CN109242037B - Tobacco leaf quality similarity measurement method - Google Patents
Tobacco leaf quality similarity measurement method Download PDFInfo
- Publication number
- CN109242037B CN109242037B CN201811118342.8A CN201811118342A CN109242037B CN 109242037 B CN109242037 B CN 109242037B CN 201811118342 A CN201811118342 A CN 201811118342A CN 109242037 B CN109242037 B CN 109242037B
- Authority
- CN
- China
- Prior art keywords
- quality
- tobacco leaves
- similarity
- parameter
- tobacco
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Expired - Fee Related
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
Landscapes
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Manufacture Of Tobacco Products (AREA)
Abstract
The invention discloses a tobacco leaf quality similarity measurement method, which measures the quality similarity of tobacco leaves to be evaluated and other different types of raw material tobacco leaves by constructing a single-parameter similarity measurement function and a multi-parameter weight coefficient function. The method is based on the quality data mean value of tobacco leaves with the same producing area and grade, effectively improves the tobacco leaf quality similarity measurement efficiency, and provides reliable data support for subsequent cigarette formula maintenance, single-material tobacco replacement or new formula research and development.
Description
Technical Field
The invention relates to the cigarette industry, in particular to a quality similarity measuring method for comprehensively measuring the quality similarity between two groups of raw material tobacco leaves based on three aspects of raw material tobacco leaf physicochemical quality parameters, raw material tobacco leaf smoke quality parameters and raw material tobacco leaf sensory product smoking parameters.
Background
It is well known that tobacco leaves are the main raw material of cigarette products, and the quality level of the tobacco leaves is related to the taste and the market occupation of finished cigarettes. However, with the increase of the domestic smoking control strength, the probability that many finished cigarettes lose the market competitiveness is increased. Unfortunately, many cigarette enterprises are still characterized by insufficient monitoring of cigarette raw material components, insufficient information production capacity, low raw material utilization rate, long research and development period of new products, lagged research and development modes, and the like, and are also punishing these enterprises which are not thought to change rapidly. In order to avoid the competition, the finished cigarettes actively innovate the research and development mode of new products in the process production, improve the utilization rate of quality process monitoring data, and strengthen the management and control of raw material tobacco leaves and auxiliary materials.
With the research and development of various new products under the competitive pressure of the cigarette product market, the quality process monitoring, the reinforcing raw material control and the like, the research discovery is that: at present, most products in the market finish the judgment and the availability evaluation of the quality of raw materials by subjective judgment methods such as expert experience, and the traditional methods cannot meet the requirements of high quality stability and formula processing adaptability of the products. In order to solve the problem of inadaptability, a method for measuring the similarity based on the tobacco quality is developed, and the method for measuring the similarity is implemented quickly and scientifically, so that the cigarette industry can recognize the internal rules of raw materials and use the raw materials in a formula to a new height, and the scientific method also becomes an important scientific research subject for improving the quality of the tobacco raw materials.
The tobacco leaf raw material quality data comprises indexes such as physical characteristics, chemical components, sensory quality, smoke, molecular spectrum data and the like. Aiming at the indexes, some measuring methods for the quality similarity of the tobacco leaves are provided in the industry. However, these methods cannot be well measured in combination with the actual conditions of cigarette enterprises, and the whole process has large data volume and complex calculation, so that optimization or improvement of related algorithms is urgently needed.
Aiming at the practical problems, a foundation is laid for researching and formulating a product research and development project management system in the future, and the fine production level and the comprehensive management level of an enterprise are improved. The method starts from the quality parameter mean value of the similar tobacco leaves, combines a single-parameter similarity measurement method and a multi-parameter similarity measurement method, and measures the quality of the tobacco leaves to be evaluated and the quality of the raw material tobacco leaves in a weighted summation mode.
