A system and method for information fusion of traditional handicraft and wisdom factory

Abstract

The application relates to the technical field of intelligent factories, and discloses a traditional handicraft and intelligent factory information fusion system and method, which comprises a data acquisition module, a data processing module, a first data analysis module, a backend management module and a second data analysis module.The data acquisition module is used for collecting first production data on a handicraft production line; the data processing module is used for obtaining the first production data, cleaning and deduplicating the first production data to obtain second production data; the first data analysis module is used for establishing a production prediction model based on the second production data to obtain a predicted production situation; the backend management module is used for receiving real-time production preset information; the second data analysis module is used for obtaining the real-time production preset information and obtaining production optimization suggestions; and the judgment module compares the predicted production situation with the production optimization suggestions to obtain a production optimization scheme.The application can effectively fuse the information of traditional handicraft and intelligent factories and improve production efficiency.

Description

Technical Field

[0001] This invention relates to the field of smart factory technology, and in particular to an information integration system and method for traditional handicrafts and smart factories. Background Technology

[0002] With the rapid development of the manufacturing industry and increasingly fierce market competition, traditional manual labor techniques are gradually revealing their limitations when facing the demands of large-scale, high-efficiency, and high-quality production. Traditional manual labor relies on manual operation, and the data entry, processing, and transmission processes are cumbersome and time-consuming, resulting in low efficiency and susceptibility to errors and omissions due to human factors, thus affecting the correctness of production decisions and the safety of product quality. Furthermore, traditional manual labor lacks real-time capability, failing to reflect changes on the production floor in an instant, limiting the rapid response capabilities of management. Meanwhile, smart factory technology, with its high efficiency, precision, and intelligence, has become an important direction for the transformation and upgrading of the manufacturing industry. Smart factories utilize advanced technologies such as the Internet of Things (IoT), big data, cloud computing, and artificial intelligence to achieve intelligent, automated, and digitalized production processes. However, the comprehensive promotion and application of smart factory technology still faces many challenges, such as high initial investment, high technical barriers, and issues related to data security and privacy protection. The comprehensive promotion and application of smart factory technology suffers from high costs and low efficiency. Currently, there is no efficient method for the information integration of traditional handicrafts and smart factories. Summary of the Invention

[0003] The purpose of this invention is to address the lack of efficient methods for integrating traditional handicrafts and smart factories in existing technologies. This invention provides a system and method for integrating the information technology of traditional handicrafts and smart factories, enabling effective integration of information technology in these two sectors and improving production efficiency.

[0004] To address the aforementioned technical problems, embodiments of the present invention provide an information integration system for traditional handicrafts and smart factories, comprising:

[0005] The data acquisition module is used to collect the initial production data from the handicraft production line.

[0006] The data processing module, connected to the data acquisition module, is used to acquire the first production data and clean and deduplicate the first production data to obtain the processed second production data.

[0007] The first data analysis module, connected to the data processing module, is used to acquire the second production data and establish a production prediction model based on the second production data in order to obtain a prediction of production conditions.

[0008] The backend management module is used to receive real-time production preset information;

[0009] The second data analysis module is connected to the backend management module and is used to obtain real-time production preset information. The second data analysis module analyzes and mines the real-time production preset information to obtain production optimization suggestions.

[0010] The judgment module, connected to the first data analysis module and the second data analysis module, is used to obtain the predicted production situation and production optimization suggestions. The judgment module compares the predicted production situation with the production optimization suggestions to obtain the production optimization plan. The judgment module is also connected to the backend management module to send the production optimization plan to the backend management module.

[0011] According to another specific embodiment of the present invention, the data acquisition module includes an RFID tag and an RFID reader. The RFID tag is set on the material to store first production data, which includes at least basic material information and production site information. The RFID reader is set at key deployment points of the manual production line according to the layout of the production line and the logistics path to read the first production data stored in the RFID tag and send the first production data to the data processing module.

[0012] According to another specific embodiment of the present invention, the production site information includes output data, working hours data, and quality data;

[0013] Real-time production preset information includes production plans, material requirements, and inventory status.

[0014] According to another specific embodiment of the present invention, the key deployment points of the manual production line include at least the entrance, exit, key process point, or quality inspection station of the manual production line.

[0015] According to another specific embodiment of the present invention, in the data processing module, the first production data is cleaned and deduplicated, wherein,

[0016] Cleaning includes: cleaning the first production data, identifying noisy data, outliers and missing values, removing noisy data and outliers and filling in missing values;

[0017] Deduplication includes: using hash tables or database indexing to check if there are duplicate data in the first production data after cleaning; if duplicate data is found, the duplicate data is removed.

