CN108009740B - Intelligent fine identification system and method for tobacco essence and flavor - Google Patents
Intelligent fine identification system and method for tobacco essence and flavor Download PDFInfo
- Publication number
- CN108009740B CN108009740B CN201711338784.9A CN201711338784A CN108009740B CN 108009740 B CN108009740 B CN 108009740B CN 201711338784 A CN201711338784 A CN 201711338784A CN 108009740 B CN108009740 B CN 108009740B
- Authority
- CN
- China
- Prior art keywords
- identification
- submodule
- sample
- data
- management
- 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
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/242—Query formulation
- G06F16/2423—Interactive query statement specification based on a database schema
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/248—Presentation of query results
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/213—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods
- G06F18/2135—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods based on approximation criteria, e.g. principal component analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2411—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on the proximity to a decision surface, e.g. support vector machines
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F21/00—Security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
- G06F21/60—Protecting data
- G06F21/62—Protecting access to data via a platform, e.g. using keys or access control rules
- G06F21/6218—Protecting access to data via a platform, e.g. using keys or access control rules to a system of files or objects, e.g. local or distributed file system or database
Abstract
The invention discloses an intelligent fine identification system and method for tobacco flavors and fragrances, wherein the system comprises a flavor and fragrance identification management module, a basic data management module, a system management and maintenance module and a system comprehensive query module which are respectively connected with the flavor and fragrance identification management module; the basic data management module is used for providing essence and spice basic attributes based on the essence and spice identification process and managing and identifying environmental information; the essence and spice identification management module is used for inputting data of the sample to be identified and identifying essence and spice in the data of the sample to be identified according to the data provided by the basic data management module; the system management and maintenance module is used for managing the system and the system authority; and the system comprehensive query module is used for querying and generating a statistical report. The invention has accurate identification and high precision, is beneficial to improving the identification and analysis efficiency of the essence and the spice, improving the automation degree of enterprises and reducing the personnel cost.
Description
Technical Field
The invention relates to the field of essence and spice identification, in particular to an intelligent fine identification system and method for tobacco essence and spice.
Background
In the tobacco industry, additives such as flavors and fragrances are essential as important processing auxiliary materials and are essential to quality control.
The traditional software essence and flavor identification and analysis method mainly obtains similarity data through methods such as included angle cosine, correlation coefficient, Euclidean distance and the like, analyzes and calculates the similarity of a sample to be detected, compares the similarity with the similarity of a standard sample, and judges the quality and the authenticity of the sample to be detected. The identification and analysis method only has two levels of overall similarity and specific component difference, the Euclidean distance treats different attributes of the sample equally, and the influence of overall variation on the distance is not considered, so that the problems of insufficient sample identification precision and poor quality are caused.
Disclosure of Invention
Aiming at the defects in the prior art, the intelligent fine identification system and method for the tobacco essence and flavor, provided by the invention, solve the problem of low identification precision of the existing essence and flavor identification system.
In order to achieve the purpose of the invention, the invention adopts the technical scheme that:
the intelligent fine identification system for the tobacco flavors and fragrances is provided, and comprises a flavor and fragrance identification management module, and a basic data management module, a system management and maintenance module and a system comprehensive query module which are respectively connected with the flavor and fragrance identification management module;
the basic data management module is used for providing essence and spice basic attributes based on the essence and spice identification process and managing and identifying environmental information;
the essence and spice identification management module is used for inputting data of the sample to be identified and identifying essence and spice in the data of the sample to be identified according to the data provided by the basic data management module;
the system management and maintenance module is used for managing the system and the system authority;
and the system comprehensive query module is used for querying and generating a statistical report.
Further, the basic data management module comprises:
the user unit management submodule is used for managing user unit information;
the identification instrument management submodule is used for establishing an identification instrument file and inputting detailed information of the identification instrument;
the supplier management submodule is used for establishing a supplier information file;
the essence and spice management submodule is used for establishing a spice type information file;
the chemical component management submodule is used for inputting various chemical components;
the recognition condition management submodule is used for inputting the recognition condition and establishing recognition environment archive information;
the identification calibration management submodule is used for recording different peak-out times and deviation degrees according to different identification conditions and components to form a standard for judging the category of chromatographic component data;
the weight and constraint range management submodule is used for setting the upper limit and the lower limit of the intensity of each component of the spice and the weight of each component of the spice;
and the training parameter setting submodule is used for setting various identification parameters.
