Intelligent management method and system for textile warehouse based on popular element information monitoring

Abstract

The present invention relates to the field of warehouse management technology, and in particular to a textile warehouse intelligent management method and system based on popular element information monitoring. The method comprises the following steps: obtaining textile transaction monitoring data of an e-commerce platform and performing popular element trend analysis, thereby obtaining textile popular trend data; obtaining textile warehouse management data and performing textile inventory cycle analysis, thereby obtaining warehouse textile inventory cycle data; performing demand textile inventory association according to textile popular trend data, thereby obtaining warehouse demand textile inventory cycle data; performing popular textile fit evaluation according to warehouse demand textile inventory cycle data, thereby obtaining popular textile fit data; performing inventory structure optimization based on popular textile fit data, thereby obtaining textile warehouse optimization management data. The present invention can improve the overall efficiency of warehouse management.

Description

Technical Field

[0001] The present invention relates to the technical field of warehouse management, and in particular to an intelligent management method and system for a textile warehouse based on popular element information monitoring. Background Art

[0002] With the rapid development of information technology and the widespread application of artificial intelligence, the production and management methods of the textile industry are also constantly improving. In recent years, the textile industry has gradually developed in the direction of intelligence and automation in order to improve management efficiency, reduce labor costs and improve the accuracy of inventory management. However, traditional inventory management often relies on manual operations such as regular inventory counting, registration, and recording, and lacks a real-time monitoring mechanism. This method is prone to lag in inventory data, a high probability of errors, and cannot reflect the actual inventory situation of the warehouse in a timely manner. In addition, when handling a large number of materials and products, warehouse managers often need to invest a lot of time and energy in inventory counting, classification and verification, resulting in high labor costs. The product design and production cycle of the textile industry is long, and it is often necessary to predict market trends in advance to adjust production plans and inventory structures in a timely manner. However, the manual experience relied on by traditional methods is often difficult to effectively capture the rapidly changing market trends, resulting in a disconnect between production plans and market demand, affecting sales and inventory turnover efficiency. Summary of the invention

[0003] Based on this, it is necessary for the present invention to provide a textile warehouse intelligent management method and system based on popular element information monitoring to solve at least one of the above technical problems.

[0004] To achieve the above purpose, a textile warehouse intelligent management method based on popular element information monitoring includes the following steps:

[0005] Step S1: acquiring textile product transaction monitoring data from an e-commerce platform, and integrating popular elements of traded textile products according to the textile product transaction monitoring data from the e-commerce platform, thereby obtaining popular element data of traded textile products; performing trend analysis of popular elements based on the popular element data of traded textile products, thereby obtaining popular trend data of textile products;

[0006] Step S2: acquiring textile warehouse management data, and locating textile products based on the textile warehouse management data, thereby obtaining warehouse textile product location data; performing textile product inventory cycle analysis based on the warehouse textile product location data, thereby obtaining warehouse textile product inventory cycle data;

[0007] Step S3: forecasting the demand for popular textile products according to the textile product fashion trend data, thereby obtaining the forecast data for the demand for popular textile products; associating the warehouse textile product inventory cycle data with the demand textile product inventory based on the forecast data for the demand for popular textile products, thereby obtaining the warehouse demand textile product inventory cycle data;

[0008] Step S4: performing a textile warehouse inventory simulation according to the warehouse demand textile product inventory cycle data, thereby obtaining textile warehouse inventory simulation data, and performing a popular textile product fitness evaluation based on the textile warehouse inventory simulation data, thereby obtaining the popular textile product fitness data;

[0009] Step S5: Optimize the inventory cycle of warehouse textile products based on the popular textile product fit data to obtain optimized inventory cycle data of popular textile products; optimize the textile warehouse inventory structure of textile warehouse management data according to the optimized inventory cycle data of popular textile products to obtain optimized management data of textile warehouses, and transmit it to the textile warehouse management platform to perform the inventory structure optimization task.

[0010] The present invention can timely capture market trends and provide data support for production and inventory management by acquiring textile product transaction monitoring data from an e-commerce platform and integrating popular elements. Trend analysis helps predict future market demand, making production plans more accurate and avoiding fabric backlogs or out-of-stock phenomena. By acquiring textile warehouse management data and locating textile products, accurate tracking of inventory can be achieved, human errors can be reduced, and warehouse management efficiency can be improved. Inventory cycle analysis enables warehouse managers to better control inventory status, rationally allocate resources, and optimize storage space and costs. Optimizing the inventory cycle based on demand forecast data helps adjust the inventory structure and ensure that popular textile products in the warehouse match market demand, thereby improving inventory turnover. Through inventory simulation and fitness evaluation, the adaptation of different popular textile products to the existing inventory structure can be predicted, providing a strong basis for inventory adjustment. The ultimate goal of inventory cycle optimization is to improve the overall efficiency of warehouse management, and through data-driven inventory structure optimization, reduce excess inventory, reduce the risk of unsalable goods, improve the response speed and flexibility of the overall supply chain, and ultimately achieve the intelligent and automated transformation of textile industry inventory management.

[0011] Optionally, step S1 specifically includes:

[0012] Step S11: acquiring textile product transaction monitoring data on the e-commerce platform, and performing data preprocessing on the textile product transaction monitoring data on the e-commerce platform, thereby obtaining textile product transaction monitoring data to be processed;

[0013] Step S12: extracting features of traded textile products according to the textile product transaction monitoring data to be processed, thereby obtaining fabric data of traded textile products and color data of traded textile products;

[0014] Step S13: analyzing the popular elements of textile fabrics based on the traded textile fabric data, thereby obtaining the popular elements data of textile fabrics;

[0015] Step S14: integrating the color data of traded textile products with the popular elements of traded textile products according to the popular elements data of textile product fabrics, thereby obtaining the popular elements data of traded textile products;

[0016] Step S15: Performing a trend analysis of popular elements based on the popular element data of traded textile products, thereby obtaining the popular trend data of textile products.

[0017] The present invention can effectively screen out relevant and valuable data by obtaining the textile transaction monitoring data of the e-commerce platform and performing data preprocessing, and ensure that the subsequent analysis is based on accurate and clean data. After this preprocessing, the textile transaction data to be processed can exclude noise and redundant information, thereby improving the accuracy and reliability of data analysis. Then, the key information of fabrics and colors can be extracted from the traded textile products through feature extraction, which not only provides a data basis for subsequent analysis, but also helps to deeply understand consumers' purchasing preferences and market trends. In the process of analyzing the popular elements of fabrics, the popular fabric trends in the current market can be accurately identified, providing intuitive market guidance for designers and brand owners, and enhancing the market competitiveness of products. Associating and integrating popular elements with color data can not only reveal the interactive relationship between fabrics and colors in the market, but also further help predict possible consumer demand and popular trends in the future market. Based on the trend analysis of popular elements, enterprises can adjust production and sales strategies in advance, optimize inventory management, and improve market response speed, thereby gaining an advantage in the fierce market competition. The beneficial effects of these steps are mainly reflected in accurately grasping market demand, enhancing product innovation capabilities, improving operational efficiency and accurately predicting future trends, thereby bringing sustained competitive advantages and business value to e-commerce platforms and their related industries.

