CN117151345A - Enterprise management intelligent decision platform based on AI technology - Google Patents
Enterprise management intelligent decision platform based on AI technology Download PDFInfo
- Publication number
- CN117151345A CN117151345A CN202311411400.7A CN202311411400A CN117151345A CN 117151345 A CN117151345 A CN 117151345A CN 202311411400 A CN202311411400 A CN 202311411400A CN 117151345 A CN117151345 A CN 117151345A
- Authority
- CN
- China
- Prior art keywords
- data
- unit
- decision
- module
- analysis
- 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.)
- Pending
Links
- 238000005516 engineering process Methods 0.000 title claims abstract description 36
- 238000007726 management method Methods 0.000 claims abstract description 58
- 238000010801 machine learning Methods 0.000 claims abstract description 24
- 238000000034 method Methods 0.000 claims abstract description 23
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 21
- 238000007405 data analysis Methods 0.000 claims abstract description 21
- 230000010354 integration Effects 0.000 claims abstract description 21
- 238000013480 data collection Methods 0.000 claims abstract description 15
- 238000007781 pre-processing Methods 0.000 claims abstract description 15
- 238000007418 data mining Methods 0.000 claims abstract description 14
- 238000012800 visualization Methods 0.000 claims abstract description 13
- 238000012502 risk assessment Methods 0.000 claims abstract description 7
- 239000000284 extract Substances 0.000 claims abstract description 5
- 238000012545 processing Methods 0.000 claims description 51
- 238000004458 analytical method Methods 0.000 claims description 45
- 238000012417 linear regression Methods 0.000 claims description 23
- 238000013145 classification model Methods 0.000 claims description 22
- 238000005065 mining Methods 0.000 claims description 15
- 238000013500 data storage Methods 0.000 claims description 14
- 238000004088 simulation Methods 0.000 claims description 13
- 238000004140 cleaning Methods 0.000 claims description 12
- 238000010606 normalization Methods 0.000 claims description 12
- 238000012549 training Methods 0.000 claims description 10
- 230000002159 abnormal effect Effects 0.000 claims description 9
- 238000006243 chemical reaction Methods 0.000 claims description 9
- 238000003066 decision tree Methods 0.000 claims description 9
- 238000007621 cluster analysis Methods 0.000 claims description 6
- 238000003058 natural language processing Methods 0.000 claims description 6
- 238000012300 Sequence Analysis Methods 0.000 claims description 5
- 238000003064 k means clustering Methods 0.000 claims description 5
- YHXISWVBGDMDLQ-UHFFFAOYSA-N moclobemide Chemical compound C1=CC(Cl)=CC=C1C(=O)NCCN1CCOCC1 YHXISWVBGDMDLQ-UHFFFAOYSA-N 0.000 claims description 5
- 238000012360 testing method Methods 0.000 claims description 5
- 238000010586 diagram Methods 0.000 claims description 4
- 238000007619 statistical method Methods 0.000 claims description 4
- 230000005540 biological transmission Effects 0.000 claims description 3
- 238000004364 calculation method Methods 0.000 claims description 3
- 238000002790 cross-validation Methods 0.000 claims description 3
- 230000008451 emotion Effects 0.000 claims description 3
- 238000012544 monitoring process Methods 0.000 claims description 3
- 238000013481 data capture Methods 0.000 claims description 2
- 238000012731 temporal analysis Methods 0.000 claims 1
- 238000000700 time series analysis Methods 0.000 claims 1
- 230000004044 response Effects 0.000 abstract 1
- 238000013473 artificial intelligence Methods 0.000 description 17
- 238000004519 manufacturing process Methods 0.000 description 15
- 239000002994 raw material Substances 0.000 description 5
- 230000001419 dependent effect Effects 0.000 description 3
- 230000000007 visual effect Effects 0.000 description 3
- 206010063385 Intellectualisation Diseases 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 238000012423 maintenance Methods 0.000 description 2
- 238000012795 verification Methods 0.000 description 2
- 239000002699 waste material Substances 0.000 description 2
- 201000004569 Blindness Diseases 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000010485 coping Effects 0.000 description 1
- 238000003745 diagnosis Methods 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 230000003278 mimic effect Effects 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 230000008447 perception Effects 0.000 description 1
- 230000001932 seasonal effect Effects 0.000 description 1
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
-
- 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
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- 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
- G06Q10/0635—Risk analysis of enterprise or organisation activities
Landscapes
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Engineering & Computer Science (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- Operations Research (AREA)
- Game Theory and Decision Science (AREA)
- Development Economics (AREA)
- Marketing (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Educational Administration (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention relates to the technical field of decision management, and provides an enterprise management intelligent decision platform based on an AI technology, which comprises a data collection and integration module, a data preprocessing module, a data analysis and mining module, a visualization and reporting module, a decision support module, an automation and intelligent module and a display terminal; the invention can process large-scale and multi-source data and extract various information therefrom, thereby helping enterprises to better understand the operation and market conditions of the enterprises, and simultaneously helping to eliminate errors and redundancy in the data, improve the data quality and ensure the consistency and availability of the data; providing personalized decision support, supporting quick response to market changes and operation problems; automated business processes and tasks, predicting future trends using machine learning algorithms, identifying potential risks and providing real-time risk assessment; machine learning and automation techniques are used to detect and repair anomalies in data to ensure data quality.
