Big data analysis method applied to enterprise lean management system

Abstract

The invention discloses a big data analysis method applied to an enterprise lean management system. The analysis method comprises the following steps: step 1, constructing a big data analysis model; extracting enterprise lean management system data; 2, analyzing the extracted enterprise lean management system data; step 3, preprocessing the analyzed data; 4, importing the preprocessed data into a big data analysis model for analysis; the method has the advantages that data obtained after data cleaning, feature selection, feature scaling, data transformation and data set splitting are imported into the big data analysis model for analysis, interference is reduced, and data analysis accuracy is improved; the analyzed data is stored in the storage library, the corresponding data can be searched according to the input keyword, and the searched corresponding data can be exported, so that the use convenience is further improved, and the experience feeling during use is improved.

Description

Technical Field

[0001] The present invention belongs to the technical field of enterprise lean management big data analysis, and specifically relates to a big data analysis method applied to an enterprise lean management system. Background Art

[0002] Most small and medium-sized enterprises are in an era of low profits with weak management foundation, uneven personnel quality, rising costs and more intense competition. Through refined management, they can reduce costs, improve management, increase efficiency and enhance corporate competitiveness. Implementing refined management is a necessity for corporate development and an inevitable path to improving management levels.

[0003] Refined management is actually a kind of consciousness and concept. Attitude determines everything. If you want to successfully implement refined management, you must change your thinking and attitude. Refined management means to do every job well with an attitude of continuous improvement, a rigorous and pragmatic style, and a serious and responsible sense of responsibility. Refined management requires the participation of all employees. Only when everyone participates in refined management can it be implemented and effective. The implementation of all management models cannot be done by bosses and managers alone. All employees must participate in refined management automatically and consciously to maximize their potential. Managing things through processes and managing people through systems will bring about benefits. The OEC daily settlement management model emphasizes that everything that everyone does every day should be included in the scope of strict and detailed management and control. Refined management requires that everything is managed, planned, and summarized, and that data speaks for itself.

[0004] A lean manufacturing production management system and method based on data analysis with application number CN202310203539.6 discloses collecting first production data of a manufacturing plant that needs to perform lean manufacturing, and based on the data type of the first production data, storing the first production data in a preset historical summary database; obtaining an analysis subject, and according to the analysis subject, retrieving the second production data corresponding to the historical summary database; performing data analysis on the second production data to obtain analysis results; according to the analysis results, determining the pre-adjusted production process in the production process of the manufacturing plant, determining the target production process after the pre-adjusted production process is adjusted, and performing corresponding management.

[0005] The existing big data analysis methods applied to enterprise lean management systems require the retrieval of production data from historical summary databases. The data is relatively single, which affects the accuracy of data analysis and has great interference problems. Summary of the invention

[0006] The purpose of the present invention is to provide a big data analysis method applied to an enterprise lean management system to reduce interference and improve the accuracy of data analysis.

[0007] To achieve the above object, the present invention provides the following technical solution: a big data analysis method applied to an enterprise lean management system, the analysis method is as follows:

[0008] Step 1: Build a big data analysis model and extract enterprise lean management system data;

[0009] Step 2: Analyze the extracted enterprise lean management system data;

[0010] Step 3: Preprocess the parsed data;

[0011] Step 4: Import the preprocessed data into the big data analysis model for analysis.

[0012] As a preferred technical solution of the present invention, a method for extracting enterprise lean management system data is as follows: data satisfying at least one preset dimensional information is obtained from a system database according to at least one preset dimensional information, and the obtained data is displayed according to at least one preset dimensional information.

[0013] As a preferred technical solution of the present invention, the preset dimensional information is one or a combination of at least two of the employee's output, quality, cost, enthusiasm, and creativity.

[0014] As a preferred technical solution of the present invention, the parsing method is as follows: according to the storage rules of the data, a parsing function for parsing and processing data is defined for each data; a data parser is defined for each parsing function; a mapping relationship between corresponding data parsers and parsing functions is established; the parsing function, data parser and mapping relationship corresponding to each data are organized in the form of a dynamic link library; according to the defined data parser and the established mapping relationship between the data parser and the parsing function, the data parser required for data parsing is configured, and the parsing function is called according to the configured data parser information to complete the parsing of the data.

