Product traceability direction management and control system based on whole process monitoring

Abstract

The invention discloses a product traceability direction management and control system based on full-process monitoring, and relates to the technical field of product traceability management. The full-process management and control platform is in communication connection with a product data acquisition module, a product identification analysis module, a product data management module, a data traceability analysis module, a product abnormity management module, a process optimization module and an interaction management module. According to the product traceability direction management and control system based on full-process monitoring, through comprehensive monitoring and recording of raw material sources, production dates, processing details and quality inspection results, it is ensured that products meet preset quality standards in each production link, once any deviation is found, the system can immediately give out early warning, and the product traceability direction management and control system is convenient to use. In addition, a large amount of data is analyzed through a machine learning algorithm, key factors influencing the product quality can be recognized, and therefore a scientific basis is provided for quality improvement.

Description

Technical Field

[0001] The present invention relates to the technical field of product traceability management, and in particular to a product traceability direction control system based on full-process monitoring. Background Art

[0002] As consumers pay more and more attention to product quality and safety, companies are facing increasing pressure to ensure that the products they produce meet high quality standards. By real-time monitoring of key parameters in the production process and recording information at each production link, including the source of raw materials, production equipment status, operator records and test results, the quality of each product can be traced back to the source. This systematic quality traceability capability helps companies discover and solve problems in the production process, continuously improve production processes, and improve the overall quality and consistency of products.

[0003] In the existing technology, due to the problems existing in various production processes of products and the different abnormality judgment standards, it is difficult to quickly and accurately locate the problem products, which in turn affects the elimination of problem products. Therefore, how to mine and analyze the traceability data, discover potential problems and trends, and optimize the production process is the problem we need to solve. To this end, a product traceability direction control system based on full-process monitoring is proposed. Summary of the invention

[0004] To achieve the above objectives, the present invention is implemented through the following technical solutions: a product traceability direction control system based on full-process monitoring, including a full-process control platform, wherein the full-process control platform is communicatively connected with a product data acquisition module, a product identification parsing module, a product data management module, a data traceability analysis module, a product abnormality management module, a process optimization module and an interactive management module, wherein the modules are electrically connected by signals; The product data collection module is used to collect product status data in each production process and pre-process the collected product status data. It is the basis of the traceability system and ensures the integrity and accuracy of the information; The product identification parsing module is used to assign a unique identification code to each product, associate all relevant data of the product through the identification code, and improve the speed and accuracy of information retrieval through the unique identification code; The product data management module is used to perform database modeling, store and manage the collected product status data, ensure the security and reliability of the data, and provide long-term data support for the enterprise; The data traceability analysis module, combined with machine learning algorithms, mines and analyzes the stored full-process product status data, identifies potential problems and trends, and evaluates the quality status of products; The product anomaly management module is used to perform product anomaly analysis based on the results of data traceability analysis, set anomaly determination thresholds, locate problematic products, generate quality control reports to assist in anomaly warnings, provide a basis for quality improvement, help respond to quality issues in a timely manner, and improve risk control capabilities; The process optimization module optimizes the production process with problems based on the results of data traceability analysis and product anomaly analysis, improves production efficiency and product quality, and helps enterprises to continuously improve and enhance their competitiveness; The interactive management module is used to manage the product status data of the entire process and the product traceability analysis results, and provide a query interface for users, including consumers, corporate employees and managers, to query the product traceability information, enhance interaction with consumers, improve transparency, and enhance consumer trust.