Disclosure of Invention
Aiming at the defects of the existing problems, the quality similarity between two groups of raw material tobacco leaves is comprehensively measured in three aspects of raw material tobacco leaf physicochemical quality parameters, raw material tobacco leaf smoke quality parameters and raw material tobacco leaf sensory product smoking parameters by combining with a cigarette raw material quality database. The evaluation method adopts a comprehensive evaluation method of single-parameter similarity analysis and multi-parameter similarity weighted summation, so that the similarities and the differences among tobacco leaves in different producing areas and grades are effectively evaluated. In order to achieve the aim, the invention provides a method for measuring the tobacco leaf quality similarity, which comprises the following specific steps:
(1) acquiring physicochemical values of various quality parameters of a raw material sample to be evaluated through a quality database;
(2) by a vector SmRepresenting tobacco leaf quality parametersThe elements are sorted according to the priority of the quality parameters, the serial number is represented by n, and m represents the number of the quality parameters;
(3) The relative difference of the two quality parameters is determined, and the relative difference function formula is as follows:
wherein, a certain parameter value of the tobacco leaves to be evaluated is t, and the value of the parameter corresponding to the tobacco leaves with different producing areas and grades is x;
(4) evaluating single parameter similarity: constructing a single-parameter similarity evaluation function, and calculating a single-parameter similarity value with a similarity matrix of Rp(ii) a The single parameter similarity evaluation function formula is as follows:
wherein p and t represent actual values of two tobacco leaf quality parameters to be evaluated;
(5) according to the priority order of the parameters, a weight function is constructed, the weighted value of each parameter is calculated,
the formula is as follows:
the matrix is F;
(6) evaluating the similarity of multiple quality parameters: constructing a multi-quality parameter similarity evaluation function of the tobacco leaves, wherein the formula is as follows:
wherein i represents the number of quality parameters, j represents the number of tobacco leaf samples, and m represents the number of elements;
(7) carrying out similarity measurement on the mean values of various parameters of tobacco leaves in different producing areas and grades, and determining the tobacco leaves with similar quality according to the R value from large to small, wherein the formula is as follows:
the quality parameters in the step (1) are physical and chemical quality parameters of the raw material tobacco leaves, smoke quality parameters of the raw material tobacco leaves and sensory quality absorption parameters of the raw material tobacco leaves.
The physical and chemical quality parameters of the raw material tobacco leaves are nicotine, total sugar, reducing sugar, total nitrogen, potassium and chlorine.
The quality parameters of the flue gas of the raw material tobacco leaves comprise tar amount, flue gas nicotine amount, flue gas CO amount, suction port number, filtering efficiency and total dilution rate.
The smoking parameters of the raw material tobacco leaf sensory product are aroma quality, aroma quantity, miscellaneous gas, aftertaste, strength, irritation, combustibility, concentration and gray.
In the step (5), n represents the priority ranking serial number of the quality parameters, m represents the number of the quality parameters, b (b is more than or equal to 0 and less than or equal to 1) is input as an initial value based on a human-computer interaction interface, and the initial value is calculated according to a formula
Calculating a parameter a value; substituting the n, m, a, b values into a weighting coefficient function formula
A weighted value for each parameter is calculated.
According to the inherent quality characteristics of the tobacco leaves, the tobacco leaf quality parameters are divided into three aspects of tobacco leaf physicochemical quality parameters, raw material tobacco leaf smoke quality parameters and raw material tobacco leaf sensory product smoking parameters.
The physical and chemical quality parameters of the raw material tobacco mainly comprise nicotine, total sugar, reducing sugar, total nitrogen, potassium and chlorine.
The quality parameters of the flue gas of the raw material tobacco leaves mainly comprise six items of tar content, flue gas nicotine content, flue gas CO content, suction port number, filtering efficiency and total dilution rate.
The smoking parameters of the raw material tobacco leaf sensory product mainly comprise nine items of aroma quality, aroma quantity, miscellaneous gas, aftertaste, strength, irritation, combustibility, concentration and gray.
The tobacco leaf quality parameters can be added and deleted according to actual requirements, so that the reliability and robustness of the similarity measurement are improved.
And recording the quality data of the tobacco leaves in different producing areas and grades into a database based on an online or offline detection mode to generate a quality database of the incoming tobacco leaves.