[0018] Optionally, step S13 is specifically:

[0019] Step S131: performing textile fabric transaction volume statistics based on the textile fabric transaction data, thereby obtaining high-frequency transaction fabric data and low-frequency transaction fabric data;

[0020] Step S132: performing fabric transaction periodicity identification on the high-frequency transaction fabric data, thereby obtaining transaction periodic fabric data and non-transaction periodic fabric data;

[0021] Step S133: seasonal fabric element integration is performed according to the transaction periodic fabric data, thereby obtaining seasonal fabric element data;

[0022] Step S134: integrating non-periodic fabric elements according to the low-frequency transaction fabric data and the non-transaction periodic fabric data, thereby obtaining non-periodic fabric element data;

[0023] Step S135: performing fabric element popular time series merging on seasonal fabric element data and non-periodic fabric element data, thereby obtaining fabric popular element data for textile products.

[0024] The present invention performs textile fabric transaction volume statistics based on textile fabric transaction data, which can effectively separate high-frequency transaction and low-frequency transaction data in the fabric market, thereby providing a clear data basis for subsequent analysis. This process can not only reveal which fabrics are actively traded in the market, but also reflect which fabrics are sparsely traded, providing accurate market demand trends for fabric suppliers and manufacturers. This data differentiation makes the focus of subsequent analysis more precise, which helps to better predict market changes in actual operations. The periodic identification of high-frequency trading fabric data makes it possible to mine regular trading patterns from frequently traded fabrics. This identification helps to find fabrics that are active in a specific period, thereby achieving accurate seasonality or trend prediction. For example, some fabrics may have a surge in trading volume during specific seasons, festivals or promotional activities. By identifying these periodic characteristics, fabric manufacturers can adjust production plans according to market demand and reduce inventory risks. The step of integrating seasonal fabric elements can further closely combine the fabric trading pattern with seasonal characteristics, and extract the most popular fabric features in each season or specific period. This integration not only helps to reveal which fabric elements are most popular in the market in a certain season, but also provides guidance on fabric design for designers and manufacturers, promoting timely product updates and market adaptability. Through this process, the seasonal demand for fabrics can be accurately grasped, and companies can launch products that match market demand at the right time. On the other hand, the integration of non-periodic fabric elements can effectively identify the characteristics of fabrics that are not affected by seasonal or cyclical factors. These non-periodic fabric elements often have certain uniqueness and personalized needs. Although they are less frequently traded in the market, once these elements are identified, companies can grasp potential market segments. The effective implementation of this process can provide fabric designers with more innovative inspiration and promote the development of market diversification. The popular time series merging of seasonal and non-periodic fabric element data provides more comprehensive data support for fabric design and production. By merging different types of fabric elements and conducting time series analysis, more accurate predictions of popular trends can be obtained, helping fabric companies adjust product lines and marketing strategies.

[0025] Optionally, step S134 is specifically:

[0026] According to the seasonal fabric element data, seasonal fabrics are eliminated from the low-frequency transaction fabric data, so as to obtain the low-frequency transaction fabric data to be analyzed;

[0027] Integrate the low-frequency transaction fabric data to be analyzed into fabric elements, so as to obtain low-frequency transaction fabric element data;

[0028] Perform fabric element integration on non-trading periodic fabric data, thereby obtaining non-trading periodic fabric element data;

[0029] Fabric element similarity calculation is performed based on low-frequency transaction fabric element data and non-transaction periodic fabric element data, thereby obtaining fabric element similarity data;

[0030] Based on the fabric element similarity data, the non-transaction periodic fabric data is subjected to high similarity fabric element elimination to obtain non-periodic fabric element data.

[0031] The present invention seasonally removes low-frequency transaction fabric data through seasonal fabric element data, effectively removes the noise caused by seasonal fluctuations, and makes subsequent analysis more focused on long-term trends and non-seasonal changes, thereby improving the stability and accuracy of the data. Fabric element integration can unify the various fabric characteristics in low-frequency transaction data into a standardized fabric element data set, which not only simplifies the data structure, but also makes it easier to identify the key features of the fabric in subsequent analysis, thereby improving the calculation efficiency of the model. For the integration of non-trading periodic fabric data, it is helpful to eliminate the interference of periodic fluctuations, extract fabric elements that are not related to periodicity in the data, and thus obtain a smoother and more stable fabric characteristic set, so that the model can better reflect the intrinsic characteristics of the fabric. The calculation of fabric element similarity can reveal which fabrics are closer in characteristics by quantifying the similarity between different fabric elements. This process provides a scientific basis for the design of subsequent classification, clustering and recommendation systems. Eliminating high-similarity fabric elements based on fabric element similarity data can avoid repeated calculations or redundant analysis, reduce unnecessary data volume, and make the final data set more streamlined and efficient.

[0032] Optionally, step S14 is specifically:

[0033] Step S141: performing color combination frequency statistics on the traded textile product color data, thereby obtaining high-frequency traded textile product color combination data;

[0034] Step S142: classifying the high-frequency traded textile product color combination data by textile product size, thereby obtaining high-frequency traded large-size textile product color combination data and high-frequency traded small-size textile product color combination data;

[0035] Step S143: performing large-size textile element matching frequency calculation on textile fabric popular element data and high-frequency large-size textile color combination data, thereby obtaining large-size textile element-color combination matching frequency data, and performing large-size textile element integration according to the large-size textile element-color combination matching frequency data, thereby obtaining large-size textile element data;

[0036] Step S144: performing small-size textile element matching frequency calculation on textile fabric popular element data and high-frequency trading small-size textile color combination data, thereby obtaining small-size textile element-color combination matching frequency data, and performing small-size textile element integration according to the small-size textile element-color combination matching frequency data, thereby obtaining small-size textile element data;

[0037] Step S145: performing intersection screening of popular textile product elements according to the large-size textile product element data and the small-size textile product element data, so as to obtain popular textile product element data for transactions.

[0038] The present invention can effectively identify and extract the popular color combinations and fabric elements of fabrics in the market by systematically conducting a comprehensive analysis on the color, size and popular element data of traded fabrics, thereby providing an important reference basis for designers, manufacturers and market decision makers. In the whole process, firstly, by counting the frequency of fabric colors, it is possible to reveal which color combinations are more frequent in market transactions, thereby providing color matching trend data for subsequent design and production. Next, combined with the size classification of fabrics, the market demand can be further subdivided, and the unique color combination frequency of large-sized and small-sized fabrics can be identified, which provides a more accurate direction for customized production. Further, the frequency calculation of element matching is performed for large-sized and small-sized fabrics respectively, which can extract the popular fabric elements and color matching trends of fabrics of different sizes, and then provide a scientific element integration method for the design of fabrics, so that the design can keep up with market demand. Through the final intersection screening, the popular elements of large-sized and small-sized fabrics are intersected, which can accurately capture the generally applicable and popular fabric elements in the market, which not only helps to improve the market adaptability and acceptance of the product, but also provides strong support for the market positioning and promotion strategy of the brand. In general, this method can achieve accurate prediction and optimization of textile product trends by systematically analyzing textile product colors and elements from multiple dimensions, promote product design innovation, enhance market competitiveness, and provide scientific decision-making support for the weaving industry.