[0018] According to another specific embodiment of the present invention, in the first data analysis module, a production forecasting model is established based on the second production data to obtain a predicted production situation, including:

[0019] For production data, time series analysis is used to establish a production forecasting model in order to obtain production trends.

[0020] For quality data, a classification algorithm is used to build a classification model in order to obtain the type and cause of quality problems;

[0021] For time data, regression analysis is used to establish an optimization model to obtain optimization suggestions for the production process.

[0022] According to another specific embodiment of the present invention, before establishing the production forecasting model, the second production data is further preprocessed, including normalization or standardization.

[0023] According to another specific embodiment of the present invention, the analysis methods used in the second data analysis module include statistical analysis, correlation analysis and / or regression analysis, and the mining methods used include classification, clustering or association rule mining.

[0024] According to another specific embodiment of the present invention, before the second data analysis module analyzes and mines the real-time production preset information, it further includes:

[0025] After receiving the real-time production preset information, the second data analysis module verifies the real-time production preset information.

[0026] After verification, the second data analysis module cleans and deduplicates the real-time production preset information.

[0027] According to another specific embodiment of the present invention, the back-end management module includes at least an MES system or an ERP system.

[0028] According to another specific embodiment of the present invention, a visualization module is further included, which is connected to the first data analysis module, and the predicted production situation is visualized through the visualization module.

[0029] According to another specific embodiment of the present invention, a monitoring module is further included for monitoring the data interaction between the second data analysis module and the backend management module.

[0030] According to another specific embodiment of the present invention, an evaluation module is also included, which evaluates the optimized production process by determining evaluation indicators.

[0031] According to another specific embodiment of the present invention, the evaluation indicators include at least production efficiency, product quality and production cost.

[0032] The embodiments of the present invention also provide a method for the information integration of traditional handicrafts and smart factories, including:

[0033] The data collection step involves collecting the first production data from the handicraft production line.

[0034] The data processing steps include acquiring the first production data, cleaning and deduplicating the first production data to obtain the processed second production data.

[0035] The first data analysis step involves acquiring the processed second production data and establishing a production forecasting model based on the second production data to predict production conditions.

[0036] Backend management steps include retrieving real-time production preset information;

[0037] The second data analysis step involves acquiring real-time production preset information, analyzing and mining this information to obtain production optimization suggestions.

[0038] The judgment step involves obtaining the predicted production situation and production optimization suggestions, comparing the predicted production situation with the production optimization suggestions, and thus obtaining a production optimization plan.

[0039] Compared with the prior art, the present invention has the following beneficial effects:

[0040] In this application, the data acquisition module collects first production data from the manual production line and transmits it to the data processing module. The data processing module cleans and deduplicates the first production data. Data cleaning ensures accuracy and reliability, and deduplication prevents duplicate calculations or misleading conclusions in subsequent analysis. The data processing module transmits the processed second production data to the first data analysis module. The first data analysis module builds a production prediction model based on the second production data to predict future production conditions, providing support for production decisions. The second data analysis module interacts with the backend management module, analyzing and mining the real-time production preset information sent by the backend management module to obtain production optimization suggestions. The judgment module compares the production prediction obtained by the first data analysis module with the production optimization suggestions obtained by the second data analysis module to obtain a production optimization plan, which is then sent to the backend management module. Based on the received production optimization plan, the backend management module assists managers in optimizing the production process.

[0041] The information fusion system for traditional handicrafts and smart factories provided by this invention enables real-time collection and processing of production data from handicrafts, thereby improving the accuracy and usefulness of the data. Furthermore, the production data from handicrafts can interact with the data from the backend smart factory, providing a scientific basis and data support for production optimization, reducing decision-making risks, and improving production efficiency and quality. Attached Figure Description

[0042] Figure 1This diagram illustrates a structural block diagram of an information integration system for traditional handicrafts and smart factories provided by an embodiment of the present invention.

[0043] Figure 2 The flowchart illustrates an embodiment of the present invention of a method for the information integration of traditional handicrafts and smart factories. Detailed Implementation

[0044] The following specific embodiments illustrate the implementation of the present invention. Those skilled in the art can easily understand other advantages and effects of the present invention from the content disclosed in this specification. Although the description of the present invention is presented in conjunction with preferred embodiments, this does not mean that the features of the invention are limited to these embodiments. On the contrary, the purpose of describing the invention in conjunction with embodiments is to cover other options or modifications that may be derived based on the claims of the present invention. To provide a deep understanding of the invention, many specific details will be included in the following description. The invention may also be implemented without using these details. Furthermore, to avoid confusion or obscuring the focus of the invention, some specific details will be omitted in the description. It should be noted that, unless otherwise specified, the embodiments and features in the embodiments of the present invention can be combined with each other.

