Industrial production big data resource analysis system

Abstract

The invention discloses an industrial production big data resource analysis system. An operation method of the system comprises the following steps of 1, obtaining production cost data and external market data through system integration; 2, determining abnormal cost influence factors through cost analysis; 3, comparing the factory cost with the market cost and generating a report; and 4, real-time personalized cost optimization suggestions are realized through a cost optimization module, a cost data acquisition and integration module is used for acquiring and integrating cost data of factory operation in various aspects in real time, and an abnormal cost analysis module is used for identifying and analyzing potential abnormal fluctuations in factory cost. Reason analysis of the abnormal cost is provided; the factory and market cost comparison and optimization suggestion module is used for analyzing the relation between the factory cost and the market price and generating cost optimization suggestions, and the system has the advantages of being fast in real-time response and comprehensive in cost analysis.

Description

Technical Field

[0001] The present invention relates to the technical field of production cost analysis, and in particular to an industrial production big data resource analysis system. Background Art

[0002] In modern industrial production, cost control is crucial to the long-term success of an enterprise. Effective cost management not only directly affects the profitability of an enterprise, but also determines the ability of an enterprise to survive and develop in the fierce market competition. Faced with the ever-changing market environment and competitive pressure, enterprises must use advanced technical means to improve the level of cost control to adapt to the rapidly changing market demand.

[0003] Traditional cost management methods often rely on offline and batch processing, which is difficult to meet the current industrial demand for real-time data and fine management. Moreover, traditional cost management systems cannot comprehensively collect various cost data related to factory operations, such as raw material costs, labor costs, and equipment maintenance costs, resulting in insufficient decision-making basis. In addition, with the dynamic changes in the market, traditional cost control methods are slow to respond and cannot meet the needs of rapid adjustment of production strategies, resulting in reduced production efficiency and thus damage to corporate interests. Therefore, a more innovative and efficient industrial production big data resource analysis system is needed that can comprehensively and real-time monitor costs and provide personalized optimization suggestions to improve production efficiency and reduce costs. Therefore, it is necessary to design an industrial production big data resource analysis system with fast real-time response and comprehensive cost analysis. Summary of the invention

[0004] The purpose of the present invention is to provide an industrial production big data resource analysis system to solve the problems raised in the above background technology.

[0005] In order to solve the above technical problems, the present invention provides the following technical solutions: an industrial production big data resource analysis system, the operation method of the system comprises the following steps:

[0006] Step 1: Obtain production cost data and external market data through system integration;

[0007] Step 2: Determine the factors affecting abnormal costs through cost analysis;

[0008] Step 3: Compare the factory cost with the market cost and generate a report;

[0009] Step 4: Implement real-time personalized cost optimization recommendations through the cost optimization module.

[0010] According to the above technical solution, the step of obtaining production cost data and external market data through system integration includes:

[0011] The system obtains production cost data and external market data through integration;

[0012] Set up a cost data collection module in the system, covering raw material costs, labor costs, and equipment maintenance costs;

[0013] Data acquisition is achieved through system integration with various departments, including financial systems, production management systems, and supply chain management systems, using API technology and standardized interfaces to achieve direct communication;

[0014] Integrate with external data sources, such as supplier systems or market data;

[0015] Data quality control, including data validation, error detection and correction.

[0016] According to the above technical solution, the step of determining the abnormal cost influencing factors by performing cost analysis includes:

[0017] Conduct abnormal cost detection;

[0018] Analyze the causes of abnormal costs and improve production costs;

[0019] Conduct correlation analysis on outliers to determine the causes of abnormal costs.

[0020] According to the above technical solution, the step of performing abnormal cost detection includes:

[0021] For the real-time cost data collected in step 1, different cost categories are grouped into different cost category data sets, and then the mean μ and standard deviation δ of the data sets are calculated. The mean Standard Deviation For each real-time cost data point, the Z score formula is used to calculate its Z score, which is the degree of deviation of the cost data point from the average value of the category. Then, the Z-score threshold is set according to business needs and sensitivity. When the Z-score exceeds 2, it is judged as abnormal cost and marked as an outlier. These outliers indicate that the cost of a certain cost category has experienced abnormal fluctuations or changes. Subsequently, the marked outliers are further analyzed to determine the cause of the anomaly.