[0039] Optionally, step S2 specifically includes:

[0040] Step S21: obtaining textile warehouse management data, and dividing the textile warehouse management data into time windows, thereby obtaining textile warehouse time window management data;

[0041] Step S22: extracting RFID read-write records of the textile warehouse time window management data, thereby obtaining RFID read-write data of the textile warehouse window;

[0042] Step S23: performing textile product RFID tag identification according to the textile warehouse window RFID reading and writing data, thereby obtaining textile product window RFID tag data;

[0043] Step S24: locating the warehouse textile products based on the textile product window RFID tag data, thereby obtaining warehouse textile product positioning data;

[0044] Step S25: Performing inventory cycle analysis of textile products according to the warehouse textile product location data, thereby obtaining warehouse textile product inventory cycle data.

[0045] The present invention can provide a clear time frame for subsequent management and analysis by acquiring and dividing the time window of textile warehouse management data, thereby ensuring the timeliness and relevance of the data, so that the management can dynamically adjust and optimize warehouse resources in different time periods. Next, by extracting the RFID read-write records, it is possible to accurately track each item in the warehouse, significantly improve the automation and accuracy of item management, and avoid the errors and lags caused by manual records. Further, by identifying the RFID tags of textile products, it is not only possible to improve the efficiency of warehouse management, but also to accurately identify the location, status and category of each item, providing data support for subsequent logistics management, inventory counting and other work. Combining the RFID tag data to locate the location of textile products in the warehouse, real-time tracking and dynamic updating can be achieved, ensuring that the positioning of each textile product is accurate and correct, and providing efficient support for warehouse management. Finally, by periodically analyzing the inventory data, it is possible to deeply understand the storage cycle of each textile product, help managers analyze key indicators such as inventory turnover rate and liquidity of items, thereby optimizing the inventory structure, reducing unnecessary inventory backlogs and capital occupation, improving the operating efficiency of the warehouse, and reducing costs. The entire process, from data acquisition to analysis, is progressive, which comprehensively improves the automation, accuracy and efficiency of warehouse management, making the operation of the entire textile warehouse more intelligent and data-based, and has high practical significance and application value.

[0046] Optionally, step S25 is specifically:

[0047] Step S251: performing textile product positioning time distribution statistics according to the textile product positioning data in the warehouse, thereby obtaining textile product positioning time distribution data;

[0048] Step S252: classifying the textile product positioning time distribution data according to the positioning time, thereby obtaining short-term textile product positioning data and long-term textile product positioning data;

[0049] Step S253: Calculating the short-term positioning cycle of the textile product tag according to the short-term textile product positioning data, thereby obtaining the textile product scheduling cycle data;

[0050] Step S254: Calculating the long-term positioning period of the textile product tag according to the long-term textile product positioning data, thereby obtaining textile product storage period data;

[0051] Step S255: performing periodic time series merging of the textile product scheduling cycle data and the textile product storage cycle data, thereby obtaining warehouse textile product inventory cycle data.

[0052] The present invention can clearly distinguish short-term and long-term textile product positioning data by statistics and classification of positioning time, thereby providing reliable data support for the calculation of subsequent scheduling and storage cycles. Short-term positioning data can help warehouse managers accurately calculate the scheduling cycle of textile products, making the circulation of textile products in the warehouse more efficient, reducing inventory backlogs, and ensuring that textile products can be dispatched to the required places in time. Long-term positioning data is helpful to calculate the storage cycle of textile products, and by accurately grasping the storage time of each textile product, it avoids the space waste and obsolete inventory problems that may be caused by long-term storage. Combined with the calculation results of short-term and long-term cycles, the scheduling cycle and storage cycle are finally merged in time sequence, which helps to comprehensively optimize the inventory management of the warehouse and improve the overall operational efficiency. This process not only improves the resource utilization rate of the warehouse, but also reduces the logistics cost to a certain extent, and makes the warehouse management more refined, and can more accurately predict and respond to inventory requirements under different situations. At the same time, reasonable cycle planning can also extend the shelf life of textile products, reduce the risk of inventory obsolescence, and improve the responsiveness and adaptability of the storage system.

[0053] Optionally, step S3 specifically includes:

[0054] Step S31: constructing a textile product popular element prediction model according to textile product popular trend data, and predicting textile product popular elements according to the textile product popular element prediction model, thereby obtaining textile product predicted popular element data;

[0055] Step S32: Associating the textile product transaction monitoring data with the textile product predicted popular element data to be processed, thereby obtaining textile product transaction data associated with the predicted popular element;

[0056] Step S33: forecasting the demand of associated popular textile products based on the predicted transaction data of textile products associated with popular elements, thereby obtaining forecast data of the demand of popular textile products;

[0057] Step S34: performing statistics on high-demand textile products according to the popular textile product demand forecast data, thereby obtaining high-demand popular textile product data;

[0058] Step S35: Associating the warehouse textile product inventory cycle data with the high-demand popular textile product inventory based on the high-demand popular textile product data, thereby obtaining the warehouse demand textile product inventory cycle data.

[0059] The popular element prediction model of textile products constructed by the present invention based on the popular trend data can accurately predict the popular textile elements in the future, help manufacturers and designers understand the market dynamics in advance, and thus adjust product design and production strategies in time. The prediction model of popular elements is further combined with textile transaction data, so that the prediction of market demand not only takes into account the changes in fashion trends, but also reflects the actual consumer transaction behavior in real time, and realizes the effective integration of popular elements and transaction data. This prediction association provides more timely and targeted market feedback information. Further based on the demand forecast of these associated data, it is possible to accurately provide the demand for textile products in the future for each link in the supply chain, thereby optimizing the production and inventory management strategy. The prediction ability at this stage can especially effectively reduce the risk of inventory backlog and out-of-stock, ensure the efficient operation of the supply chain, and avoid waste of resources and capital retention. By screening and counting high-demand textile products on the demand forecast data, it is further clarified which products may become the "hot-selling products" in the market in the future, thereby providing a more scientific and data-driven basis for production planning, logistics scheduling and inventory management. Combined with the inventory cycle data of the warehouse, the inventory association analysis of high-demand popular textile products can accurately evaluate the matching degree between existing inventory and market demand. The effective implementation of this link will help improve the efficiency of inventory management, avoid overproduction or excess inventory, and ensure the smooth connection of all links in the supply chain. Especially in the rapidly changing fashion industry, it can help companies respond to market changes more flexibly and quickly adjust production and distribution plans.