The quality parameters of the tobacco leaves in the same producing area and grade can be regarded as a one-dimensional matrix, the quality parameters have priorities, such as nicotine, total sugar, irritation and strength, when the similarity of the tobacco leaves is measured, the priorities are higher than other parameters, and the weighting coefficients are relatively large.
The higher the priority parameter, the more forward it is in the quality parameter vector.
By a vector SmAnd (3) expressing the quality parameters of the tobacco leaves, arranging the elements according to the priority of the indexes, and expressing the number of the elements by m.
And constructing a single parameter similarity evaluation function based on the exponential function, wherein the parameter needs to meet the condition that the similarity is 1 when two parameter values are equal. When the difference between the two parameter values is positive, the function has a monotonically increasing characteristic. When the difference value is negative, the function has a monotone decreasing characteristic.
Assuming that a certain parameter value of the tobacco leaves to be evaluated is t, the value of the corresponding parameter of the tobacco leaves with different producing areas and grades is x, and the relative difference of the two parameters can be determined through the 
And (4) showing.
Based on the above characteristics, the function r is constructedd＝e-d。
Aiming at the similarity evaluation of multiple parameters, the invention adopts a method of weighted summation of multiple single-parameter similarities, so that a coefficient matrix for the similarity evaluation of multiple parameters needs to be established. The weighting coefficients are gradually decreased in the priority order of the parameters, but the sum of all the weighting coefficients must be 1.
The constructed weight function has good adaptability, and the weight coefficient can be automatically generated according to the parameter m and the main variable factor.
Introducing a weight function based on the weight function characteristics
n represents SmThe element numbers of the vector, b the adjustable parameters and a the decision coefficients.
In order to satisfy the condition that the sum of all parameter weighting coefficients is 1, the adjustable parameter needs to satisfy that b is more than or equal to 0 and less than or equal to 1.
Substituting 1-m into the weighting function
Based on the characteristic that the sum is equal to 1, the decision coefficient of the weight function can be obtained
When a is 0, b is 1, and the weight of each parameter is then
Constructing a multi-parameter similarity evaluation function of the tobacco leaves, wherein the formula is as follows:
carrying out similarity measurement on the mean values of various parameters of tobacco leaves with different producing areas and grades, wherein the expression is as follows:
a tobacco leaf quality similarity measurement method comprises the following steps:
and acquiring the physicochemical values of all quality parameters of the sample to be evaluated through a quality database.
Inputting decimal between 0 and 1 as initial value of b based on the man-machine interaction interface according to formula
And calculating the value of the parameter a.
Substituting 1,2 … m into the formula
And calculating a weighted value of each parameter, wherein the matrix of the weighted value is F.
The value of a certain parameter of the tobacco leaves to be evaluated is t, the value of the corresponding parameter of the tobacco leaves with different producing areas and grades is x, and the relative difference of the two parameters is determined by
And (4) showing.
By a function rd＝e-dCalculating the similarity of each parameter of the tobacco leaves in the producing area and the grade and other tobacco leaves in the database, wherein the similarity matrix is Rp。
By the formula R ═ RpF, calculating the similarity of the producing area and the grade tobacco leaves and other tobacco leaves in the database.
And determining the tobacco leaves with similar quality according to the arrangement of the R values from large to small.
The invention has the advantages that:
the method is based on the quality data mean value of the tobacco leaves with the same producing area and grade, effectively improves the tobacco leaf quality similarity measurement efficiency, and provides reliable data support for subsequent cigarette formula maintenance, single-material tobacco replacement or new formula research and development.
Drawings
Fig. 1 is a schematic flow chart of a tobacco quality similarity measurement method according to the present invention.
Fig. 2 is a system architecture diagram based on a tobacco quality similarity measurement method according to the present invention.
DETAILED DESCRIPTION OF EMBODIMENT (S) OF INVENTION
The present invention is further described with reference to the following specific examples, but the scope of the present invention is not limited by the examples, and it is within the scope of the present invention if those skilled in the art make some insubstantial modifications and adaptations of the present invention based on the above disclosure.