[0005] Preferably, in the product data acquisition module, the collection and preprocessing process of product status data includes: Specify the types of product status data that need to be collected throughout the entire production process, including the source of raw materials, production date, processing details, and quality inspection results. The source of raw materials records key information such as the supplier, batch, and quality certification of the raw materials. The production date records the date and time when the product starts production. Processing details include production process parameters, processing equipment usage, processing steps, etc. The quality inspection results include the data and results of raw material inspection, process inspection, and finished product inspection. Deploy data monitoring and collection points throughout the entire production process to ensure that all production processes that require data collection are covered, and configure corresponding hardware equipment to collect product status data. Hardware equipment includes barcode scanners, RFID readers, sensors, etc. The collected product status information is preprocessed. The preprocessing operations include data cleaning, data conversion, and data encryption steps. Data cleaning removes duplicate data to ensure that there are no duplicate records in the data set. Missing data is filled or deleted according to the context. Obviously erroneous data, such as unreasonable values ​​or formats, are corrected or deleted. The collected data is converted into a format suitable for storage and analysis through data conversion. For data in different units, unit conversion is performed to ensure consistency. Encryption technology is used to encrypt sensitive data, such as raw material supplier information, quality inspection results, etc., to ensure the security of data transmission and prevent data leakage or tampering.

[0006] Preferably, in the product identification resolution module, the identification code allocation process includes: Use the Universal Unique Identifier (UUID) to generate a globally unique identification code for each product to ensure the uniqueness, scalability and stability of the identification code to meet the needs of different fields and products. The identification code contains the product identification (DI) and the production identification (PI). The product identification (DI) is a fixed and mandatory part used to identify the model and specifications of the product; the production identification (PI) is a variable and non-mandatory part that contains information related to the production process; Assign the generated unique identification code to each product, associate it with the relevant information of the product (source of raw materials, production date, processing details, quality inspection results), and attach the data carrier of the identification code to the product to ensure that the identification code is clear and readable; When querying relevant information of a product, the product identification resolution module receives a resolution request, which includes a unique identification code of the product to be queried; After receiving the resolution request, the product identification resolution module uses the resolution algorithm to resolve the received identification code, finds the product information associated with the identification code by calling related services, returns the found product information, and completes the resolution process. The returned information includes the product's raw material source, production date, processing details, quality inspection results, etc.

[0007] Preferably, in the product data management module, the process of database modeling and storing product status data includes: Based on data structure and query requirements, install and configure MySQL relational database management system, run MySQL configuration tool to initialize MySQL data directory, configure my.cnf configuration file, set server parameters, including server settings, database creation and user permission configuration, set MySQL root user password, and create a new administrator user to improve security; Integrate the collected product status data of the entire process, and use ETL tools to integrate and transform the data, extract the data from the source system, clean and transform it, and load it into the MySQL database to ensure the integrity and consistency of the data; Create an API to provide a data access interface, provide corresponding data access and operation permissions for different users and systems, and assign data access permissions based on user roles and needs to ensure data security; Configure MySQL's general query log to record all database operations, implement audit policies, and regularly check log files to track and audit data usage.

[0008] Preferably, in the data traceability analysis module, the product quality status evaluation process includes: Extract product status data from the database, extract feature data related to product quality, namely, raw material quality, key parameters in the production process, and inspection results, and score the raw material quality, key parameters in the production process, and inspection results to obtain a product status feature set; Use product status feature set data combined with neural network models to build a product trend evaluation model, and evaluate the accuracy and generalization ability of the model through cross-validation and A / B testing methods to ensure the effectiveness of the model; Use product trend assessment models to identify high-incidence periods of quality defects in data, group similar production processes or products through cluster analysis, and analyze the relationship between raw materials and product quality to identify key factors affecting product quality; Based on the analysis results of the product trend assessment model, the quality trend assessment coefficient is calculated, and trend analysis is performed on the product status data of the entire process to identify the changing trend of product quality over time; Based on the results of trend analysis, evaluate the quality status of the product and determine whether the product meets the quality standards.

[0009] Preferably, the calculation process of the quality trend assessment coefficient is: Collect all relevant product status data, extract raw material quality scores, key production parameter scores, and inspection result scores; Calculate the historical average values ​​of raw material quality scores and key production parameter scores as the material quality benchmark value and key production parameter benchmark value, and calculate the historical standard deviations of raw material quality scores and key production parameter scores; The sigmoid function is used to calculate the mapping quality of the raw material quality score and the key production parameter score, and the ratio of the test result score to the highest test result score is calculated; The calculated results of the raw material quality score, key production parameter score, and inspection result score are respectively raised to the power of the corresponding weight coefficient, and the three weighted results are multiplied to obtain the quality trend assessment coefficient.