[0060] Optionally, step S4 specifically includes:

[0061] Step S41: performing textile warehouse inventory simulation according to warehouse demand textile product inventory cycle data and textile product forecast popular element data, thereby obtaining textile warehouse inventory simulation data;

[0062] Step S42: Calculate the inventory scheduling cycle of popular textile products on the textile warehouse inventory simulation data, so as to obtain the inventory scheduling cycle data of popular textile products;

[0063] Step S43: extracting the predicted popular cycle of textile elements from the predicted popular element data of textile products, thereby obtaining the predicted popular cycle data of textile elements;

[0064] Step S44: Calculating the scheduling cycle error of the popular textile product inventory scheduling cycle data and the textile product element prediction popular cycle data, thereby obtaining the inventory textile product scheduling cycle error data;

[0065] Step S45: Perform a fitness evaluation of popular textile products based on the inventory textile product scheduling cycle error data, thereby obtaining fitness data of popular textile products.

[0066] The present invention can more accurately predict future inventory demand, optimize inventory management, and reduce the risk of excess or shortage of inventory by performing inventory simulation according to warehouse demand and textile inventory cycle data. At the same time, by combining popular element data to predict textile products, market trends can be grasped in a timely manner, product matching can be improved, and outdated styles can be avoided. Further scheduling cycle calculation ensures the efficiency of inventory scheduling, making inventory turnover more flexible and reducing storage costs. By extracting the prediction cycle of popular elements, the popular change trends of various textile products can be accurately grasped, providing data support for procurement and production plans, and helping to improve the response speed of the supply chain. Calculating the scheduling cycle error can accurately identify the shortcomings in inventory management, further improve the accuracy and efficiency of decision-making, and avoid unnecessary deviations in inventory management. The final fitness evaluation helps to judge the degree of fit between popular textile products and market demand and optimize the product portfolio.

[0067] Optionally, the present invention further provides a textile warehouse intelligent management system based on popular element information monitoring, which is used to execute the textile warehouse intelligent management method based on popular element information monitoring as described above, and the textile warehouse intelligent management system based on popular element information monitoring includes:

[0068] The popular element trend analysis module is used to obtain the textile product transaction monitoring data of the e-commerce platform, and integrate the popular elements of the traded textile products according to the textile product transaction monitoring data of the e-commerce platform, so as to obtain the popular element data of the traded textile products; based on the popular element data of the traded textile products, the popular element trend analysis is performed to obtain the textile product popular trend data;

[0069] The textile product inventory cycle analysis module is used to obtain textile warehouse management data, and locate textile products based on the textile warehouse management data, thereby obtaining warehouse textile product location data; perform textile product inventory cycle analysis based on the warehouse textile product location data, thereby obtaining warehouse textile product inventory cycle data;

[0070] The textile product demand forecasting module is used to forecast the demand of popular textile products according to the textile product fashion trend data, so as to obtain the forecast data of the demand of popular textile products; based on the forecast data of the demand of popular textile products, the warehouse textile product inventory cycle data is associated with the demand textile product inventory, so as to obtain the warehouse demand textile product inventory cycle data;

[0071] A textile product fitness evaluation module is used to simulate the textile warehouse inventory according to the warehouse demand textile product inventory cycle data, thereby obtaining textile warehouse inventory simulation data, and to evaluate the fitness of popular textile products based on the textile warehouse inventory simulation data, thereby obtaining the fitness data of popular textile products;

[0072] The inventory cycle optimization module is used to optimize the inventory cycle of warehouse textile products based on the popular textile product suitability data, so as to obtain optimized popular textile product inventory cycle data; optimize the textile warehouse inventory structure of the textile warehouse management data according to the optimized popular textile product inventory cycle data, so as to obtain the textile warehouse optimized management data, and transmit it to the textile warehouse management platform to perform the inventory structure optimization task.

[0073] The intelligent management system for textile warehouses based on popular element information monitoring of the present invention can implement any one of the intelligent management methods for textile warehouses based on popular element information monitoring of the present invention, and is used to combine the medium for operation and signal transmission between various modules to complete the intelligent management method for textile warehouses based on popular element information monitoring. The internal modules of the system cooperate with each other to improve the overall efficiency of warehouse management. BRIEF DESCRIPTION OF THE DRAWINGS

[0074] Other features, objects and advantages of the present invention will become more apparent from the detailed description of non-limiting embodiments thereof made with reference to the following drawings:

[0075] Figure 1 It is a schematic diagram of the steps of the intelligent management method of textile warehouses based on popular element information monitoring of the present invention;

[0076] Figure 2 Detailed step flow diagram of step S1 in the present invention;

[0077] Figure 3 Detailed step flow diagram of step S2 in the present invention;

[0078] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0079] The technical method of the present invention is described clearly and completely below in conjunction with the accompanying drawings. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by technicians in this field without creative work are within the scope of protection of the present invention.

[0080] In addition, the accompanying drawings are only schematic illustrations of the present invention and are not necessarily drawn to scale. The same reference numerals in the figures represent the same or similar parts, and their repeated description will be omitted. Some of the block diagrams shown in the accompanying drawings are functional entities and do not necessarily correspond to physically or logically independent entities. The functional entities can be implemented in software form, or implemented in one or more hardware modules or integrated circuits, or implemented in different networks and / or processor methods and / or microcontroller methods.

[0081] It should be understood that, although the terms "first", "second", etc. may be used herein to describe various units, these units should not be limited by these terms. These terms are used only to distinguish one unit from another unit. For example, without departing from the scope of the exemplary embodiments, the first unit may be referred to as the second unit, and similarly the second unit may be referred to as the first unit. The term "and / or" used herein includes any and all combinations of one or more of the listed associated items.

[0082] To achieve this, please refer to Figures 1 to 3 The present invention provides a textile warehouse intelligent management method based on popular element information monitoring, the method comprising the following steps:

[0083] Step S1: acquiring textile product transaction monitoring data from an e-commerce platform, and integrating popular elements of traded textile products according to the textile product transaction monitoring data from the e-commerce platform, thereby obtaining popular element data of traded textile products; performing trend analysis of popular elements based on the popular element data of traded textile products, thereby obtaining popular trend data of textile products;

[0084] In this embodiment, by acquiring the textile transaction monitoring data of the e-commerce platform in real time (for example, obtaining sales data, customer preferences, browsing data, etc. through the API interface), analyzing the popular elements of different textile products (such as style, color, material, etc.), the popular elements that dominate the transaction can be extracted. These data are integrated through methods such as cluster analysis and frequency statistics to form a popular element data set. Subsequently, based on the historical transaction data, the trend of popular elements is predicted using methods such as time series analysis or regression analysis to obtain textile product popular trend data. For example, using Python's pandas and sklearn libraries, using machine learning algorithms to model historical data, predict which elements will become hot-selling trends in the next few months. For example, using the API interface of the e-commerce platform to regularly pull transaction data (such as Tmall, JD.com and other platforms), and using Python to process these data, the trend elements of popular textile products are analyzed through clustering algorithms.