[0022] According to the above technical solution, the step of performing correlation analysis on the abnormal values ​​to determine the cause of the abnormal cost includes:

[0023] Based on domain knowledge, we select key variables related to outliers, and then use correlation analysis methods to measure the linear relationship between raw material costs and other variables. Then, we calculate the correlation. When the correlation coefficient exceeds the set threshold, the correlation between the two can be identified. Specifically, when the Z value of raw material cost exceeds the set threshold within a period of time, the key variables related to raw materials, including supply chain delivery time (X1), production volume (X2) and market demand (X3), are selected according to the principles of domain knowledge. Then, we collect data on the key variables in the corresponding time period. Then, we use the Pearson correlation coefficient to calculate. Among them, r xy is the Pearson correlation coefficient between variables X and Y, X i and Y i is the raw material cost and the value of the key variable at the ith data point, and are the means of raw material costs and key variables respectively. For X1, X2 and X3, the correlation coefficients r are calculated with the raw material costs respectively. x1Y 、r x2Y and r x3Y , and then compare the relationship between the correlation coefficient and the threshold. When the correlation coefficient exceeds the threshold specified by the system, it is considered to have a significant correlation. Managers can confirm the cause of abnormal raw material costs based on the correlation. Through this step, the system can identify unreasonable values ​​in factory costs, associate abnormal values, and analyze their causes.

[0024] According to the above technical solution, the step of comparing the factory cost with the market cost and generating a report includes:

[0025] In order to achieve real-time observation and monitoring, the market data collected in step one is processed through data warehouse and real-time data stream processing technology. In addition, the system conducts cost analysis of the factory every week, combines the real-time observed market data, and reviews the raw material cost and production cost data; using data analysis tools and statistical methods, the system can show the relationship between the factory's costs and market changes to relevant managers, discover potential influencing factors, and then generate a market cost report; through the market cost report generated regularly every week, the system compares and analyzes the factory's costs with market prices; this report not only includes key market data and raw material cost trends, but also covers important information on competitors' prices; using charts, graphics and text, the system ensures that the report is easy to understand and helps decision makers quickly obtain key information.

[0026] According to the above technical solution, the step of implementing real-time personalized cost optimization suggestions through the cost optimization module includes:

[0027] By analyzing market cost reports, the system can identify bottlenecks and optimization space in the supply chain; adopt supply chain visualization and real-time inventory optimization algorithms to achieve more efficient supply chain operations; in addition, based on the analysis results of market cost reports, the system can discover inefficiencies or resource waste in the production process; introduce intelligent manufacturing technology, automated production equipment, and the ability to monitor and adjust production parameters in real time to improve production efficiency and reduce production costs; the system not only provides comprehensive cost optimization suggestions, but also provides personalized suggestions based on the specific context and needs of the enterprise; this can be adjusted and optimized through machine learning algorithms based on the company's historical data and actual operations to better meet the needs of the company. The system should be able to continuously update the analysis results and provide timely suggestions when needed.

[0028] According to the above technical solution, the system includes:

[0029] Cost data collection and integration module, used to obtain and integrate cost data from all aspects of factory operations in real time to ensure a comprehensive data foundation;

[0030] Abnormal cost analysis module, used to identify and analyze potential abnormal fluctuations in factory costs and provide cause analysis of abnormal costs;

[0031] The factory cost comparison and optimization suggestion module is used to analyze the relationship between the factory cost and the market price, generate real-time personalized cost optimization suggestions, improve efficiency and reduce production costs.