Description
Technical Field
The invention relates to the technical field of decision management, in particular to an enterprise management intelligent decision platform based on an AI technology.
Background
AI (artificial intelligence) technology is a class of computer systems and algorithms that simulate and mimic human intelligence and learning capabilities; it is intended to enable a computer to perform tasks that typically require human intelligence, including perception, understanding, decision making, and problem solving.
An enterprise management intelligent decision-making platform is a platform for assisting an enterprise manager in making decisions by utilizing artificial intelligence and data analysis technologies; the goal of the enterprise management intelligent decision platform is to help the management layer make more intelligent strategy and operation decisions by providing real-time data, analysis and insight, thereby improving the efficiency, competitiveness and profitability of the enterprise.
The Chinese patent application number is: 202110909428.8 an enterprise asset management intelligent decision system based on the industrial Internet comprises a data resource management system, an intelligent decision system and an intelligent equipment management platform; the data resource management system includes: the system comprises an enterprise operation cockpit module, an intelligent scheduling module, an equipment fault early warning module, a channel consumption insight module, a product sales prediction module and an intelligent model engine module; the intelligent decision system is used for importing enterprise data into a pre-trained algorithm model and outputting a fault decision scheme according to enterprise data information; the intelligent equipment management platform comprises asset management, operation and maintenance management and fault diagnosis; the intelligent decision and management are carried out on equipment, operation and resources of an enterprise through the cooperative combination of a local MES, ERP, WMS system and a cloud machine learning algorithm, global optimization is carried out on manufacturing enterprises, and the enterprise is helped to realize intelligent and digital manufacturing; however, the industrial internet technology in the invention requires complex infrastructure and system composition in implementation and maintenance, and requires professional engineers and technicians to manage, has higher implementation cost and technical difficulty, and is highly dependent on the quality and availability of data; in contrast, the AI technology has lower deployment cost and technical difficulty, and can process partial noisy data.
In summary, the present invention provides an enterprise management intelligent decision platform based on AI technology to solve the above problems.
Disclosure of Invention
The invention provides an enterprise management intelligent decision platform based on an AI technology, which is constructed by the AI technology, and has lower deployment cost and technical difficulty so as to solve the problem of high dependence on the quality and availability of data in the prior art.
An enterprise management intelligent decision platform based on AI technology, comprising:
a data collection and integration module for collecting data from the data sources and integrating the data into a centralized database, the data being the raw data;
the data preprocessing module is used for receiving the original data integrated by the data collecting and integrating module, cleaning, converting and normalizing the original data and transmitting the processed data to the database;
the data analysis and mining module is used for extracting the preprocessed data transmitted by the data preprocessing module from the database, analyzing the preprocessed data, extracting the data source information in the data collection and integration module from the database, mining rules and correlations in the data, and transmitting the analysis result to the database;
the visualization and reporting module is used for receiving the data analysis result transmitted by the data analysis and mining module, visualizing the data analysis result, generating a chart and a report, and transmitting the chart and the report to the database;
the decision support module is used for receiving the charts and reports transmitted by the visualization and reporting module, integrating the auxiliary decision-making tools and the historical data and transmitting the auxiliary decision-making tools and the historical data to the database;
and the automation and intelligent module is used for receiving the tool and the historical data transmitted by the decision support module, constructing a machine learning model and automatically making policies.
The preferable technical scheme is that the enterprise management intelligent decision platform further comprises a safety and compliance module, a deployment and integration module;
the safety and compliance module is used for calling the operation data of the automation and intelligent module and ensuring the safety and compliance of the data in the operation of the automation and intelligent module, and the safety and compliance module comprises identity verification, access control and data encryption functions;
the deployment and integration module is used for integrating the data collection and integration module, the data preprocessing module, the data analysis and mining module, the visualization and reporting module, the decision support module, the automation and intelligence module and the security and compliance module into an IT infrastructure, and comprises hardware, cloud services, data storage and network connection.
The data collection and integration module comprises a data source access unit, a data grabbing unit, a data storage unit and a data quality management unit;
the data source access unit is used for connecting and accessing a data source, wherein the data source comprises a database, a file system and an API interface, and transmits data source information to the data grabbing unit;
the data grabbing unit extracts data from the original data obtained by the data source access unit by using a crawler technology and an API calling method, and transmits the extracted data to the data storage unit;
the data storage unit is used for receiving the data transmitted by the data grabbing unit and storing the data into a database, wherein the database is a relational database;
the data quality management unit is used for monitoring and evaluating the quality of the data stored in the data storage unit.
