A noble metal product quality traceability and digital management system

Abstract

The application discloses a kind of noble metal product quality traceability and digital management system, it is related to noble metal quality management technical field, to solve the technical problem that current traditional pre-production post-detection mode can cause noble metal resource waste, including data acquisition module, customization quality control module, real-time analysis early warning module, data traceability management module, block chain storage module, and process self-learning optimization module, each module is modular design and is configurable component, data intercommunication linkage operation is realized between modules through standard interface.The application realizes the dynamic monitoring and instant adjustment effect of production process parameters by embedding real-time analysis early warning module and customization quality control module, solves the problem that current traditional pre-production post-detection mode can cause noble metal resource waste.System uses production detection mode, real-time acquisition key quality control point data in production process, reduces noble metal loss rate, realizes resource zero waste.

Description

Technical Field

[0001] This invention relates to the field of precious metal quality management technology, and more specifically, to a quality traceability and digital management system for precious metal products. Background Technology

[0002] Precious metal products, due to their high value and wide applicability, occupy an important position in jewelry, industrial manufacturing, investment and collection, and their quality is directly related to consumer rights, market fairness, and sustainable industrial development. With global economic development and upgrading consumer demand, the processing technology of precious metal products is becoming increasingly diversified, encompassing various types such as hydraulic pressing, lost-wax casting, additive manufacturing, and subtractive manufacturing. Different processes have significantly different requirements for production processes and quality control standards, making traditional, standardized quality control models inadequate for meeting personalized and customized production needs.

[0003] In the production of high-precision customized precious metal medals, coins, and bars, complex processes such as raw material melting and rolling, stamping and embossing are involved. The requirements for precious metal content and appearance quality are extremely high. The customized process itself has a strong personalized attribute, and the design scheme, process path, and parameter requirements of different orders often have significant differences.

[0004] The existing traditional "production first, inspection later" model, with its fixed production process as its core design logic, means that once the inspection results are unsatisfactory, the high-value precious metal raw materials already invested cannot be recovered and reused. The special process of customized products determines that their production process is irreversible. For example, commemorative medals formed by special stamping and electroforming cannot be restored to their original form through rework, inevitably resulting in a serious waste of precious metal resources. Moreover, customized products are often deeply tied to specific scenarios and needs, such as commemorative coins for major events and exclusive themed jewelry. Orders often have strict delivery cycles and specific requirements, and it is difficult to find similar products that can be substituted. If the delivery is delayed or the customized requirements cannot be met due to unsatisfactory finished product inspection, it will directly constitute a breach of contract. The company will not only have to bear high penalties for breach of contract, but may also lose core customer resources. In view of this, we propose a quality traceability and digital management system for precious metal products. Summary of the Invention

[0005] The purpose of this invention is to overcome the shortcomings of the prior art, adapt to the needs of reality, and provide a quality traceability and digital management system for precious metal products, so as to solve the technical problem of waste of precious metal resources that may be caused by the current traditional production-after-testing model.

[0006] To solve the above-mentioned technical problems, the present invention provides the following technical solution: a quality traceability and digital management system for precious metal products, including a data acquisition module, a customized quality control module, a real-time analysis and early warning module, a data traceability management module, a blockchain evidence storage module, and a process self-learning optimization module. Each module adopts a modular design and is a configurable component. The modules achieve data interconnection and linkage operation through standardized interfaces.

[0007] The data acquisition module connects to quality control nodes, testing equipment, and third-party testing and inspection institutions with CMA / CNAS qualifications throughout the entire production process of precious metal products, enabling online acquisition of production, testing, and third-party testing data across the entire chain.

[0008] The customized quality control module generates a customized quality control process for each product based on its processing technology and design requirements.

[0009] The real-time analysis and early warning module intelligently analyzes the collected data and sets quality alarm thresholds, and intervenes in production immediately when an alarm is triggered.

[0010] The data traceability management module digitizes and archives all process data, enabling rapid querying of quality data and full-process traceability.