[0045] It should be noted that in this specification, similar reference numerals and letters in the following figures indicate similar items. Therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures.

[0046] The terms “first”, “second”, etc., are used only to distinguish descriptions and should not be interpreted as indicating or implying relative importance.

[0047] In the description of this embodiment, it should also be noted that, unless otherwise explicitly specified and limited, the terms "set up," "connected," and "linked" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; and they can refer to the internal connection of two components. Those skilled in the art can understand the specific meaning of the above terms in this embodiment based on the specific circumstances.

[0048] To make the objectives, technical solutions, and advantages of the present invention clearer, the embodiments of the present invention will be described in further detail below with reference to the accompanying drawings.

[0049] like Figure 1 As shown, Figure 1 This is a structural block diagram of an information integration system for traditional handicrafts and smart factories provided in an embodiment of the present invention. In this embodiment, the information integration system for traditional handicrafts and smart factories includes:

[0050] Data acquisition module 11 is used to collect the first production data on the handicraft production line;

[0051] The data processing module 12 is connected to the data acquisition module 11 and is used to acquire the first production data and clean and deduplicate the first production data to obtain the processed second production data.

[0052] The first data analysis module 13 is connected to the data processing module 12 and is used to acquire the second production data and establish a production prediction model based on the second production data in order to obtain the predicted production situation.

[0053] Backend management module 14 is used to receive real-time production preset information;

[0054] The second data analysis module 15 is connected to the backend management module 14 and is used to obtain real-time production preset information. The second data analysis module 15 analyzes and mines the real-time production preset information to obtain production optimization suggestions.

[0055] The judgment module 16 is connected to the first data analysis module 13 and the second data analysis module 15. It is used to obtain the predicted production situation and production optimization suggestions. The judgment module 16 compares the predicted production situation with the production optimization suggestions to obtain the production optimization plan. The judgment module 16 is connected to the backend management module 14 to send the production optimization plan to the backend management module 14.

[0056] Using this technical solution, the data acquisition module 11 in this application can collect the first production data from the manual production line and transmit it to the data processing module 12. The data processing module 12 can clean and deduplicate the first production data. By cleaning the data, the accuracy and reliability of the data are ensured. By deduplicate processing of the cleaned data, duplicate calculations or misleading conclusions can be avoided in subsequent analysis. The data processing module 12 transmits the processed second production data to the first data analysis module 13. The first data analysis module 13 establishes a production prediction model based on the second production data to predict future production conditions and provide support for production decisions. The second data analysis module 15 interacts with the backend management module 14. The second data analysis module 15 analyzes and mines the real-time production preset information sent by the backend management module 14 to obtain production optimization suggestions. The judgment module 16 compares the production prediction obtained by the first data analysis module 13 with the production optimization suggestions obtained by the second data analysis module 15 to obtain a production optimization plan and sends the production optimization plan to the backend management module 14. The backend management module 14 can assist managers in optimizing the production process based on the received production optimization plan.

[0057] The information fusion system for traditional handicrafts and smart factories provided by this invention enables real-time collection and processing of production data from handicrafts, thereby improving the accuracy and usefulness of the data. Furthermore, the production data from handicrafts can interact with the data from the backend smart factory, providing a scientific basis and data support for production optimization, reducing decision-making risks, and improving production efficiency and quality.

[0058] Specifically, the data acquisition module 11 collects first production data from the production site. This data, after cleaning and deduplication, yields second production data, which is used to build a production prediction model. The production prediction model uses this second production data to predict future production conditions, such as production efficiency and quality trends. The backend management module 14 sends real-time production preset information to the second data analysis module 15. The second data analysis module 15 analyzes and mines this information to identify bottlenecks and optimization points in the production process, obtaining corresponding production optimization suggestions. The judgment module 16, based on the predicted production conditions and optimization suggestions, compares them to obtain a production optimization plan, which is then sent to the backend management module 14 for management personnel to use and reference. For example, if the first data analysis module 13 predicts a potential decrease in efficiency for a certain process based on the production prediction model, and the second data analysis module 15 also shows a similar trend in its optimization suggestions, the judgment module 16, after comparing the two results, generates a production optimization plan that includes adjusting the sequence of the process and optimizing resource allocation. Thus, through the data acquisition module 11, data processing module 12, first data analysis module 13, backend management module 14, second data analysis module 15, and judgment module 16, the entire system collects data from the production site, predicts future production conditions through the production prediction model, and optimizes and adjusts the production process based on real-time production preset information. This not only solves the drawbacks of traditional information entry, but also improves the level of intelligence by enabling information interaction between the backend management module 14, the second data analysis module 15, and the judgment module 16.

