CN109949101B - Big data concept-based cigarette material cost analysis method - Google Patents
Big data concept-based cigarette material cost analysis method Download PDFInfo
- Publication number
- CN109949101B CN109949101B CN201910235444.6A CN201910235444A CN109949101B CN 109949101 B CN109949101 B CN 109949101B CN 201910235444 A CN201910235444 A CN 201910235444A CN 109949101 B CN109949101 B CN 109949101B
- Authority
- CN
- China
- Prior art keywords
- data
- cost
- cigarette
- analysis
- cigarette material
- 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.)
- Active
Links
Images
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a cigarette material cost analysis method based on a big data concept, which belongs to the field of tobacco cost control and comprises the following steps of 1, establishing a database used by each production material in a cigarette production link; step 2, mining and analyzing data in the database by using a big data technology according to the database of the materials, analyzing the material use condition of each link in the cigarette production process, and providing a basis for controlling cost; step 3, establishing a multi-target nonlinear programming mathematical model as a cigarette material cost scene analysis model to optimize the scale of multiple suppliers of cigarette materials and centralization of supplied products; the invention promotes cost management of suppliers, creates a set of cigarette material cost analysis method system based on coupling of big data mining technology and statistical method, and overcomes the defect and deficiency that the former cost analysis method excessively depends on manual experience.
Description
Technical Field
The invention belongs to the field of tobacco cost analysis, and particularly relates to a cigarette material cost analysis method based on a big data concept.
Background
The conventional cigarette material cost analysis method adopts a manual experience mode. In the aspect of reducing the purchasing cost of cigarette materials, the cigarette industry companies in all provinces basically adopt 'one-time cutting' or adjust the purchasing cost of various cigarette materials based on simple judgment of purchasing statistical data.
The technical problems in the process of manually analyzing the cost of the cigarette material are as follows: (1) the data collection integrity is poor, and the sample size of the sampled data is small. (2) The analysis lacks theoretical basis, the data analysis means is single, the data judgment is mainly based on experience judgment, and the potential rules and values among data cannot be fully mined. (3) The cigarette material cost related data sources are dispersed, the data volume is large, the association relationship is complex, and the authenticity of the data is difficult to distinguish. (4) Some cost control effects cannot be evaluated, and cost reduction and efficiency improvement effects are affected. (5) The real cost profit of the cigarette material supplier cannot be mastered without data support and scientific and systematic analysis model, so that the profit of the cigarette can be controlled.
Disclosure of Invention
Aiming at the defects in the conventional technology, the invention provides a cigarette material cost analysis method based on a big data concept, which provides ideas of multi-factor correlation cost analysis of cigarette material cost, analysis and pricing of new cigarette product material cost, cigarette material cost prediction and cost evaluation and diagnosis of supply enterprises, and is realized by relying on big data technology; the method is characterized by developing a cigarette material cost analysis method with the functions of multi-dimensional analysis, decision support, fine management and the like, establishing a multi-target nonlinear programming mathematical model as a cigarette material cost scene analysis model, designing an intelligent optimization algorithm such as a genetic algorithm and the like for realization, and providing a reasonable cost budget for cigarette production.
In order to achieve the purpose, the invention is realized by the following technical scheme: the cigarette material cost analysis method based on the big data concept comprises the following steps:
step 1, establishing a database used by each production material in a cigarette production link;
step 2, mining and analyzing data in the database by using a big data technology according to the database, analyzing the material use condition of each link in the cigarette production process, and providing a basis for controlling cost;
step 3, establishing a multi-target nonlinear programming mathematical model as a cigarette material cost scene analysis model to optimize the scale of multiple suppliers of cigarette materials and centralization of supplied products;
and 4, explaining and evaluating the cigarette material cost scene analysis result, giving a set of near-real cost of the cigarette material, and promoting cost management of a supplier.
Preferably, in the step (1), a data dictionary is formed by collecting and sorting the use data of each production material in the cigarette production link, analyzing and identifying various data items and data structures, and the data dictionary is stored as a database;
in the cigarette production link, the production material data comprises the production area distribution, the purchase cost, the transportation cost and the like of various material raw materials, and a basic support of the analysis method is formed.
Preferably, in the step (2), firstly, preprocessing of data is performed, including noise elimination, derivation and calculation of default value data, duplicate recording elimination, completion of data type conversion, and the like;
then establishing a big data diagnosis model based on mathematical statistics, analyzing historical homogeneous data, and realizing the rationality test of each cost data of the cigarette material; meanwhile, a data correction model is adopted, a certain confidence coefficient is selected, and unreasonable data are corrected.