[0011] The blockchain evidence storage module provides tamper-proof evidence storage of quality data throughout the entire process and generates a product quality ID card with a unique identification code.

[0012] The process self-learning optimization module completes the correlation modeling between process parameters and product quality based on the historical data of the entire process, realizes the autonomous iterative optimization of the quality control process, and achieves the overall quality control and full life cycle digital traceability of precious metal products through simultaneous production and testing.

[0013] Preferably, the data acquisition module includes a multi-dimensional data acquisition unit and a device docking unit;

[0014] The equipment docking unit establishes a configurable data connection with precious metal content detection, hardness detection, appearance quality detection, process parameter monitoring equipment, and third-party testing data systems;

[0015] The multi-dimensional data acquisition unit collects data on precious metal content, quality, harmful element content, production environment parameters, equipment operating parameters, and third-party testing reports at each quality control node at a preset frequency.

[0016] Preferably, the real-time analysis and early warning module includes an AI algorithm analysis unit, an early warning push unit, and a production intervention unit;

[0017] The AI ​​algorithm analysis unit performs correlation analysis on production process parameters and test data, identifies the correlation between process parameters and product quality, and automatically pushes process adjustment suggestions.

[0018] The early warning push unit supports the custom configuration of multi-level quality alarm thresholds, and pushes early warning information to staff through the production management system and SMS when an alarm is triggered.

[0019] The production intervention unit supports configurable operations such as production suspension and process rollback after an alarm.

[0020] Preferably, the customized quality control module includes a process matching unit and a quality control node configuration unit;

[0021] The process matching unit is compatible with precious metal product processing technologies such as hydraulic pressing, lost-wax casting, additive manufacturing, and subtractive manufacturing.

[0022] The quality control node configuration unit matches corresponding quality control nodes, testing standards, and process parameter monitoring dimensions according to the technical characteristics of different processing technologies, generates exclusive quality control processes, and supports flexible parameter configuration. The configured customized quality control processes are then sent to the data acquisition module and the real-time analysis and early warning module as the basis for data acquisition and quality early warning.

[0023] Preferably, the data traceability management module includes a visualization dashboard unit, a multi-dimensional retrieval unit, and a standardized archiving unit;

[0024] The visualization dashboard unit monitors the quality status of each quality control node in real time, enabling the second-level location of quality problems.

[0025] The multi-dimensional retrieval unit supports quality data retrieval based on multiple conditions, such as product batch, part number, production process, and third-party testing number, enabling reverse traceability.

[0026] The standardized archiving unit classifies and archives production, testing, and third-party data according to national standards and industry specifications. The archived data supports export in multiple formats and serves as a valid basis for product quality evaluation and judicial appraisal.

[0027] Preferably, the blockchain evidence storage module includes a data upload unit and a quality ID generation unit;

[0028] The data on-chain unit supports configurable data source filtering and stores raw material purity test data, process parameters of each process, semi-finished and finished product test data, and third-party test report information on the blockchain.

[0029] The quality ID generation unit generates a unique identification code for each product. The identification code can be scanned to query the product's quality data throughout the entire process, meeting the evidence requirements for customer auditing and shipment coordination.

[0030] Preferably, the process self-learning optimization module includes a data modeling unit, a process iteration unit, and an effect verification unit;

[0031] The data modeling unit constructs a correlation model between process parameters and product quality based on production, testing, and third-party historical data accumulated by the data acquisition module, and explores the optimal range of process parameters.

[0032] The process iteration unit pushes optimization suggestions for quality control processes and parameter thresholds to the customized quality control module based on the output results of the correlation model.

[0033] The effect verification unit compares and analyzes the quality control data after the optimization suggestions are implemented with historical data to verify the quality improvement effect and feeds it back to the data modeling unit to complete the model iteration.

[0034] Preferably, the numerical modeling unit of the process self-learning optimization module supports configurable selection of algorithm models, and can switch different data analysis models according to the process type of precious metal products, adapt to the parameter modeling requirements of different processes, and improve the adaptability of the model to the process.