[0059] Furthermore, the production optimization suggestions obtained through the second data analysis module 15 can also be used to verify the production prediction model established by the first data analysis module 13, to evaluate the accuracy of the model, and to update or adjust the model when necessary.

[0060] In this embodiment, the data processing module 12, the first data analysis module 13, and the second data analysis module 15 are integrated on a cloud platform, and a database is built on the cloud platform to realize the storage, processing, analysis, and visualization of data.

[0061] Furthermore, the data acquisition module 11 includes RFID tags and RFID readers. The RFID tags are set on the materials to store the first production data, which includes at least basic material information and production site information. The RFID readers are set at key deployment points of the manual production line according to the layout of the production line and the logistics path to read the first production data stored in the RFID tags and send the first production data to the data processing module 12.

[0062] This technological solution enables the real-time collection of production data from the handicraft industry, providing data support for production management and decision-making.

[0063] In this embodiment, materials include raw materials, semi-finished products, and finished products. Basic material information includes the material's name, model, batch number, production date, processing status, and quality inspection results. By acquiring the initial production data stored in the RFID tags through an RFID reader, production efficiency and material tracking and quality traceability capabilities are improved.

[0064] Specifically, based on the specific needs of the manual production line (including production process, material types, information requirements, etc.), appropriate RFID tags are selected to store initial production data. In addition, each RFID tag stores a unique identification code for accurate tracking and management of the initial production data. The identification code is designed according to encoding rules and is unique, readable, and scalable. The identification code can be stored and recorded in a database for subsequent management and retrieval. More specifically, when selecting RFID tags, key considerations include the tag's durability (such as waterproofing, dustproofing, and resistance to high and low temperatures), anti-interference capabilities, information storage capacity, read / write distance, and cost, as well as preventing information loss or errors when writing the encoded information into the RFID tag.

[0065] RFID tags are affixed to raw materials, semi-finished products, or finished products. Qualified RFID readers are deployed at key points according to production needs to ensure that the information in the RFID tags can be effectively read on the manual production line. The cloud platform connects to the RFID readers, uploading the collected initial production data. Upon receiving the initial production data, the cloud platform stores it in its database for centralized storage and management of the data from the data acquisition module 11, providing a data foundation for subsequent data processing.

[0066] First, based on the specific environment of the production line (such as humidity, temperature, dust, etc.), tags with corresponding durability (such as waterproof, dustproof, and high / low temperature resistance) are selected to ensure stable operation in harsh environments. Second, the tags' anti-interference capabilities are considered to avoid information interference problems that may occur in the complex electromagnetic environment of the production site. Third, based on the complexity and update frequency of production information, tags with sufficient information storage capacity and appropriate read / write distance are selected to meet production management needs. Finally, considering the company's cost budget, cost-effective tags are selected to maximize economic benefits. After deployment, RFID readers are used to test and verify the RFID tags to ensure that the tags can be read normally and that the stored information is accurate. If problems are found, the RFID tags need to be adjusted or replaced in a timely manner. This ensures the stability of the tags and the accuracy of the data, reducing the risk of system failures and data errors. In this embodiment, an RFID reader is used to write the encoded information into the RFID tag. Through wireless communication between the RFID reader and the RFID tag, the encoded first production data and identification code are written into the storage unit of the RFID tag. To ensure the stability and accuracy of the writing process, a suitable and compatible communication protocol and verification mechanism are required to ensure that the data is not interfered with or tampered with during transmission and writing, and to avoid data loss or errors due to poor communication.

[0067] For example, key deployment points of a manual production line include at least the entrance, exit, critical process point, or quality inspection station of the manual production line.

[0068] This technical solution involves deploying RFID readers at key points in the production process of traditional manual production lines to ensure real-time and accurate collection of production data.

[0069] Specifically, when deploying RFID readers, factors such as tag reading and writing distance, production line layout, and logistics flow direction should be considered, and RFID readers should be deployed at corresponding key deployment points.

[0070] When determining the installation location of RFID readers, the layout of the production line and the logistics path should be considered to ensure that the first production data of RFID tags during the logistics flow can be captured to the maximum extent. This ensures that the first production data in the RFID tags can be read stably, accurately and efficiently, which helps to reduce information omissions and errors in the production process.

[0071] In this embodiment, the RFID reader is installed in the following locations:

[0072] Production line entrance: Install a reader at the starting point where materials enter the production line to record the time and batch information of materials entering the assembly line.

[0073] Critical process points: Install readers at the entrance and exit of each critical process point (such as cutting station and sewing station) to record the dwell time and processing status of materials at each process point.