[0010] Preferably, the calculation expression of the quality trend evaluation coefficient is: ; in, It is the quality trend assessment coefficient, which reflects the overall quality status of the product. Score the quality of raw materials, is a comprehensive score for key production parameters, Score the test results. The benchmark value for raw material quality scoring, It is the comprehensive scoring benchmark value of key production parameters. is the standard deviation of the raw material quality score, The standard deviation of the scores for key production parameters, The highest score for the test results. , and are weight coefficients, corresponding to the relative importance of raw material quality, key production parameters and test results in the overall quality score, The value is between 0 and 1.

[0011] Preferably, in the product abnormality management module, the abnormality warning process includes: Based on the results of data traceability analysis, potential factors affecting product quality are identified and the correlation between factors is analyzed to more accurately predict and identify product anomalies; Review historical product quality data, analyze the fluctuation range and trend of product quality, and set the abnormality judgment threshold of product quality in combination with product production demand standards and industry standards to determine whether the product is in an abnormal state; By comparing actual data with the abnormality judgment threshold, the problematic product batches or individuals are located, and the abnormal products are marked for subsequent quality control and improvement; According to the analysis results, a quality control report is automatically generated, including detailed information of abnormal products, analysis of abnormal causes, and suggestions for improvement measures. The quality control report should clearly and accurately reflect the product quality status and provide a basis for quality improvement; Use the information in the quality control report to set up an abnormal warning mechanism. When the product quality approaches or exceeds the abnormal judgment threshold, send a warning signal to relevant personnel via email, text message, or system notification so that they can respond and handle it in a timely manner.

[0012] Preferably, in the process optimization module, the process of optimizing the production process includes: Analyze the specific causes and occurrence links of product abnormalities based on quality control reports and abnormal warning mechanisms, identify abnormal product batches or individuals, and trace related problems in their production processes; Based on the results of abnormal analysis, clarify the specific goals of production process optimization, such as improving production efficiency, reducing defective product rates, and reducing equipment failures, and design corresponding optimization plans for the identified problems and potential factors; Conduct preliminary evaluation of the optimization plan to ensure its feasibility and effectiveness, and adjust and optimize the plan based on the evaluation results to ensure the best implementation effect; Develop a detailed implementation plan, clarify the goals and timetable for each stage. During the implementation process, pay close attention to changes in production processes and fluctuations in product quality, and adjust the optimization plan based on actual conditions to ensure that its implementation effect meets expectations.

[0013] Preferably, in the interaction management module, the query process of product traceability information includes: Integrate product status data collected from various links of production, processing, transportation, and sales, including raw material sources, production date, batch number, quality inspection report, logistics information, etc., to form a complete product life cycle data chain; According to user needs, users are divided into three categories: consumers, enterprise employees and managers. Different query interfaces and functional permissions are designed for different roles. Among them, the consumer query interface provides product traceability information query function. Consumers can query detailed information of the product, including the source of raw materials, production date, quality inspection report, etc., by scanning the QR code on the product or entering information such as batch number. The enterprise employee query interface provides internal data management functions. Employees can query, update and maintain product status data, and view traceability analysis reports. The manager query interface provides comprehensive data monitoring and analysis functions. Managers can view product status data, traceability analysis reports and user query records in real time to make decisions; Set up interactive functions on the query interface, such as consumer evaluation, suggestion feedback, etc., to encourage consumers to participate in the supervision and improvement of product quality, and provide real-time online customer service functions to answer consumer questions and enhance interaction with consumers; Regularly update product status data to ensure the accuracy and timeliness of traceability information, and regularly review and optimize traceability analysis reports to improve the accuracy and reliability of analysis.