Example 1
In order to realize the tobacco leaf similarity measurement function and facilitate operation, a tobacco leaf quality similarity measurement system is developed based on Java language. The system architecture based on the tobacco quality similarity measurement method provided by the invention is shown in fig. 2.
The system has the following characteristics:
the human-computer interaction interface adopts a bootstrap (the main components are HTML and Javascript) development interface, and the effects of simplicity, easiness in use, more humanization, attractiveness and elegant appearance are realized.
The basic interface adopts AJAX and Spring as the support of the upper interface effect, and the reaction speed of interface interaction and the stability of functions are ensured.
The function implementation module adopts a mode of combining mybatis dynamic link library and Spring, and the mode is adopted to conveniently realize componentization or modularization of the whole system.
The database adopts SqlServer, combines XML file and Properties configuration file, realizes more flexible data storage.
As shown in fig. 1, the system work flow is as follows:
inputting decimal between 0 and 1 as initial value of b based on the man-machine interface according to formula
And calculating the value of the parameter a.
Substituting 1,2 … m into the formula
And calculating a weighted value of each parameter, wherein the matrix of the weighted value is F.
The value of a certain parameter of the tobacco leaves to be evaluated is t, the value of the corresponding parameter of the tobacco leaves with different producing areas and grades is x, and the relative difference of the two parameters is determined by
And (4) showing.
By a function rd＝e-dCalculating the producing area, grade tobacco leaf and numberSimilarity of each parameter of other tobacco leaves in the database, wherein a similarity matrix is Rp。
By the formula R ═ RpF, calculating the similarity of the producing area and the grade tobacco leaves and other tobacco leaves in the database.
And determining the tobacco leaves with similar quality according to the arrangement of the R values from large to small.
And b is 0.5, and m is 10, and the data are recorded into the system.
According to the preset parameter priority, the parameters for evaluating the similarity of the tobacco leaves are nicotine, total sugar, tar, total particulate matter, smoke, aftertaste, strength, irritation, chlorine and miscellaneous gas respectively.
The priority of the quality parameters can be drawn up according to actual conditions.
The quality parameters of the tobacco leaves to be analyzed are recorded through the system, and the parameter values are shown in the table 1.
TABLE 1 quality parameters of tobacco leaves to be analyzed
The system retrieves the raw tobacco quality data from the simulation database, and the data are shown in table 2.
TABLE 2 raw tobacco quality data
Substituting b-0.5 and m-10 into the formula
Calculated a equals 0.17.
Based on
The function-calculated weight coefficient matrix F is shown in table 3.
TABLE 3 weight coefficient matrix
Based on
The function calculates the relative difference between the two parameters as shown in table four.
TABLE 4 table of relative difference of parameters
By a function rd＝e-dCalculating the similarity of each parameter of the tobacco leaves in the producing area and the grade and other tobacco leaves in the database, wherein the similarity R ispThe comparative table is shown in Table 5.
TABLE 5 Multi-parameter similarity comparison Table
Based on R ═ RpF, calculating the similarity of the producing area and the grade tobacco leaves with other tobacco leaves in the database, and showing in table 6.
TABLE 6 comparison table of similarity between tobacco leaves to be evaluated and different tobacco leaves
The tobacco leaf raw material similarity measurement method provided by the invention is based on analysis of each parameter mean value of the same type of tobacco leaves. Compared with the traditional method, the method provided by the invention can rapidly provide the similarity of the quality of the raw material tobacco leaves, and provides reliable data support for cigarette formula maintenance, single-material tobacco replacement or new formula research and development.
The above description is not intended to limit the present invention, and the present invention is not limited to the above description, and variations, modifications, additions and substitutions made in the industry or in other industries within the spirit of the invention are also within the scope of the invention.