[0035] Preferably, the data traceability management module further includes a data synchronization unit, which establishes a real-time configurable data connection with the blockchain evidence storage module and the process self-learning optimization module to synchronously update the traceability data and process optimization model data, ensuring the consistency and timeliness of data in each module, and the synchronization frequency can be adjusted as needed.

[0036] Preferably, the unique identification code generated by the quality ID card generation unit is associated with the product's full-process traceability data and the process optimization suggestions output by the process self-learning optimization module. The identification code is presented in the form of a QR code or barcode. The scanning query interface supports customized display of basic product information, test data, process parameters, and additional information related to process optimization. Moreover, the query permissions support hierarchical configuration to adapt to the different query needs of enterprises, customers, and regulatory authorities.

[0037] Compared with the prior art, the beneficial effects of the present invention are:

[0038] 1. This invention, by embedding a real-time analysis and early warning module and a customized quality control module, achieves dynamic monitoring and immediate adjustment of production process parameters, solving the problem of precious metal resource waste that may occur in the current traditional production-first-test-later model. The system adopts a production-while-testing mode, collecting data from key quality control points in real time during production. It uses an AI algorithm analysis unit to predict quality deviations, and triggers an early warning and intervenes in production immediately upon detecting an anomaly, avoiding batch rework. This reduces the scrapping of high-value raw materials due to substandard finished products, lowers the precious metal loss rate, achieves zero resource waste, and solves the problem of precious metal resource waste that may occur in the current traditional production-first-test-later model.

[0039] 2. This invention also uses a process self-learning optimization module to perform correlation modeling on the entire production and testing data, explore the optimal matching range between process parameters and product quality, and push parameter adjustment and process optimization suggestions to the customized quality control module. This continuously improves process stability and product first-pass yield, further reduces raw material loss caused by process fluctuations, and shortens the production debugging cycle. It provides technical support for on-time order delivery and extends the core effects of resource saving and order fulfillment guarantee.

[0040] 3. This invention also uses a blockchain-based evidence storage module to store data such as raw material purity, process parameters, and test results in an immutable manner. Combined with a unique identification code generation function, it creates a unique quality ID for each customized product. This not only allows customers and regulatory authorities to intuitively view product quality traceability information, but also enables rapid proof of product quality compliance during order fulfillment, avoiding delivery delays caused by quality disputes. At the same time, it enhances customers' trust in the quality of customized products, reduces the risk of order default, and extends the security of order fulfillment and improves customer satisfaction. Attached Figure Description

[0041] Figure 1 This is a flowchart illustrating the overall method of the present invention;

[0042] Figure 2 This is a flowchart of the customized quality control process generation method of the present invention;

[0043] Figure 3 This is a flowchart of the real-time quality early warning and production intervention method of the present invention;

[0044] Figure 4 This is a flowchart of the process self-learning optimization closed-loop method of the present invention. Detailed Implementation

[0045] like Figures 1 to 4 As shown, the present invention relates to a quality traceability and digital management system for precious metal products, including a data acquisition module, a customized quality control module, a real-time analysis and early warning module, a data traceability management module, a blockchain evidence storage module, and a process self-learning optimization module. Each module adopts a modular design and is a configurable component. The modules achieve data interoperability and linkage through standardized interfaces.

[0046] The data acquisition module connects to the quality control nodes, testing equipment, and third-party testing and inspection institutions with CMA / CNAS qualifications throughout the entire production process of precious metal products, realizing the online acquisition of production, testing, and third-party testing data across the entire chain, including multi-dimensional data acquisition units and equipment docking units;

[0047] The device docking unit adopts standardized hardware communication interfaces and software data interfaces to establish configurable data connections with various testing and production equipment throughout the precious metal production process. It also connects to the testing data management system of third-party testing and inspection institutions with CMA and CNAS qualifications. The testing equipment includes, but is not limited to, precious metal content testing equipment, micro-Vickers hardness testing equipment, appearance quality testing equipment, and harmful element content testing equipment. The production equipment includes, but is not limited to, process parameter monitoring equipment such as melting and rolling mills, stamping machines, and electroforming equipment. The interface connection supports both wired and wireless dual-mode connections and allows for flexible addition or removal of docking equipment based on enterprise equipment updates without altering the core system architecture.