[0085] Step S2: acquiring textile warehouse management data, and locating textile products based on the textile warehouse management data, thereby obtaining warehouse textile product location data; performing textile product inventory cycle analysis based on the warehouse textile product location data, thereby obtaining warehouse textile product inventory cycle data;

[0086] In this embodiment, after obtaining textile warehouse management data (including inventory quantity, storage location, inventory turnover speed, etc.) through the textile warehouse management platform, the textile products in the warehouse can be accurately located through a location algorithm (such as a location-based clustering algorithm) to generate warehouse textile product location data. Then, by analyzing the inventory cycle of each textile product (for example, using inventory turnover rate or ABC classification method), the storage time and turnover cycle of each textile product can be calculated. At this time, data mining technology is used to aggregate and analyze the inventory cycle data to determine which textile products have too long storage cycles and which need to be updated faster. The SQL database can be used to extract inventory data from the warehouse management system to calculate the average inventory cycle of each type of textile product.

[0087] Step S3: forecasting the demand for popular textile products according to the textile product fashion trend data, thereby obtaining the forecast data for the demand for popular textile products; associating the warehouse textile product inventory cycle data with the demand textile product inventory based on the forecast data for the demand for popular textile products, thereby obtaining the warehouse demand textile product inventory cycle data;

[0088] In this embodiment, based on the popular trend data, the future demand for popular textile products is predicted by a demand forecasting algorithm (such as ARIMA, LSTM and other time series forecasting models). Then, the predicted demand is associated with the inventory cycle data of textile products in the warehouse to identify textile products with possible inventory shortages or surpluses, and form demand textile product inventory association data. Specifically, the demand forecast results can be merged with the inventory data, and data association rules (such as the Apriori algorithm) can be used to find out which textile products need to increase production or replenish inventory to ensure that they match market demand.

[0089] Step S4: performing a textile warehouse inventory simulation according to the warehouse demand textile product inventory cycle data, thereby obtaining textile warehouse inventory simulation data, and performing a popular textile product fitness evaluation based on the textile warehouse inventory simulation data, thereby obtaining the popular textile product fitness data;

[0090] In this embodiment, inventory simulation (such as Monte Carlo simulation) is performed based on the inventory cycle data of warehouse demand textile products, and the influence of variables such as different inventory strategies, supply and demand changes, and transportation time are simulated to predict the changing trend of inventory levels. At the same time, based on the fitness evaluation of popular textile products (for example, using a multi-dimensional evaluation method to score the matching degree of popular elements and inventory textile products), it is evaluated which textile products are more suitable for current market demand and the inventory structure that needs to be adjusted is determined. Specifically, the NumPy library in Python can be used for simulation, combined with the fitness evaluation model, and the fitness of popular textile products can be evaluated through machine learning or artificial rules.

[0091] Step S5: Optimize the inventory cycle of warehouse textile products based on the popular textile product fit data to obtain optimized inventory cycle data of popular textile products; optimize the textile warehouse inventory structure of textile warehouse management data according to the optimized inventory cycle data of popular textile products to obtain optimized management data of textile warehouses, and transmit it to the textile warehouse management platform to perform the inventory structure optimization task.

[0092] In this embodiment, the inventory cycle of textile products in the warehouse is optimized based on an optimization algorithm (such as a genetic algorithm, a particle swarm optimization, etc.). Based on the fitness data of popular textile products, the inventory cycle of textile products in the warehouse is optimized. For example, for textile products with low fitness, their inventory cycle can be reduced, and inventory efficiency can be improved by accelerating turnover; while for textile products with high fitness, a longer inventory cycle can be maintained to avoid the additional costs caused by frequent replenishment. Then, according to the optimized inventory cycle data, the inventory structure of the warehouse is further optimized. For example, by reasonably allocating the inventory ratio of high-demand popular textile products and low-demand textile products, the warehouse space allocation is adjusted, and finally a more in line with the changes in market demand inventory management structure is formed. These optimization strategies will be transmitted and executed in real time through the textile warehouse management platform to ensure that the optimization tasks are implemented efficiently. The optimized data can be entered in the warehouse management platform (such as SAP or Oracle WMS system) to trigger inventory adjustment or structure improvement tasks to optimize warehouse space utilization and inventory turnover efficiency.

[0093] Optionally, step S1 specifically includes:

[0094] Step S11: acquiring textile product transaction monitoring data on the e-commerce platform, and performing data preprocessing on the textile product transaction monitoring data on the e-commerce platform, thereby obtaining textile product transaction monitoring data to be processed;

[0095] In this embodiment, the textile product data of user transactions is obtained through the API interface of the e-commerce platform, and the data includes product ID, category, sales volume, transaction time, price, user evaluation, etc. Data preprocessing includes removing missing values, outlier detection, format standardization (such as unifying the date format), and sentiment analysis or keyword extraction of unstructured data (such as user evaluation text) to ensure the accuracy and consistency of the data.

[0096] Step S12: extracting features of traded textile products according to the textile product transaction monitoring data to be processed, thereby obtaining fabric data of traded textile products and color data of traded textile products;

[0097] In this embodiment, the main features of textile products, such as fabric type (such as cotton, linen, wool, etc.) and color (such as red, blue, gray, etc.) are extracted from the textile product transaction data to be processed. These features are extracted by text mining technology in product descriptions, or by image recognition technology (such as convolutional neural network CNN) to extract color and texture information from product images.

[0098] Step S13: analyzing the popular elements of textile fabrics based on the traded textile fabric data, thereby obtaining the popular elements data of textile fabrics;

[0099] In this embodiment, by counting the frequency of occurrence of fabric categories in historical transaction data and combining it with industry trend reports, we analyze which fabrics (such as nylon, wool, silk, etc.) are more popular in a certain period of time. We further use data mining methods to discover changes in fabric demand related to seasons, holidays, etc.

[0100] Step S14: integrating the color data of traded textile products with the popular elements of traded textile products according to the popular elements data of textile product fabrics, thereby obtaining the popular elements data of traded textile products;

[0101] In this embodiment, based on the fashion trends of textile fabrics, the corresponding color data (for example, according to RGB values ​​or Pantone color card values) are matched to analyze which fabric types are usually used with specific colors. When integrating data, a multidimensional correlation analysis method is used to find the strong correlation between fabrics and colors.

[0102] Step S15: Performing a trend analysis of popular elements based on the popular element data of traded textile products, thereby obtaining the popular trend data of textile products.

