A method and system for constructing and intelligently analyzing quality data in the whole process of cigarette production and manufacturing

Abstract

The application belongs to the technical field of cigarette production and manufacturing, and provides a cigarette production and manufacturing whole-process quality data platform construction and intelligent analysis method and system, which comprises the following steps: S1, constructing a "collection-storage-management-use-treatment" integrated quality data platform; S2, designing a process quality theme domain data model in the data asset layer, constructing an enterprise-level quality index dictionary and unified analysis dimension; S3, encapsulating common quality analysis algorithms into callable microservices, and providing them to the front-end application in the form of low code / API for calling; the application realizes unified collection, storage, management and service of quality data by constructing a "collection-storage-management-use-treatment" integrated quality data platform, effectively solving the problem of data islands; at the same time, by constructing an enterprise-level quality index dictionary and unified analysis dimension, standardized quality analysis tools and methods are provided, and the quality analysis efficiency and accuracy are improved.

Description

Technical Field

[0001] This invention belongs to the field of cigarette manufacturing technology, specifically a method and system for constructing and intelligently analyzing a quality data platform for the entire cigarette manufacturing process. Background Technology

[0002] The cigarette manufacturing process involves massive amounts of quality data, covering multiple stages such as raw material procurement, production and processing, and finished product inspection. However, the industry currently suffers from problems such as fragmented data management, inconsistent data standards, and insufficient data analysis capabilities.

[0003] Specifically, different departments use their own independent data systems with different data formats and storage methods, making it difficult to integrate and share data. At the same time, the lack of a unified quality indicator system and analysis model makes it difficult for data analysis results to accurately reflect quality problems in the production process and to provide effective support for production decisions.

[0004] To address this, those skilled in the art have proposed a method and system for constructing and intelligently analyzing a quality data platform for the entire cigarette manufacturing process. This system can integrate quality data from the entire cigarette manufacturing process, realize data assetization and service provision, and offer intelligent analysis capabilities. Summary of the Invention

[0005] To address the aforementioned technical problems, this invention provides a method and system for constructing and intelligently analyzing a quality data platform for the entire cigarette manufacturing process. This addresses the issues in existing technologies where different departments use their own independent data systems with varying data formats and storage methods, making data integration and sharing difficult. Furthermore, the lack of a unified quality indicator system and analysis model makes it difficult for data analysis results to accurately reflect quality issues in the production process and provide effective support for production decisions.

[0006] A method for constructing and intelligently analyzing a quality data platform for the entire cigarette manufacturing process includes the following steps:

[0007] S1. Construct an integrated quality data platform that combines data acquisition, storage, management, application, and governance, including a data acquisition layer, a storage and computing layer, a data asset layer, a data service layer, and a technical support layer.

[0008] S2. Design a process quality subject domain data model at the data asset layer, and build an enterprise-level quality indicator dictionary and unified analysis dimensions;

[0009] S3. Encapsulate common quality analysis algorithms into callable microservices and provide them to front-end applications in a low-code / API manner.

[0010] Preferably, the data acquisition layer collects raw material quality data, production equipment operation data, process parameter data, and finished product inspection data in real time throughout the entire cigarette production process through various data interfaces and sensors.

[0011] Preferably, the storage and computing layer adopts an integrated data lake warehouse architecture, supports the storage and computing of structured, semi-structured and unstructured data, and provides data cleaning, transformation and loading functions.

[0012] Preferably, the process quality subject domain data model designed in the data asset layer includes a raw material quality model, a production process quality model, and a finished product quality model. Each model is associated with a unique identifier to form a complete quality data chain.

[0013] Preferably, the enterprise-level quality indicator dictionary includes critical quality characteristic indicators (CTQ), process capability indicators (CPK), and quality cost indicators, wherein the CPK calculation formula is:

[0014] ;

[0015] Where USL is the upper specification limit and LSL is the lower specification limit. The mean, The standard deviation is denoted as .

[0016] Preferably, the API interfaces provided by the data service layer include data query interfaces, data analysis interfaces, and data visualization interfaces, which can be called by front-end applications through the RESTful protocol.