Preferably, in the step (3), according to the input cigarette material supply amount and the predicted profit margin range, the mathematical model is optimized to obtain the number of suppliers corresponding to the maximum profit of the specified cigarette material type or specification, and the optimization scheme of the supply material type and supply amount of each supplier, so as to establish the multi-objective nonlinear programming mathematical model.
Preferably, in the step (4), the analysis result is displayed and operated visually in a form of graph and table, and the result is interpreted and evaluated in text, based on the steps 1 to 4, a cigarette material cost analysis system based on big data concept is constructed, and the cost analysis system includes the following 4 parts: the system comprises a basic supporting layer, a data storage layer, a data fusion layer and a user display layer.
Preferably, the confidence coefficient of the data correction model is selected by adopting a confidence interval estimation method of small sample mean numberWith a confidence of 0.95, by the cost x of various raw materials provided to all enterprises producing similar materials ij (j =1,2.. Multidot., n) normal distribution regression was performed to obtain a mean value μ of normal distribution i Sum variance σ i And analyzing whether the data falls in a confidence interval or not by adopting t test, and if the data exceeds the confidence interval, comparing the data and correcting by adopting a maximum likelihood estimation correction model.
Preferably, the specific algorithm of the multi-target nonlinear programming mathematical model is as follows:
the specific algorithm of the multi-target nonlinear programming mathematical model is as follows:
an objective function:
the main constraint conditions are as follows:
the target function represents the same cigarette material supplier, optimizes the supplier data and maximizes the profit after the cigarette material amount supplied by each supplier is optimized; x is a radical of a fluorine atom 1 To x 7 Respectively representing the cost of the first to seventh raw materials;
x 8 to x 12 Respectively represents the depreciation and maintenance cost, labor cost, energy cost, plate material cost and other costs of equipment in the production and manufacturing cost; x is a radical of a fluorine atom 13 To x 16 Respectively represent financial expense, sales expense, management expense and other expenses in the operation expense; x is a radical of a fluorine atom 17 Representing a non-tax settlement price; x is the number of 18 Represents the aggregate cost of raw material cost; x is the number of 19 Represents the total cost of production and manufacture; x is the number of 20 Represents the aggregate cost of the business; x is the number of 21 Representing the business income of the enterprise in the current year; mu.s 1 Representing the mean value obtained by normal distribution statistics; i represents the loan interest rate in the current year; a represents the upper cost rate swing limit.
Preferably, a cigarette material cost analysis system with the functions of multi-dimensional analysis, decision support, fine management and the like is established through the cooperative work among the basic supporting layer, the data storage layer, the data fusion layer and the user display layer, and each layer of the system respectively comprises the following contents:
the basic supporting layer comprises business data, cost data and financial data;
the data storage layer comprises the database;
the data fusion layer comprises an intelligent analysis engine, a data verification model, a data diagnosis model and a data correction model;
the user display layer comprises cost analysis, scene analysis, new product pricing analysis, cost evaluation and diagnosis; and establishing a uniform information security guarantee mechanism for each layer to form a test material cost analysis software platform.
The invention has the beneficial effects that:
1. a set of cigarette material cost analysis method system based on coupling of big data mining technology and mathematical statistics method is established to support lean purchasing of cigarette materials;
2. based on a cost analysis mathematical model related to multiple factors of the cigarette material cost, the multi-dimensional analysis of the cigarette material cost according to the material type, specification and supplier is realized, the reasonable cost and profit margin of the supplier are obtained, the reasonable pricing of the cigarette material purchase for the new cigarette product and old product improvement can be basically and reasonably guided, the cost reduction and efficiency improvement effects of the supplier and the product centralization are predicted, and the cost control level of the cigarette material supplier is diagnosed;
3. a cigarette material cost analysis software platform with the functions of multi-dimensional analysis, decision support, fine management and the like is developed and operated, the storage, extraction and processing of big cigarette material cost data are realized, manual analysis is changed into system second-level analysis, the analysis accuracy and efficiency are improved, and the aim of lean cigarette material purchase is fulfilled by boosting cigarettes in Yunnan.
Drawings
FIG. 1 is a flow chart for genetic algorithm solution of the model;
FIG. 2 is a cigarette material cost analysis system;
FIG. 3 cigarette material cost analysis software platform
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is further described in detail with reference to the accompanying drawings and examples, which are not intended to limit the present invention.