[0074] Quality Inspection Station: Readers are installed at the entrance and exit of the quality inspection station to record the quality inspection results and inspection time of the materials.

[0075] Production line exit: Install a reader at the end of the production line where materials leave to record the time and quantity of finished products leaving the production line.

[0076] By adopting the above technical solution, and through analyzing the specific needs of the manual production line and selecting RFID tags, it is ensured that RFID technology can meet the actual needs of the manual production line, avoiding blind application of technology and waste of resources. Secondly, by assigning unique identification codes to RFID tags and reading the first production data through RFID readers, a foundation is provided for automatic information collection, accurate tracking and management, improving the accuracy and reliability of the data.

[0077] For example, in this embodiment, the data processing module 12 cleans and deduplicates the first production data, wherein...

[0078] Cleaning includes: cleaning the first production data, identifying noisy data, outliers and missing values, removing noisy data and outliers and filling in missing values;

[0079] Deduplication includes: using hash tables or database indexing to check if there are duplicate data in the first production data after cleaning; if duplicate data is found, the duplicate data is removed.

[0080] This technical solution cleans and deduplicates the first production data to obtain the processed second production data. This ensures the accuracy, stability, and scalability of the data while removing useless information, thus guaranteeing the quality of the production data and providing a reliable data source for subsequent data analysis.

[0081] It is worth noting that in other embodiments, other suitable cleaning and deduplication methods can be selected based on the data type or the expected output results.

[0082] Specifically, during the cleaning process, statistical methods, such as standard deviation and interquartile range, can be used to identify noisy data, outliers, and missing values ​​in the first production data. Alternatively, machine learning algorithms, such as Isolation Forest, LOF (Local Outlier Factor), and One-Class SVM, can be used to identify noisy data, outliers, and missing values.

[0083] Optionally, for abnormal data, further analysis can be conducted to identify the cause of the anomaly and take corresponding measures to address it.

[0084] When missing values ​​are identified, appropriate filling methods can be selected based on the data type and business logic, such as mean filling, median filling, mode filling, or prediction filling. Alternatively, records containing a large number of missing values ​​can be deleted.

[0085] When performing deduplication, hash tables and database indexes can be used to quickly check the uniqueness of data. In another embodiment, for complex data structures, rules can be defined to determine whether duplicate data exists. For example, the DISTINCT keyword or GROUP BY statement in SQL can be used for deduplication; alternatively, sets (such as Python's set) or specialized data processing libraries (such as pandas' drop_duplicates() method) can be used programmatically for deduplication.

[0086] For example, in this embodiment, the first data analysis module 13 establishes a production prediction model based on the second production data to obtain a predicted production situation, including:

[0087] For production data, time series analysis is used to establish a production forecasting model in order to obtain production trends.

[0088] For quality data, a classification algorithm is used to build a classification model in order to obtain the type and cause of quality problems;

[0089] For time data, regression analysis is used to establish an optimization model to obtain optimization suggestions for the production process.

[0090] Based on the second production data, the aforementioned machine learning methods are used to model and predict future production conditions, such as predicting inventory demand and identifying potential production bottlenecks. In turn, the predicted production conditions are used to formulate production plans, optimize resource allocation, and improve production efficiency and resource utilization.

[0091] It is worth noting that the machine learning methods used for modeling include, but are not limited to, regression analysis, time series analysis, and classification algorithms. For example, for production data (such as data on changes in production volume over time), time series analysis can be used for trend analysis. By calculating indicators such as moving averages and seasonal indices, the trend of production changes and seasonal fluctuations can be clearly seen. In other embodiments, algorithms such as neural networks and random forests can also be included. For example, ARIMA models and exponential smoothing can be used to predict future production conditions to obtain predictive production information. When using these methods, the appropriate algorithm can be selected for modeling based on whether the business problem is classification, regression, or clustering, as well as the data type, processing objective, expected output results, system resources and limitations, and algorithm performance.

[0092] For example, before building the production forecasting model, the second production data is preprocessed, including normalization or standardization.

[0093] This technical approach can eliminate the dimensional differences between different data sets, improving the convergence speed and performance of the model. Specifically, the preprocessed second production data can be divided into training and testing sets for training and evaluating the production prediction model.

[0094] Furthermore, in the second data analysis module 15, the analytical methods employed include statistical analysis, correlation analysis, and / or regression analysis, and the mining methods employed include classification, clustering, or association rule mining.