[0017] Preferably, the technical support layer includes a data governance module and a security module. The data governance module is responsible for data standard setting, data quality monitoring and data lifecycle management, while the security module provides data encryption, access control and auditing functions.

[0018] Preferably, the encapsulated general quality analysis algorithm microservice includes a control chart analysis microservice, a cluster analysis microservice, and a regression analysis microservice, wherein the control chart analysis microservice uses X-bar and R control charts, and the calculation formula is as follows:

[0019] ;

[0020] ;

[0021] in, For the first Each sample value This represents the number of samples.

[0022] Preferably, the low-code / API approach is provided for front-end applications to call, supporting the rapid construction of quality analysis applications by dragging and dropping components and configuring parameters, thereby reducing the system development threshold and cost.

[0023] A quality data platform construction and intelligent analysis system for the entire cigarette manufacturing process, employing the aforementioned methods, integrates, stores, analyzes, and services quality data from the entire cigarette manufacturing process, including:

[0024] The data acquisition layer is used to collect quality data from all stages of cigarette production.

[0025] The storage and computing layer adopts a unified data lake warehouse architecture to achieve unified data storage and efficient computing;

[0026] At the data asset layer, a data model for the process quality subject domain is constructed to form an enterprise-level quality indicator dictionary and a unified analysis dimension.

[0027] The data service layer provides microservice interfaces for quality analysis algorithms through APIs and analytical model services;

[0028] The technical support layer is responsible for data governance and security, ensuring data quality and security.

[0029] Compared with the prior art, the present invention has the following beneficial effects:

[0030] The present invention relates to a quality data platform construction and intelligent analysis application system for the entire cigarette manufacturing process. By constructing an integrated quality data platform encompassing "collection-storage-management-application-treatment," it achieves unified collection, storage, management, and service of quality data, effectively solving the problem of data silos. Simultaneously, by constructing an enterprise-level quality indicator dictionary and unified analysis dimensions, it provides standardized quality analysis tools and methods, improving the efficiency and accuracy of quality analysis. Furthermore, the system integrates microservice interfaces for various quality analysis algorithms, supporting the rapid construction of various quality applications, promoting in-depth mining and utilization of quality data, and providing strong support for improving the quality of cigarette manufacturing. Attached Figure Description

[0031] Figure 1 This is a flowchart of the method for constructing and intelligently analyzing a quality data platform for the entire cigarette manufacturing process according to the present invention.

[0032] Figure 2 This is a framework diagram of the quality data platform construction and intelligent analysis system for the entire cigarette production and manufacturing process of the present invention. Detailed Implementation

[0033] The embodiments of the present invention will be described in further detail below with reference to the accompanying drawings and examples. The following examples are for illustrative purposes only and should not be construed as limiting the scope of the invention.

[0034] Example: This invention provides a method for constructing and intelligently analyzing a quality data platform for the entire cigarette manufacturing process, such as... Figure 1 As shown, it includes the following steps:

[0035] S1. Construct an integrated quality data platform that combines data acquisition, storage, management, application, and governance, including a data acquisition layer, a storage and computing layer, a data asset layer, a data service layer, and a technical support layer.

[0036] S2. Design a process quality subject domain data model at the data asset layer, and build an enterprise-level quality indicator dictionary and unified analysis dimensions;

[0037] S3. Encapsulate common quality analysis algorithms into callable microservices and provide them to front-end applications in a low-code / API manner.

[0038] As shown above, this method achieves comprehensive integration and efficient management of quality data by constructing an integrated quality data platform encompassing "collection-storage-management-application-treatment." It designs a process quality subject domain data model at the data asset layer and constructs an enterprise-level quality indicator dictionary, providing standardized analysis tools and unified dimensions, thus improving analysis efficiency and accuracy. Simultaneously, it encapsulates general quality analysis algorithms as microservices and provides them via low-code / API methods, supporting rapid construction of quality applications, reducing development costs, promoting in-depth mining and utilization of quality data, and providing strong support for improving the quality of cigarette production.