The data preprocessing module comprises a data cleaning unit, a data conversion unit and a data normalization unit;
the data cleaning unit comprises a missing value processing subunit, an abnormal value processing subunit and a repeated data processing subunit;
the missing value processing subunit is used for deleting the missing value, replacing the missing value and interpolating;
the abnormal value processing subunit is used for identifying and marking abnormal values;
the repeated data processing subunit is used for identifying and deleting repeated data and combining a plurality of similar data into one;
the data conversion unit comprises a feature selection subunit, a feature coding subunit, a feature scaling subunit and a text data processing subunit;
the feature selection subunit is configured to select a feature that is most relevant and has a most information value from the large-scale dataset;
the characteristic coding subunit is used for coding and converting the characteristics in the original data;
the characteristic scaling subunit is used for scaling the numerical ranges of different characteristics to a uniform scale;
the text data processing subunit is used for processing and analyzing text data;
the data normalization unit comprises a normalization value subunit, a category imbalance processing subunit and a time sequence data processing subunit;
the normalized numerical value subunit is used for converting the value of the numerical value characteristic into a normalized value in a unified range;
the class unbalance processing subunit is used for processing the class unbalance problem existing in the data set;
the time series data processing subunit is used for processing and analyzing the time series data;
the data cleaning unit firstly operates, identifies and corrects problems in data, then operates the data conversion unit to convert the cleaned data format, and finally operates the data normalization unit to process scale differences among different features.
The data analysis and mining module comprises a data summary and description statistics unit, an association rule mining unit, a cluster analysis unit, a time sequence analysis unit, a text analysis and natural language processing unit;
the data summarization and description statistical unit is used for carrying out summarization and descriptive statistical analysis on data, and comprises calculation of average value, median, standard deviation, maximum value and minimum value, and transmission of obtained data characteristics to the association rule mining unit and the cluster analysis unit;
the association rule mining unit searches association rules in the data by using an Apriori algorithm, and combines the mining result with the data characteristics of the data abstract and description statistics unit;
the clustering analysis unit uses a K-means clustering algorithm to divide the data into different categories, analyzes a cluster structure in the data, and combines the analysis result with the data of the data summary and the description statistics unit;
the time sequence analysis unit is used for processing the time sequence data and analyzing the time trend by using an ARIMA model;
the text analysis and natural language processing unit is used for processing and analyzing text data and carrying out emotion analysis and entity identification.
In a preferred technical solution, the visualization and reporting module visualizes the data by using Plotly to generate a line graph, a bar graph, a pie graph and a thermodynamic diagram.
The preferable technical scheme is that the decision support module comprises a decision tree and flow unit, a report and analysis unit, a prediction and simulation unit, a multi-condition analysis unit, a risk assessment unit, a decision support tool unit and a decision history recording unit;
the decision tree and the flow unit are used for creating and customizing a decision tree, a flow chart and a decision path;
the report and analysis unit is used for generating a sales report, a financial analysis report and a market trend analysis result;
the prediction and simulation unit uses AI technology to perform sales prediction and market demand simulation;
the multi-condition analysis unit analyzes future sales data based on market conditions and product types and the operation results of the comprehensive report and analysis unit, the prediction and simulation unit;
the risk assessment unit is used for assessing market risk, competition risk and supply chain risk;
the decision support tool unit is used for integrating decision-making auxiliary tools, including SWOT and PESEL analysis tools;
the decision history record unit is used for storing detailed information of each decision, including time, participators, basis and result of the decision.
The automatic and intelligent module comprises an automatic decision rule unit, a machine learning model management unit and an automatic decision support unit;
the automatic decision rule unit is used for defining and managing automatic decision rules, and comprises the steps of automatically adjusting stock level according to sales data, automatically distributing customer service resources according to customer feedback, and transmitting the automatic decision rules to the machine learning model management unit;
the machine learning model management unit is used for receiving the automatic decision rule transmitted by the automatic decision rule unit, taking the automatic decision rule as an initial parameter of the machine learning model, constructing a prediction model and a classification model based on the historical data transmitted by the decision support module, optimizing the prediction model and the classification model in real time, and transmitting the prediction model and the classification model to the automatic decision support unit;
the automatic decision support unit is used for analyzing the prediction model and the classification model transmitted by the machine learning model management unit, generating a decision basis and simulating an optimal decision path.
According to the preferred technical scheme, the machine learning model management unit classifies historical data transmitted by the decision support module into a training set and a test set, applies a linear regression algorithm to the training set, performs model training on a prediction model and a classification model, evaluates the performances of the prediction model and the classification model according to a preset mean square error and an accuracy index, and further analyzes the generalization capability of the model by using a cross-validation technology, wherein the linear regression algorithm comprises a simple linear regression model and a multiple linear regression model, and the formula of the simple linear regression model is as follows:
；
in the method, in the process of the invention,is the intercept (I)>Is the slope, X is the independent variable, Y is the dependent variable;
the multiple linear regression model formula is:
；
in the method, in the process of the invention,is the intercept (I)>，/>Is the coefficient of the respective variable.
Compared with the prior art, the invention has the following beneficial effects:
1. the invention extracts data from the database, the file system and the API interface by using the crawler technology and the API calling method, eliminates errors and redundancies in the data by using the data preprocessing module, and improves the data quality, thereby integrating the data of different data sources into one database, and enabling enterprises to acquire comprehensive and accurate data information.