Further, the essence and spice identification management module comprises:
the to-be-identified sample management submodule is used for importing sample data to be identified and carrying out data query and data preprocessing;
the standard sample data input submodule is used for importing standard sample data, establishing a fingerprint spectrum, graphing the standard sample data and displaying sample component information;
the standard sample training submodule is used for processing and analyzing standard sample data, constructing network nerves and comparing standard sample information to obtain and display a standard sample training result;
and the to-be-identified sample identification submodule is used for processing and analyzing the sample data to obtain a training result and an identification analysis result of the to-be-identified sample.
Further, the system management and maintenance module comprises:
the database connection submodule is used for connecting a database;
the database backup submodule is used for backing up files in the database;
the database log compression submodule is used for compressing log files in the database;
the database recovery submodule is used for recovering the files in the database;
the user switching submodule is used for returning to a login interface and changing a login user;
the password changing submodule is used for changing the user password;
and the help submodule is used for providing a system use instruction.
Further, the system comprehensive query module comprises:
the sample query submodule is used for querying the input sample data, generating a query result and checking the specific information of the sample;
the report inquiry submodule is used for inquiring the output report data;
and the batch quality query submodule is used for checking the sample quality identification result and the specific identification information of the same batch of the same supplier.
The intelligent fine identification method of the tobacco flavor and fragrance is provided, and comprises the following steps:
s1, inputting essence basic attributes and management identification environmental information in the essence identification process through the basic data management module; importing the data of the sample to be identified into a database through a sample to be identified management submodule;
s2, preprocessing the sample data to be identified through a sample management submodule to be identified;
s3, importing the data of the standard sample into a database through a standard sample data entry submodule, and establishing a standard sample fingerprint;
s4, training data of the standard sample through the standard sample training submodule to obtain a training result of the standard sample data;
s5, training the sample data to be recognized according to the training result of the standard sample data through the sample recognition submodule to be recognized, and obtaining the training result of the sample data to be recognized;
s6, performing dimensionality reduction on the training result of the sample data to be recognized according to a principal component analysis method;
s7, respectively carrying out recognition analysis on the training results of the sample data to be recognized after the dimensionality reduction treatment according to an included angle cosine method, a neural network method, a support vector machine and a Mahalanobis distance algorithm, and respectively obtaining recognition analysis results of the included angle cosine method, the neural network method, the support vector machine and the Mahalanobis distance algorithm;
s8, respectively judging whether the identification and analysis results respectively obtained by an included angle cosine method, a neural network method, a support vector machine and a Mahalanobis distance algorithm are consistent with the standard sample fingerprint, if so, entering a step S9, otherwise, increasing the number of standard samples and returning to the step S3;
s9, analyzing similarity and difference of the identification and analysis results obtained by an included angle cosine method, a neural network method, a support vector machine and a Mahalanobis distance algorithm respectively, and obtaining an analysis report.
Further, step S1 includes the following method:
establishing user unit information through a user unit management submodule;
establishing an identification instrument file through an identification instrument management submodule, inputting the name, specification and model, using units, custodians, performance states, source mode manufacturers and identification benchmark default deviation of the identification instrument, and setting a reading initial row and a reading column of sample data to be identified;
inputting the name of a supplier of the sample to be identified, the enterprise property and address of the supplier, a contact person of the supplier, a contact telephone and a mailbox of the contact person through a supplier management sub-module to form a supplier file;
inputting the name of the essence through an essence management submodule;
inputting a chemical name and a corresponding chemical formula thereof through a chemical component management submodule;
inputting the auxiliary device information of the identification instrument through the identification condition management submodule;
selecting test conditions and chemical components through the identification calibration management submodule, and selecting an identification reference and an upper deviation, a lower deviation or a deviation rate;
setting upper limit values and lower limit values of weight and intensity of the identification datum through a weight and constraint range management submodule;
setting the training times, the learning rate, the hidden layer training function, the training error, the principal component extraction proportion and the principal component factor number of a to-be-identified sample identification submodule through a training parameter setting submodule;
and importing the data of the sample to be identified into a database through a sample to be identified management submodule.
