea, the cth n The t-th meteorological parameter n The value of a preset time point.

[0071] S800, iterate through E, based on e n Obtain the target tea grade b n .

[0072] Optionally, the S800 includes:

[0073] S810, Obtain the nth sequence w to be matched. n w n =(w n,1 ,w n,2 ,w n,3 ,w n,4 ), w n,1 For level 4 tea, the cth... n The t-th meteorological parameter n The range of values ​​for a preset time point, w n,2 For level 3 tea, the cth... n The t-th meteorological parameter n The range of values ​​for a preset time point, w n,3 For level 2 tea, the cth... n The t-th meteorological parameter n The range of values ​​for a preset time point, w n,4 For level 1 tea, the cth... n The t-th meteorological parameter n The range of values ​​for a preset time point.

[0074] In this embodiment, a higher grade indicates a higher priority for the tea, and correspondingly a higher quality tea; when the c-th grade... n The t-th meteorological parameter n When the value at a preset time point is positively correlated with the standard priority of tea, w n,1 The data in is greater than w n,2 The data in w n,2 The data in is greater than w n,3 The data in w n,3 The data in is greater than w n,4 The data in the middle; when the cth... n The t-th meteorological parameter n When the value at a preset time point is negatively correlated with the standard priority of tea, w n,1 The data in is less than w n,2 The data in w n,2 The data in is less than w n,3 The data in w n,3 The data in is less than w n,4 The data in the middle.

[0075] Optionally, in this embodiment w n,1 w n,2 w n,3 and w n,4 This is a scope pre-determined based on tea industry standards and expert opinions.

[0076] S820, e n In w n In the matching, if e n ∈w n,1 Then b n The value is determined to be 4; if e n ∈w n,2 Then b n The value is determined to be 3; if e n ∈w n,3 Then b n The value is determined to be 2; if e n ∈w n,4 Then b n The value is determined to be 1.

[0077] S900, obtain the priority z' of the target tea leaves, z' = ∑ N n＝1 (a n ×b n ), 0 n <1,∑ N n＝1 a n =1.

[0078] This invention obtains a list of meteorological parameters for tea samples, which stores the values ​​of each meteorological parameter for each tea sample at each preset time point. It also obtains a standard priority sequence for the tea samples, where each element corresponds to a standard priority for a tea sample. Furthermore, this invention obtains an original sequence composed of the values ​​of different tea samples corresponding to the same meteorological parameter at the same preset time point, and obtains the Pearson correlation coefficient between each original sequence and the standard priority sequence. If the Pearson correlation coefficient between an original sequence and the standard priority sequence is greater than or equal to a preset Pearson correlation coefficient threshold, the meteorological parameter number and preset time point number corresponding to that original sequence are appended to the target parameter sequence. Thus, this invention can obtain all meteorological parameter numbers and preset time point numbers that are relatively relevant to the tea priority. Based on the weights corresponding to each meteorological parameter number and preset time point number in the target parameter sequence, this invention can predict the priority of the target tea, achieving the purpose of automatically determining the tea priority.

[0079] While specific embodiments of the invention have been described in detail by way of example, those skilled in the art should understand that the examples are for illustrative purposes only and not intended to limit the scope of the invention. It should also be understood that various modifications can be made to the embodiments without departing from the scope and spirit of the invention. The scope of the invention is defined by the appended claims.​