[0014] The present invention provides a product traceability direction control system based on full-process monitoring. It has the following beneficial effects: 1. The product traceability control system based on full-process monitoring ensures that the product meets the predetermined quality standards in each production link by comprehensively monitoring and recording the source of raw materials, production date, processing details, and quality inspection results. Once any deviation is found, the system can immediately issue an early warning, prompting relevant personnel to take corrective measures. In addition, through the analysis of large amounts of data through machine learning algorithms, the key factors affecting product quality can be identified, thereby providing a scientific basis for quality improvement.

[0015] 2. The product traceability direction control system based on full-process monitoring has formed a complete data chain for the entire product production life cycle by integrating data from multiple links such as production, processing, and logistics. It not only greatly improves the accuracy of product traceability, so that each product can be accurately traced to its source, but also significantly improves the transparency of product information. Consumers can easily obtain detailed information about the product, including the source of raw materials, production date, quality inspection report, etc., by simply scanning the product, which helps companies to continuously optimize production processes, reduce defects, and improve product reliability and safety. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 This is a module structure diagram of a product traceability direction control system based on full-process monitoring of the present invention; Figure 2 is a flow chart for evaluating the quality status of the product of the present invention; Figure 3 The figure is a flow chart for calculating the quality trend evaluation coefficient of the present invention. DETAILED DESCRIPTION

[0017] The present invention is further described in detail below in conjunction with the accompanying drawings and specific embodiments. The embodiments of the present invention are provided for the purpose of illustration and description, and are not intended to be exhaustive or to limit the present invention to the disclosed forms. Many modifications and variations will be apparent to those of ordinary skill in the art. The embodiments are selected and described in order to better illustrate the principles and practical applications of the present invention, and to enable those of ordinary skill in the art to understand the present invention and thereby design various embodiments with various modifications suitable for specific uses.

[0018] The first embodiment, as Figure 1 As shown, the present invention provides a technical solution: a product traceability direction control system based on full-process monitoring, including a full-process control platform, the full-process control platform is communicatively connected with a product data acquisition module, a product identification parsing module, a product data management module, a data traceability analysis module, a product abnormality management module, a process optimization module and an interactive management module, wherein the modules are electrically connected by signals; The product data collection module is used to collect product status data in each production process and pre-process the collected product status data. It is the basis of the traceability system, ensuring the integrity and accuracy of the information. It clearly defines the types of product status data in the entire production process that need to be collected, namely, the source of raw materials, production date, processing details, and quality inspection results. Among them, the source of raw materials records key information such as the supplier, batch, and quality certificate of the raw materials. The production date records the date and time when the product starts production. The processing details include production process parameters, processing equipment usage, processing steps, etc. The quality inspection results include the data and results of raw material inspection, process inspection, and finished product inspection. Data monitoring and collection points are deployed throughout the entire process of product production to ensure that all production processes that need to collect data can be covered, and the corresponding The hardware equipment collects product status data, wherein the hardware equipment includes barcode scanners, RFID readers, sensors, etc., performs data preprocessing on the collected product status information, and the preprocessing operation includes data cleaning, data conversion, and data encryption steps, wherein data cleaning removes duplicate data to ensure that there are no duplicate records in the data set, fills or deletes missing data according