Data processing method for obtaining tobacco leaf baking curve and electronic equipment

Abstract

The invention provides a data processing method for acquiring a tobacco leaf baking curve and electronic equipment. The method comprises the following steps: acquiring a basic data list D in a current database; on the basis of D, obtaining classification data corresponding to a plurality of classifications, sorting the classification data corresponding to any classification according to a high-to-low order of the first-class cigarette proportion, and obtaining the first N pieces of data which are sorted in the front as intermediate data corresponding to the classification; taking basic data meeting a set condition in the intermediate data as target data of the classification to obtain a target data set corresponding to the classification; on the basis of curing barn information corresponding to any basic data in the target data set, included curing time information is obtained, and a curing category corresponding to each piece of curing time information is obtained; and based on the first category data, the second category data and the third category data corresponding to the category, obtaining a tobacco leaf baking curve of each category corresponding to the category. According to the method, the tobacco leaf baking curve can be objectively and accurately obtained.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of data processing, in particular to a data processing method for obtaining a tobacco leaf baking curve and an electronic device. BACKGROUND

[0002] The process level of tobacco leaf baking in the current tobacco industry is quite different. Because different varieties of tobacco, different planting conditions and different parts have different technical requirements for baking, it is difficult to give a unified standard, so the temperature and humidity control of the baking room in the current tobacco baking process mainly depends on the experience of the baking workers. This leads to inconsistency of the baking process. At present, each province can only give a universal tobacco baking recommended curve that does not distinguish specific regions and tobacco parts, and each village or tobacco station adjusts according to its own tobacco situation, which makes it difficult to control the baking quality. SUMMARY

[0003] In view of the above technical problems, the technical scheme adopted by the present application is: The embodiment of the present application provides a data processing method for obtaining a tobacco leaf baking curve, which comprises the following steps: S100, obtaining a basic data list D={D1, D2,..., Dm} in a current database, D i ,..., D m}, D i is the i th basic data, the value of i is 1 to m, and m is the number of basic data; D i =(U i ,A i ,S i ,K i ,I i ,V i ,PA i , BR i ), U i is the ID of the tobacco farmer corresponding to D i , A i is the ID of the geographical area corresponding to D i , S i is the ID of the tobacco variety corresponding to D i , K i is the proportion of superior tobacco corresponding to D i , I i is the return value corresponding to D i , V i is the yield per mu corresponding to D i , PA i is the planting area corresponding to D i , and BR i is the baking room information corresponding to D i , wherein the baking room information includes dry bulb temperature, wet bulb temperature and baking time.

[0004] S200, obtaining n1 based on D n2 categories of classification data, and any category C pq The corresponding classification data is sorted in descending order of the proportion of high-grade tobacco, and the first N data in the sorted classification data is obtained as C pq The corresponding intermediate data MC pq ; wherein any category C pq The corresponding classification data is composed of the basic data in D that belongs to geographic area p and tobacco variety q, p is valued at 1 to n1, q is valued at 1 to n2; n1 is the number of geographic areas in the first union set AS1, n2 is the number of tobacco varieties in the second union set AS2, AS1=A1∪A2∪……∪A i ……∪A m , AS2=S1∪S2∪……∪S i ……∪S m .

[0005] S300, obtaining MC pq The basic data that meets the set condition is the target data of C pq , obtaining C pq The corresponding target data set TC pq ; wherein the set condition is: return value / planting area=acreage yield.

[0006] S400, for any basic data in TC pq , based on the corresponding curing house information, obtain the contained curing information, and obtain the corresponding curing category of each curing information; wherein each curing information includes corresponding dry ball temperature, wet ball temperature and curing time; the curing category includes first curing category, second curing category and third curing category, the first curing category is the category of curing lower tobacco, the second curing category is the category of curing middle tobacco, and the third curing category is the category of curing upper tobacco.

[0007] S500, respectively based on the first category data, the second category data and the third category data corresponding to C pq , obtaining the first category tobacco curing curve, the second category tobacco curing curve and the third category tobacco curing curve corresponding to C pq ; wherein the first category data includes the curing information belonging to the first curing category in the curing house information corresponding to all basic data of TC pq , the second category data includes the curing information belonging to the second curing category in the curing house information corresponding to all basic data of TC pq , and the third category data includes the curing information belonging to the third curing category in the curing house information corresponding to all basic data of TC pqThe baking information that belongs to the third baking category in the baking room information corresponding to all the basic data.