[0032] According to the above technical solution, the cost data collection and integration module includes:

[0033] System integration and production cost data acquisition module, which is used to integrate with internal systems through API technology to achieve real-time cost data acquisition;

[0034] External data source integration and quality control module, used to integrate external data sources, such as supplier systems, and perform data quality control to ensure accuracy;

[0035] The cost data collection module establishment module is used to establish the cost data collection module within the system and is responsible for obtaining cost data from all aspects.

[0036] According to the above technical solution, the abnormal cost analysis module includes:

[0037] Real-time cost data analysis module, used to perform Z-score analysis on real-time cost data and identify abnormal costs;

[0038] Abnormal cost cause analysis module, used to determine the key factors of abnormal cost through correlation analysis method;

[0039] The abnormal cost correlation analysis module is used to select key variables based on domain knowledge, calculate correlation coefficients, and confirm the causes of abnormal costs.

[0040] Compared with the prior art, the beneficial effects achieved by the present invention are as follows: the present invention firstly realizes the comprehensive collection of production costs and external market data through system integration, using API technology and standardized interfaces, and then realizes the detection of abnormal costs and the determination of influencing factors through cost analysis, detects abnormal costs using the Z-score method, and deeply analyzes the causes of abnormal values ​​through correlation analysis, and then monitors market dynamics in real time and realizes real-time personalized cost optimization suggestions. The method has the characteristics of fast real-time response of the system and comprehensive cost analysis. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0042] Figure 1 A flowchart of an industrial production big data resource analysis method provided in Example 1 of the present invention;

[0043] Figure 2 A schematic diagram of the module composition of an industrial production big data resource analysis system provided in Example 2 of the present invention. DETAILED DESCRIPTION

[0044] 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.

[0045] Embodiment 1: Figure 1 This is a flowchart of an industrial production big data resource analysis method provided in Example 1 of the present invention. This embodiment can be applied to the scenario of industrial production cost analysis control. The method can be executed by an industrial production big data resource analysis system provided in this embodiment. Figure 1 As shown, the method specifically comprises the following steps:

[0046] Step 1: Obtain production cost data and external market data through system integration;

[0047] In an embodiment of the present invention, a cost data collection module is provided in the system to collect cost data of various aspects closely related to factory operation, including raw material cost, labor cost and equipment maintenance cost;

[0048] Exemplarily, data acquisition is achieved by integrating with the systems of various departments, including financial systems, production management systems, and supply chain management systems. Specifically, API technology is used, and then through standardized interfaces, direct communication between systems is achieved, so that real-time cost data can be obtained from the source. In addition, in addition to integration with internal systems, the system also integrates external data sources, such as supplier systems or market data. After the cost data collection is completed, data quality control is performed on the collected data, including data verification, error detection and correction, to ensure that the collected cost data is accurate and reliable. In this step, a cost data collection module is established to provide a reliable foundation for subsequent cost analysis, optimization suggestions and decision-making.

[0049] Step 2: Determine the factors affecting abnormal costs through cost analysis;

[0050] In the embodiment of the present invention, abnormal cost detection is performed, and the causes of abnormal cost are analyzed, so as to improve production cost;

[0051] For example, for the real-time cost data collected in step 1, different cost categories are grouped into different cost category data sets, and then the average value μ and standard deviation δ of the data sets are calculated. The average value Standard Deviation For each real-time cost data point, the Z score formula is used to calculate its Z score, which is the degree of deviation of the cost data point from the average value of the category. Then, we set the threshold of Z score according to business requirements and sensitivity. When the Z score exceeds 2, it is considered abnormal cost and marked as an outlier. These outliers indicate that the cost of a certain cost category has experienced abnormal fluctuation or change. Then, we further analyze the marked outliers to determine the cause of the abnormality.