to the context, corrects or deletes obviously erroneous data, such as unreasonable values ​​or formats, and converts the collected data into a format suitable for storage and analysis through data conversion. For data in different units, unit conversion is performed to ensure consistency, and encryption technology is used to encrypt sensitive data, such as raw material supplier information, quality inspection results, etc., to ensure the security of data transmission and prevent data leakage or tampering; The product identification parsing module is used to assign a unique identification code to each product, associate all relevant data of the product through the identification code, improve the speed and accuracy of information retrieval through the unique identification code, and use the universal unique identifier (UUID) to generate a globally unique identification code for each product to ensure the uniqueness, scalability and stability of the identification code to meet the needs of different fields and products. The identification code contains the product identification (DI) and the production identification (PI). The product identification (DI) is a fixed and mandatory part used to identify the model and specifications of the product; the production identification (PI) is a variable and non-mandatory part that contains information related to the production process. The generated unique identification code is assigned For each product, establish an association with the relevant information of the product (raw material source, production date, processing details, quality inspection results), and attach a data carrier of the identification code to the product to ensure that the identification code is clear and readable. When querying the relevant information of the product, the product identification resolution module receives the resolution request, which contains the unique identification code of the product to be queried. After receiving the resolution request, the product identification resolution module uses the resolution algorithm to resolve the received identification code, finds the product information associated with the identification code by calling the relevant service, returns the found product information, and completes the resolution process. The returned information includes the raw material source, production date, processing details, quality inspection results, etc. of the product; The product data management module is used to perform database modeling, store and manage the collected product status data, ensure data security and reliability, and provide long-term data support for enterprises. Based on data structure and query requirements, install and configure the MySQL relational database management system, run the MySQL configuration tool to initialize the MySQL data directory, configure the my.cnf configuration file, set server parameters, including server settings, database creation and user permission configuration, and set the MySQL root user password. Create a new administrator user to improve security, integrate the collected full-process product status data, and use ETL tools to integrate and transform data. Extract data from the source system, clean and transform it, and load it into the MySQL database to ensure data integrity and consistency. Create an API to provide a data access interface, provide corresponding data access and operation permissions for different users and systems, and assign data access permissions based on user roles and needs to ensure data security. Configure MySQL's general query log to record all database operations, implement audit policies, and regularly check log files to track and audit data usage; The data traceability analysis module uses machine learning algorithms to mine and analyze the stored full-process product status data, identify potential problems and trends, and evaluate product quality status; The product anomaly management module is used to analyze product anomalies based on the results of data traceability analysis, set anomaly determination thresholds, locate problematic products, and generate quality control reports to assist in anomaly warnings, providing a basis for quality improvement, helping to respond to quality issues in a timely manner, and improving risk control capabilities; The process optimization module optimizes the production process with problems based on the results of data traceability analysis and product anomaly analysis, improves production efficiency and product quality, and helps enterprises to continuously improve and enhance their competitiveness; The interactive management module is used to manage the product status data of the entire process and the product traceability analysis results, and provide a query interface for users, including consumers, corporate employees and managers, to query the product traceability information, enhance interaction with consumers, improve transparency, and enhance consumer trust.