[0008] The present invention has at least the following beneficial effects: The data processing method for obtaining tobacco curing curves provided in this embodiment of the invention can obtain tobacco curing curves corresponding to different regions, varieties and parts of tobacco leaves based on actual curing data, thereby providing the most accurate curing curves possible for curing different regions, varieties and parts of tobacco leaves.

[0009] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description

[0010] 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.

[0011] Figure 1 A flowchart of a data processing method for obtaining tobacco curing curves provided in an embodiment of the present invention; Figure 2 This is a schematic diagram of the tobacco curing curve in one embodiment of the present invention. Detailed Implementation

[0012] 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.

[0013] This invention provides a data processing method for obtaining tobacco curing curves, such as... Figure 1 As shown, the method may include the following steps: S100, retrieve the basic data list D={D1, D2, ..., D...} in the current database. i , ..., D m}, D i Let i be the i-th basic data, where i ranges from 1 to m, and m is the number of basic data.

[0014] In this embodiment of the invention, basic data can be acquired according to a set time period, for example, once a year.i = (U i , A i , S i , K i , I i , V i , PA i , BR i ), U i is the ID of the corresponding tobacco farmer, A i is the ID of the corresponding geographical area, i.e. the name of the area to which the tobacco farmer belongs. S i is the ID of the corresponding tobacco variety, i.e. the name of the tobacco variety. K i is the proportion of superior tobacco corresponding to D i , I i is the return value corresponding to D i , i.e. the income obtained by the tobacco farmer from the sale of all the tobacco leaves to be cured in the corresponding year. V i is the yield per mu corresponding to D i , PA i is the planting area corresponding to D i , BR i is the curing house information corresponding to D i , which is all the process curve information in the corresponding year, including dry ball temperature, wet ball temperature and curing time. Specifically, BR i = (T i i , T i d ), T i w is the dry ball temperature information in BR i , T d i = { (t i d , Tem i d ), (t i1 d , Tem i1 d ), …, (t i2 d , Tem i2 d ), …, (t ij d , Tem ij d ), …, (t ig（i） d , Tem ig（i） d ), t ij i is the jth record time in BR d ​​ij t d ij corresponding dry-bulb temperature, j is 1 to g(i), g(i) is the number of recording time in BR i T w i t i w i = { (t w i1 , Tem w i1 ), (t w i2 , Tem w i2 ), …, (t w ij , Tem w ij ), …, (t w ig（i） , Tem w ig（i） )}, Tem w ij t w ij corresponding wet-bulb temperature.

[0015] In the embodiment of the present application, the interval between two adjacent recording times can be 10 minutes. The dry-bulb temperature and the wet-bulb temperature can be obtained based on the corresponding Internet of Things device.

[0016] In the embodiment of the present application, the upper-grade tobacco can be obtained according to the standard of national standard GB 2635-1992. The standard of the national standard GB 2635-1992 defining the upper-grade tobacco includes: middle orange one C1F, middle orange two C2F, middle orange three C3F, middle lemon one C1L, middle lemon two C2L, upper orange one B1F, upper orange two B2F, upper lemon one B1L, upper red one B1R, perfect ripening one H1F, lower orange one X1F.

[0017] Further, the dry-bulb temperature and the wet-bulb temperature are temperatures smoothed to a set precision. The temperature data obtained from the Internet of Things device can have a temperature precision of 0.1 degree. However, in the case of manual operation and reference to the curve, the temperature precision can be 0.5 degree, that is, the set precision is 0.5 degree, so it is necessary to smooth the temperature precision from 0.1 degree to 0.5 degree. The specific smoothing formula can be: [rawdate_tem / 0.5] 0.5, rawdate_tem is the dry-bulb temperature or the wet-bulb temperature.

[0018] S200, based on D, obtaining n1 n2 classification data corresponding to any classification C​pq The corresponding category data are sorted in descending order of the proportion of superior cigarettes, and the first N data points from the sorted category data are taken as C. pq Corresponding intermediate data MC pq ; where any category C pq The corresponding classification data consists of basic data from D, where geographical regions belong to geographical region p and tobacco varieties belong to variety q. The values ​​of p range from 1 to n1, and the values ​​of q range from 1 to n2. n1 represents the number of geographical regions in the first union AS1, and n2 represents the number of tobacco varieties in the second union AS2. AS1 = A1 ∪ A2 ∪ … ∪ A i ...∪A m AS2 = S1∪S2∪……∪S i ...∪S m .

[0019] In an illustrative embodiment of the present invention, N=[Q [10%], Q is C pq The number of data points in the corresponding category data, [ ] indicates rounding.