[0103] In this embodiment, the popular trends in the next few months are predicted by combining the popular element data of fabrics and colors with time series analysis technology (such as ARIMA model or LSTM neural network). For example, using LSTM neural network and based on the transaction data and popular element data of the past five years, it is predicted which fabrics (such as "knitted" or "silk") and which colors (such as "light pink" or "dark green") will become popular in the next year. This analysis result can guide brand design and marketing decisions.

[0104] Optionally, step S13 is specifically:

[0105] Step S131: performing textile fabric transaction volume statistics based on the textile fabric transaction data, thereby obtaining high-frequency transaction fabric data and low-frequency transaction fabric data;

[0106] In this embodiment, the data of fabrics traded for textile products are summarized and counted, and the fabrics are divided into high-frequency traded fabrics and low-frequency traded fabrics according to the trading frequency. For example, fabric A has a high trading frequency in a week, while fabric B has a low trading frequency. By quantifying the trading volume of each fabric in different time periods, it is possible to identify which fabrics are high-frequency traded fabrics and which fabrics are low-frequency traded fabrics. High-frequency traded fabrics are usually fabrics with high seasonal or daily demand, such as cotton and denim, while low-frequency traded fabrics are new fabrics or fabrics for special purposes, such as wool and silk. Statistics can be performed by time dimension (for example, by month or by week) to obtain the trading volume change trend of different fabrics.

[0107] Step S132: performing fabric transaction periodicity identification on the high-frequency transaction fabric data, thereby obtaining transaction periodic fabric data and non-transaction periodic fabric data;

[0108] In this embodiment, in the high-frequency trading fabric data, fabrics with obvious periodic characteristics are identified by time series analysis methods (such as seasonal decomposition methods). For example, through time series analysis, it is found that the trading data of fabric A shows obvious fluctuations throughout the year, reflecting the changes in seasonal demand, while the trading data of fabric B has no obvious periodicity and only shows random fluctuations, so fabric A is a periodic fabric. For example, the trading volume of some fabrics such as cotton fabrics increases significantly in spring and summer, while winter fabrics such as wool are frequently traded in autumn and winter. These fabric data with periodic fluctuations can further extract trading periodic data and separate non-periodic data that does not conform to the periodic fluctuation pattern.

[0109] Step S133: seasonal fabric element integration is performed according to the transaction periodic fabric data, thereby obtaining seasonal fabric element data;

[0110] In this embodiment, seasonal elements are integrated for transaction periodic fabric data. For example, woolen, cashmere and other fabrics may have a large transaction volume in winter, while cotton, linen, silk and other fabrics with good air permeability may be preferred in summer. The material and function (such as moisture absorption and air permeability) of these fabrics are regarded as seasonal elements. These elements are classified and sorted to form seasonal fabric element data. These data may include seasonal characteristics such as fabric material (cotton, linen), function (such as moisture absorption and air permeability). According to the characteristics of climate, season and consumer demand, seasonal integration of transaction periodic fabric data can be performed to focus on popular fabrics in a certain season or under specific climatic conditions.

[0111] Step S134: integrating non-periodic fabric elements according to the low-frequency transaction fabric data and the non-transaction periodic fabric data, thereby obtaining non-periodic fabric element data;

[0112] In this embodiment, when integrating the non-periodic fabric elements of low-frequency trading fabric data and non-trading periodic fabric data, it is first necessary to identify the non-periodic characteristics of these fabrics. For example, some special fabrics such as environmentally friendly materials or high-tech fabrics, although the trading volume is low, are not affected by seasonal changes or cycles. When integrating the elements of such fabric data, cluster analysis can be used to identify the key features of the materials and material properties of these fabrics and classify them as non-periodic elements. These non-periodic elements often show sudden growth in market demand.

[0113] Step S135: performing fabric element popular time series merging on seasonal fabric element data and non-periodic fabric element data, thereby obtaining fabric popular element data for textile products.

[0114] In this embodiment, when seasonal fabric element data and non-periodic fabric element data are merged in fabric element popular time series, a popular time series model can be established to predict and merge the popular time of seasonal and non-periodic fabric elements according to the popular trends of historical data. For example, seasonal fabric A is popular in spring and autumn, while non-periodic fabric B tends to be stable throughout the year but gradually becomes a normalized popular fabric. Through this popular time series merging, a more comprehensive and accurate set of fabric popular element data can be generated. By merging seasonal and non-periodic fabric element data, a basis can be provided for future trend prediction.

[0115] Optionally, step S134 is specifically:

[0116] According to the seasonal fabric element data, seasonal fabrics are eliminated from the low-frequency transaction fabric data, so as to obtain the low-frequency transaction fabric data to be analyzed;

[0117] In this embodiment, low-frequency transaction fabric data often contains seasonal elements, such as woolen fabrics in winter and cotton and linen fabrics in summer. First, seasonal fabric elements related to seasonality are screened out by analyzing the properties of seasonal fabrics (such as material, material characteristics, etc.), and these seasonal fabrics are removed from the low-frequency transaction data. Specifically, seasonal fabric elements in low-frequency transaction data can be marked and removed through data matching technology (such as similarity calculation, classification algorithm, etc.) based on the typical properties of seasonal fabrics (such as thin and light materials commonly used in summer or heavy and heavy fabrics commonly used in winter). For example, some customers will buy winter fabrics at a low price in summer in order to stock up on winter fabrics in advance.

[0118] Integrate the low-frequency transaction fabric data to be analyzed into fabric elements, so as to obtain low-frequency transaction fabric element data;

[0119] In this embodiment, the low-frequency traded fabric data to be analyzed is integrated into fabric elements to obtain low-frequency traded fabric element data. This is done by extracting element information (such as fiber type, dyeing method, fabric structure, etc.) of each fabric and performing standardization processing, so that the element data of each fabric can be compared and analyzed under a unified standard. For example, the main components of each fabric, such as cotton, silk, nylon, etc., are disassembled and presented in a unified coding method to form a data set.

[0120] Perform fabric element integration on non-trading periodic fabric data, thereby obtaining non-trading periodic fabric element data;

[0121] In this embodiment, the non-trading periodic fabric data generally refers to fabrics that are traded outside of a specific period (such as the Spring Festival, National Day and other holidays). In this process, the non-trading periodic fabric data is first extracted separately, and then integrated according to the constituent elements of the fabric (such as fiber type, surface treatment, etc.). The specific method can be to classify the fabrics into different categories according to the similarity of their elements through cluster analysis. The data processed in this way helps to eliminate redundant information in non-periodic fabrics and provide a clear data framework for subsequent processing.

[0122] Fabric element similarity calculation is performed based on low-frequency transaction fabric element data and non-transaction periodic fabric element data, thereby obtaining fabric element similarity data;

[0123] In this embodiment, based on the low-frequency transaction fabric element data to be analyzed and the non-transaction periodic fabric element data, the similarity between fabric elements is calculated to help determine which fabric elements belong to the high similarity category. During implementation, algorithms such as cosine similarity and Euclidean distance can be used to compare elements of different fabrics. For example, for two fabrics A and B, first extract their fiber type, color, and weaving method and other element data, calculate their distance or similarity in the feature space, and obtain a similarity score. In this way, the potential relationship between fabrics can be identified, providing a basis for further elimination steps.