[0095] By employing the above technical solutions, statistical, correlation, or regression analyses are used to analyze real-time production preset information to summarize the basic characteristics of the data, reveal the inherent connections and patterns between data points, and utilize data mining methods to extract valuable information and patterns from large amounts of data, such as production trends, anomaly detection, and efficiency optimization points. This identifies potential problems in the production process, such as bottlenecks, resource waste, and inefficient operations, as well as potential optimization points, such as opportunities to improve production efficiency, reduce costs, and improve quality, providing a basis for production optimization and decision-making. Through the above analysis and data mining methods, further production optimization suggestions are proposed. These suggestions may include adjusting the process sequence, optimizing resource allocation, and improving process parameters, aiming to improve production efficiency, reduce production costs, and enhance product quality.

[0096] Specifically, in this embodiment, the analysis methods include statistical analysis, correlation analysis, and regression analysis, wherein...

[0097] Statistical analysis was used to calculate the real-time production preset information to obtain descriptive statistics;

[0098] Correlation analysis and regression analysis are used to analyze real-time production preset information to obtain the relationships between variables.

[0099] In this embodiment, descriptive statistics include the mean, median, mode, and standard deviation. Descriptive statistics can be used to summarize the characteristics of the data and understand its central tendency and dispersion.

[0100] After calculating descriptive statistics, they can be plotted into histograms, box plots, and other charts to visually represent the distribution of the data.

[0101] Correlation analysis and regression analysis are used to analyze real-time production preset information to obtain the relationships between variables, including: using correlation coefficients and regression coefficients, such as Pearson correlation coefficient and Spearman rank correlation coefficient, to quantify the strength and direction of the linear relationship between two or more variables.

[0102] In correlation and regression analysis, variables refer to the attributes of different data. For example, variables can be production volume, production cost, product quality, and productivity. Correlation coefficients or regression coefficients are used to measure the relationship between production volume and production cost, or between product quality and productivity, thereby revealing the inherent connections between the data.

[0103] After quantifying the variables, charts such as scatter plots can be used to display the variables, obtain the correlation between variables, and identify potential data associations.

[0104] The following algorithms can be used when performing data mining:

[0105] Classification: Real-time production preset information is divided into different categories or groups, such as normal production, abnormal production, etc. Classification can be performed using algorithms such as decision trees, random forests, and support vector machines.

[0106] Clustering: Grouping similar real-time production information into a single group to discover the inherent structure and patterns of the data. Commonly used clustering algorithms include K-means and hierarchical clustering.

[0107] Association rule mining method: Identify the correlation between different items (such as different processes and different equipment) in real-time production preset information; use Apriori algorithm or FP-Growth algorithm to mine frequent itemsets and association rules to discover potential patterns and regularities in the production process.

[0108] Furthermore, before the second data analysis module 15 analyzes and mines the real-time production preset information, it also includes:

[0109] After receiving the real-time production preset information, the second data analysis module 15 verifies the real-time production preset information.

[0110] After verification, the second data analysis module 15 cleans and deduplicates the real-time production preset information.

[0111] For example, the backend management module 14 includes at least an MES system or an ERP system.

[0112] Specifically, the second data analysis module 15 verifies the production preset information sent by the backend management module 14, including checking the data format, range, and consistency to ensure that no data is lost or omitted during transmission, and that the data content meets the expected format, range, and logical requirements. Data verification significantly improves the accuracy and reliability of the data received by the second data analysis module 15, laying a solid foundation for subsequent data processing and analysis. This helps reduce decision-making errors and production problems caused by data errors, thereby improving overall production efficiency and quality.

[0113] Once abnormal data or errors are detected during the verification process, the system immediately triggers an exception handling mechanism. This mechanism includes recording detailed information about the abnormal data (such as source, time, and content), and classifying, labeling, or isolating this data according to preset rules to prevent further disruption to normal production processes. This provides the system with the ability to handle unexpected situations. When abnormal data or errors are received, the system can respond quickly and take appropriate measures to prevent these data from adversely affecting normal production processes. This not only helps maintain the stability and continuity of production processes but also reduces potential risks and losses caused by data errors.

[0114] After verification, cleaning and deduplication algorithms are used to identify and remove noisy, outlier, or duplicate data, thereby obtaining processed production data. Data cleaning and deduplication further ensure the quality of the data used for analysis.

[0115] Furthermore, it also includes a monitoring module, which is connected to the second data analysis module 15 and the backend management module 14, and is used to monitor the data interaction between the second data analysis module 15 and the backend management module 14.

[0116] By monitoring the data interaction between the second data analysis module 15 and the backend management module 14 in real time, the accuracy and timeliness of the data are ensured.

[0117] Furthermore, it also includes an evaluation module, which is connected to the backend management module 14. The evaluation module evaluates the optimized production process by determining evaluation indicators.

[0118] For example, evaluation metrics may include at least production efficiency, product quality, and production cost.