[0020] S300, MC pq The basic data that meets the set conditions is used as C pq The target data is used to obtain C. pq The corresponding target dataset TC pq The condition set is: return value / planting area = output value per mu.

[0021] S400, for TC pq Based on any basic data in the data, and the corresponding curing barn information, the curing batch information contained in the curing barn information is obtained, and the curing category corresponding to each curing batch information is obtained; wherein, each curing batch information includes the corresponding dry bulb temperature, wet bulb temperature and curing time; the curing category includes a first curing category, a second curing category and a third curing category, the first curing category is the category for curing the lower tobacco leaves, the second curing category is the category for curing the middle tobacco leaves, and the third curing category is the category for curing the upper tobacco leaves.

[0022] In this embodiment of the invention, if the baking oven information records the specific start and end dates of each baking cycle, the corresponding baking curve is extracted according to the start-end date of each baking cycle. If not, a baking cycle can be selected from the data segment where the dry bulb temperature is continuously in the range of 20-75℃ and continues to rise every 10 minutes.

[0023] The roasting category corresponding to each roasting cycle can be determined based on the actual situation. Generally, the first roasting cycle is for the lower tobacco leaves, the middle one or two roasting cycles are for the middle tobacco leaves, and the last roasting cycle is for the upper tobacco leaves.

[0024] S500, respectively based on C pq corresponding first category data, second category data and third category data, obtain C pq corresponding first category tobacco baking curve, second category tobacco baking curve and third category tobacco baking curve; wherein, the first category data includes TC pq corresponding to all the basis data corresponding to the first baking category of the baking information of the baking times information, the second category data includes TC pq corresponding to all the basis data corresponding to the second baking category of the baking information of the baking times information, the third category data includes TC pq corresponding to all the basis data corresponding to the third baking category of the baking information of the baking times information.

[0025] Through S500, the baking curves corresponding to different regions, different varieties and different tobacco parts can be obtained, a total of n1 n2 3 tobacco baking curves.

[0026] Further, in S500, the first category data, the second category data and the third category data are data after preprocessing.

[0027] In the embodiments of the present application, the preprocessing can include filling in missing values and replacing abnormal values. Wherein, the missing values, i.e. missing dry bulb temperature and missing wet bulb temperature, can be obtained by checking data continuity. The abnormal values can be obtained based on k-means clustering algorithm. After k-means clustering for each category data, similar values of the same category are automatically clustered, and abnormal values become obvious, so that the abnormal values in each category data, i.e. abnormal dry bulb temperature and abnormal wet bulb temperature, can be obtained. Those skilled in the art know that the specific process of k-means clustering can be prior art.

[0028] In the embodiments of the present application, the missing values and the abnormal values can be filled in and replaced by linear interpolation method. When linear interpolation method is used for calculation, the x-axis can be baking time, and the y-axis can be dry bulb temperature or wet bulb temperature. Those skilled in the art know that any method of filling in missing values and replacing abnormal values by linear interpolation method belongs to the protection scope of the present application.

[0029] Further, S500 specifically includes: S501, obtain C pqAny roasting information corresponding to the category data h corresponds to length information and temperature information, wherein the length information includes yellowing period length, color fixing period length and dry muscle period length, and the temperature information includes wet bulb temperature and dry bulb temperature corresponding to the yellowing period length, wet bulb temperature and dry bulb temperature corresponding to the color fixing period length, and wet bulb temperature and dry bulb temperature corresponding to the dry muscle period length; the value of h is 1 to 3, and the category data h∈ (first category data, second category data, third category data).

[0030] In the embodiment of the present application, the division temperature and the stable temperature point of the yellowing stage, the color fixing stage and the dry muscle stage in the roasting process are based on GB / T 23219-2008. The yellowing period length is the duration corresponding to the starting point of the corresponding roasting and the dry bulb temperature of 42℃, the color fixing period length is the duration corresponding to the dry bulb temperature from 43℃ to 54℃, and the dry muscle period length is the duration corresponding to the dry bulb temperature from 55℃ to the corresponding roasting end of the corresponding roasting.

[0031] S502, obtaining C pq The average value of the length r corresponding to all the roasting information corresponding to the category data h is taken as the length r corresponding to the category data; wherein the value of r is 1 to 3, and the length r∈ (yellowing period length, color fixing period length, dry muscle period length). S503, obtaining C pq The temperature not belonging to the length r corresponding to the category data h among the wet bulb temperature and the dry bulb temperature corresponding to the length r is set to be null, that is, only the dry bulb temperature and the wet bulb temperature corresponding to the length corresponding to the category data are retained, to obtain the target wet bulb temperature and the target dry bulb temperature corresponding to the length r corresponding to the category data.