Further, the preprocessing method in step S2 is:
and combining or deleting the similar identification bases in the sample data to be identified.
Further, step S9 is followed by the steps of:
and S10, inquiring the analysis report through the system comprehensive inquiry module and generating a statistical report.
The invention has the beneficial effects that: the invention adopts the identification and analysis method of four modes of principal component analysis-included angle cosine, principal component analysis-support vector machine and principal component analysis-neural network and principal component analysis-mahalanobis distance algorithm for parallel identification and consistency check, has accurate identification and high precision, is beneficial to improving the identification and analysis efficiency of the essence and the spice, improving the automation degree of enterprises and reducing the personnel cost.
Drawings
FIG. 1 is a block diagram of the present system;
FIG. 2 is a flow chart of the method.
Detailed Description
The following description of the embodiments of the present invention is provided to facilitate the understanding of the present invention by those skilled in the art, but it should be understood that the present invention is not limited to the scope of the embodiments, and it will be apparent to those skilled in the art that various changes may be made without departing from the spirit and scope of the invention as defined and defined in the appended claims, and all matters produced by the invention using the inventive concept are protected.
As shown in fig. 1, the intelligent fine identification system for tobacco flavors and fragrances comprises a flavor and fragrances identification management module, and a basic data management module, a system management and maintenance module and a system comprehensive query module which are respectively connected with the flavor and fragrances identification management module;
the basic data management module is used for providing essence and spice basic attributes based on the essence and spice identification process and managing and identifying environmental information;
the essence and spice identification management module is used for inputting data of the sample to be identified and identifying essence and spice in the data of the sample to be identified according to the data provided by the basic data management module;
the system management and maintenance module is used for managing the system and the system authority;
and the system comprehensive query module is used for querying and generating a statistical report.
The basic data management module comprises:
the user unit management submodule comprises all user unit structure information and user unit detailed information and is used for realizing the management of user units;
the identification instrument management submodule is used for establishing a test instrument file and inputting detailed information of the test instrument, including an instrument name, a specification model, a performance state, an instrument picture and the like, which are related to other basic information;
the supplier management submodule is used for establishing a supplier information file which comprises information such as a supplier name, a contact person and a contact telephone and inquiring the defined supplier information through different inquiry conditions;
the essence and spice management submodule is used for establishing spice type information files which comprise spice names, remarks and other information and are the most basic information of the system, and defined spice information can be inquired through different inquiry conditions;
the chemical component management submodule is used for managing various chemical components and carrying out definition management on the various chemical components, so that the system can extract related data when identifying the perfume components and can inquire the data according to names;
the identification condition management submodule is used for inputting relevant conditions during identification, including information of an identification instrument and a used chromatographic column and providing archive information for a subsequent identification environment;
the identification calibration management submodule is used for inputting different peak-out times and deviation degrees according to different identification conditions and components, taking the peak-out times and the deviation degrees as standards for judging the types of the chromatographic component data, and inquiring the defined data through different inquiry conditions after the definition is finished;
the weight and constraint range management submodule is used for setting the upper limit and the lower limit of the intensity of each component of the spice and the weight of each component of the spice and providing a standard reference value for the subsequent sample identification;
and the training parameter setting submodule is used for setting various identification parameters, and the accuracy of the detection result is influenced by changing the parameters.