[0052] For example, the specific process of further analyzing the marked outliers is as follows: based on domain knowledge, key variables related to the outliers are selected, and then the linear relationship between the raw material cost and other variables is measured using the correlation analysis method, and then the correlation is calculated. When the correlation coefficient exceeds the set threshold, the correlation between the two can be determined. Specifically, when the Z value of the raw material cost exceeds the set threshold within a period of time, the key variables related to the raw materials, including supply chain delivery time (X1), production volume (X2) and market demand (X3) are selected according to the domain knowledge principle, and then the data on the key variables in the corresponding time period are collected, and then the Pearson correlation coefficient is used for calculation. Among them, r xy is the Pearson correlation coefficient between variables X and Y, X i and Y i is the raw material cost and the value of the key variable at the ith data point, and are the means of raw material costs and key variables respectively. For X1, X2 and X3, the correlation coefficients r are calculated with the raw material costs respectively. x1Y 、r x2Y and r x3Y , and then compare the relationship between the correlation coefficient and the threshold. When the correlation coefficient exceeds the threshold specified by the system, it is considered to have a significant correlation. The manager can confirm the cause of the abnormal raw material cost based on the correlation. Through this step, the system can identify unreasonable values ​​in the factory cost, associate the abnormal values, and analyze the causes, so as to better achieve cost rectification or control.

[0053] Step 3: Compare the factory cost with the market cost and generate a report;

[0054] In the embodiment of the present invention, a market data collection module is established; by cooperating with market price data providers, it is ensured that commodity price dynamics related to raw material costs are obtained in a timely manner; in addition, web crawler technology is used to regularly capture relevant information on the online market platform, including competitor price changes, supply and demand relationships, etc.;

[0055] Exemplarily, in order to achieve real-time observation and monitoring, the market data collected in step one is processed through data warehouse and real-time data stream processing technology, and every week, the system conducts cost analysis of the factory, combines the real-time observed market data, and reviews internal data such as raw material costs and production costs; using data analysis tools and statistical methods, the system can show the relationship between the factory's costs and market changes to relevant managers, discover potential influencing factors, and then generate a market cost report; through the market cost report generated regularly every week, the system compares and analyzes the factory's costs with market prices; this report not only includes key market data and raw material cost trends, but also covers important information such as competitor prices; using charts, graphics and text, the system ensures that the report is easy to understand and helps decision makers quickly obtain key information.

[0056] Step 4: Implement real-time personalized cost optimization recommendations through the cost optimization module.

[0057] In the embodiment of the present invention, cost optimization is performed. In the above steps, if there is a market production cost that is greater than the factory production cost, the system will identify potential cost optimization opportunities; ensure that the system can process a large amount of real-time data and has the ability to respond quickly;

[0058] For example, by analyzing market cost reports, the system can identify bottlenecks and optimization space in the supply chain; adopt supply chain visualization, real-time inventory optimization algorithms, etc. to achieve more efficient supply chain operations; in addition, based on the analysis results of market cost reports, the system can discover inefficiencies or resource waste in the production process; introduce intelligent manufacturing technology, automated production equipment, and the ability to monitor and adjust production parameters in real time, thereby improving production efficiency and reducing production costs; the system not only provides comprehensive cost optimization suggestions, but also provides personalized suggestions based on the specific context and needs of the enterprise; this can be adjusted and optimized through machine learning algorithms based on the company's historical data and actual operating conditions to better meet the needs of the company. The system should be able to continuously update the analysis results and provide timely suggestions when needed to ensure that the company remains agile and competitive in a highly competitive market.

[0059] Embodiment 2: Embodiment 2 of the present invention provides an industrial production big data resource analysis system, Figure 2 A schematic diagram of the module composition of an industrial production big data resource analysis system provided in the second embodiment of the present invention is shown in FIG. Figure 2 As shown, the system includes:

[0060] Cost data collection and integration module, used to obtain and integrate cost data from all aspects of factory operations in real time to ensure a comprehensive data foundation;

[0061] Abnormal cost analysis module, used to identify and analyze potential abnormal fluctuations in factory costs and provide cause analysis of abnormal costs;

[0062] The factory cost comparison and optimization suggestion module is used to analyze the relationship between the factory cost and the market price, generate real-time personalized cost optimization suggestions, improve efficiency and reduce production costs;