[0032] S504, respectively, C pq The target wet bulb temperature and the target dry bulb temperature corresponding to the length r corresponding to the category data h are fitted to obtain the dry bulb temperature fitting line segment r and the wet bulb temperature fitting line segment r corresponding to the length r.

[0033] In the embodiment of the present application, the least square method can be used for fitting. In the fitting process, the roasting length can be taken as the x-axis and the dry bulb temperature or the wet bulb temperature as the y-axis for fitting.

[0034] S505, respectively, r dry bulb temperature fitting line segments and r wet bulb temperature fitting line segments are spliced to obtain the tobacco leaf roasting curve corresponding to the category, that is, C pq The first category tobacco leaf roasting curve, the second category tobacco leaf roasting curve and the third category tobacco leaf roasting curve corresponding.

[0035] In one illustrative embodiment, the obtained illustrative tobacco leaf roasting curve can be as shown in Figure 2 .

[0036] Further, in another embodiment of the present application, in the fitting process, in S504, part of the target wet bulb temperature and target dry bulb temperature data can be fitted as sample data, and part of the data can be fitted as test data. In this way, in S505, for each category, a predicted tobacco curing curve based on sample data and a test tobacco curing curve based on test data can be obtained. The performance of the predicted tobacco curing curve can be determined by calculating the error between the predicted tobacco curing curve and the test tobacco curing curve. Specifically, if the error between the predicted tobacco curing curve and the test tobacco curing curve is less than a set threshold, it indicates that the performance of the predicted tobacco curing curve is better, and the predicted tobacco curing curve can be used as the tobacco curing curve of the corresponding category. If it is greater than the set threshold, the fitting can be performed again, or the reference tobacco curing curve of the corresponding category can be used as the tobacco curing curve of the category. The reference tobacco curing curve of each category corresponding to any category can be the last tobacco curing curve. Further, the method provided by the embodiment of the present application further includes the following steps: S600, n1 The first category tobacco curing curve, the second category tobacco curing curve and the third category tobacco curing curve corresponding to n2 categories are stored in the memory.

[0037] S700, in response to receiving the tobacco curing curve query information, the corresponding tobacco curing curve is obtained from the memory and displayed, wherein the tobacco curing curve query information at least includes the ID of the geographic area, the ID of the tobacco variety and the curing category.

[0038] Further, the method provided by the embodiment of the present application further includes the following steps: In response to receiving new basic data, the received basic data is stored in the current database; and S100 is executed.

[0039] By adding a new curing curve every year, the results are cleaned, classified and labeled again by the above method, the corresponding higher level curing curve is screened out and integrated into the database, the new data is integrated into the existing process curve by using the above method, and the iteration update of the curing curve is completed, so that the performance of the process curve can be continuously improved.

[0040] The electronic device of one embodiment of the present application includes at least one memory; and a processor in communication connection with the at least one memory; wherein the memory stores instructions executable by the at least one processor, and the instructions are configured to execute the scheme described in any of the above embodiments. Therefore, the electronic device has the same technical effects as any of the above embodiments, which will not be repeated here.

[0041] It should be understood that the various forms of flow shown above can be used to reorder, add, or remove steps. For example, the steps described in the present disclosure can be performed in parallel, in series, or in a different order, as long as the desired results of the technology disclosed herein are achieved, which is not limited herein.

[0042] The above detailed description does not constitute a limitation on the protection scope of the present application. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent replacements, and improvements made within the spirit and principles of the present application shall be included in the protection scope of the present application.