[0048] The multi-dimensional data acquisition unit collects data on precious metal content, quality, harmful element content, production environment parameters, equipment operating parameters, and third-party testing reports at each quality control node at a preset frequency. Specifically, the acquisition frequency can be preset by the user, and different acquisition frequencies can be set according to the importance of production processes and quality control nodes. The collected data covers two major categories: production data and testing data. Production data includes production environment parameters (temperature, humidity, cleanliness) and equipment operating parameters (speed, temperature, current, voltage) for each process, as well as basic information on outsourced billets. Testing data includes precious metal content, quality, hardness, harmful element content, and appearance quality test results for each quality control node, as well as on-site testing data and structured data from formal testing reports issued by third-party inspection and testing institutions. All collected data undergoes standardized format conversion to ensure that subsequent modules can directly call and analyze the data.

[0049] The customized quality control module generates a customized quality control process for each product based on the product processing technology and design requirements, including a process matching unit and a quality control node configuration unit.

[0050] The process matching unit has built-in basic quality control models for four types of core precious metal processing technologies: hydraulic pressure, lost-wax casting, additive manufacturing, and subtractive manufacturing. It can automatically match the corresponding basic model according to the product process type of the enterprise. At the same time, it supports the addition and modification of custom process models to adapt to the special processing technologies developed by the enterprise.

[0051] The quality control node configuration unit matches corresponding quality control nodes, testing standards, and process parameter monitoring dimensions to the technical characteristics of different processing technologies, generating a customized quality control process and supporting flexible parameter configuration. Specifically, based on the basic model matched by the process matching unit, it automatically matches corresponding quality control nodes, testing standards, and process parameter monitoring dimensions to the design requirements and quality standards of specific products, generating a customized quality control process for each product. The quality control nodes can cover the entire production process, including raw material entry, outsourced processing, production processing, semi-finished product inspection, and finished product warehousing. The testing indicators, pass thresholds, and testing frequencies of each quality control node can be flexibly configured. For example, for the 3D hard gold additive manufacturing process, core quality control nodes such as gold purity, electroforming solution parameters, and micro Vickers hardness are automatically configured. For the hydraulic stamping coin bar process, core quality control nodes such as melting and rolling bar uniformity and final stamping quality are automatically configured. The configured customized quality control process can be sent to the data acquisition module and the real-time analysis and early warning module as the basis for data acquisition and quality early warning.

[0052] The real-time analysis and early warning module intelligently analyzes the collected data and sets quality alarm thresholds. When an alarm is triggered, it immediately intervenes in production. It includes an AI algorithm analysis unit, an early warning push unit, and a production intervention unit.

[0053] The AI ​​algorithm analysis unit incorporates multi-dimensional data analysis algorithms to perform correlation analysis on the collected production process parameters and test data, identifying the intrinsic relationship between process parameters and product quality. For example, it analyzes the correlation between the pH value and temperature of the 3D hard gold electroforming solution and the gold content and hardness of the product, and analyzes the correlation between the number of imprints in the hydraulic process and the appearance quality of the product. Based on the correlation analysis results, it automatically pushes process parameter adjustment suggestions to the production end to guide on-site operators to optimize the production process.

[0054] The early warning push unit supports custom configuration of multi-level quality alarm thresholds. Users can set early warning thresholds, first-level alarm thresholds, and second-level alarm thresholds according to product quality standards. Different thresholds correspond to different quality risk levels. When the test data or process parameters reach the corresponding threshold, the system pushes early warning information to designated staff through both pop-up windows and SMS in the production management system (MES). The early warning information includes core content such as risk quality control nodes, risk data, and risk levels, ensuring that staff are aware of quality risks as soon as possible.