The essence spices discernment management module includes:
the to-be-identified sample management submodule is used for importing sample data to be identified, carrying out data query and data preprocessing and associating the sample data with a sample identification interface;
the standard sample data input sub-module is used for importing standard sample data, has the functions of data query, data preprocessing and the like, can automatically establish a fingerprint spectrum, realizes the charification of the sample data, and can visually reflect the component information of the sample;
the standard sample training submodule is used for automatically finishing standard sample data processing and analysis, constructing a neural network, comparing sample information and the like on the basis of correctly selecting a recognition instrument, testing conditions and inputting a standard sample, finally obtaining a standard sample training result, storing the result in a file format, and only displaying a brief result in an interface;
and the to-be-recognized sample identification submodule is used for automatically finishing the processing and analysis of the to-be-recognized sample data on the basis of correctly selecting the recognition instrument, recognizing conditions and inputting the to-be-recognized sample, finally obtaining the training result of the to-be-recognized sample, generating a chart and displaying the brief recognition result in the interface.
The system management and maintenance module comprises:
the database connection submodule is used for connecting a database;
the database backup submodule is used for backing up files in the database;
the database log compression submodule is used for compressing log files in the database;
the database recovery submodule is used for recovering the files in the database;
the user switching submodule is used for returning to a login interface and changing a login user;
the password changing submodule is used for changing the user password;
and the help submodule is used for providing a system use instruction.
The system comprehensive query module comprises:
the sample query submodule is used for querying the input sample data according to various query conditions, generating a query result in a table form and clicking to check the specific information of the sample;
the report query submodule is used for querying the output report data according to the input query conditions, generating a query result in a table form and clicking to check the specific information of the report;
and the batch quality query submodule is used for checking the quality identification results of the flavors and fragrances of the same batch of the same supplier according to the input query conditions, and can click to check the specific information of the sample identification results.
As shown in figure 2, the intelligent fine identification method of the tobacco flavor and fragrance comprises the following steps:
s1, inputting essence basic attributes and management identification environmental information in the essence identification process through the basic data management module; importing the data of the sample to be identified into a database through a sample to be identified management submodule;
s2, preprocessing the sample data to be identified through a sample management submodule to be identified;
s3, importing the data of the standard sample into a database through a standard sample data entry submodule, and establishing a standard sample fingerprint;
s4, training data of the standard sample through the standard sample training submodule to obtain a training result of the standard sample data;
s5, training the sample data to be recognized according to the training result of the standard sample data through the sample recognition submodule to be recognized, and obtaining the training result of the sample data to be recognized;
s6, performing dimensionality reduction on the training result of the sample data to be recognized according to a principal component analysis method;
s7, respectively carrying out recognition analysis on the training results of the sample data to be recognized after the dimensionality reduction treatment according to an included angle cosine method, a neural network method, a support vector machine and a Mahalanobis distance algorithm, and respectively obtaining recognition analysis results of the included angle cosine method, the neural network method, the support vector machine and the Mahalanobis distance algorithm;
s8, respectively judging whether the identification and analysis results respectively obtained by an included angle cosine method, a neural network method, a support vector machine and a Mahalanobis distance algorithm are consistent with the standard sample fingerprint, if so, entering a step S9, otherwise, increasing the number of standard samples and returning to the step S3;
s9, analyzing similarity and difference of the identification and analysis results obtained by an included angle cosine method, a neural network method, a support vector machine and a Mahalanobis distance algorithm respectively, and obtaining an analysis report.
Step S1 includes the following method:
establishing user unit information through a user unit management submodule;
establishing an identification instrument file through an identification instrument management submodule, inputting the name, specification and model, using units, custodians, performance states, source mode manufacturers and identification benchmark default deviation of the identification instrument, and setting a reading initial row and a reading column of sample data to be identified;
inputting the name of a supplier of the sample to be identified, the enterprise property and address of the supplier, a contact person of the supplier, a contact telephone and a mailbox of the contact person through a supplier management sub-module to form a supplier file;
inputting the name of the essence through an essence management submodule;
inputting a chemical name and a corresponding chemical formula thereof through a chemical component management submodule;
inputting the auxiliary device information of the identification instrument through the identification condition management submodule;
selecting test conditions and chemical components through the identification calibration management submodule, and selecting an identification reference and an upper deviation, a lower deviation or a deviation rate;
setting upper limit values and lower limit values of weight and intensity of the identification datum through a weight and constraint range management submodule;
setting the training times, the learning rate, the hidden layer training function, the training error, the principal component extraction proportion and the principal component factor number of a to-be-identified sample identification submodule through a training parameter setting submodule;
and importing the data of the sample to be identified into a database through a sample to be identified management submodule.