Claims

1. A data processing method for obtaining tobacco leaf curing curves, characterized in that, The method includes the following steps: S100, retrieve the basic data list D={D1, D2, ..., D...} in the current database. i , ..., D m }, D i Let D be the i-th basic data, where i ranges from 1 to m, and m is the number of basic data; i =(U i A i S i K i I i V i PA i BR i ), U i D i The corresponding tobacco farmer's ID, A i D i The corresponding geographic region ID, S i D i The corresponding tobacco variety ID, K i D i The corresponding proportion of high-quality tobacco, I i D i The corresponding return value, V i D i The corresponding output value per acre, PA i D i Corresponding planting area, BR i D i The corresponding baking oven information includes dry bulb temperature, wet bulb temperature, and baking time; S200, based on D, obtain n1 Given n2 categories of classification data, and assigning any category C to... pq The corresponding category data are sorted in descending order of the proportion of superior cigarettes, and the first N data points from the sorted category data are taken as C. pq Corresponding intermediate data MC pq ; where any category C pq The corresponding classification data consists of basic data from D, where geographical regions belong to geographical region p and tobacco varieties belong to variety q. The values ​​of p range from 1 to n1, and the values ​​of q range from 1 to n2. n1 represents the number of geographical regions in the first union AS1, and n2 represents the number of tobacco varieties in the second union AS2. AS1 = A1 ∪ A2 ∪ … ∪ A i ...∪A m AS2 = S1∪S2∪……∪S i ...∪S m ; S300, MC pq The basic data that meets the set conditions is used as C pq The target data is used to obtain C. pq The corresponding target dataset TC pq The condition set is: Return value / Planting area = Output value per mu; S400, for TC pq Based on any basic data in the data, and the corresponding curing barn information, the curing batch information is obtained, and the curing category corresponding to each curing batch information is obtained. Each curing batch information includes the corresponding dry bulb temperature, wet bulb temperature, and curing time. The curing categories include a first curing category, a second curing category, and a third curing category. The first curing category is for curing the lower tobacco leaves, the second curing category is for curing the middle tobacco leaves, and the third curing category is for curing the upper tobacco leaves. S500, based on C pq Obtain C from the corresponding first category data, second category data, and third category data. pq The corresponding curing curves for Category I, Category II, and Category III tobacco leaves; among them, Category I data includes TC. pq The corresponding basic data includes the baking batch information belonging to the first baking category in the oven information, and the second category data includes TC. pq The corresponding basic data includes the baking batch information belonging to the second baking category in the oven information, and the third category data includes TC. pq The baking information that belongs to the third baking category in the baking room information corresponding to all the basic data.

2. The method according to claim 1, characterized in that, The S500 specifically includes: S501, Get C pq The corresponding baking time and temperature information for any baking time in the category data h are as follows: the time information includes the yellowing period, the color fixing period, and the drying period; the temperature information includes the wet-bulb and dry-bulb temperatures corresponding to the yellowing period, the color fixing period, and the drying period; the value of h is from 1 to 3, and the category data h ∈ (first category data, second category data, third category data); S502, Get C pq The average of the baking times corresponding to all baking information of the corresponding category data h is taken as the duration r of that category data; where r takes the value from 1 to 3, and the duration r ∈ (yellowing period duration, color fixing period duration, dry rib period duration). S503, C pq For the wet-bulb temperature and dry-bulb temperature corresponding to the duration r of the corresponding category data h, the temperature that does not belong to the duration r of the corresponding category data is set to a null value, so as to obtain the target wet-bulb temperature and target dry-bulb temperature corresponding to the duration r of the corresponding category data. S504, respectively for C pq The target wet-bulb temperature and target dry-bulb temperature corresponding to the corresponding category data h and the corresponding duration r are fitted to obtain the corresponding dry-bulb temperature fitting line segment r and wet-bulb temperature fitting line segment r. S505, the r dry-bulb temperature fitting line segments and the r wet-bulb temperature fitting line segments are spliced ​​together to obtain the corresponding tobacco curing curve.

3. The method according to claim 1, characterized in that, In S500, the first category data, the second category data, and the third category data are preprocessed data.

4. The method according to claim 3, characterized in that, The preprocessing includes filling missing values ​​and replacing outliers.

5. The method according to claim 4, characterized in that, The outliers were obtained based on the k-means clustering algorithm, and missing values ​​were filled and outliers were replaced using linear interpolation.

6. The method according to claim 1, characterized in that, It also includes the following steps: S600, n1 The curing curves for the first, second, and third categories of tobacco leaves corresponding to n2 categories are stored in the memory.

7. The method according to claim 6, characterized in that, It also includes the following steps: S700, in response to receiving tobacco curing curve query information, retrieves the corresponding tobacco curing curve from the memory and displays it, wherein the tobacco curing curve query information includes at least the ID of the geographical region, the ID of the tobacco variety, and the curing category.

8. The method according to claim 1, characterized in that, It also includes the following steps: In response to receiving new basic data, store the received basic data in the current database; execute S100.

9. The method according to claim 1, characterized in that, The dry-bulb temperature and the wet-bulb temperature are temperatures smoothed to a set accuracy.

10. An electronic device, characterized in that, It includes a processor and a memory; the processor performs the steps of the method as described in any one of claims 1 to 8 by invoking a program or instruction stored in the memory.

Images