[0039] Specifically, the data acquisition layer uses various data interfaces and sensors to collect raw material quality data, production equipment operation data, process parameter data, and finished product inspection data in real time throughout the entire cigarette production process.

[0040] As can be seen from the above, this data acquisition layer, through various data interfaces and sensors, can collect raw material quality data, production equipment operation data, process parameter data, and finished product inspection data in real time and accurately throughout the entire cigarette production process. This effectively eliminates data silos, ensures the comprehensiveness and timeliness of the data, and provides a solid data foundation for subsequent data storage, analysis, and decision-making.

[0041] Specifically, the storage and computing layer adopts an integrated data lake warehouse architecture, supports the storage and computing of structured, semi-structured and unstructured data, and provides data cleaning, transformation and loading functions.

[0042] As can be seen from the above, the storage and computing layer adopts an integrated data lake warehouse architecture, which can efficiently support the unified storage and computing of structured, semi-structured and unstructured data, while providing data cleaning, transformation and loading functions. This not only enhances the flexible processing capability of data, but also ensures data quality, providing reliable and comprehensive data support for subsequent data analysis and mining.

[0043] Specifically, the data asset layer design includes a process quality subject domain data model comprising a raw material quality model, a production process quality model, and a finished product quality model. Each model is linked by a unique identifier to form a complete quality data chain.

[0044] As can be seen from the above, the process quality subject domain data model designed in this data asset layer covers the raw material quality model, the production process quality model, and the finished product quality model. The close association between each model is achieved through unique identifiers, forming a complete and traceable quality data chain. This greatly improves the systematicness and refinement of quality management and provides strong data support for in-depth analysis of quality problems and optimization of production processes.

[0045] Specifically, the enterprise-level quality indicator dictionary includes Key Quality Qualities (CTQ), Process Capability (CPK), and Quality Cost indicators, where the CPK calculation formula is:

[0046] ;

[0047] Where USL is the upper specification limit and LSL is the lower specification limit. The mean, The standard deviation is denoted as .

[0048] As can be seen from the above, this enterprise-level quality indicator dictionary covers key quality characteristic indicators (CTQ), process capability indicators (CPK), and quality cost indicators. Among them, CPK is calculated through clearly defined upper specification limit (USL), lower specification limit (LSL), mean, and standard deviation. It not only unifies the quality assessment standard and makes process capability quantifiable and visible, but also provides a scientific basis and data support for accurately identifying production capacity bottlenecks and continuously improving quality.

[0049] Specifically, the API interfaces provided by the data service layer include data query interfaces, data analysis interfaces, and data visualization interfaces, which can be called by front-end applications through the RESTful protocol.

[0050] As can be seen from the above, the data service layer provides API interfaces including data query interfaces, data analysis interfaces, and data visualization interfaces, and supports front-end applications to call them through the RESTful protocol. It realizes efficient integration and flexible calling of data services, reduces the coupling between systems, improves the real-time and convenience of data interaction, and provides front-end applications with powerful and unified data support and analysis capabilities.

[0051] Specifically, the technical support layer includes a data governance module and a security module. The data governance module is responsible for data standard setting, data quality monitoring and data lifecycle management, while the security module provides data encryption, access control and auditing functions.

[0052] As shown above, this technical support layer encompasses a data governance module and a security module. The data governance module is responsible for data standard setting, quality monitoring, and lifecycle management to ensure the standardization and accuracy of data. The security module provides data encryption, access control, and auditing functions to guarantee data security. This achieves dual protection of data governance and security, not only improving the systematic nature and reliability of data management but also providing solid support for compliant data use and privacy protection.

[0053] Specifically, the encapsulated general quality analysis algorithm microservices include control chart analysis microservices, cluster analysis microservices, and regression analysis microservices. The control chart analysis microservice uses X-bar and R control charts, and the calculation formula is as follows:

[0054] ;

[0055] ;

[0056] in, For the first Each sample value This represents the number of samples.