Claims (5)
1. A tobacco leaf quality similarity measurement method is characterized by comprising the following specific steps:
(1) acquiring physicochemical values of various quality parameters of a raw material sample to be evaluated through a quality database;
(2) by a vector SmExpressing the quality parameters of the tobacco leaves, wherein the elements are sorted according to the priority of the quality parameters, the serial number is expressed by n, and m expresses the number of the quality parameters;
(3) the relative difference of the two quality parameters is determined, and the relative difference function formula is as follows:
wherein, a certain parameter value of the tobacco leaves to be evaluated is t, and the value of the parameter corresponding to the tobacco leaves with different producing areas and grades is x;
(4) evaluating single parameter similarity: constructing a single-parameter similarity evaluation function, and calculating a single-parameter similarity value rx(ii) a The single parameter similarity value evaluation function formula is as follows:
wherein x and t represent actual values of two tobacco leaf quality parameters to be evaluated;
(5) according to the priority sequence of the parameters, a weight function is constructed, and the weighted value of each parameter is calculated, wherein the formula is as follows:
the matrix is F;
(6) evaluating the similarity of multiple quality parameters: constructing a multi-quality parameter similarity evaluation function of the tobacco leavesThe formula is as follows:
wherein j represents a similarity measure with the j sample; wherein i represents the number of quality parameters, j represents the number of tobacco leaf samples, and m represents the number of elements;
(7) Carrying out similarity measurement on the mean values of various parameters of the tobacco leaves in different producing areas and grades, and determining the tobacco leaves with similar quality according to the RR values in a descending order, namely the sample with the maximum RR value is a target similar sample; the steps of calculating the similarity and searching for the target sample are as follows:
acquiring physicochemical values of various quality parameters of a sample to be evaluated through a quality database;
inputting decimal between 0 and 1 as initial value of b based on the man-machine interaction interface according to formula
Calculating a parameter a value;
substituting 1,2 … m into the formula
Calculating the weighted value of each parameter, wherein the matrix of the weighted value is F;
a certain parameter value of the tobacco leaves to be evaluated is t, and the value of the parameter corresponding to the tobacco leaves in different producing areas and grades is x; according to a single parameter similarity formula, sequentially calculating the similarity of each parameter of the tobacco leaves in the producing area and the grade and other tobacco leaves in the database, wherein a similarity matrix is Rx；
By the formula RR ═ RjF, calculating similarity values of the producing area and the grade tobacco leaves and other tobacco leaves in the database;
and determining the tobacco leaves with similar quality according to the arrangement of the RR values from large to small.
2. The tobacco leaf quality similarity measurement method according to claim 1, wherein: the quality parameters in the step (1) are physical and chemical quality parameters of the raw material tobacco leaves, smoke quality parameters of the raw material tobacco leaves and sensory quality absorption parameters of the raw material tobacco leaves.
3. The tobacco quality similarity measurement method according to claim 2, wherein: the physical and chemical quality parameters of the raw material tobacco leaves are nicotine, total sugar, reducing sugar, total nitrogen, potassium and chlorine.
4. The tobacco quality similarity measurement method according to claim 2, wherein: the quality parameters of the flue gas of the raw material tobacco leaves comprise tar content, flue gas nicotine content, flue gas CO content, suction opening number, filtering efficiency and total dilution rate.