[0119] Specifically, after production is carried out based on the optimization suggestions, the evaluation module evaluates the effect of the optimized production process based on the real-time production data collected by the backend management module 14, providing an important basis for enterprises to continuously improve their production processes.

[0120] Furthermore, it also includes a visualization module, which is connected to the first data analysis module 13, and uses the visualization module to visualize the predicted production data.

[0121] Optionally, in this embodiment, the predicted production status can be presented to managers through an intuitive web page. For example, commonly used charts, including line charts, bar charts, pie charts, scatter plots, heat maps, etc., can be used to intuitively display the predicted production data through visual elements such as color, size, and shape, enabling managers to grasp the production status at a glance and improve their work efficiency and decision-making ability.

[0122] Optionally, a second data analysis module 15 and a visualization module are provided to present production optimization suggestions to managers through the visualization module.

[0123] According to the information integration system for traditional handicrafts and smart factories provided by this invention, RFID tags are set on materials in the handicraft production line, and RFID readers are set up at key deployment points. The RFID readers read the RFID tags to obtain the first production data of the handicraft production line. The RFID readers are connected to the data processing module 12 to send the first production data to the data processing module 12. The data processing module 12 stores the first production data in a database and cleans and deduplicates the first production data to improve its accuracy and usefulness. The processed second production data is then sent to the first data analysis module 13. The first data analysis module 13 establishes a production prediction model based on the second production data to obtain predicted production conditions, which provide a basis for production optimization. The visualization module presents the predicted production conditions visually through a web interface, enabling managers to quickly and intuitively grasp the production status and provide support for decision-making. The second data analysis module 15 interacts with the backend management module 14. Based on the real-time production information sent by the backend management module 14, the second data analysis module 15 cleans and deduplicates the real-time production information to obtain processed production data. By analyzing and mining the processed production data, production optimization suggestions are obtained. The judgment module 16 is connected to both the first data analysis module 13 and the second data analysis module 15 to obtain predicted production conditions and production optimization suggestions. The judgment module 16 compares the predicted production conditions with the production optimization suggestions to obtain a production optimization plan for management personnel to reference. The judgment module 16 sends the production optimization plan to the backend management module 14, allowing management personnel to optimize the production process according to the plan, thereby improving production efficiency and product quality while reducing production costs.

[0124] This invention achieves real-time and accurate collection of production data in handicrafts through RFID tags and RFID readers, avoiding the tedious, time-consuming, and error-prone data entry problems of traditional manual operations. This immediacy ensures efficient operation of the production process while reducing the negative impact of human factors on production decisions and product quality. The data processing and data analysis modules enable intelligent analysis of production data, which is then displayed to managers through an intuitive and user-friendly web interface. This real-time visualization not only enhances management's control over the production site but also promotes rapid response and accurate decision-making, optimizing production resource allocation and process arrangement. The judgment module connects to the first and second data analysis modules, and the second data analysis module interfaces with the backend management module, breaking down information silos and promoting data interconnection. This not only improves data consistency and accuracy but also enables multiple aspects such as production planning, inventory management, and quality control to collaborate based on the same set of real-time data, improving overall operational efficiency. It combines the flexibility of traditional manual operations with the advanced technology of smart factories. This invention provides a more economical and feasible path for the transformation and upgrading of the manufacturing industry. It does not require the complete abandonment of existing handicraft production lines, but rather uses information technology to carry out intelligent transformation, thereby reducing initial investment and technical barriers, accelerating the popularization and application of smart factory technology, helping enterprises achieve refined management and intelligent production, improving production efficiency and product quality, and enhancing market competitiveness.

[0125] like Figure 2 As shown, Figure 2 This is a flowchart illustrating a method for integrating traditional handicrafts and smart factories using information technology, provided in an embodiment of the present invention. In this embodiment, the method for integrating traditional handicrafts and smart factories using information technology includes the following steps:

[0126] Data acquisition step S21: Collect the first production data from the handicraft production line;

[0127] Data processing step S22: Obtain first production data, and clean and deduplicate the first production data to obtain processed second production data;

[0128] The first data analysis step S23 involves acquiring the processed second production data and establishing a production prediction model based on the second production data to obtain a predicted production situation.

[0129] Backend management step S24: Retrieve real-time production preset information;

[0130] The second data analysis step S25 involves obtaining real-time production preset information, analyzing and mining the real-time production preset information to obtain production optimization suggestions.

[0131] In step S26, the predicted production situation and production optimization suggestions are obtained. The predicted production situation and production optimization suggestions are compared to obtain a production optimization plan.