[0015] As a preferred technical solution of the present invention, the preprocessing includes data cleaning, feature selection, feature scaling, data transformation, and data set splitting.

[0016] As a preferred technical solution of the present invention, it also includes a storage repository for storing the analyzed data.

[0017] As a preferred technical solution of the present invention, the method for viewing the data keywords in the repository is as follows: open the repository, enter keywords at the search end of the repository, and search for corresponding data according to the entered keywords.

[0018] As a preferred technical solution of the present invention, the method for searching and exporting corresponding data is as follows: select the corresponding data to be searched, click the export command to export, and when exporting, you can select the type of data to be exported and encrypt the exported data.

[0019] Compared with the prior art, the present invention has the following beneficial effects:

[0020] Data cleaning, feature selection, feature scaling, data transformation, and data set splitting are imported into the big data analysis model for analysis to reduce interference and improve the accuracy of data analysis;

[0021] The analyzed data is stored in the repository, and the corresponding data can be searched according to the input keywords. The corresponding data can also be exported, which further increases the convenience of use and improves the experience when using it. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] Figure 1 This is a flow chart of the big data analysis method of the present invention. DETAILED DESCRIPTION

[0023] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0024] Example 1

[0025] See also Figure 1 , which is the first embodiment of the present invention, and provides a big data analysis method applied to an enterprise lean management system, comprising the following steps:

[0026] Step 1: Build a big data analysis model and extract enterprise lean management system data;

[0027] Step 2: Analyze the extracted enterprise lean management system data;

[0028] Step 3: Preprocess the parsed data;

[0029] Step 4: Import the preprocessed data into the big data analysis model for analysis.

[0030] In this embodiment, preferably, the method for extracting enterprise lean management system data is as follows: data satisfying at least one preset dimensional information is obtained from a system database according to at least one preset dimensional information, and the obtained data is displayed according to at least one preset dimensional information.

[0031] In this embodiment, preferably, the preset dimension information is one or a combination of at least two of the employee's output, quality, cost, enthusiasm, and creativity.

[0032] In this embodiment, preferably, the parsing method is as follows: according to the storage rules of the data, define a parsing function for parsing and processing the data for each data; define a data parser for each parsing function; establish a mapping relationship between corresponding data parsers and parsing functions; organize the parsing functions, data parsers and mapping relationships corresponding to each data in the form of a dynamic link library; according to the defined data parsers and the established mapping relationship between the data parsers and the parsing functions, configure the data parsers required for data parsing, and call the parsing function according to the configured data parser information to complete the parsing of the data.

[0033] In this embodiment, preferably, preprocessing includes data cleaning, feature selection, feature scaling, data transformation, and data set splitting; data cleaning is the process of processing data containing errors, missing values, outliers, or duplicate data problems. Common cleaning operations include deleting duplicate data, filling missing values, correcting erroneous values, and processing outliers to ensure the integrity and consistency of the data; feature selection is to select the most relevant and representative feature subsets from the original data to reduce the dimension of the input features and improve the effect and efficiency of the model. Common feature selection methods include filtering methods, wrapping methods, and embedded methods; feature scaling is to scale the feature allocation data to the same scale to avoid certain features having too much impact on the model when calculating distance or loss; common feature scaling methods include standardization and normalization; data transformation is to convert and restructure the original data to improve the analysis effect. Common data transformation methods include logarithmic transformation, power transformation, normalization, discretization, and one-hot encoding. The specific method depends on the data type and the needs of the analysis task; data set splitting is the process of dividing the original data into training set, validation set and test set. The training set is used for model training and parameter estimation, the validation set is used to adjust the model's hyperparameters and evaluate model performance, and the test set is used to evaluate the generalization ability of the final model.