[0055] The production intervention unit supports configurable operations for production suspension and process retracing after an alarm. It is linked with the enterprise's production equipment control system. When the data reaches the first-level or higher alarm threshold, it supports configurable operations for production suspension and process retracing remotely or automatically by the system. At the same time, the system automatically marks the relevant data of risk nodes, which makes it easy for staff to quickly investigate the cause of quality problems. Production can only be resumed after the problem is resolved, thus blocking the transmission of quality risks in the production process.

[0056] The data traceability management module digitizes and archives all process data, enabling rapid querying of quality data and full-process traceability, including a visual dashboard unit, a multi-dimensional retrieval unit, and a standardized archiving unit.

[0057] The visualization dashboard unit displays the quality status of each quality control node, production equipment operating parameters, quality alarm information and other content in real time in the form of charts and data panels. It supports multi-dimensional display by production batch, processing technology and production workshop. Staff can intuitively grasp the overall production quality through the dashboard and realize the second-level location of quality problems.

[0058] The multi-dimensional search unit supports quality data retrieval based on single or multiple conditions such as product batch, part number, production process, third-party testing number, and production time. It also supports reverse traceability, which allows tracing the quality data of finished products back to the corresponding semi-finished products, raw materials, production process parameters, and testing personnel, as well as forward traceability, which allows tracing the quality of all semi-finished and finished products formed from raw materials. The traceability results can generate a visual traceability report.

[0059] The standardized archiving unit classifies and archives all process data, including production data, testing data, third-party testing data, quality alarm data, and process adjustment data, in accordance with national standards and industry specifications for the precious metals industry. The archived data supports export in multiple formats such as Excel, PDF, and CSV, and has anti-tampering characteristics, which can serve as a valid basis for product quality evaluation, results, and judicial appraisal.

[0060] The data traceability management module also includes a data synchronization unit. The data synchronization unit establishes a real-time configurable data connection with the blockchain evidence storage module and the process self-learning optimization module. The data synchronization frequency can be adjusted by the user as needed and can be set to second-level, minute-level, or hour-level synchronization. The core function is to realize the real-time synchronous update of traceability data and process optimization model data, ensuring the consistency and timeliness of data between modules and avoiding data silos.

[0061] The blockchain evidence storage module provides tamper-proof evidence storage of quality data throughout the entire process and generates a product quality ID card with a unique identification code, including a data on-chain unit and a quality ID card generation unit.

[0062] The data upload unit supports configurable data source filtering. Users can select the data sources to be uploaded to the blockchain for evidence storage according to their needs, such as selecting only the test data of the core quality control nodes, or selecting the entire process of production and testing data. The filtered data sources include raw material purity test data, process parameters of each process, semi-finished and finished product test data, third-party test report information, etc., all of which are distributed and stored through blockchain technology to ensure that the data is tamper-proof and traceable. The hash value of the uploaded data can be queried in real time to verify the authenticity of the data.

[0063] The quality ID card generation unit generates a unique identification code for each precious metal product. This identification code serves as the product's "quality ID card" and can be printed on the product or its packaging in the form of a QR code, barcode, or other formats. By scanning this identification code, customers, regulatory authorities, and company staff can query the product's full-process quality data. The content displayed on the quality ID card can be customized. Basic information includes the product name, product number, manufacturer's name, production address, production date, measured precious metal content, and measured quality. It can also be used to input product highlight parameters such as smoothness, hardness, and salt spray test results that exceed national standards, as well as key points for product quality supervision and spot checks, to meet the evidence requirements of customer audits, shipment coordination, and regulatory inspections.

[0064] The process self-learning optimization module completes the correlation modeling between process parameters and product quality based on the historical data of the entire process, realizes the autonomous iterative optimization of the quality control process, and realizes the quality control and full life cycle digital traceability of precious metal products by testing while production. It includes a data modeling unit, a process iteration unit, and an effect verification unit.