2. The method uses the Apriori algorithm, the K-means clustering algorithm and the ARIMA model to analyze and mine the data, uses the Plotly to convert complex data into a visual and understandable chart and report, helps enterprises mine information from massive data, provides visual, accurate and real-time data presentation, and supports data-driven decision making, thereby improving the operation efficiency of the enterprises, reducing risks and enhancing the competitiveness of the enterprises.
3. The invention uses AI technology, SWOT and PESEL analysis tools and linear regression algorithm to construct the prediction model and the classification model, thereby generating decision basis, simulating the optimal decision path, realizing the automation and intelligent decision of enterprises, helping enterprise management personnel to predict possible risks, reducing complicated manual operation, improving the working efficiency of personnel, reducing the blindness of decision, providing powerful support for the establishment and execution of enterprise strategy, enabling enterprises to better adapt to rapidly changing market environment, and improving the competitiveness.
Drawings
Fig. 1 is a schematic diagram of the overall structure of the present invention.
Detailed Description
Embodiments of the present invention are described in further detail below with reference to the accompanying drawings and examples. The following examples are illustrative of the invention but are not intended to limit the scope of the invention.
As shown in fig. 1, the present invention provides an enterprise management intelligent decision platform based on AI technology, comprising:
a data collection and integration module for collecting data from the data sources and integrating the data into a centralized database, the data being the raw data;
the data preprocessing module is used for receiving the original data integrated by the data collecting and integrating module, cleaning, converting and normalizing the original data and transmitting the processed data to the database;
the data analysis and mining module is used for extracting the preprocessed data transmitted by the data preprocessing module from the database, analyzing the preprocessed data, extracting the data source information in the data collection and integration module from the database, mining rules and correlations in the data, and transmitting the analysis result to the database;
the visualization and reporting module is used for receiving the data analysis result transmitted by the data analysis and mining module, visualizing the data analysis result, generating a chart and a report, and transmitting the chart and the report to the database;
the decision support module is used for receiving the charts and reports transmitted by the visualization and reporting module, integrating the auxiliary decision-making tools and the historical data and transmitting the auxiliary decision-making tools and the historical data to the database;
and the automation and intelligent module is used for receiving the tool and the historical data transmitted by the decision support module, constructing a machine learning model and automatically making policies.
As an embodiment of the present invention, the enterprise management intelligent decision platform further includes a security and compliance module, a deployment and integration module;
the safety and compliance module is used for calling the operation data of the automation and intelligent module and ensuring the safety and compliance of the data in the operation of the automation and intelligent module, and the safety and compliance module comprises identity verification, access control and data encryption functions;
the deployment and integration module is used for integrating the data collection and integration module, the data preprocessing module, the data analysis and mining module, the visualization and reporting module, the decision support module, the automation and intelligence module and the security and compliance module into an IT infrastructure, and comprises hardware, cloud services, data storage and network connection.
As one embodiment of the present invention, the data collection and integration module includes a data source access unit, a data capture unit, a data storage unit, and a data quality management unit;
the data source access unit is used for connecting and accessing a data source, wherein the data source comprises a database, a file system and an API interface, and transmits data source information to the data grabbing unit;
the data grabbing unit extracts data from the original data obtained by the data source access unit by using a crawler technology and an API calling method, and transmits the extracted data to the data storage unit;
the data storage unit is used for receiving the data transmitted by the data grabbing unit and storing the data into a database, wherein the database is a relational database;
the data quality management unit is used for monitoring and evaluating the quality of the data stored in the data storage unit.
As one embodiment of the present invention, the data preprocessing module includes a data cleaning unit, a data conversion unit, and a data normalization unit;
the data cleaning unit comprises a missing value processing subunit, an abnormal value processing subunit and a repeated data processing subunit;
the missing value processing subunit is used for deleting the missing value, replacing the missing value and interpolating;
the abnormal value processing subunit is used for identifying and marking abnormal values;
the repeated data processing subunit is used for identifying and deleting repeated data and combining a plurality of similar data into one;
the data conversion unit comprises a feature selection subunit, a feature coding subunit, a feature scaling subunit and a text data processing subunit;
the feature selection subunit is configured to select a feature that is most relevant and has a most information value from the large-scale dataset;
the characteristic coding subunit is used for coding and converting the characteristics in the original data;
the characteristic scaling subunit is used for scaling the numerical ranges of different characteristics to a uniform scale;
the text data processing subunit is used for processing and analyzing text data;
the data normalization unit comprises a normalization value subunit, a category imbalance processing subunit and a time sequence data processing subunit;
the normalized numerical value subunit is used for converting the value of the numerical value characteristic into a normalized value in a unified range;
the class unbalance processing subunit is used for processing the class unbalance problem existing in the data set;
the time series data processing subunit is used for processing and analyzing the time series data;
the data cleaning unit firstly operates, identifies and corrects problems in data, then operates the data conversion unit to convert the cleaned data format, and finally operates the data normalization unit to process scale differences among different features.