[0124] Based on the fabric element similarity data, the non-transaction periodic fabric data is subjected to high similarity fabric element elimination to obtain non-periodic fabric element data.

[0125] In this embodiment, based on the fabric element similarity data, fabric data with high similarity in elements are screened out, and non-trading periodic fabrics are eliminated. For example, if the similarity of two fabrics in terms of fiber type, weaving method, density, etc. reaches a certain preset threshold (such as 90%), they are considered to be high-similarity fabrics. According to the set threshold, high-similarity fabric element data is automatically eliminated from non-trading periodic fabric data, and the remaining fabric data is considered to be non-periodic fabric element data, thereby eliminating fabric data with high transaction volume in a specific period from non-trading periodic fabric data, providing more accurate fabric features for subsequent analysis.

[0126] Optionally, step S14 is specifically:

[0127] Step S141: performing color combination frequency statistics on the traded textile product color data, thereby obtaining high-frequency traded textile product color combination data;

[0128] In this embodiment, the color data of traded textile products is analyzed, and the goal is to obtain the color combination patterns of various textile products by frequency statistics of color combinations of various textile products in the market. In specific implementation, data mining technology can be used to identify the frequency of occurrence of different color combinations by analyzing historical transaction data. For example, if the frequency of occurrence of textile products in the combination of blue and white is high in a certain trading cycle, the combination can be identified as a "high frequency" combination, thereby facilitating subsequent analysis. Technical implementation can use the Pandas library in the Python language to process and count the color data and output the frequency distribution of color combinations.

[0129] Step S142: classifying the high-frequency traded textile product color combination data by textile product size, thereby obtaining high-frequency traded large-size textile product color combination data and high-frequency traded small-size textile product color combination data;

[0130] In this embodiment, after obtaining the color combination frequency data, the next step is to classify the textile products according to their sizes. First, the traded textile products are classified according to their sizes, and the color combination data of "large size" and "small size" textile products are screened out respectively. Specifically, a size standard can be set, for example, "large size" refers to textile products with a size greater than a certain threshold (such as 90cm×90cm), while "small size" refers to textile products with a size less than the threshold. Technically, the textile product data can be conditionally filtered by size information to obtain color combination data sets of large size and small size textile products.

[0131] Step S143: performing large-size textile element matching frequency calculation on textile fabric popular element data and high-frequency large-size textile color combination data, thereby obtaining large-size textile element-color combination matching frequency data, and performing large-size textile element integration according to the large-size textile element-color combination matching frequency data, thereby obtaining large-size textile element data;

[0132] In this embodiment, the frequency of element matching of large-sized textile products is calculated by combining the color combination data of large-sized textile products and the data of popular fabric elements. When implementing, it is first necessary to obtain the popular elements of the fabric (such as material, material characteristics, etc.), and then calculate the matching frequency of each element and color by matching with the color combination of large-sized textile products. For example, if the frequency of a certain material and the blue color combination of large-sized textile products is high, it can be concluded that the matching combination is a popular combination. In this way, the frequency data of fabric element-color combination matching of large-sized textile products can be obtained.

[0133] Step S144: performing small-size textile element matching frequency calculation on textile fabric popular element data and high-frequency trading small-size textile color combination data, thereby obtaining small-size textile element-color combination matching frequency data, and performing small-size textile element integration according to the small-size textile element-color combination matching frequency data, thereby obtaining small-size textile element data;

[0134] In this embodiment, the frequency of element matching of small-sized textile products is calculated by combining the color combination data of small-sized textile products and the data of popular fabric elements. When implementing, it is first necessary to obtain the popular elements of the fabric (such as material, material characteristics, etc.), and then calculate the matching frequency of each element and color by matching with the color combination of small-sized textile products. For example, if the frequency of a certain material and the blue color combination of small-sized textile products is high, it can be concluded that the matching combination is a popular combination. In this way, the frequency data of fabric element-color combination matching of small-sized textile products can be obtained.

[0135] Step S145: performing intersection screening of popular textile product elements according to the large-size textile product element data and the small-size textile product element data, so as to obtain popular textile product element data for transactions.

[0136] In this embodiment, after obtaining the popular element data of large-sized and small-sized textile products, the intersection screening of elements is performed to find the common popular elements between the two. The popular elements existing in both large-sized and small-sized textile products are identified and integrated. For example, if a certain combination of fabric elements and color elements is common in both large-sized textile products and small-sized textile products, the combination can be determined as a popular element, and the popular element data of traded textile products finally obtained is the common popular elements of textile products of the two sizes.

[0137] Optionally, step S2 specifically includes:

[0138] Step S21: obtaining textile warehouse management data, and dividing the textile warehouse management data into time windows, thereby obtaining textile warehouse time window management data;

[0139] In this embodiment, the inventory data of all textiles in the warehouse is obtained in real time through the Internet of Things (IoT) sensors and the warehouse management system (WMS), including the entry time, exit time, quantity, category and other information of the goods. By setting a time window (such as daily, weekly or monthly) to divide the data, it can help managers analyze the operation efficiency of the warehouse by time dimension. For example, within a one-month time window, the inventory turnover rate and storage time of each fabric can be analyzed, thereby providing data support for optimizing inventory management.

[0140] Step S22: extracting RFID read-write records of the textile warehouse time window management data, thereby obtaining RFID read-write data of the textile warehouse window;

[0141] In this embodiment, in each time window, the fabrics in the warehouse are attached with RFID tags, and the RFID tags of the fabrics in the warehouse are scanned by the RFID reader to obtain all the related read and write records. These records include the specific time of each entry and exit of the warehouse, the ID, quantity and location of the item, etc. By reading these RFID data, the flow of each fabric can be accurately tracked, helping to accurately grasp the status of each textile in the warehouse.

[0142] Step S23: performing textile product RFID tag identification according to the textile warehouse window RFID reading and writing data, thereby obtaining textile product window RFID tag data;

[0143] In this embodiment, by connecting with the ERP system or WMS system, the specific label information of the fabric is identified according to the RFID read and write data. A unique identifier (such as fabric type, production batch, color, size, etc.) is stored on the RFID tag of each fabric, and the RFID tag is automatically scanned to accurately identify the information of each fabric reserved in the RFID tag. For example, a scanning path can scan all the tags in the warehouse in sequence, and quickly match the detailed information of the fabric according to the scanned ID.

[0144] Step S24: locating the warehouse textile products based on the textile product window RFID tag data, thereby obtaining warehouse textile product positioning data;

[0145] In this embodiment, by installing multiple RFID reading devices and positioning systems in various areas of the warehouse, the geographic location of each fabric in the warehouse is obtained in real time. When the RFID tag of the fabric is scanned, the location of the fabric can be accurately identified in combination with the existing warehouse map. For example, by combining RFID with indoor positioning technology (such as UWB technology), the shelf or specific location of each fabric can be accurately determined, thereby achieving accurate inventory management.