[0034] Example 2

[0035] See also Figure 1 , which is a second embodiment of the present invention, and which provides a big data analysis method applied to an enterprise lean management system, comprising the following steps:

[0036] Step 1: Build a big data analysis model and extract enterprise lean management system data;

[0037] Step 2: Analyze the extracted enterprise lean management system data;

[0038] Step 3: Preprocess the parsed data;

[0039] Step 4: Import the preprocessed data into the big data analysis model for analysis.

[0040] In this embodiment, preferably, the method for extracting enterprise lean management system data is as follows: data satisfying at least one preset dimensional information is obtained from a system database according to at least one preset dimensional information, and the obtained data is displayed according to at least one preset dimensional information.

[0041] In this embodiment, preferably, the preset dimension information is one or a combination of at least two of the employee's output, quality, cost, enthusiasm, and creativity.

[0042] In this embodiment, preferably, the parsing method is as follows: according to the storage rules of the data, define a parsing function for parsing and processing the data for each data; define a data parser for each parsing function; establish a mapping relationship between corresponding data parsers and parsing functions; organize the parsing functions, data parsers and mapping relationships corresponding to each data in the form of a dynamic link library; according to the defined data parsers and the established mapping relationship between the data parsers and the parsing functions, configure the data parsers required for data parsing, and call the parsing function according to the configured data parser information to complete the parsing of the data.

[0043] In this embodiment, preferably, preprocessing includes data cleaning, feature selection, feature scaling, data transformation, and data set splitting; data cleaning is the process of processing data containing errors, missing values, outliers, or duplicate data problems. Common cleaning operations include deleting duplicate data, filling missing values, correcting erroneous values, and processing outliers to ensure the integrity and consistency of the data; feature selection is to select the most relevant and representative feature subsets from the original data to reduce the dimension of the input features and improve the effect and efficiency of the model. Common feature selection methods include filtering methods, wrapping methods, and embedded methods; feature scaling is to scale the feature allocation data to the same scale to avoid certain features having too much impact on the model when calculating distance or loss; common feature scaling methods include standardization and normalization; data transformation is to convert and restructure the original data to improve the analysis effect. Common data transformation methods include logarithmic transformation, power transformation, normalization, discretization, and one-hot encoding. The specific method depends on the data type and the needs of the analysis task; data set splitting is the process of dividing the original data into training set, validation set and test set. The training set is used for model training and parameter estimation, the validation set is used to adjust the model's hyperparameters and evaluate model performance, and the test set is used to evaluate the generalization ability of the final model.

[0044] In this embodiment, preferably, a storage repository for storing the analyzed data is also included.

[0045] In this embodiment, preferably, the method for viewing the data keywords in the storage repository is as follows: open the storage repository, enter the keywords at the search end of the storage repository, and search for corresponding data according to the entered keywords.

[0046] In this embodiment, preferably, the method for finding corresponding data and exporting it is as follows: select the corresponding data to be found, click the export command to export, and when exporting, you can select the type of data to be exported and encrypt the exported data.

[0047] Big data analysis models include PEST analysis model, 5W2H analysis model, logic tree analysis model, 4P marketing theory model, and user behavior model; PEST analysis model includes

[0048] Political environment: Key indicators: political system, economic system, fiscal policy, tax policy, industrial policy, investment policy, government subsidy level, and public participation in politics;

[0049] The economic environment has two aspects: macro and micro. Macro: a country's national income, gross national product and changes, which reflect the level and speed of national economic development through these indicators. Micro: the income level, consumption preferences, savings and employment level of consumers in the region where the enterprise is located, which determine the current and future market size of the enterprise.

[0050] Key indicators: GDP and growth rate, total import and export volume and growth rate, interest rate, exchange rate, inflation rate, consumer price index, disposable income of residents, unemployment rate, and labor productivity;

[0051] Social environment: includes the educational level and cultural level, religious beliefs, customs, aesthetic views, and values ​​of residents in a country or region. Cultural level reflects the needs of residents. Religious beliefs and customs may prohibit or resist certain activities. Values ​​may affect residents' recognition of organizational goals and the existence of organizational activities. Aesthetic views may affect people's attitudes toward the content, methods, and results of organizational activities.