As one embodiment of the invention, the data analysis and mining module comprises a data summary and description statistics unit, an association rule mining unit, a cluster analysis unit, a time sequence analysis unit, a text analysis and natural language processing unit;
the data summarization and description statistical unit is used for carrying out summarization and descriptive statistical analysis on data, and comprises calculation of average value, median, standard deviation, maximum value and minimum value, and transmission of obtained data characteristics to the association rule mining unit and the cluster analysis unit;
the association rule mining unit searches association rules in the data by using an Apriori algorithm, and combines the mining result with the data characteristics of the data abstract and description statistics unit;
the clustering analysis unit uses a K-means clustering algorithm to divide the data into different categories, analyzes a cluster structure in the data, and combines the analysis result with the data of the data summary and the description statistics unit;
the time sequence analysis unit is used for processing the time sequence data and analyzing the time trend by using an ARIMA model;
the text analysis and natural language processing unit is used for processing and analyzing text data and carrying out emotion analysis and entity identification.
As one embodiment of the invention, the visualization and reporting module visualizes the data by generating a line graph, a bar graph, a pie chart, and a thermodynamic diagram using Plotly.
As one embodiment of the invention, the decision support module comprises a decision tree and flow unit, a report and analysis unit, a prediction and simulation unit, a multi-condition analysis unit, a risk assessment unit, a decision support tool unit and a decision history recording unit;
the decision tree and the flow unit are used for creating and customizing a decision tree, a flow chart and a decision path;
the report and analysis unit is used for generating a sales report, a financial analysis report and a market trend analysis result;
the prediction and simulation unit uses AI technology to perform sales prediction and market demand simulation;
the multi-condition analysis unit analyzes future sales data based on market conditions and product types and the operation results of the comprehensive report and analysis unit, the prediction and simulation unit;
the risk assessment unit is used for assessing market risk, competition risk and supply chain risk;
the decision support tool unit is used for integrating decision-making auxiliary tools, including SWOT and PESEL analysis tools;
the decision history record unit is used for storing detailed information of each decision, including time, participators, basis and result of the decision.
As one embodiment of the present invention, the automation and intellectualization module includes an automatic decision rule unit, a machine learning model management unit, an automatic decision support unit;
the automatic decision rule unit is used for defining and managing automatic decision rules, and comprises the steps of automatically adjusting stock level according to sales data, automatically distributing customer service resources according to customer feedback, and transmitting the automatic decision rules to the machine learning model management unit;
the machine learning model management unit is used for receiving the automatic decision rule transmitted by the automatic decision rule unit, taking the automatic decision rule as an initial parameter of the machine learning model, constructing a prediction model and a classification model based on the historical data transmitted by the decision support module, optimizing the prediction model and the classification model in real time, and transmitting the prediction model and the classification model to the automatic decision support unit;
the automatic decision support unit is used for analyzing the prediction model and the classification model transmitted by the machine learning model management unit, generating a decision basis and simulating an optimal decision path.
As one embodiment of the present invention, the machine learning model management unit classifies the historical data transmitted by the decision support module into a training set and a test set, applies a linear regression algorithm to the training set, performs model training on the prediction model and the classification model, and evaluates the performances of the prediction model and the classification model according to a preset mean square error and an accuracy index, and further analyzes the generalization capability of the model by using a cross-validation technique, wherein the linear regression algorithm comprises a simple linear regression model and a multiple linear regression model, and the formula of the simple linear regression model is as follows:
；
in the method, in the process of the invention,is the intercept (I)>Is the slope, X is the independent variable, Y is the dependent variable; in an enterprise management intelligent decision platform, a simple linear regression model is applied to simple decision scenes, such as predicting the relationship between sales volume and advertising charge, the relationship between employee wages and working years, and the like;
the multiple linear regression model formula is:
；
in the method, in the process of the invention,is the intercept (I)>Is the coefficient of the respective variable; in an enterprise management intelligent decision platform, a multiple linear regression model is applied to complex decision scenarios, such as analyzing images of market demand, advertising investment, and seasonal factors versus sales.
Examples
Taking the problem of a quarter production plan of an enterprise as an example, the enterprise produces a plurality of products, and each product has different sales forecast, production time and raw material requirements; the conventional production plan depends on manual decision, so that the problems of low production efficiency and excessive or insufficient inventory are caused, and the enterprise now hopes to optimize the production plan by means of an enterprise management intelligent decision platform based on AI technology so as to improve the production efficiency, reduce the cost and meet the market demands, and the method comprises the following steps:
firstly, a data collection and integration module collects sales data, production data, raw material supply data and other related data of an enterprise in the past years from an enterprise database, a file system and an API interface by using a crawler technology and an API calling method, and integrates the data into a relational database; then the data preprocessing module cleans, converts and normalizes the original data; the data analysis and mining module then performs summary and descriptive statistical analysis on the data, including sales trends, seasonality, product attributes, raw material supply and the like, calculates the average value, median, standard deviation, maximum value and minimum value of each item of data, searches for association rules in the data by using an Apriori algorithm, classifies the data into different categories by using a K-means clustering algorithm, analyzes cluster structures in the data, analyzes time trends by using an ARIMA model, then generates a visual chart by using a Plotly by using a visualization and reporting module, and then performs sales prediction and market demand simulation by using an AI technology by using a decision support module, integrates SWOT and PESEL analysis tools, and retrieves and uploads decision history data.