[0065] The data modeling unit, based on production, testing, and third-party historical data accumulated by the data acquisition module, constructs a correlation model between process parameters and product quality, explores the influence of process parameters on product quality, and then determines the optimal process parameter range for each process. This unit supports configurable selection of algorithm models, allowing switching between different data analysis models according to the process type of precious metal products. For example, a regression analysis model can be selected for additive manufacturing processes, while a cluster analysis model can be selected for hydraulic processes, adapting to the parameter modeling needs of different processes and improving the model's adaptability to the process.

[0066] The process iteration unit automatically pushes optimization suggestions for the quality control process and parameter thresholds to the customized quality control module based on the optimal process parameter range and process optimization conclusions output by the data modeling unit. For example, it may adjust the pass threshold of a certain quality control node, add a quality control node for a certain process, or optimize the detection frequency. Staff can choose whether to adopt the optimization suggestions based on the actual production situation. The adopted optimization suggestions will be automatically updated to the quality control process of the customized quality control module to realize the iterative upgrade of the quality control process.

[0067] The effect verification unit compares and analyzes the quality control data after the optimization suggestions are implemented with the historical data before optimization. From the dimensions of product defect rate, precious metal loss rate, and process stability, it verifies the product quality improvement effect after the optimization of process parameters and quality control process. The verification results are fed back to the data modeling unit in real time as the basis for model iteration, realizing the continuous optimization of the associated model. This ensures that the model always fits the latest production process and quality status of the enterprise, forming a closed loop of process optimization including data collection, modeling analysis, process optimization, effect verification, and model iteration.

[0068] The embodiments disclosed in this invention are preferred embodiments, but are not limited thereto. Those skilled in the art can easily understand the spirit of this invention based on the above embodiments and make different extensions and variations, but as long as they do not depart from the spirit of this invention, they are all within the protection scope of this invention.

Claims

1. A quality traceability and digital management system for precious metal products, characterized in that, It includes a data acquisition module, a customized quality control module, a real-time analysis and early warning module, a data traceability management module, a blockchain evidence storage module, and a process self-learning optimization module. Each module adopts a modular design and is a configurable component. The modules can communicate and operate together through standardized interfaces. The data acquisition module connects to quality control nodes, testing equipment, and third-party testing and inspection institutions with CMA / CNAS qualifications throughout the entire production process of precious metal products, enabling online acquisition of production, testing, and third-party testing data across the entire chain. The customized quality control module generates a customized quality control process for each product based on its processing technology and design requirements. The real-time analysis and early warning module intelligently analyzes the collected data and sets quality alarm thresholds, and intervenes in production immediately when an alarm is triggered. The data traceability management module digitizes and archives all process data, enabling rapid querying of quality data and full-process traceability. The blockchain evidence storage module provides tamper-proof evidence storage of quality data throughout the entire process and generates a product quality ID card with a unique identification code. The process self-learning optimization module completes the correlation modeling between process parameters and product quality based on the historical data of the entire process, realizes the autonomous iterative optimization of the quality control process, and achieves the overall quality control and full life cycle digital traceability of precious metal products through simultaneous production and testing.

2. The precious metal product quality traceability and digital management system according to claim 1, characterized in that, The data acquisition module includes a multi-dimensional data acquisition unit and a device docking unit; The equipment docking unit establishes a configurable data connection with precious metal content detection, hardness detection, appearance quality detection, process parameter monitoring equipment, and third-party testing data systems; The multi-dimensional data acquisition unit collects data on precious metal content, quality, harmful element content, production environment parameters, equipment operating parameters, and third-party testing reports at each quality control node at a preset frequency.