[0052] Key indicators: population size, gender ratio, age structure, birth rate, death rate, ethnic structure, female fertility rate, lifestyle, purchasing habits, education status, urban characteristics, religious beliefs;

[0053] Technological environment: the development and changes of technological means directly related to the field in which the enterprise is located, the investment and support focus of national scientific and technological development, the technological development trends and total research and development expenses in the field, and the speed of technology transfer and technology commercialization;

[0054] Key indicators: invention and progress of new technologies, depreciation and scrapping speed, technology update speed, technology dissemination speed, technology commercialization speed, national key support projects, and national R&D expenditures;

[0055] Logical tree analysis model: list all sub-problems of a problem in layers, starting from the highest level and gradually expanding downwards; treat a known problem as a tree trunk, consider which problems this problem is related to, add related problems as branches to the trunk, and by analogy, the problem will be expanded into a problem tree; the logical tree can ensure the integrity of the problem-solving process, break down the work into specific tasks that are easy to operate, determine the priority of each part, and clarify the responsibility of individuals; the three principles of logical tree analysis method: elementization: summarize the same problem into elements; framework: form a framework with each element, and abide by the principle of no duplication and no omission; association: the elements in the framework maintain the necessary relationship with each other, simple but not isolated;

[0056] The 5W2H analysis model has a wide range of application scenarios and can be used to analyze user behavior and product business;

[0057] The 4P marketing theory model is mainly used to analyze the overall operation of a company or one of its product lines, and to assist in making decisions on short-term operation plans and programs through analysis conclusions.

[0058] Although the embodiments of the present invention have been shown and described, as detailed above, it will be understood by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A big data analysis method applied to an enterprise lean management system, characterized by: The analysis method is as follows: Step 1: Build a big data analysis model and extract enterprise lean management system data; Step 2: Analyze the extracted enterprise lean management system data; Step 3: Preprocess the parsed data; Step 4: Import the preprocessed data into the big data analysis model for analysis.

2. The big data analysis method applied to an enterprise lean management system according to claim 1, characterized in that: The method for extracting enterprise lean management system data is as follows: according to at least one preset dimension information, data satisfying at least one preset dimension information is acquired from a system database, and the acquired data is displayed according to at least one preset dimension information.

3. The big data analysis method applied to the enterprise lean management system according to claim 2 is characterized by: The preset dimension information is one or a combination of at least two of the employee's output, quality, cost, enthusiasm, and creativity.

4. The big data analysis method applied to an enterprise lean management system according to claim 1, characterized in that: The parsing method is as follows: according to the data storage rules, a parsing function for parsing and processing data is defined for each data; a data parser is defined for each parsing function; a mapping relationship between corresponding data parsers and parsing functions is established; the parsing function, data parser and mapping relationship corresponding to each data are organized in the form of a dynamic link library; according to the defined data parser and the established mapping relationship between the data parser and the parsing function, the data parser required for data parsing is configured, and the parsing function is called according to the configured data parser information to complete the parsing of the data.

5. The big data analysis method applied to an enterprise lean management system according to claim 1, characterized in that: The preprocessing includes data cleaning, feature selection, feature scaling, data transformation, and data set splitting.

6. The big data analysis method applied to an enterprise lean management system according to claim 1, characterized in that: It also includes a repository for storing the analyzed data.

7. The big data analysis method applied to an enterprise lean management system according to claim 6, characterized in that: The method for viewing the data keywords in the repository is as follows: open the repository, enter a keyword at the search end of the repository, and search for corresponding data based on the entered keyword.

8. The big data analysis method applied to the enterprise lean management system according to claim 7 is characterized by: The method to find the corresponding data and export it is as follows: Select the corresponding data to be found, click the export command to export, and when exporting, you can select the type of data to be exported and encrypt the exported data.

Images