1. Establishing a database used by each production material in the cigarette production link;
taking the Yunnan region as an example, according to the sampling principle, respectively setting n information acquisition points in each city and each autonomous region of Yunnan province, obtaining cost information such as each product selling price, preferential strategies, transportation charging and the like of related cigarette material manufacturers through investigation and data collection, classifying, combining and summarizing the collected data according to the characteristics such as the region, the material type and the like, designing and building a reasonable data table and a data dictionary, and building a cigarette material cost database;
according to the particularity of cigarette materials and the requirement of specific data analysis and processing, the same group of data is allowed to be used for multiple times, and the data classification method is carried out according to different space-time characteristics. Thus, the scientificity, the rationality and the usefulness of the basic data are ensured.
2. According to the database of the materials, a big data technology is used for mining and analyzing the data in the database, analyzing the material use condition of each link in the cigarette production process and providing a basis for controlling the cost;
taking Yunnan Zhongyan company as an example, technical personnel of the purchasing department of the enterprise take the database to extract the required data, and firstly, preprocessing works such as noise elimination, deduction and calculation of default data, elimination of repeated records, completion of data type conversion and the like are carried out; then, data transformation work such as dimension reduction processing is carried out; then, data diagnosis and discrimination are carried out, a confidence interval estimation method of small sample average number is adopted, the confidence coefficient is set to be 0.95, and the cost x of various raw materials provided for all enterprises producing similar materials is calculated ij (j =1, 2.. Once.n.) normal distribution regression was performed to obtain the mean value μ of normal distribution i Sum variance σ i . And analyzing whether the data fall in a confidence interval or not by adopting t test, and if the data exceed the confidence interval, comparing the data and correcting by adopting a maximum likelihood estimation correction model.
Through data mining analysis, the reliability of the cost database is enhanced and serves as a basis for controlling cost, and meanwhile, basic support is provided for the cigarette material cost scene analysis model.
3. Establishing a multi-target nonlinear programming mathematical model as a cigarette material cost scene analysis model to optimize the scale of multiple suppliers of cigarette materials and centralization of supplied products;
multi-target nonlinear programming mathematical model
The specific algorithm of the multi-target nonlinear programming mathematical model is as follows:
an objective function:
the main constraint conditions are as follows:
the target function represents the same cigarette material supplier, optimizes the supplier data and maximizes the profit after the cigarette material amount supplied by each supplier is optimized; x is a radical of a fluorine atom 1 To x 7 Respectively representing the cost of the first to seventh raw materials;
x 8 to x 12 Respectively representing equipment depreciation and maintenance cost, labor cost, energy cost, plate material cost and other costs in the production and manufacturing expenses; x is the number of 13 To x 16 Respectively representing financial expense, sales expense, management expense and other expenses in the operation expense; x is the number of 17 Representing a non-tax settlement price; x is the number of 18 Represents the total cost of raw material cost; x is the number of 19 Represents the total cost of production and manufacture; x is a radical of a fluorine atom 20 Represents the total cost of the operation; x is the number of 21 Representing the business income of the enterprise in the current year; mu.s 1 Represents the mean value obtained by normal distribution statistics; i represents the loan interest rate in the current year; a represents the upper limit of the variation cost rate;
the model is complex, the general solving algorithm can not solve the optimal solution, intelligent optimization algorithms such as a genetic algorithm are designed for solving the optimal solution, and the flow chart of the genetic algorithm solving of the model is shown in figure 1.
4. The analysis result of the cigarette material cost scene is explained and evaluated, the near-real cost of a set of cigarette materials is provided, and the cost management of a supplier is promoted.
And displaying and operating the analysis result in a visual mode in a graph and a table mode, and performing text explanation and evaluation on the result.
Based on the above processing procedures, as shown in fig. 2, the invention develops a set of cigarette material cost analysis system based on big data concept, which comprises the following 4 parts:
a basic support layer, service data, cost data and financial data;
a data store layer, the database;
the system comprises a data fusion layer, an intelligent analysis engine, a data verification model, a data diagnosis model and a data correction model;
a user display layer, cost analysis, scene analysis, new product pricing analysis and cost evaluation.
Correspondingly, as shown in fig. 3, a uniform information security mechanism is established for each layer, and a cigarette material cost analysis software platform is developed. The user only needs simple operation, and the software platform performs analysis and calculation on the background and returns clear and understandable analysis results and guidance opinions to the user.