Then, enterprise management staff presets a mean square error and an accuracy index in an automation and intelligent module, the automation and intelligent module classifies the historical data transmitted by the decision support module into a training set and a testing set, the training set uses a linear regression algorithm to construct a multiple linear regression prediction model and a multiple linear regression classification model, and the performances of the multiple linear regression prediction model and the multiple linear regression classification model are evaluated according to the preset mean square error and accuracy index; finally, the automation and intellectualization module predicts sales of each product in the next quarter based on the multiple linear regression prediction model and the multiple linear regression classification model by utilizing the relation between sales and production plans, and combines sales prediction with production resources, raw material supply chains and inventory information to generate an optimal production plan, including determining time and quantity of each product produced to meet market demands and avoid inventory waste.
Through implementing the enterprise management intelligent decision platform based on the AI technology, the enterprise can improve the accuracy of the production plan, reduce the overstock and stock backlog, optimize the utilization of production resources, improve the production efficiency, reduce the waste of raw materials and reduce the cost, thereby more flexibly coping with the change of market demands and making more timely decisions.
The embodiments of the present invention have been shown and described for the purpose of illustration and description, it being understood that the above embodiments are illustrative and not to be construed as limiting the invention, and that variations, modifications, alternatives and variations may be made therein by one of ordinary skill in the art without departing from the scope of the invention.
Claims (9)
1. An enterprise management intelligent decision platform based on AI technology, which is characterized by comprising:
a data collection and integration module for collecting data from the data sources and integrating the data into a centralized database, the data being the raw data;
the data preprocessing module is used for extracting the original data integrated by the data collection and integration module from the database, cleaning, converting and normalizing the original data, and transmitting the processed data to the database;
the data analysis and mining module is used for extracting the preprocessed data transmitted by the data preprocessing module from the database, analyzing the preprocessed data, extracting the data source information in the data collection and integration module from the database, mining rules and correlations in the data, and transmitting the analysis result to the database;
the visualization and reporting module is used for extracting the data analysis results transmitted by the data analysis and mining module from the database, visualizing the data analysis results, generating a chart and a report, and transmitting the chart and the report to the database;
the decision support module is used for extracting the charts and reports transmitted by the visualization and reporting module from the database, integrating the auxiliary decision-making tools and the historical data and transmitting the auxiliary decision-making tools and the historical data to the database;
and the automation and intelligent module is used for extracting tools and historical data transmitted by the decision support module from the database, constructing a machine learning model and automatically making policies.
2. The AI-technology-based enterprise management intelligent decision platform of claim 1, further comprising a security and compliance module, a deployment and integration module;
the safety and compliance module is used for calling the operation data of the automation and intelligent module and ensuring the safety and compliance of the data in the operation of the automation and intelligent module;
the deployment and integration module is used to integrate data collection and integration modules, data preprocessing modules, data analysis and mining modules, visualization and reporting modules, decision support modules, automation and intelligence modules, security and compliance modules into an IT infrastructure.
3. The intelligent decision-making platform for enterprise management based on AI technology as claimed in claim 1, wherein the data collection and integration module comprises a data source access unit, a data capture unit, a data storage unit and a data quality management unit;
the data source access unit is used for connecting and accessing a data source, wherein the data source comprises a database, a file system and an API interface, and transmits data source information to the data grabbing unit;
the data grabbing unit extracts data from the original data obtained by the data source access unit by using a crawler technology and an API calling method, and transmits the extracted data to the data storage unit;
the data storage unit is used for receiving the data transmitted by the data grabbing unit and storing the data into a database;
the data quality management unit is used for monitoring and evaluating the quality of the data stored in the data storage unit.
4. The enterprise management intelligent decision platform based on AI technology as claimed in claim 1, wherein the data preprocessing module comprises a data cleaning unit, a data conversion unit and a data normalization unit;
the data cleaning unit comprises a missing value processing subunit, an abnormal value processing subunit and a repeated data processing subunit;
the missing value processing subunit is used for deleting the missing value, replacing the missing value and interpolating;
the abnormal value processing subunit is used for identifying and marking abnormal values;
the repeated data processing subunit is used for identifying and deleting repeated data and combining a plurality of similar data into one;
the data conversion unit comprises a feature selection subunit, a feature coding subunit, a feature scaling subunit and a text data processing subunit;
the feature selection subunit is configured to select a feature that is most relevant and has a most information value from the large-scale dataset;
the characteristic coding subunit is used for coding and converting the characteristics in the original data;
the characteristic scaling subunit is used for scaling the numerical ranges of different characteristics to a uniform scale;
the text data processing subunit is used for processing and analyzing text data;
the data normalization unit comprises a normalization value subunit, a category imbalance processing subunit and a time sequence data processing subunit;
the normalized numerical value subunit is used for converting the value of the numerical value characteristic into a normalized value in a unified range;
the class unbalance processing subunit is used for processing the class unbalance problem existing in the data set;
the time series data processing subunit is used for processing and analyzing the time series data;
the data cleaning unit firstly operates, identifies and corrects problems in data, then operates the data conversion unit to convert the cleaned data format, and finally operates the data normalization unit to process scale differences among different features.