[0057] As can be seen from the above, the encapsulated general quality analysis algorithm microservice includes a control chart analysis microservice (using X-bar and R control charts), a cluster analysis microservice, and a regression analysis microservice. Among them, the control chart analysis can monitor the stability of the production process in real time by accurately calculating the sample mean and range, promptly detect abnormal fluctuations, provide a scientific basis for process control and quality improvement, and effectively improve the controllability of the production process and the stability of product quality.

[0058] Specifically, the low-code / API approach is provided for front-end applications to call, supporting the rapid construction of quality analysis applications by dragging and dropping components and configuring parameters, thereby reducing the system development threshold and cost.

[0059] As can be seen from the above, this low-code / API approach provides front-end applications with the ability to quickly build quality analysis applications by dragging and dropping components and configuring parameters. This innovation greatly reduces the technical threshold and cost of system development, accelerates the deployment and iteration of quality analysis applications, enables non-professional developers to participate efficiently, and promotes the intelligent and democratic process of quality management.

[0060] Working Principle: This method achieves intelligent and efficient quality management by constructing a layered architecture: The data acquisition layer uses multiple interfaces and sensors to collect full-process data in real time. After cleaning and integration by the integrated data lake architecture of the storage and computing layer, a process quality subject domain data model is formed and a complete quality data chain is constructed; The technical support layer ensures data standardization through data governance and ensures data security through a security module; The core algorithm layer encapsulates analytical microservices such as control charts and clustering, and combines them with an enterprise-level quality indicator dictionary to achieve quantitative assessment of process capabilities; Finally, the analytical capabilities are exposed to front-end applications through low-code / API methods, supporting drag-and-drop rapid development of quality analysis tools, forming a closed-loop management system from data acquisition to intelligent decision-making.

[0061] The following table compares the effectiveness of the method for constructing and intelligently analyzing the quality data platform for the entire cigarette manufacturing process with existing technical solutions (background technology currently suffers from problems such as fragmented data management, inconsistent data standards, and insufficient data analysis capabilities).

[0062] Comparison Projects Existing technical problems This method Data Management Data is stored in a scattered manner, making centralized management difficult. Adopting an integrated data lake warehouse architecture, combining a distributed file system with a columnar database, it achieves low-cost storage and efficient querying of massive amounts of data, and unifies data entry and exit points. Data Standards Inconsistent standards and chaotic data entity relationships Construct a data model for the process quality subject domain (raw material / process / finished product quality), define standardized data entities and relationships, and unify measurement methods and thresholds through a quality indicator dictionary. Analytical ability Weak analytical capabilities and lack of real-time processing It integrates a real-time computing engine (stream data processing formula), supports algorithms such as CPK calculation, control chart analysis (X-bar / R), and K-means clustering, and enables dynamic quality analysis and anomaly detection. Real-time High latency makes it difficult to respond to real-time demands. Real-time streaming data processing capabilities, combined with state transition functions to achieve millisecond-level response, support real-time monitoring and decision-making in the production process. Data governance Lack of quality control and delayed problem detection An integrated data quality rule monitoring and evaluation mechanism (evaluation method formula) is used to detect data quality issues in real time and trigger corrective actions.

[0063] The comparison table clearly presents the differences between this cigarette production and manufacturing process quality data platform solution and existing industry technical solutions: addressing the problems of data dispersion, inconsistent standards, weak real-time analysis capabilities, and lagging governance in existing solutions, this solution systematically solves core pain points such as data integration, quality control, real-time decision-making, and security assurance through innovative designs such as an integrated data lake warehouse architecture, standardized quality models, real-time computing engines, AES encryption and access control, dynamic visualization, and quality monitoring and evaluation mechanisms. This significantly improves the refinement, intelligence, and real-time level of cigarette production quality management.

[0064] A quality data platform construction and intelligent analysis system for the entire cigarette manufacturing process, such as... Figure 2 As shown, the above method is used to integrate, store, analyze, and service quality data throughout the entire cigarette manufacturing process, including:

[0065] The data acquisition layer is used to collect quality data from all stages of cigarette production.