Claims

1. A method for processing tea samples, characterized in that, Includes the following steps: S100, Obtain the meteorological parameter list R for the tea sample, R=(r1,r2,…,r i ,…,r u ), r i For the meteorological parameters of the i-th tea sample, r i =(r i,1 ,r i,2 ,…,r i,m ,…,r i,M ), r i,m Let r be the sequence of the m-th meteorological parameter of the i-th tea sample. i,m =(r 1 i,m ,r 2 i,m ,…,r j i,m ,…,r v i,m ), r j i,m Let be the value of the m-th meteorological parameter corresponding to the j-th preset time point for the i-th tea sample, where j ranges from 1 to v, v is the number of preset time points, m ranges from 1 to M, M is the number of meteorological parameters, and i ranges from 1 to u, u is the number of tea samples; M=8, v=8, the first meteorological parameter is the average temperature, the second meteorological parameter is the accumulated temperature, the third meteorological parameter is the effective accumulated temperature, the fourth meteorological parameter is the average daily temperature range, and the fifth meteorological parameter is the number of days with suitable temperature. The 6th meteorological parameter is the number of rainy days, the 7th meteorological parameter is the cumulative sunshine hours, the 8th meteorological parameter is the average humidity, the 1st preset time point is 10 days before harvest, the 2nd preset time point is 20 days before harvest, the 3rd preset time point is 30 days before harvest, the 4th preset time point is 40 days before harvest, the 5th preset time point is 50 days before harvest, the 6th preset time point is 60 days before harvest, the 7th preset time point is 70 days before harvest, and the 8th preset time point is 80 days before harvest. S200, Obtain the standard priority sequence Z of the tea samples, Z=(z1,z2,…,z…). i ,…,z u ), z i The standard priority for the i-th tea sample; S300, iterate through R, and r j i,m Added to the j-th original sequence H of the m-th meteorological parameter in the preset sequence. m,j H m,j =(r j 1,m ,r j 2,m ,…,r j i,m ,…,r j u,m ), H m,j It is initialized to a null value; S400, obtain the original list P of Pearson correlation coefficients, P=(p 1,1 ,p 1,2 ,…,p 1,j ,…,p 1,v ,p 2,1 ,p 2,2 ,…,p 2,j ,…,p 2,v ,…,p m,1 ,p m,2 ,…,p m,j ,…,p m,v ,…,p M,1 ,p M,2 ,…,p M,j ,…,p M,v ), p m,j For H m,j Pearson correlation coefficient with Z; S500, iterate through P, if |p m,j If |≥p0, then p m,j The corresponding key information (m,j) is appended to the preset target parameter sequence G, resulting in G=(g1,g2,…,g n ,…,g N ), g n For the nth key piece of information added to G, g n =(c n ,t n ), c n For g n The included meteorological parameter numbers, t n For g n The preset time point number is included, where n ranges from 1 to N, N is the number of key information points appended to G, and G is initialized to null; p0 is the preset Pearson correlation coefficient threshold. S600, Obtain the target weight sequence A, A=(a1,a2,…,a…). n ,…,a N ), a n For the cth n The t-th meteorological parameter n Weights at preset time points; S700, Obtain the target tea data E, E=(e1,e2,…,e n ,…,e N ), e n For the target tea, the cth n The t-th meteorological parameter n The value of a preset time point; S800, iterate through E, based on e n Obtain the target tea grade b n ; S900, Obtain the priority z' of the target tea leaves, z' = ∑ N n=1 (a n ×b n ), 0 n <1,∑ N n=1 a n =1.​ 2. The method for processing tea samples according to claim 1, characterized in that, The process of obtaining p0 includes: S510, randomly select Q meteorological parameter records from R for tea samples, obtaining a selection list R', R'=(r'1,r'2,…,r'). q ,…,r' Q ), r' q Let r' be the record of meteorological parameters for the q-th tea sample randomly selected from R. q =(r' q,1 ,r' q,2 ,…,r' q,m ,…,r' q,M ), r' q,m Let r' be the sequence of the m-th meteorological parameter of the q-th tea sample randomly drawn from R. q,m =(r 1,1 q,m ,r 2,1 q,m ,…,r j,1 q,m ,…,r v,1 q,m ), r j,1 q,m Let be the value of the m-th meteorological parameter corresponding to the j-th preset time point of the q-th tea sample randomly selected from R; q ranges from 1 to Q, where Q is the preset number of samples. <M; S520, Obtain the standard priority sequence Z' for extracting tea samples, Z'=(z'1,z'2,…,z'). q ,…,z' Q ), z' q The standard priority of the qth tea sample randomly drawn from R; S530, iterate through R', and r j,1 q,m Added to the j-th extraction sequence H' of the preset m-th meteorological parameter m,j , thus obtaining H' m,j =(r j,1 1,m ,r j,1 2,m ,…,r j,1 q,m ,…,r j,1 Q,m ), H' m,j It is initialized to a null value; S540, Obtain the Pearson correlation coefficient extraction list P', P'=(p' 1,1 ,p' 1,2 ,…,p' 1,j ,…,p' 1,v ,p' 2,1 ,p' 2,2 ,…,p' 2,j ,…,p' 2,v ,…,p' m,1 ,p' m,2 ,…,p' m,j ,…,p' m,v ,…,p' M,1 ,p' M,2 ,…,p' M,j ,…,p' M,v ), p' m,j For H' m,j Pearson correlation coefficient with Z'; set the first variable k=1; S550, iterate through P', if |p' m,j |≥p k Then p' m,j The corresponding key information (m,j) is appended to the preset k-th extraction parameter sequence G' k , to obtain G' k =(g' 1,k ,g' 2,k ,…,g' f(k),k ,…,g' F(k),k ), g' f(k) To be added to G' k The f(k)th key piece of information, g' f(k) =(c' f(k) ,t' f(k) ), c' f(k) for g' f(k) The included meteorological parameter number, t' f(k) for g' f(k) The preset time points are included, and the value of f(k) ranges from 1 to F(k), where F(k) is the value appended to G'. k The amount of key information, G' k p is initialized to null; k p is the preset threshold for the k-th Pearson correlation coefficient. k =p1-(k-1)×Δp, where Δp is the preset step size of the Pearson correlation coefficient; S560, traverse G' k The c'th tea leaf sample randomly drawn from R will be the qth tea leaf sample. f(k) The t'th meteorological parameter f(k) The values ​​at each preset time point are appended to the k-th data vector X of the q-th tea sample randomly drawn from R. k,q X k,q It is initialized to a null value; S570, classify the randomly selected tea samples from R based on the similarity between the k-th data vectors of any two randomly selected tea samples from R, and obtain the classification result Y. k =(y 1,k ,y 2,k ,…,y x(k),k ,…,y φ(k),k ), y x(k),k Let x(k) be the set of tea samples included in the x(k)th category obtained by classification, where x(k) ranges from 1 to φ(k) and φ(k) is the number of categories. S580, traverse Y k , obtain Y k The mean variance δ k δ k =(∑ φ(k) x(k)=1 δ k,x(k) ) / φ(k), δ k,x(k) For y x(k),k The variance of the standard priority of the Chinese tea samples; S590, if δ k If the value is greater than δ, then k = k + 1, and repeat S560-S580 until δ > 0. k ≤δ0, p k Let p0 be the variance threshold and δ0 be the preset variance threshold.