[0132] While the present invention has been illustrated and described with reference to certain preferred embodiments, those skilled in the art should understand that the above description is a further detailed explanation of the invention in conjunction with specific embodiments, and should not be construed as limiting the specific implementation of the invention to these descriptions. Various changes in form and detail can be made by those skilled in the art, including several simple deductions or substitutions, without departing from the spirit and scope of the invention.

Claims

1. An information integration system for traditional handicrafts and smart factories, characterized in that, include: The data acquisition module is used to collect the initial production data from the handicraft production line. A data processing module, connected to the data acquisition module, is used to acquire the first production data and clean and deduplicate the first production data to obtain the processed second production data. The first data analysis module is connected to the data processing module and is used to acquire the second production data and establish a production prediction model based on the second production data to obtain a predicted production situation. The backend management module is used to receive real-time production preset information; The second data analysis module is connected to the backend management module and is used to obtain the real-time production preset information. The second data analysis module analyzes and mines the real-time production preset information to obtain production optimization suggestions. The judgment module, connected to the first data analysis module and the second data analysis module, is used to obtain the predicted production situation and the production optimization suggestions. The judgment module compares the predicted production situation with the production optimization suggestions to obtain a production optimization plan. The judgment module is also connected to the backend management module to send the production optimization plan to the backend management module.

2. The system according to claim 1, characterized in that, The data acquisition module includes an RFID tag and an RFID reader / writer. The RFID tag is set on the material and is used to store the first production data. The first production data includes at least basic material information and production site information. The RFID reader is set up at key deployment points on the manual production line according to the layout of the production line and the logistics path, so as to read the first production data stored in the RFID tag and send the first production data to the data processing module.

3. The system according to claim 2, characterized in that, The production site information includes output data, working hours data, and quality data; The real-time production preset information includes production plans, material requirements, and inventory status.

4. The system according to claim 2, characterized in that, The key deployment points of the manual production line include at least the entrance, exit, key process points, or quality inspection stations of the manual production line.

5. The system according to claim 1, characterized in that, In the data processing module, the first production data is cleaned and deduplicated, wherein... The cleaning process includes: cleaning the first production data, identifying noisy data, outliers, and missing values, removing the noisy data and outliers, and filling in the missing values; The deduplication process includes: using a hash table or database indexing method to check whether there is duplicate data in the cleaned first production data; if duplicate data is found, the duplicate data is removed.

6. The system according to claim 3, characterized in that, In the first data analysis module, a production forecasting model is established based on the second production data to obtain predicted production conditions, including: For the aforementioned production data, a time series analysis method is used to establish the production forecasting model in order to obtain the production trend; For the aforementioned quality data, a classification model is established using a classification algorithm to obtain the type and cause of the quality problem; For the aforementioned work time data, regression analysis was used to establish an optimization model to obtain optimization suggestions for the production process.

7. The system according to claim 6, characterized in that, Before establishing the production forecasting model, the second production data is preprocessed, including normalization or standardization.

8. The system according to claim 1, characterized in that, The analysis methods used in the second data analysis module include statistical analysis, correlation analysis and / or regression analysis, and the mining methods include classification, clustering or association rule mining.

9. The system according to claim 1, characterized in that, Before the second data analysis module analyzes and mines the real-time production preset information, it also includes: After receiving the real-time production preset information, the second data analysis module verifies the real-time production preset information; After verification, the second data analysis module cleans and deduplicates the real-time production preset information.

10. The system according to claim 1, characterized in that, The backend management module includes at least an MES system or an ERP system.

11. The system according to claim 1, characterized in that, It also includes a visualization module, which is connected to the first data analysis module, and the visualization module is used to visualize the predicted production situation.

12. The system according to claim 1, characterized in that, It also includes a monitoring module for monitoring the data interaction between the second data analysis module and the backend management module.

13. The system according to claim 1, characterized in that, It also includes an evaluation module, which evaluates the optimized production process by determining evaluation indicators.

14. The system according to claim 13, characterized in that, Evaluation indicators should include at least production efficiency, product quality, and production cost.

15. A method for integrating traditional handicrafts and smart factories through information technology, characterized in that, include: The data collection step involves collecting the first production data from the handicraft production line. The data processing steps involve acquiring the first production data and cleaning and deduplicating it to obtain the processed second production data. The first data analysis step involves acquiring the processed second production data and establishing a production forecasting model based on the second production data to obtain a forecast of production conditions. Backend management steps include retrieving real-time production preset information; The second data analysis step involves acquiring the real-time production preset information, analyzing and mining the real-time production preset information to obtain production optimization suggestions. The judgment step involves obtaining the predicted production situation and the production optimization suggestions, comparing the predicted production situation with the production optimization suggestions, and thus obtaining a production optimization plan.

Images