[0066] The storage and computing layer adopts a unified data lake warehouse architecture to achieve unified data storage and efficient computing;

[0067] At the data asset layer, a data model for the process quality subject domain is constructed to form an enterprise-level quality indicator dictionary and a unified analysis dimension.

[0068] The data service layer provides microservice interfaces for quality analysis algorithms through APIs and analytical model services;

[0069] The technical support layer is responsible for data governance and security, ensuring data quality and security.

[0070] As shown above, this system collects quality data from all stages of cigarette production in real time through the data acquisition layer, and utilizes a data lake warehouse architecture in the storage and computing layer to achieve unified data storage and efficient computation. The data asset layer constructs a process quality subject domain data model and an enterprise-level quality indicator dictionary, providing a unified analysis dimension. The data service layer provides microservice interfaces for quality analysis algorithms through APIs and analysis model services. The technical support layer ensures data governance and security. This system effectively solves the problem of data silos, improves the efficiency and accuracy of quality analysis, promotes the in-depth mining and utilization of quality data, and provides strong support for improving the quality of cigarette production and manufacturing.

[0071] Specifically, the data acquisition layer adopts distributed data acquisition technology, supports real-time or batch acquisition of multi-source heterogeneous data, and integrates a data cleaning and preprocessing module. The data cleaning and preprocessing module uses the following algorithm for data cleaning:

[0072] ;

[0073] in, This is the original data. For the preset data cleaning rules, This is a data cleaning function used to remove noise, fill in missing values, and correct erroneous data.

[0074] As can be seen from the above, the distributed data acquisition technology adopted by this data acquisition layer can efficiently support the real-time or batch acquisition of multi-source heterogeneous data, ensuring the comprehensiveness and timeliness of the data. At the same time, the integrated data cleaning and preprocessing module effectively cleans the raw data using preset data cleaning rules and functions, removing noise, filling missing values ​​and correcting erroneous data, significantly improving the quality and usability of the data, and providing a more accurate and reliable data foundation for subsequent data analysis and decision-making.

[0075] Specifically, the storage and computing layer adopts a data lake warehouse integrated architecture, combining a distributed file system with a columnar database to achieve low-cost storage and efficient querying of massive amounts of data. It also integrates a real-time computing engine to support real-time processing and analysis of streaming data. The real-time computing engine uses the following formula for streaming data processing:

[0076] ;

[0077] in, for Input data at any time, for The system state at time -1, where g is the state transition function used to generate... The processing results at any given moment.

[0078] As can be seen from the above, the data lake warehouse architecture adopted by this storage and computing layer, through the ingenious combination of distributed file system and columnar database, not only achieves low-cost storage of massive data, but also ensures efficient data query capabilities; at the same time, it integrates a real-time computing engine, uses state transition functions to process and analyze streaming data in real time, can quickly respond to data changes, and generate timely and accurate processing results, providing strong data support for real-time monitoring and decision-making in cigarette production and manufacturing.

[0079] Specifically, the data asset layer constructs a process quality subject domain data model, which includes multiple subject domains such as raw material quality, production process quality, and finished product quality. Each subject domain defines detailed data entities and relationships, and a quality indicator dictionary is constructed using the following method:

[0080] ;

[0081] in, For quality attributes, For measurement methods, For the threshold, Functions are built for the indicators to generate specific quality metrics.

[0082] As can be seen from the above, the process quality subject domain data model constructed by this data asset layer covers multiple key subject domains such as raw material quality, production process quality, and finished product quality. It also defines the data entities and relationships under each subject domain in detail. By constructing a quality indicator dictionary through specific methods, it realizes the standardization and unified management of quality indicators, making quality analysis more systematic and scientific, and providing accurate data basis and effective analysis tools for quality control and improvement in cigarette production.

[0083] Specifically, in the quality analysis algorithm microservice interface provided by the data service layer, the CPK calculation service uses the following formula to calculate the process capability index:

[0084] ;

[0085] Where USL is the upper specification limit and LSL is the lower specification limit. The mean, The standard deviation is denoted as .