The preprocessing method in step S2 includes:
and combining or deleting the similar identification bases in the sample data to be identified.
Step S9 is followed by the step of:
and S10, inquiring the analysis report through the system comprehensive inquiry module and generating a statistical report.
In one embodiment of the invention, the BP neural network method: the method has a self-learning function and an association storage function, can quickly search an optimized solution, and has high-efficiency prediction capability. The method is an error back propagation algorithm, and the reliability of identification is high.
Angle cosine method: the cosine value of the included angle between two vectors in the vector space is used as a measure for measuring the difference between two individuals. The closer the cosine value is to 1, the more similar the two vectors are.
A support vector machine: the method is a two-class classification algorithm, and the basic idea is to find an optimal classification hyperplane on a feature space to distinguish two classes of samples. And then the aim of multi-classification solving is achieved through multiple times of two classification.
Mahalanobis distance algorithm: it represents the covariance distance of the data, which is an efficient way to compute the similarity of two unknown sample sets. The method is not influenced by dimensions, the mahalanobis distance between two points is irrelevant to the measurement unit of the original data, and the interference of the correlation between variables can be eliminated.
Principal component analysis method: is a technique for analyzing and simplifying data sets. After the principal component analysis, a plurality of variables are converted into a few comprehensive data indexes, the comprehensive data indexes can reflect most of original information, and the data is simplified while the data is guaranteed not to be distorted to the maximum extent.
The invention adopts the identification and analysis method of four modes of principal component analysis-included angle cosine, principal component analysis-support vector machine and principal component analysis-neural network and principal component analysis-mahalanobis distance algorithm for parallel identification and consistency check, has accurate identification and high precision, is beneficial to improving the identification and analysis efficiency of the essence and the spice, improving the automation degree of enterprises and reducing the personnel cost.
Claims (1)
1. An intelligent fine identification method for tobacco flavors and fragrances is characterized in that based on an intelligent fine identification system for tobacco flavors and fragrances, the system comprises a flavor and fragrance identification management module, and a basic data management module, a system management and maintenance module and a system comprehensive query module which are respectively connected with the flavor and fragrance identification management module;
the basic data management module is used for providing essence and spice basic attributes and management and identification environment information based on an essence and spice identification process;
the essence and spice identification management module is used for inputting data of a sample to be identified and identifying essence and spice in the data of the sample to be identified according to the data provided by the basic data management module;
the system management and maintenance module is used for managing the system and the system authority;
the system comprehensive query module is used for querying and generating a statistical report;
the basic data management module comprises:
the user unit management submodule is used for managing user unit information;
the identification instrument management submodule is used for establishing an identification instrument file and inputting detailed information of the identification instrument;
the supplier management submodule is used for establishing a supplier information file;
the essence and spice management submodule is used for establishing a spice type information file;
the chemical component management submodule is used for inputting various chemical components;
the recognition condition management submodule is used for inputting the recognition condition and establishing recognition environment archive information;
the identification calibration management submodule is used for recording different peak-out times and deviation degrees according to different identification conditions and components to form a standard for judging the category of chromatographic component data;
the weight and constraint range management submodule is used for setting the upper limit and the lower limit of the intensity of each component of the spice and the weight of each component of the spice;
the training parameter setting submodule is used for setting various identification parameters;
the essence and spice recognition management module comprises:
the to-be-identified sample management submodule is used for importing sample data to be identified and carrying out data query and data preprocessing;
the standard sample data input submodule is used for importing standard sample data, establishing a fingerprint spectrum, graphing the standard sample data and displaying sample component information;
the standard sample training submodule is used for processing and analyzing standard sample data, constructing network nerves and comparing standard sample information to obtain and display a standard sample training result;