[0063] In some embodiments of the present invention, the cost data collection and integration module includes:

[0064] System integration and production cost data acquisition module, which is used to integrate with internal systems through API technology to achieve real-time cost data acquisition;

[0065] External data source integration and quality control module, used to integrate external data sources, such as supplier systems, and perform data quality control to ensure accuracy;

[0066] The cost data collection module establishment module is used to establish the cost data collection module in the system and is responsible for obtaining cost data from all aspects;

[0067] In some embodiments of the present invention, the abnormal cost analysis module includes:

[0068] Real-time cost data analysis module, used to perform Z-score analysis on real-time cost data and identify abnormal costs;

[0069] Abnormal cost cause analysis module, used to determine the key factors of abnormal cost through correlation analysis method;

[0070] Abnormal cost correlation analysis module, which is used to select key variables based on domain knowledge, calculate correlation coefficients, and confirm the causes of abnormal costs;

[0071] In some embodiments of the present invention, the factory and market cost comparison and optimization suggestion module includes:

[0072] Market data collection and analysis module, used to analyze the relationship between the factory's cost and market price every week through the market data collection module;

[0073] Market cost report generation module, used to generate weekly market cost reports, comparing key market data and competitor prices;

[0074] The cost optimization suggestion module is used to analyze market cost reports, and the system provides real-time personalized cost optimization suggestions, including supply chain, production process and labor resource allocation.

[0075] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device.

[0076] Finally, it should be noted that the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art can still modify the technical solutions described in the aforementioned embodiments or replace some of the technical features therein by equivalents. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A method for analyzing industrial production big data resources, characterized in that: The method comprises the following steps: Step 1: Obtain production cost data and external market data through system integration; Step 2: Determine the factors affecting abnormal costs through cost analysis; Step 3: Compare the factory cost with the market cost and generate a report; Step 4: Implement real-time personalized cost optimization suggestions through the cost optimization module.

2. The industrial production big data resource analysis method according to claim 1, characterized in that: The step of obtaining production cost data and external market data through system integration includes: The system obtains production cost data and external market data through integration; Set up a cost data collection module in the system, covering raw material costs, labor costs, and equipment maintenance costs; Data acquisition is achieved through system integration with various departments, including financial systems, production management systems, and supply chain management systems, using API technology and standardized interfaces to achieve direct communication; Integrate with external data sources, such as supplier systems or market data; Data quality control, including data validation, error detection and correction.

3. The industrial production big data resource analysis method according to claim 1, characterized in that: The step of determining the abnormal cost influencing factors by performing cost analysis includes: Conduct abnormal cost detection; Analyze the causes of abnormal costs and improve production costs; Conduct correlation analysis on outliers to determine the causes of abnormal costs.

4. The industrial production big data resource analysis method according to claim 3 is characterized by: The step of performing abnormal cost detection includes: For the real-time cost data collected in step 1, different cost categories are grouped into different cost category data sets, and then the mean μ and standard deviation δ of the data sets are calculated. The mean For each real-time cost data point, the Z score formula is used to calculate its Z score, which is the degree of deviation of the cost data point from the average value of the category. Then, the Z-score threshold is set according to business needs and sensitivity. When the Z-score exceeds 2, it is judged as abnormal cost and marked as an outlier. These outliers indicate that the cost of a certain cost category has experienced abnormal fluctuations or changes. Subsequently, the marked outliers are further analyzed to determine the cause of the anomaly.