[0086] As can be seen from the above, the CPK calculation service provided by this data service layer uses a specific formula to calculate the process capability index. This formula comprehensively considers key factors such as the upper specification limit (USL), lower specification limit (LSL), process mean and standard deviation, which can accurately quantify the capability of the production process, help enterprises to discover fluctuations and anomalies in the production process in a timely manner, and provide scientific basis and decision support for optimizing production processes and improving product quality.

[0087] Specifically, the control chart analysis service provided by the data service layer uses X-bar and R-charts. The X-bar control chart is used to monitor changes in the process mean, while the R-chart is used to monitor fluctuations in process variability. The center line and control limits of the X-bar control chart are calculated as follows:

[0088]

[0089] in, The target mean, The mean range These are control chart constants.

[0090] As can be seen from the above, the control chart analysis service provided by this data service layer can simultaneously monitor the mean change and variation fluctuation of the production process by using X-bar and R control charts. Among them, the X-bar control chart uses the target mean, average range and control chart constant to accurately calculate the center line and control limits, effectively identify abnormal trends in the production process, and help enterprises take timely measures to adjust production parameters to ensure the stability of the production process and the uniformity of product quality.

[0091] Specifically, the clustering analysis service provided by the data service layer uses the K-means clustering algorithm to achieve data clustering by iteratively optimizing the following objective function:

[0092] ;

[0093] in, For the number of clusters, For the first One cluster, For the first The center point of each cluster, These are data points in the cluster.

[0094] As can be seen from the above, the clustering analysis service provided by this data service layer adopts the K-means clustering algorithm and achieves data clustering by iteratively optimizing a specific objective function. This algorithm can automatically divide the data into groups with similar characteristics based on the number of clusters, the cluster centers, and the data points, effectively identifying the inherent structure and patterns in the data, helping enterprises to discover potential problems and improvement points in the production process, and providing strong support for refined management and quality improvement.

[0095] Specifically, the data governance module of the technical support layer integrates a data quality monitoring and evaluation mechanism, monitors data in real time through preset data quality rules, and evaluates data quality using the following methods:

[0096] ;

[0097] in, For the number of data quality rules, For the first The weight of each rule, For the first The evaluation results of the rules.

[0098] As can be seen from the above, the data governance module of this technical support layer, by integrating data quality monitoring and evaluation mechanisms and using preset data quality rules to monitor data in real time, and by using specific methods to evaluate data quality, can comprehensively and objectively reflect the accuracy and reliability of data, promptly identify and correct data quality problems, ensure the integrity and consistency of quality data throughout the entire cigarette production and manufacturing process, and provide a solid data foundation for data analysis and decision-making.

[0099] Specifically, the data security module of the technical support layer uses encryption technology to protect the security of data transmission and storage, and integrates an access control mechanism to ensure that only authorized users can access specific data resources. The encryption technology uses the AES encryption algorithm, and its encryption process can be represented as follows:

[0100]

[0101] in, Plain text data For encryption key, This is the AES encryption function.

[0102] As can be seen from the above, the data security module of this technical support layer uses the AES encryption algorithm to encrypt and protect the transmitted and stored data, while integrating a strict access control mechanism to ensure the confidentiality, integrity and availability of data during transmission and storage, effectively preventing data leakage and unauthorized access, and providing a solid guarantee for the security of quality data throughout the entire cigarette production and manufacturing process.

[0103] Specifically, the system also integrates a visualization module, which intuitively displays quality analysis results through charts, dashboards, and other forms, and supports interactive exploration and analysis by users. The visualization module uses front-end libraries such as D3.js or ECharts to achieve dynamic visualization of data.

[0104] As can be seen from the above, the visualization module integrated into the system uses advanced front-end libraries such as D3.js or ECharts to achieve dynamic data visualization. It can clearly present quality analysis results in the form of intuitive and vivid charts and dashboards, supporting users to conduct interactive exploration and in-depth analysis. This greatly improves the efficiency of data understanding and the accuracy of decision-making, helping enterprises to quickly identify quality problems and take effective improvement measures.