the to-be-identified sample identification submodule is used for processing and analyzing sample data to obtain a training result and an identification analysis result of the to-be-identified sample;
the system management and maintenance module comprises:
the database connection submodule is used for connecting a database;
the database backup submodule is used for backing up files in the database;
the database log compression submodule is used for compressing log files in the database;
the database recovery submodule is used for recovering the files in the database;
the user switching submodule is used for returning to a login interface and changing a login user;
the password changing submodule is used for changing the user password;
the help submodule is used for providing a system use instruction;
the system comprehensive query module comprises:
the sample query submodule is used for querying the input sample data, generating a query result and checking the specific information of the sample;
the report inquiry submodule is used for inquiring the output report data;
the batch quality query submodule is used for checking the sample quality identification result and the specific identification information of the same batch of the same supplier;
the method comprises the following steps:
s1, inputting essence basic attributes and management identification environmental information in the essence identification process through the basic data management module; importing the data of the sample to be identified into a database through a sample to be identified management submodule;
s2, preprocessing the sample data to be identified through a sample management submodule to be identified;
s3, importing the data of the standard sample into a database through a standard sample data entry submodule, and establishing a standard sample fingerprint;
s4, training data of the standard sample through the standard sample training submodule to obtain a training result of the standard sample data;
s5, training the sample data to be recognized according to the training result of the standard sample data through the sample recognition submodule to be recognized, and obtaining the training result of the sample data to be recognized;
s6, performing dimensionality reduction on the training result of the sample data to be recognized according to a principal component analysis method;
s7, respectively carrying out recognition analysis on the training results of the sample data to be recognized after the dimensionality reduction treatment according to an included angle cosine method, a neural network method, a support vector machine and a Mahalanobis distance algorithm, and respectively obtaining recognition analysis results of the included angle cosine method, the neural network method, the support vector machine and the Mahalanobis distance algorithm;
s8, respectively judging whether the identification and analysis results respectively obtained by an included angle cosine method, a neural network method, a support vector machine and a Mahalanobis distance algorithm are consistent with the standard sample fingerprint, if so, entering a step S9, otherwise, increasing the number of standard samples and returning to the step S3;
s9, analyzing similarity and difference of identification and analysis results obtained by an included angle cosine method, a neural network method, a support vector machine and a Mahalanobis distance algorithm respectively, and obtaining an analysis report;
s10, inquiring the analysis report through the system comprehensive inquiry module and generating a statistical report;
the step S1 includes the following method:
establishing user unit information through a user unit management submodule;
establishing an identification instrument file through an identification instrument management submodule, inputting the name, specification and model, using units, custodians, performance states, source mode manufacturers and identification benchmark default deviation of the identification instrument, and setting a reading initial row and a reading column of sample data to be identified;
inputting the name of a supplier of the sample to be identified, the enterprise property and address of the supplier, a contact person of the supplier, a contact telephone and a mailbox of the contact person through a supplier management sub-module to form a supplier file;
inputting the name of the essence through an essence management submodule;
inputting a chemical name and a corresponding chemical formula thereof through a chemical component management submodule;
inputting the auxiliary device information of the identification instrument through the identification condition management submodule;
selecting test conditions and chemical components through the identification calibration management submodule, and selecting an identification reference and an upper deviation, a lower deviation or a deviation rate;
setting upper limit values and lower limit values of weight and intensity of the identification datum through a weight and constraint range management submodule;
setting the training times, the learning rate, the hidden layer training function, the training error, the principal component extraction proportion and the principal component factor number of a to-be-identified sample identification submodule through a training parameter setting submodule;