5. The tobacco quality similarity measurement method according to claim 2, wherein: the smoking parameters of the sensory tobacco leaf raw materials comprise aroma quality, aroma quantity, miscellaneous gas, aftertaste, strength, irritation, combustibility, concentration and gray.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811118342.8A CN109242037B (en) | 2018-09-20 | 2018-09-20 | Tobacco leaf quality similarity measurement method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811118342.8A CN109242037B (en) | 2018-09-20 | 2018-09-20 | Tobacco leaf quality similarity measurement method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109242037A CN109242037A (en) | 2019-01-18 |
| CN109242037B true CN109242037B (en) | 2022-06-28 |
Family
ID=65056829
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811118342.8A Expired - Fee Related CN109242037B (en) | 2018-09-20 | 2018-09-20 | Tobacco leaf quality similarity measurement method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109242037B (en) |
Families Citing this family (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110301666B (en) * | 2019-05-28 | 2021-07-09 | 广东中烟工业有限责任公司 | Method for widening application range of tobacco leaf raw materials of cigarette products by feeding in groups |
| CN111855929B (en) * | 2020-07-06 | 2021-04-30 | 浙江工商大学 | Method for evaluating similarity of fruit powder raw materials |
| CN112782115B (en) * | 2020-12-25 | 2023-06-20 | 河南中烟工业有限责任公司 | Method for detecting consistency of sensory characteristics of cigarettes based on near infrared spectrum |
| CN114978853A (en) * | 2022-05-16 | 2022-08-30 | 中国联合网络通信集团有限公司 | Management information base adaptation method, device, equipment and storage medium |
| CN115099625A (en) * | 2022-06-27 | 2022-09-23 | 湖北中烟工业有限责任公司 | Computer system and cigarette formula module substitution method |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7627191B2 (en) * | 2006-08-14 | 2009-12-01 | Xerox Corporation | Image manipulation |
| CN104063599B (en) * | 2014-06-26 | 2017-02-15 | 江苏中烟工业有限责任公司 | Index screening and processing method for evaluating quality of tobacco leaves |
| CN107860868B (en) * | 2017-11-03 | 2020-09-18 | 福建中烟工业有限责任公司 | Tobacco matching method and system |
| CN107784452A (en) * | 2017-11-14 | 2018-03-09 | 江苏中烟工业有限责任公司 | A kind of objective integrated evaluating method of tobacco style characteristic similarity |
-
2018
- 2018-09-20 CN CN201811118342.8A patent/CN109242037B/en not_active Expired - Fee Related
Also Published As
| Publication number | Publication date |
|---|---|
| CN109242037A (en) | 2019-01-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109242037B (en) | Tobacco leaf quality similarity measurement method | |
| CN110245802B (en) | Cigarette empty-head rate prediction method and system based on improved gradient lifting decision tree | |
| CN109597968B (en) | SMT big data-based solder paste printing performance influence factor analysis method | |
| CN108304970B (en) | Method and system for rapidly predicting storage period of apples and controlled atmosphere storage monitoring system | |
| CN107341613B (en) | Method for assisting balance replacement of leaf group formula | |
| CN113190967B (en) | Multi-objective screening-based fine cigarette material combination method | |
| CN101387625A (en) | Comprehensive assessment method for flue-cured tobacco growing district | |
| CN111681084B (en) | E-commerce platform recommendation method based on social relationship influence factors | |
| CN106529584A (en) | Flue-cured tobacco aroma type and quality judgment intelligent evaluation method | |
| CN116316599A (en) | Intelligent electricity load prediction method | |
| CN113568368B (en) | Self-adaptive determination method for industrial control data characteristic reordering algorithm | |
| CN106644983A (en) | Spectrum wavelength selection method based on PLS-VIP-ACO algorithm | |
| CN110990782B (en) | Cigarette sensory quality evaluation method based on weighted hesitation fuzzy power aggregation operator | |
| CN112613953A (en) | Commodity selection method, system and computer readable storage medium | |
| CN112801388A (en) | Power load prediction method and system based on nonlinear time series algorithm | |
| CN115310539A (en) | 1D-CNN cigarette filter stick quality detection method based on attention mechanism | |
| CN102488309A (en) | Intelligent tobacco formulation method | |
| CN113657452A (en) | Tobacco leaf quality grade classification prediction method based on principal component analysis and super learning | |
| CN108614536B (en) | Complex network construction method for key factors of cigarette shred making process | |
| CN113496324A (en) | Spray quality prediction method, spray quality prediction device, electronic equipment and storage medium | |
| CN110196797A (en) | Automatic optimization method and system suitable for credit scoring card system | |
| CN112881333B (en) | Near infrared spectrum wavelength screening method based on improved immune genetic algorithm | |
| CN110866221B (en) | Detection method for threshing and redrying data accuracy | |
| CN110009024A (en) | A kind of data classification method based on ID3 algorithm | |
| CN115660720A (en) | Cigarette sales prediction method and equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20220628 |