The invention mainly achieves the following effects through specific implementation
A set of cigarette material cost analysis method system based on coupling of big data mining technology and mathematical statistics method is established to support lean purchasing of cigarette materials;
based on a cost analysis mathematical model associated with multiple factors of the cigarette material cost, the multidimensional analysis of the cigarette material cost according to the material type, specification and supplier is realized, the reasonable cost and profit margin of the supplier are obtained, the reasonable pricing of the cigarette material purchase for the new and old cigarette product reconstruction can be reasonably guided basically, the cost reduction and efficiency improvement effects of the supplier and the product centralization are predicted, and the cost control level of the cigarette material supplier is diagnosed;
a cigarette material cost analysis software platform with the functions of multi-dimensional analysis, decision support, fine management and the like is developed and operated, the storage, extraction and processing of big cigarette material cost data are realized, manual analysis is changed into system second-level analysis, the analysis accuracy and efficiency are improved, and the aim of lean cigarette material purchase is fulfilled by boosting cigarettes in Yunnan.
The technical content of the present invention is further illustrated by the examples only, so as to facilitate the reader to understand more easily. The general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the invention. Therefore, the present invention is not limited to the embodiments shown herein, and any technical extension or re-creation performed by the present invention is protected by the present invention.
Claims (5)
1. A cigarette material cost analysis method based on big data concept is characterized by comprising the following steps: the cigarette material cost analysis method based on the big data concept comprises the following steps: step 1, establishing a database used by each production material in a cigarette production link; step 2, mining and analyzing data in the database by using a big data technology according to the database, analyzing the material use condition of each link in the cigarette production process, and providing a basis for controlling cost; step 3, establishing a multi-target nonlinear programming mathematical model as a cigarette material cost scene analysis model to optimize the scale of multiple suppliers of cigarette materials and centralization of supplied products; step 4, the tobacco material cost scene analysis result is explained and evaluated, the near-real cost of a set of tobacco materials is given, and the cost management of suppliers is promoted;
in the step 2, firstly, preprocessing data, including noise elimination, deduction and calculation of default value data, elimination of repeated records and completion of data type conversion;
then establishing a big data diagnosis model based on mathematical statistics, analyzing historical homogeneous data, and realizing the rationality test of each cost data of the cigarette material; meanwhile, correcting the unreasonable data by adopting a data correction model and the selected confidence coefficient;
the confidence coefficient of the data correction model is set to be 0.95 by adopting a confidence interval estimation method of small sample mean, and the cost of various raw materials provided for all enterprises producing similar materials is reduced
Performing normal distribution regression to obtain average value of normal distribution
Sum variance
Analyzing whether the data falls in a confidence interval or not by adopting t test, and if the data exceeds the confidence interval, comparing the data and correcting by adopting a maximum likelihood estimation correction model;
the specific algorithm of the multi-target nonlinear programming mathematical model is as follows: an objective function:
the main constraint conditions are as follows:
the target function represents the same cigarette material supplier, optimizes the supplier data and maximizes the profit after the cigarette material amount supplied by each supplier is optimized;
to
Respectively represent the cost of the first to seventh raw materials;
2. The cigarette material cost analysis method based on big data concept according to claim 1, characterized in that: in the step 1, a data dictionary is formed by collecting and sorting the use data of each production material in the cigarette production link, analyzing and identifying various data items and data structures, and is stored as a database; in the cigarette production link, the production material data comprises the production area distribution, the purchasing cost and the transportation cost of various material raw materials, and forms the basic support of the analysis method.
3. The cigarette material cost analysis method based on big data concept according to claim 1, characterized by comprising the following steps: in the step 3, according to the input cigarette material supply amount and the predicted profit margin range, the mathematical model is optimized to obtain the number of suppliers corresponding to the maximum profit of the specified cigarette material type or specification, and the optimization scheme of the supply material type and the supply amount of each supplier, so as to establish the multi-objective nonlinear programming mathematical model.
4. The cigarette material cost analysis method based on big data concept according to claim 1, characterized in that: in the step 4, the analysis result is displayed and operated in a visual mode in a graph and table mode, the result is interpreted and evaluated in a text mode, based on the steps 1-4, a cigarette material cost analysis system based on a big data idea is constructed, and the cost analysis system comprises the following 4 parts: the system comprises a basic supporting layer, a data storage layer, a data fusion layer and a user display layer.