5. The enterprise management intelligent decision platform based on AI technology of claim 1, wherein the data analysis and mining module comprises a data summary and description statistics unit, an association rule mining unit, a cluster analysis unit, a time series analysis unit, a text analysis and natural language processing unit;
the data summarization and description statistical unit is used for carrying out summarization and descriptive statistical analysis on data, and comprises calculation of average value, median, standard deviation, maximum value and minimum value, and transmission of obtained data characteristics to the association rule mining unit and the cluster analysis unit;
the association rule mining unit searches association rules in the data by using an Apriori algorithm, and combines the mining result with the data characteristics of the data abstract and description statistics unit;
the clustering analysis unit uses a K-means clustering algorithm to divide the data into different categories, analyzes a cluster structure in the data, and combines the analysis result with the data of the data summary and the description statistics unit;
the time sequence analysis unit is used for processing the time sequence data and analyzing the time trend by using an ARIMA model;
the text analysis and natural language processing unit is used for processing and analyzing text data and carrying out emotion analysis and entity identification.
6. The intelligent decision platform for enterprise management based on AI technology of claim 1, wherein the means for visualizing and reporting data is by generating line, bar, pie, and thermodynamic diagrams using Plotly.
7. The intelligent decision platform for enterprise management based on AI technology of claim 1, wherein the decision support module comprises a decision tree and flow unit, a report and analysis unit, a prediction and simulation unit, a multi-condition analysis unit, a risk assessment unit, a decision support tool unit, a decision history unit;
the decision tree and the flow unit are used for creating and customizing a decision tree, a flow chart and a decision path;
the report and analysis unit is used for generating a sales report, a financial analysis report and a market trend analysis result;
the prediction and simulation unit uses AI technology to perform sales prediction and market demand simulation;
the multi-condition analysis unit analyzes future sales data based on market conditions and product types and the operation results of the comprehensive report and analysis unit, the prediction and simulation unit;
the risk assessment unit is used for assessing market risk, competition risk and supply chain risk;
the decision support tool unit is used for integrating decision-making auxiliary tools, including SWOT and PESEL analysis tools;
the decision history record unit is used for storing detailed information of each decision, including time, participators, basis and result of the decision.
8. The intelligent decision platform for enterprise management based on AI technology of claim 1, wherein the automation and intelligence module comprises an automatic decision rule unit, a machine learning model management unit, an automated decision support unit;
the automatic decision rule unit is used for defining and managing automatic decision rules, and comprises the steps of automatically adjusting stock level according to sales data, automatically distributing customer service resources according to customer feedback, and transmitting the automatic decision rules to the machine learning model management unit;
the machine learning model management unit is used for receiving the automatic decision rule transmitted by the automatic decision rule unit, taking the automatic decision rule as an initial parameter of the machine learning model, constructing a prediction model and a classification model based on the historical data transmitted by the decision support module, optimizing the prediction model and the classification model in real time, and transmitting the prediction model and the classification model to the automatic decision support unit;
the automatic decision support unit is used for analyzing the prediction model and the classification model transmitted by the machine learning model management unit, generating a decision basis and simulating an optimal decision path.
9. The intelligent decision-making platform for enterprise management based on AI technology of claim 8, wherein the machine learning model management unit classifies the historical data transmitted by the decision support module into a training set and a test set, applies a linear regression algorithm to the training set, model-trains the prediction model and the classification model, and evaluates the performance of the prediction model and the classification model according to a preset mean square error and accuracy index, applies to the test set, and further analyzes the generalization capability of the model by using a cross-validation technology.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311411400.7A CN117151345A (en) | 2023-10-30 | 2023-10-30 | Enterprise management intelligent decision platform based on AI technology |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311411400.7A CN117151345A (en) | 2023-10-30 | 2023-10-30 | Enterprise management intelligent decision platform based on AI technology |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117151345A true CN117151345A (en) | 2023-12-01 |
Family
ID=88884673
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311411400.7A Pending CN117151345A (en) | 2023-10-30 | 2023-10-30 | Enterprise management intelligent decision platform based on AI technology |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117151345A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117350774A (en) * | 2023-12-05 | 2024-01-05 | 山东大学 | Urban sports building material budget execution control method and system based on big data |