3. The precious metal product quality traceability and digital management system according to claim 2, characterized in that, The real-time analysis and early warning module includes an AI algorithm analysis unit, an early warning push unit, and a production intervention unit; The AI ​​algorithm analysis unit performs correlation analysis on production process parameters and test data, identifies the correlation between process parameters and product quality, and automatically pushes process adjustment suggestions. The early warning push unit supports the custom configuration of multi-level quality alarm thresholds, and pushes early warning information to staff through the production management system and SMS when an alarm is triggered. The production intervention unit supports configurable operations such as production suspension and process rollback after an alarm.

4. The precious metal product quality traceability and digital management system according to claim 3, characterized in that, The customized quality control module includes a process matching unit and a quality control node configuration unit; The process matching unit is compatible with precious metal product processing technologies such as hydraulic pressing, lost-wax casting, additive manufacturing, and subtractive manufacturing. The quality control node configuration unit matches corresponding quality control nodes, testing standards, and process parameter monitoring dimensions according to the technical characteristics of different processing technologies, generates exclusive quality control processes, and supports flexible parameter configuration. The configured customized quality control processes are then sent to the data acquisition module and the real-time analysis and early warning module as the basis for data acquisition and quality early warning.

5. The precious metal product quality traceability and digital management system according to claim 4, characterized in that, The data traceability management module includes a visual dashboard unit, a multi-dimensional search unit, and a standardized archiving unit; The visualization dashboard unit monitors the quality status of each quality control node in real time, enabling the second-level location of quality problems. The multi-dimensional retrieval unit supports quality data retrieval based on multiple conditions, such as product batch, part number, production process, and third-party testing number, enabling reverse traceability. The standardized archiving unit classifies and archives production, testing, and third-party data according to national standards and industry specifications. The archived data supports export in multiple formats and serves as a valid basis for product quality evaluation and judicial appraisal.

6. The precious metal product quality traceability and digital management system according to claim 5, characterized in that, The blockchain evidence storage module includes a data upload unit and a quality ID card generation unit; The data on-chain unit supports configurable data source filtering and stores raw material purity test data, process parameters of each process, semi-finished and finished product test data, and third-party test report information on the blockchain. The quality ID generation unit generates a unique identification code for each product. The identification code can be scanned to query the product's quality data throughout the entire process, meeting the evidence requirements for customer auditing and shipment coordination.

7. The precious metal product quality traceability and digital management system according to claim 6, characterized in that, The process self-learning optimization module includes a data modeling unit, a process iteration unit, and an effect verification unit. The data modeling unit constructs a correlation model between process parameters and product quality based on production, testing, and third-party historical data accumulated by the data acquisition module, and explores the optimal range of process parameters. The process iteration unit pushes optimization suggestions for quality control processes and parameter thresholds to the customized quality control module based on the output results of the correlation model. The effect verification unit compares and analyzes the quality control data after the optimization suggestions are implemented with historical data to verify the quality improvement effect and feeds it back to the data modeling unit to complete the model iteration.

8. The precious metal product quality traceability and digital management system according to claim 7, characterized in that, The process self-learning optimization module's numerical modeling unit supports configurable selection of algorithm models, allowing for switching between different data analysis models based on the process type of precious metal products. This adapts to the parameter modeling requirements of different processes, improving the model's adaptability to the process.

9. The precious metal product quality traceability and digital management system according to claim 8, characterized in that, The data traceability management module also includes a data synchronization unit. The data synchronization unit establishes a real-time configurable data connection with the blockchain evidence storage module and the process self-learning optimization module to synchronize and update traceability data and process optimization model data, ensuring the consistency and timeliness of data in each module. The synchronization frequency can be adjusted as needed.

10. A quality traceability and digital management system for precious metal products according to claim 9, characterized in that, The unique identification code generated by the quality ID card generation unit is associated with the product's full-process traceability data and the process optimization suggestions output by the process self-learning optimization module. The identification code is presented in the form of a QR code or barcode. The scanning query interface supports customized display of basic product information, test data, process parameters and process optimization-related additional information, and the query permissions support hierarchical configuration to adapt to the different query needs of enterprises, customers and regulatory authorities.

Images