5. The industrial production big data resource analysis method according to claim 3 is characterized by: The step of performing correlation analysis on the abnormal values ​​to determine the cause of the abnormal cost includes: Based on domain knowledge, we select key variables related to outliers, and then use correlation analysis methods to measure the linear relationship between raw material costs and other variables. Then, we calculate the correlation. When the correlation coefficient exceeds the set threshold, the correlation between the two can be identified. Specifically, when the Z value of raw material cost exceeds the set threshold within a period of time, the key variables related to raw materials, including supply chain delivery time (X1), production volume (X2) and market demand (X3), are selected according to the principles of domain knowledge. Then, we collect data on the key variables in the corresponding time period. Then, we use the Pearson correlation coefficient to calculate. Among them, r xy is the Pearson correlation coefficient between variables X and Y, X i and Y i is the raw material cost and the value of the key variable at the ith data point, and are the means of raw material costs and key variables respectively. For X1, X2 and X3, the correlation coefficients r are calculated with the raw material costs respectively. x1Y 、r x2Y and r x3Y , and then compare the relationship between the correlation coefficient and the threshold. When the correlation coefficient exceeds the threshold specified by the system, it is considered to have a significant correlation. Managers can confirm the cause of abnormal raw material costs based on the correlation. Through this step, the system can identify unreasonable values ​​in factory costs, associate abnormal values, and analyze their causes.

6. The industrial production big data resource analysis method according to claim 1, characterized in that: The steps of comparing the factory cost with the market cost and generating a report include: In order to achieve real-time observation and monitoring, the market data collected in step one is processed through data warehouse and real-time data stream processing technology. In addition, the system conducts cost analysis of the factory every week, combines the real-time observed market data, and reviews the raw material cost and production cost data; using data analysis tools and statistical methods, the system can show the relationship between the factory's costs and market changes to relevant managers, discover potential influencing factors, and then generate a market cost report; through the market cost report generated regularly every week, the system compares and analyzes the factory's costs with market prices; this report not only includes key market data and raw material cost trends, but also covers important information on competitors' prices; using charts, graphics and text, the system ensures that the report is easy to understand and helps decision makers quickly obtain key information.

7. The industrial production big data resource analysis method according to claim 1, characterized in that: The step of implementing real-time personalized cost optimization suggestions through the cost optimization module includes: By analyzing market cost reports, the system can identify bottlenecks and optimization space in the supply chain; adopt supply chain visualization and real-time inventory optimization algorithms to achieve more efficient supply chain operations; in addition, based on the analysis results of market cost reports, the system can discover inefficiencies or resource waste in the production process; introduce intelligent manufacturing technology, automated production equipment, and the ability to monitor and adjust production parameters in real time to improve production efficiency and reduce production costs; the system not only provides comprehensive cost optimization suggestions, but also provides personalized suggestions based on the specific context and needs of the enterprise; this can be adjusted and optimized through machine learning algorithms based on the company's historical data and actual operations to better meet the needs of the company. The system should be able to continuously update the analysis results and provide timely suggestions when needed.

8. An industrial production big data resource analysis system, characterized by: The system comprises: Cost data collection and integration module, used to obtain and integrate cost data from all aspects of factory operations in real time to ensure a comprehensive data foundation; Abnormal cost analysis module, used to identify and analyze potential abnormal fluctuations in factory costs and provide cause analysis of abnormal costs; The factory cost comparison and optimization suggestion module is used to analyze the relationship between the factory cost and the market price, generate real-time personalized cost optimization suggestions, improve efficiency and reduce production costs.

9. The industrial production big data resource analysis system according to claim 8, characterized in that: The cost data collection and integration module includes: System integration and production cost data acquisition module, which is used to integrate with internal systems through API technology to achieve real-time cost data acquisition; External data source integration and quality control module, used to integrate external data sources, such as supplier systems, and perform data quality control to ensure accuracy; The cost data collection module establishment module is used to establish the cost data collection module within the system and is responsible for obtaining cost data from all aspects.

10. The industrial production big data resource analysis system according to claim 8, characterized in that: The abnormal cost analysis module includes: Real-time cost data analysis module, used to perform Z-score analysis on real-time cost data and identify abnormal costs; Abnormal cost cause analysis module, used to determine the key factors of abnormal cost through correlation analysis method; The abnormal cost correlation analysis module is used to select key variables based on domain knowledge, calculate correlation coefficients, and confirm the causes of abnormal costs.

Images