[0019] The second embodiment is based on the first embodiment. Figure 2 , Figure 3 As shown in the figure, in the data traceability analysis module, the evaluation process of product quality status includes: Extract product status data from the database, and extract feature data related to product quality from it, which are raw material quality, key parameters in the production process, and inspection results. Score the raw material quality, key parameters in the production process, and inspection results to obtain a product status feature set. Use the product status feature set data in combination with a neural network model to build a product trend evaluation model. Use cross-validation and A / B testing methods to evaluate the accuracy and generalization ability of the model to ensure the effectiveness of the model. Use the product trend evaluation model to identify the high-incidence periods of quality defects in the data. Use cluster analysis to group similar production processes or products, analyze the relationship between raw materials and product quality, and find out the key factors affecting product quality. Based on the analysis results of the product trend evaluation model, calculate the quality trend evaluation coefficient, perform trend analysis on the product status data of the entire process, identify the changing trend of product quality over time, and evaluate the quality status of the product based on the results of the trend analysis to determine whether the product meets the quality standards. Furthermore, the calculation process of the quality trend assessment coefficient is as follows; Collect all relevant product status data, extract raw material quality scores, key production parameter scores, and inspection result scores, calculate the historical averages of raw material quality scores and key production parameter scores, use them as material quality benchmarks and key production parameter benchmarks, and calculate the historical standard deviations of raw material quality scores and key production parameter scores. Apply the sigmoid function to calculate the mapping quality of the raw material quality scores and key production parameter scores, and calculate the ratio of the inspection result score to the highest inspection result score. Raise the calculation results of the raw material quality scores, key production parameter scores, and inspection result scores to the power of the corresponding weight coefficients, and multiply the three weighted results to obtain the quality trend assessment coefficient. Furthermore, the calculation expression of the quality trend evaluation coefficient is: ; in, It is the quality trend assessment coefficient, which reflects the overall quality status of the product. Score the quality of raw materials, is a comprehensive score for key production parameters, Score the test results. The benchmark value for raw material quality scoring, It is the comprehensive scoring benchmark value of key production parameters. is the standard deviation of the raw material quality score, The standard deviation of the scores for key production parameters, The highest score for the test results. , and are weight coefficients, corresponding to the relative importance of raw material quality, key production parameters and test results in the overall quality score, The value of is between 0 and 1. , and When they are close to their respective maximum values, Close to 1, it means the product quality is very high. , or When approaching their respective minimum values, Close to 0, indicating low product quality. is a S-shaped function, also known as the sigmoid function, which maps any real value to between 0 and 1 when near When , the function value is close to 0.5; when Significantly higher or lower than When , the function value is close to 1 or 0, making the function suitable for processing rating data, where ratings close to the benchmark value are mapped to medium quality, and ratings far from the benchmark value are mapped to high or low quality. By increasing the result of the sigmoid function to the weight The power of each factor is adjusted according to its importance in the overall quality assessment, and the weight coefficient , and It allows different quality dimensions to be assigned different levels of importance, and multiplies the weighted sigmoid function results of the three factors to obtain a comprehensive quality assessment coefficient , ensuring that all factors contribute to the final quality assessment and that a low score for any one factor will reduce the overall value; In the product abnormality management module, the abnormality warning process includes: Based on the results of data traceability analysis, identify potential factors affecting product quality and analyze the correlation between various factors in order to more accurately predict and identify product anomalies. Review historical product quality data, analyze the fluctuation range and trend of product quality, and set the abnormality judgment threshold of product quality in combination with product production demand standards and industry standards to determine whether the product is in an abnormal state. By comparing actual data with the abnormality judgment threshold, locate the batch or individual product with problems, and mark the abnormal products for subsequent quality control and improvement. According to the analysis results, automatically generate a quality control report, including detailed information of abnormal products, abnormal cause analysis, and improvement measures. The quality control report should clearly and accurately reflect the product quality status and provide a basis for quality improvement. Use the information in the quality control report to set up an abnormal warning mechanism. When the product quality approaches or exceeds the abnormal judgment threshold, send a warning signal to relevant personnel through email, SMS, and system notification so that they can respond and handle it in time. In the process optimization module, the process of optimizing the production process includes: According to the quality control report and abnormal warning mechanism, analyze the specific reasons and occurrence links of product abnormalities, determine the abnormal product batches or individuals, and trace the relevant problems in their production process. According to the results of abnormal analysis, clarify the specific goals of production process optimization, such as improving production efficiency, reducing defective rates, reducing equipment failures, etc., and design corresponding optimization plans for the identified problems and potential factors, conduct preliminary evaluation of the optimization plans to ensure their feasibility and effectiveness, and adjust and optimize the plans based on the evaluation results to ensure the best implementation effect. Develop a detailed implementation plan, clarify the goals and timetables for each stage, and pay close attention to changes in the production process and fluctuations in product quality during implementation, and adjust the optimization plan based on actual conditions to ensure that its implementation effect meets expectations; In the interactive management module, the query process of product traceability information includes: Integrate product status data collected from various links of production, processing, transportation, and sales, including raw material sources, production dates, batch numbers, quality inspection reports, logistics information, etc., to form a complete product life cycle data chain. According to user needs, users are divided into three categories: consumers, corporate employees, and managers. Different query interfaces and functional permissions are designed for different roles. Among them, the consumer query interface provides product traceability information query function. Consumers can query detailed product information, including raw material sources, production dates, quality inspection reports, etc., by scanning the QR code on the product or entering information such as batch numbers. The corporate employee query interface provides internal data management functions. Employees can query, update and maintain product status data, and view traceability analysis reports. The manager query interface provides comprehensive data monitoring and analysis functions. Managers can view product status data, traceability analysis reports and user query records in real time to make decisions. Interactive functions such as consumer evaluation, suggestion feedback, etc. are set on the query interface to encourage consumers to participate in the supervision and improvement of product quality. Real-time online customer service functions are provided to answer consumer questions and enhance interaction with consumers. Product status data is updated regularly to ensure the accuracy and timeliness of traceability information. Traceability analysis reports are reviewed and optimized regularly to improve the accuracy and reliability of analysis.