and importing the data of the sample to be identified into a database through a sample to be identified management submodule.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711338784.9A CN108009740B (en) | 2017-12-14 | 2017-12-14 | Intelligent fine identification system and method for tobacco essence and flavor |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711338784.9A CN108009740B (en) | 2017-12-14 | 2017-12-14 | Intelligent fine identification system and method for tobacco essence and flavor |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108009740A CN108009740A (en) | 2018-05-08 |
| CN108009740B true CN108009740B (en) | 2020-03-24 |
Family
ID=62058872
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711338784.9A Expired - Fee Related CN108009740B (en) | 2017-12-14 | 2017-12-14 | Intelligent fine identification system and method for tobacco essence and flavor |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108009740B (en) |
Families Citing this family (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109885575A (en) * | 2019-02-25 | 2019-06-14 | 四川大学 | A kind of cutting fluid intelligent finely identifying system and method |
| CN109668850A (en) * | 2019-02-28 | 2019-04-23 | 山东中医药大学 | Herbal nature recognition methods and system based on ultraviolet fingerprint |
| CN110702806A (en) * | 2019-09-09 | 2020-01-17 | 米津锐 | Reverse engineering dynamic analysis method |
| CN112419674A (en) * | 2020-10-26 | 2021-02-26 | 四川大学 | System and method for monitoring debris flow geological disasters |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102663136A (en) * | 2012-05-04 | 2012-09-12 | 中国科学院新疆理化技术研究所 | Method for resolving spectrum data of compound of natural product |
| CN103488868A (en) * | 2013-07-30 | 2014-01-01 | 中国标准化研究院 | Research method of establishing intelligent smell judging models for honey quality differences |
| CN104484730A (en) * | 2014-10-27 | 2015-04-01 | 山东建筑大学 | Batching monitoring and tracing method and system |
-
2017
- 2017-12-14 CN CN201711338784.9A patent/CN108009740B/en not_active Expired - Fee Related
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102663136A (en) * | 2012-05-04 | 2012-09-12 | 中国科学院新疆理化技术研究所 | Method for resolving spectrum data of compound of natural product |
| CN103488868A (en) * | 2013-07-30 | 2014-01-01 | 中国标准化研究院 | Research method of establishing intelligent smell judging models for honey quality differences |
| CN104484730A (en) * | 2014-10-27 | 2015-04-01 | 山东建筑大学 | Batching monitoring and tracing method and system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108009740A (en) | 2018-05-08 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108009740B (en) | Intelligent fine identification system and method for tobacco essence and flavor | |
| US20050058325A1 (en) | Fingerprint verification | |
| CN108960269B (en) | Feature acquisition method and device for data set and computing equipment | |
| CN108806718B (en) | Audio identification method based on analysis of ENF phase spectrum and instantaneous frequency spectrum | |
| WO2021174812A1 (en) | Data cleaning method and apparatus for profile, and medium and electronic device | |
| CN108363717B (en) | Data security level identification and detection method and device | |
| CN108319672B (en) | Mobile terminal bad information filtering method and system based on cloud computing | |
| CN109190698B (en) | Classification and identification system and method for network digital virtual assets | |
| CN112270596A (en) | Risk control system and method based on user portrait construction | |
| CN113052577A (en) | Method and system for estimating category of virtual address of block chain digital currency | |
| US20240127143A1 (en) | Method, device and storage medium for information processing based on data interaction | |
| CN116842330B (en) | Health care information processing method and device capable of comparing histories | |
| CN115797044B (en) | Credit wind control early warning method and system based on cluster analysis | |
| CN108268462A (en) | A kind of data quality checking system of relation integraity | |
| CN112487270A (en) | Method and device for asset classification and accuracy verification based on picture identification | |
| CN111105041A (en) | Machine learning method and device for intelligent data collision | |
| CN114580982B (en) | Method, device and equipment for evaluating data quality of industrial equipment | |
| CN112488143A (en) | Network asset localization identification method, device, equipment and storage medium | |
| CN116303375B (en) | Database maintenance analysis method, server and medium based on big data | |
| CN115640369B (en) | Piece information base data storage method applying star-shaped data model | |
| de Jongh et al. | Performance evaluation of automated fingerprint identification systems for specific conditions observed in casework using simulated fingermarks | |
| US20200327968A1 (en) | System and method of integrated unique identity management | |
| CN112115124A (en) | Data influence degree analysis method and device, electronic equipment and storage medium | |
| CN117764713A (en) | Method and device for determining credit limit, storage medium and electronic equipment | |
| CN115203683A (en) | Network security internal threat detection method |
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 |
Granted publication date: 20200324 Termination date: 20201214 |
|
| CF01 | Termination of patent right due to non-payment of annual fee |