5. The cigarette material cost analysis method based on big data concept according to claim 4, characterized in that: through the cooperative work among the basic supporting layer, the data storage layer, the data fusion layer and the user display layer, a cigarette material cost analysis system with the functions of multi-dimensional analysis, decision support and fine management is established, wherein each layer of the system respectively comprises the following contents: the basic supporting layer comprises business data, cost data and financial data; the data storage layer comprises the database; the data fusion layer comprises an intelligent analysis engine, a data verification model, a data diagnosis model and a data correction model; the user display layer comprises cost analysis, scenario analysis, new product pricing analysis, cost evaluation and diagnosis; and establishing a uniform information security guarantee mechanism for each layer to form a test material cost analysis software platform.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910235444.6A CN109949101B (en) | 2019-03-27 | 2019-03-27 | Big data concept-based cigarette material cost analysis method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910235444.6A CN109949101B (en) | 2019-03-27 | 2019-03-27 | Big data concept-based cigarette material cost analysis method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109949101A CN109949101A (en) | 2019-06-28 |
| CN109949101B true CN109949101B (en) | 2022-12-27 |
Family
ID=67011849
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910235444.6A Active CN109949101B (en) | 2019-03-27 | 2019-03-27 | Big data concept-based cigarette material cost analysis method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109949101B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111310127B (en) * | 2020-02-25 | 2021-01-22 | 武汉轻工大学 | Method and device for acquiring raw material quality range based on food product quality range |
| CN115422706A (en) * | 2022-07-26 | 2022-12-02 | 广西中烟工业有限责任公司 | Digital cigarette material design system and method |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2007102832A1 (en) * | 2006-03-09 | 2007-09-13 | Akoya, Inc. | Automated feature-based analysis for cost management of direct materials |
| CN107767167A (en) * | 2017-09-15 | 2018-03-06 | 合肥英泽信息科技有限公司 | A kind of commercial cigarette marketing big data analysis system |
| CN107909251A (en) * | 2017-10-31 | 2018-04-13 | 山东中烟工业有限责任公司 | A kind of cigarette machine overall efficiency analysis of Influential Factors method and apparatus |
-
2019
- 2019-03-27 CN CN201910235444.6A patent/CN109949101B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2007102832A1 (en) * | 2006-03-09 | 2007-09-13 | Akoya, Inc. | Automated feature-based analysis for cost management of direct materials |
| CN107767167A (en) * | 2017-09-15 | 2018-03-06 | 合肥英泽信息科技有限公司 | A kind of commercial cigarette marketing big data analysis system |
| CN107909251A (en) * | 2017-10-31 | 2018-04-13 | 山东中烟工业有限责任公司 | A kind of cigarette machine overall efficiency analysis of Influential Factors method and apparatus |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109949101A (en) | 2019-06-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Edwards et al. | Importing and firm export performance: New evidence from South Africa | |
| WO2021088499A1 (en) | False invoice issuing identification method and system based on dynamic network representation | |
| CN109949101B (en) | Big data concept-based cigarette material cost analysis method | |
| CN107609771A (en) | A kind of supplier's value assessment method | |
| CN108734567A (en) | A kind of asset management system and its appraisal procedure based on big data artificial intelligence air control | |
| CN115796404A (en) | Power utilization prediction method and system for agent electricity purchasing users | |
| CN110689437A (en) | Communication construction project financial risk prediction method based on random forest | |
| CN104346698A (en) | Catering member big data analysis and checking system based on cloud computing and data mining | |
| CN114077980A (en) | Intelligent supplier management system and intelligent supplier management method | |
| CN112614011A (en) | Power distribution network material demand prediction method and device, storage medium and electronic equipment | |
| US20150006435A1 (en) | Methods and systems for forecasting economic movements | |
| CN112328577A (en) | Agricultural big data management system and method based on county area | |
| CN112183916A (en) | Land reserve life cycle management system | |
| Nazarov et al. | Building technology and predictive analytics models in the SAP analytic cloud digital service | |
| CN112037006A (en) | Credit risk identification method and device for small and micro enterprises | |
| CN107194536A (en) | The power supply reliability negative benefit appraisal procedure and device of a kind of project investment | |
| CN114372848A (en) | Tobacco industry intelligent marketing system based on machine learning | |
| CN117171145B (en) | Analysis processing method, equipment and storage medium for enterprise management system data | |
| Kang et al. | Macroeconomic dynamics in korea during and after the global financial crisis: a bayesian DSGE approach | |
| US20170004521A1 (en) | Systems and methods for generating industry outlook scores | |
| CN111460260A (en) | Data processing system, method and medium for multi-type data | |
| CN114971696A (en) | Quotation method based on electricity consumption and flow information uploading system | |
| CN113935575A (en) | Sheet inquiry benefit measuring and calculating system for iron and steel enterprise | |
| CA3025187A1 (en) | Systems and methods for generating industry outlook scores | |
| Silva et al. | Portfolio optimization based on the pre-selection of stocks by the Support Vector Machine model |
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 |