[0020] Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field and related fields without creative work should fall within the scope of protection of the present invention. The structures, devices and operating methods not specifically described and explained in the present invention are implemented according to the conventional means in the field unless otherwise specified and limited.

Claims

1. A product traceability direction control system based on full-process monitoring, including a full-process control platform, characterized in that: The full-process control platform is communicatively connected with a product data collection module, a product identification analysis module, a product data management module, a data traceability analysis module, a product abnormality management module, a process optimization module and an interactive management module, wherein the electrical signals between the modules are connected; The product data collection module is used to collect product status data in each production process and pre-process the collected product status data; The product identification parsing module is used to assign a unique identification code to each product and associate all relevant data of the product through the identification code; The product data management module is used to perform database modeling and store and manage the collected product status data; The data traceability analysis module, combined with machine learning algorithms, mines and analyzes the stored full-process product status data, identifies potential problems and trends, and evaluates the quality status of products; The product anomaly management module is used to perform product anomaly analysis based on the results of data traceability analysis, set anomaly determination thresholds, locate problematic products, and generate quality control reports to assist in anomaly warnings; The process optimization module optimizes the production process with problems based on the results of data traceability analysis and product anomaly analysis; The interactive management module is used to manage the product status data of the entire process and the product traceability analysis results, and provide a query interface for users to query the product traceability information.

2. According to claim 1, a product traceability direction control system based on full-process monitoring is characterized by: In the product data acquisition module, the collection and preprocessing process of product status data includes: Specify the types of product status data that need to be collected throughout the entire production process, including the source of raw materials, production date, processing details, and quality inspection results; Deploy data monitoring and collection points throughout the entire production process to ensure that all production processes that require data collection are covered, and configure corresponding hardware equipment to collect product status data; The collected product status information is preprocessed, and the preprocessing operation includes data cleaning, data conversion and data encryption steps.

3. According to claim 2, a product traceability direction control system based on full-process monitoring is characterized in that: In the product identification resolution module, the identification code allocation process includes: Use the universal unique identifier to generate a globally unique identification code for each product. The identification code contains the product identification and production identification, where the product identification is a fixed and mandatory part used to identify the model and specifications of the product; the production identification is a variable and non-mandatory part that contains information related to the production process; Assign the generated unique identification code to each product, associate it with relevant information of the product, and attach a data carrier of the identification code to the product; When querying relevant information of a product, the product identification resolution module receives a resolution request, which includes a unique identification code of the product to be queried; After receiving the resolution request, the product identification resolution module uses the resolution algorithm to resolve the received identification code, finds the product information associated with the identification code by calling related services, returns the found product information, and completes the resolution process.

4. A product traceability direction control system based on full-process monitoring according to claim 3, characterized in that: In the product data management module, the process of database modeling and storing product status data includes: Based on data structure and query requirements, install and configure MySQL relational database management system, run MySQL configuration tool to initialize MySQL data directory, configure my.cnf configuration file, set server parameters, including server settings, database creation and user permission configuration, set MySQL root user password, and create a new administrator user; Integrate the collected product status data of the entire process, and use ETL tools to integrate and transform the data, extract the data from the source system, clean and transform it, and load it into the MySQL database; Create an API to provide a data access interface, provide corresponding data access and operation permissions for different users and systems, and assign data access permissions based on user roles and needs; Configure MySQL's general query log to record all database operations, implement audit policies, and check log files regularly.