[0105] The embodiments of the present invention are given for the purposes of illustration and description. Although embodiments of the present invention have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting the present invention. Any changes, modifications, substitutions and variations made by those skilled in the art to the above embodiments within the scope of the present invention should be included within the protection scope of the present invention.

Claims

1. A method for constructing and intelligently analyzing a quality data platform for the entire cigarette manufacturing process, characterized in that, Includes the following steps: S1. Construct an integrated quality data platform encompassing "collection-storage-management-application-governance," including a data acquisition layer, storage and computing layer, data asset layer, data service layer, and technical support layer; S2. Design a process quality subject domain data model at the data asset layer, and build an enterprise-level quality indicator dictionary and unified analysis dimensions; S3. Encapsulate common quality analysis algorithms into callable microservices and provide them to front-end applications in a low-code / API manner.

2. The method for constructing and intelligently analyzing a quality data platform for the entire cigarette manufacturing process as described in claim 1, characterized in that: The data acquisition layer uses various data interfaces and sensors to collect raw material quality data, production equipment operation data, process parameter data, and finished product inspection data in real time throughout the entire cigarette production process.

3. The method for constructing and intelligently analyzing a quality data platform for the entire cigarette manufacturing process as described in claim 1, characterized in that: The storage and computing layer adopts an integrated data lake warehouse architecture, which supports the storage and computing of structured, semi-structured and unstructured data, and provides data cleaning, transformation and loading functions.

4. The method for constructing and intelligently analyzing a quality data platform for the entire cigarette manufacturing process as described in claim 1, characterized in that: The data asset layer design includes a process quality subject domain data model comprising a raw material quality model, a production process quality model, and a finished product quality model. Each model is linked by a unique identifier to form a complete quality data chain.

5. The method for constructing and intelligently analyzing a quality data platform for the entire cigarette manufacturing process as described in claim 1, characterized in that: The enterprise-level quality indicator dictionary includes Key Quality Qualities (CTQ), Process Capability (CPK), and Quality Cost indicators, where the CPK calculation formula is: ; Where USL is the upper specification limit and LSL is the lower specification limit. The mean, The standard deviation is denoted as .

6. The method for constructing and intelligently analyzing a quality data platform for the entire cigarette manufacturing process as described in claim 1, characterized in that: The data service layer provides API interfaces including data query interfaces, data analysis interfaces, and data visualization interfaces, which can be called by front-end applications via the RESTful protocol.

7. The method for constructing and intelligently analyzing a quality data platform for the entire cigarette manufacturing process as described in claim 1, characterized in that: The technical support layer includes a data governance module and a security module. The data governance module is responsible for data standard setting, data quality monitoring and data lifecycle management, while the security module provides data encryption, access control and auditing functions.

8. The method for constructing and intelligently analyzing a quality data platform for the entire cigarette manufacturing process as described in claim 1, characterized in that: The encapsulated general quality analysis algorithm microservices include control chart analysis, cluster analysis, and regression analysis microservices. The control chart analysis microservice uses X-bar and R control charts, and the calculation formula is as follows: ； ； in, For the first Each sample value This represents the number of samples.

9. The method for constructing and intelligently analyzing a quality data platform for the entire cigarette manufacturing process as described in claim 1, characterized in that: The low-code / API approach is provided for front-end applications to call, supporting the rapid construction of quality analysis applications by dragging and dropping components and configuring parameters, thereby reducing the system development threshold and cost.

10. A quality data platform construction and intelligent analysis system for the entire cigarette manufacturing process, characterized in that, The method described in any one of claims 1 to 9 is used to integrate, store, analyze, and service quality data throughout the entire cigarette manufacturing process, including: The data acquisition layer is used to collect quality data from all stages of cigarette production. The storage and computing layer adopts a unified data lake warehouse architecture to achieve unified data storage and efficient computing; At the data asset layer, a data model for the process quality subject domain is constructed to form an enterprise-level quality indicator dictionary and a unified analysis dimension. The data service layer provides microservice interfaces for quality analysis algorithms through APIs and analytical model services; The technical support layer is responsible for data governance and security, ensuring data quality and security.

Images