3. The method for processing tea samples according to claim 1, characterized in that, Prior to S100, it also included: S010, Obtain the tea data L to be filtered, L={ l 1, l 2,…, l s ,…, l η }, l s For the data of the s-th tea leaf to be filtered, l s =( l 1 s,1 , l 2 s,1 ,…, l j s,1 ,…, l v s,1 , l 1 s,2 , l 2 s,2 ,…, l j s,2 ,…, l v s,2 ,…, l 1 s,m , l 2 s,m ,…, l j s,m ,…, l v s,m ,…, l 1 s,M , l 2 s,M ,…, l j s,M ,…, l v s,M ), l j s,m Let be the value of the m-th meteorological parameter corresponding to the j-th preset time point of the s-th tea to be screened, where s ranges from 1 to η, and η is the number of teas to be screened; S020, group the tea leaves to be screened according to the similarity between any two data points of the tea leaves to be screened in L, and obtain the grouping result B, B={B1,B2,…,B2}. γ ,…,B λ }, B γ Let γ be the γth group, where γ ranges from 1 to λ, and λ is the number of groups. S030, iterate through B and obtain B. γ Average priority pi γ pi γ =(∑ ξ σ=1 pi γ,σ ) / ξ,pi γ,σ For B γ The standard priority of the σ-th tea leaves to be screened, where σ ranges from 1 to ξ, and ξ is B. γ The quantity of tea leaves to be screened; S040, traverse B and delete B γ in which the absolute value of the difference from pi γ is greater than the preset difference threshold, and the updated B γ is appended to the set B' of the screened tea leaves, and B' is initialized as an empty set; S050, the tea leaves selected from B' are identified as tea samples.

4. The method for processing tea samples according to claim 1, characterized in that, The S800 includes: S810, Obtain the nth sequence w to be matched. n w n =(w n,1 ,w n,2 ,w n,3 ,w n,4 ), w n,1 For level 4 tea, the cth... n The t-th meteorological parameter n The range of values ​​for a preset time point, w n,2 For level 3 tea, the cth... n The t-th meteorological parameter n The range of values ​​for a preset time point, w n,3 For level 2 tea, the cth... n The t-th meteorological parameter n The range of values ​​for a preset time point, w n,4 For level 1 tea, the cth... n The t-th meteorological parameter n The range of values ​​for a preset time point; S820, e n In w n In the matching, if e n ∈w n,1 Then b n The value is determined to be 4; if e n ∈w n,2 Then b n The value is determined to be 3; if e n ∈w n,3 Then b n The value is determined to be 2; if e n ∈w n,4 Then b n The value is determined to be 1.

5. The method for processing tea samples according to claim 1, characterized in that, z i The methods for obtaining it include: S210, Obtain the initial sequence D of the i-th tea sample. i D i =(d i,1 ,d i,2 ,d i,3 ), d i,1 Let d be the phenol-to-amino acid ratio of the i-th tea sample. i,2 Let d be the water extract content of the i-th tea sample. i,3 Let be the caffeine content of the i-th tea sample; S220, Obtain the normalized sequence D' of the i-th tea sample. i ,D' i =(d' i,1 ,d' i,2 ,d' i,3 ), d' i,1 For d i,1 The normalized value, d' i,2 For d i,2 The normalized value, d' i,3 For d i,3 The value after normalization; S230, obtain z i , z i =β1×d' i,1 +β2×d' i,2 +β3×d' i,3 β1 is the weight corresponding to the phenol-to-amino acid ratio, β2 is the weight corresponding to the water extract content, β3 is the weight corresponding to the caffeine content, and β1+β2+β3=1.

6. The method for processing tea samples according to claim 1, characterized in that, Use the analytic hierarchy process to obtain a n .

7. The method for processing tea samples according to claim 2, characterized in that, p1 is the absolute value of the Pearson correlation coefficient, which has the largest absolute value in P'.

Images