5. A product traceability direction control system based on full-process monitoring according to claim 4, characterized in that: In the data traceability analysis module, the product quality status assessment process includes: Extract product status data from the database, extract feature data related to product quality, namely, raw material quality, key parameters in the production process, and inspection results, and score the raw material quality, key parameters in the production process, and inspection results to obtain a product status feature set; Use product status feature set data combined with neural network models to build a product trend evaluation model, and evaluate the model through cross-validation and A / B testing methods; Use product trend assessment models to identify high-incidence periods of quality defects in data, group similar production processes or products through cluster analysis, and analyze the relationship between raw materials and product quality to identify key factors affecting product quality; Based on the analysis results of the product trend assessment model, the quality trend assessment coefficient is calculated, and trend analysis is performed on the product status data of the entire process to identify the changing trend of product quality over time; Based on the results of trend analysis, evaluate the quality status of the product and determine whether the product meets the quality standards.

6. A product traceability direction control system based on full-process monitoring according to claim 5, characterized in that: The calculation process of the quality trend assessment coefficient is as follows: Collect all relevant product status data, extract raw material quality scores, key production parameter scores, and inspection result scores; Calculate the historical average values ​​of raw material quality scores and key production parameter scores as the material quality benchmark value and key production parameter benchmark value, and calculate the historical standard deviations of raw material quality scores and key production parameter scores; The sigmoid function is used to calculate the mapping quality of the raw material quality score and the key production parameter score, and the ratio of the test result score to the highest test result score is calculated; The calculated results of the raw material quality score, key production parameter score, and inspection result score are respectively raised to the power of the corresponding weight coefficient, and the three weighted results are multiplied to obtain the quality trend assessment coefficient.

7. A product traceability direction control system based on full-process monitoring according to claim 6, characterized in that: The calculation expression of the quality trend evaluation coefficient is: ； in, It is the quality trend assessment coefficient, which reflects the overall quality status of the product. Score the quality of raw materials, is a comprehensive score for key production parameters, Score the test results. The benchmark value for raw material quality scoring, It is the comprehensive scoring benchmark value of key production parameters. is the standard deviation of the raw material quality score, The standard deviation of the scores for key production parameters, The highest score for the test results. , and are weight coefficients, corresponding to the relative importance of raw material quality, key production parameters and test results in the overall quality score, The value is between 0 and 1.

8. A product traceability direction control system based on full-process monitoring according to claim 7, characterized in that: In the product abnormality management module, the abnormality warning process includes: Based on the results of data traceability analysis, identify potential factors affecting product quality and analyze the correlation between factors; Review historical product quality data, analyze the fluctuation range and trend of product quality, and set the abnormality judgment threshold of product quality in combination with product production demand standards and industry standards to determine whether the product is in an abnormal state; By comparing actual data with the abnormality judgment threshold, the problematic product batches or individuals are located and the abnormal products are marked; Based on the analysis results, a quality control report is automatically generated, including detailed information of abnormal products, analysis of abnormal causes, and suggestions for improvement measures; Use the information in the quality control report to set up an abnormal warning mechanism. When the product quality approaches or exceeds the abnormal judgment threshold, send a warning signal to relevant personnel via email, text message, or system notification.

9. A product traceability direction control system based on full-process monitoring according to claim 8, characterized in that: In the process optimization module, the process of optimizing the production process includes: Analyze the specific causes and occurrence links of product abnormalities based on quality control reports and abnormality warning mechanisms, identify abnormal product batches or individuals, and trace related problems in their production processes; Based on the results of abnormal analysis, clarify the specific goals of production process optimization, and design corresponding optimization plans for the identified problems and potential factors; Conduct preliminary evaluation of the optimization plan, and adjust and optimize the plan based on the evaluation results; Develop an implementation plan, clarify the goals and timetable for each stage. During the implementation process, pay attention to changes in production processes and fluctuations in product quality, and adjust the optimization plan based on actual conditions.

10. A product traceability direction control system based on full-process monitoring according to claim 9, characterized in that: In the interactive management module, the query process of product traceability information includes: Integrate product status data collected from various links of production, processing, transportation, and sales to form a complete product life cycle data chain; According to user needs, users are divided into three categories: consumers, enterprise employees and managers, and different query interfaces and functional permissions are designed for different roles; Set up interactive functions on the query interface and provide real-time online customer service to answer consumers' questions; Regularly update product status data, and regularly review and optimize traceability analysis reports.

Images