| CN117389236A (en) * | 2023-12-11 | 2024-01-12 | 山东三岳化工有限公司 | Propylene oxide production process optimization method and system |
| CN117763422A (en) * | 2023-12-25 | 2024-03-26 | 北京燃数科技有限公司 | SaaS (software as a service) investment system for solving investment strategy |
| CN117788082A (en) * | 2024-02-26 | 2024-03-29 | 南京南自华盾数字技术有限公司 | Power market quotation decision method and system based on electricity price prediction |
| CN117786748A (en) * | 2023-12-28 | 2024-03-29 | 广州美亿互联信息技术有限公司 | Digital analysis management system and method based on Internet |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111340246A (en) * | 2020-02-26 | 2020-06-26 | 未来地图(深圳)智能科技有限公司 | Processing method and device for enterprise intelligent decision analysis and computer equipment |
| KR102260591B1 (en) * | 2020-10-12 | 2021-06-08 | 동국대학교 산학협력단 | Data-based decision support system and operation method |
| CN113627784A (en) * | 2021-08-09 | 2021-11-09 | 浙江天能优品网络科技有限公司 | Enterprise asset management intelligent decision-making system based on industrial internet |
| CN113780667A (en) * | 2021-09-15 | 2021-12-10 | 未来地图(深圳)智能科技有限公司 | Enterprise operation prediction method and system based on AI artificial intelligence |
| CN116109280A (en) * | 2023-03-11 | 2023-05-12 | 广东德澳智慧医疗科技有限公司 | Multifunctional financial monitoring and analyzing platform based on intelligent big data and algorithm |
| CN116383198A (en) * | 2023-03-03 | 2023-07-04 | 天元大数据信用管理有限公司 | Decision analysis method and system based on big data |
-
2023
- 2023-10-30 CN CN202311411400.7A patent/CN117151345A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111340246A (en) * | 2020-02-26 | 2020-06-26 | 未来地图(深圳)智能科技有限公司 | Processing method and device for enterprise intelligent decision analysis and computer equipment |
| KR102260591B1 (en) * | 2020-10-12 | 2021-06-08 | 동국대학교 산학협력단 | Data-based decision support system and operation method |
| CN113627784A (en) * | 2021-08-09 | 2021-11-09 | 浙江天能优品网络科技有限公司 | Enterprise asset management intelligent decision-making system based on industrial internet |
| CN113780667A (en) * | 2021-09-15 | 2021-12-10 | 未来地图(深圳)智能科技有限公司 | Enterprise operation prediction method and system based on AI artificial intelligence |
| CN116383198A (en) * | 2023-03-03 | 2023-07-04 | 天元大数据信用管理有限公司 | Decision analysis method and system based on big data |
| CN116109280A (en) * | 2023-03-11 | 2023-05-12 | 广东德澳智慧医疗科技有限公司 | Multifunctional financial monitoring and analyzing platform based on intelligent big data and algorithm |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117350774A (en) * | 2023-12-05 | 2024-01-05 | 山东大学 | Urban sports building material budget execution control method and system based on big data |
| CN117350774B (en) * | 2023-12-05 | 2024-03-05 | 山东大学 | Urban sports building material budget execution control method and system based on big data |
| CN117389236A (en) * | 2023-12-11 | 2024-01-12 | 山东三岳化工有限公司 | Propylene oxide production process optimization method and system |
| CN117389236B (en) * | 2023-12-11 | 2024-02-13 | 山东三岳化工有限公司 | Propylene oxide production process optimization method and system |
| CN117763422A (en) * | 2023-12-25 | 2024-03-26 | 北京燃数科技有限公司 | SaaS (software as a service) investment system for solving investment strategy |
| CN117786748A (en) * | 2023-12-28 | 2024-03-29 | 广州美亿互联信息技术有限公司 | Digital analysis management system and method based on Internet |
| CN117788082A (en) * | 2024-02-26 | 2024-03-29 | 南京南自华盾数字技术有限公司 | Power market quotation decision method and system based on electricity price prediction |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10902368B2 (en) | Intelligent decision synchronization in real time for both discrete and continuous process industries | |
| CN117151345A (en) | Enterprise management intelligent decision platform based on AI technology | |
| US10592838B2 (en) | Risk simulation and assessment tool | |
| CN116681250A (en) | Building engineering progress supervisory systems based on artificial intelligence | |
| CN115423289B (en) | Intelligent plate processing workshop data processing method and terminal | |
| Chongwatpol | Prognostic analysis of defects in manufacturing | |
| US8326723B2 (en) | Risk and reward assessment mechanism | |
| US20230123527A1 (en) | Distributed client server system for generating predictive machine learning models | |
| CN112418738A (en) | Staff operation risk prediction method based on logistic regression | |
| CN113627784A (en) | Enterprise asset management intelligent decision-making system based on industrial internet | |
| CN117829554B (en) | Intelligent perception finished product restoration decision support system | |
| CN117787711A (en) | Arch bridge construction single-end management system based on big data | |
| CN117787569B (en) | Intelligent auxiliary bid evaluation method and system | |
| CN117522607A (en) | Enterprise financial management system | |
| Dagnino | Data analytics in the era of the industrial internet of things | |
| CN117875724A (en) | Purchasing risk management and control method and system based on cloud computing | |
| CN117076521A (en) | Operational data analysis method and system based on big data | |
| CN116777140A (en) | Enterprise business management method, device, equipment and medium | |
| Anderson et al. | A Bayesian hierarchical assessment of night shift working for offshore wind farms | |
| CN111612302A (en) | Group-level data management method and equipment | |
| CN117436718B (en) | Intelligent data management platform based on multidimensional engine | |
| CN118011990B (en) | Industrial data quality monitoring and improving system based on artificial intelligence | |
| Canitz | Machine Learning in Supply Chain Planning--When Art & Science Converge. | |
| Lee et al. | Design of decision support system for yield management in semiconductor industry: application to artificial intelligence | |
| CN117952483B (en) | Digital platform-based balance index monitoring method, system and medium thereof |
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 |