[0146] Step S25: Performing inventory cycle analysis of textile products according to the warehouse textile product location data, thereby obtaining warehouse textile product inventory cycle data.

[0147] In this embodiment, based on the location data of the fabric in the warehouse, the storage period and inventory turnover of each fabric can be further calculated. By analyzing the storage time of the inventory, the average time from the entry to the exit of a certain type of textile can be calculated, and long-term unsalable or high-turnover fabrics can be identified. For example, for a certain fabric, if its average storage period in the warehouse exceeds a predetermined value, the management personnel will be automatically reminded to make inventory adjustments or promotions.

[0148] Optionally, step S25 is specifically:

[0149] Step S251: performing textile product positioning time distribution statistics according to the textile product positioning data in the warehouse, thereby obtaining textile product positioning time distribution data;

[0150] In this embodiment, the time data of each textile product from entering the warehouse to being located is collected by sensors or RFID technology. According to the entry time and the last location time of each textile product, the location time difference of each textile product is calculated and statistical analysis is performed. For example, if a batch of textile products enters the warehouse on the same date, by comparing the location time differences of each textile product, a location time distribution diagram is generated to show the concentration trend or dispersion degree of the location time.

[0151] Step S252: classifying the textile product positioning time distribution data according to the positioning time, thereby obtaining short-term textile product positioning data and long-term textile product positioning data;

[0152] In this embodiment, the positioning duration of textile products is further classified according to the acquired positioning time distribution data. By setting a positioning time threshold, textile products with a positioning time less than a specific time (such as 5 days) are classified as "short-term positioning data", while textile products with a positioning time exceeding a specific time (such as 5 days) are classified as "long-term positioning data". The specific time threshold for classification can be set by analyzing historical data or business needs. For example, if most textile products in the warehouse are positioned within 5 days, the positioning time of less than 5 days is short-term positioning data, and the positioning time of more than 5 days is long-term positioning data.

[0153] Step S253: Calculating the short-term positioning cycle of the textile product tag according to the short-term textile product positioning data, thereby obtaining the textile product scheduling cycle data;

[0154] In this embodiment, after obtaining the short-term positioning data, the scheduling period of each textile product is further calculated. The scheduling period refers to the time from when the textile product is located to when it is taken out or used. Based on the short-term positioning data, the scheduling period of the textile product can be calculated by time series analysis. For example, the time interval between the taking-out time and the positioning time of each textile product in the short-term positioning data is calculated, which is the scheduling period.

[0155] Step S254: Calculating the long-term positioning period of the textile product tag according to the long-term textile product positioning data, thereby obtaining textile product storage period data;

[0156] In this embodiment, the long-term positioning data is used to calculate the storage cycle of textile products. The storage cycle refers to the storage time between the positioning of textile products and their final removal for use. By analyzing the long-term positioning data, it is possible to identify which textile products have been in the warehouse for a long time, so as to give priority or reclassify them. For example, the storage time of each textile product is analyzed to generate a storage cycle distribution, which helps warehouse managers determine whether it is necessary to reconfigure the inventory location to improve inventory turnover.

[0157] Step S255: performing periodic time series merging of the textile product scheduling cycle data and the textile product storage cycle data, thereby obtaining warehouse textile product inventory cycle data.

[0158] In this embodiment, the final warehouse textile inventory cycle data is obtained by merging the short-term scheduling cycle and the long-term storage cycle data. This merging process not only helps warehouse managers to fully understand the storage and scheduling of each textile product, but also can find the correlation between the storage cycle and the scheduling cycle through time series merging analysis. For example, some textile products will be dispatched only after long-term storage, and this pattern can be identified and optimized. Ultimately, the inventory cycle data generated by the system will be used to guide inventory optimization decisions, reduce storage costs, and improve warehouse management efficiency.

[0159] Optionally, step S3 specifically includes:

[0160] Step S31: constructing a textile product popular element prediction model according to textile product popular trend data, and predicting textile product popular elements according to the textile product popular element prediction model, thereby obtaining textile product predicted popular element data;

[0161] In this embodiment, based on the textile product fashion trend data, a textile product fashion element prediction model based on machine learning is constructed by analyzing the historical data of multi-dimensional factors such as fabric materials and colors. The model can use time series analysis, decision trees or deep learning algorithms (such as LSTM neural networks) to learn the laws of past popular elements and predict the textile product elements that will be popular in the future. For example, through historical sales data feedback, the combination of summer seasonal color preferences (such as "white") and a certain fabric (such as "fabric with good breathability") is predicted as a fashion trend.

[0162] Step S32: Associating the textile product transaction monitoring data with the textile product predicted popular element data to be processed, thereby obtaining textile product transaction data associated with the predicted popular element;

[0163] In this embodiment, the output of the textile popular element prediction model is used to predict and associate the textile transaction monitoring data to be processed with popular elements. For example, if the popular element of a certain season is predicted to be "a combination of white color and fabrics with good air permeability", the model will analyze the transaction data to determine which textile products (such as shirts, skirts, etc.) have the elements of this combination, and these textile products are more likely to meet the characteristics of these popular elements, thereby generating "predicted popular element associated textile transaction data".

[0164] Step S33: forecasting the demand of associated popular textile products based on the predicted transaction data of textile products associated with popular elements, thereby obtaining forecast data of the demand of popular textile products;

[0165] In this embodiment, based on the textile transaction data associated with the predicted popular elements, the demand for textile products is further predicted. This step uses a demand forecasting model (such as regression analysis, ARIMA, Bayesian model, etc.) combined with historical sales data, seasonal fluctuations and other factors to predict the demand for popular textile products in a certain period of time in the future. For example, if the transaction data of a specific popular element (such as the popularity of silk in summer) increases significantly during the forecast period, the demand for popular textile products can be inferred based on the data.

[0166] Step S34: performing statistics on high-demand textile products according to the popular textile product demand forecast data, thereby obtaining high-demand popular textile product data;

[0167] In this embodiment, statistics and screening of high-demand textile products are performed based on the demand forecast data of popular textile products. In this stage, the textile products with high demand in the future market are screened out by setting the demand threshold, and they are the focus of production and procurement. For example, if a certain "white breathable shirt" shows high potential in the demand forecast, it will be listed as a high-demand textile product. Further data analysis can be used to predict its production and sales cycle.

[0168] Step S35: Associating the warehouse textile product inventory cycle data with the high-demand popular textile product inventory based on the high-demand popular textile product data, thereby obtaining the warehouse demand textile product inventory cycle data.

[0169] In this embodiment, after obtaining the data of popular textile products with high demand, inventory association is performed in combination with the inventory cycle data of textile products in the warehouse. The similarity between the characteristics of textile products in the data of popular textile products with high demand and the characteristics of textile products in the warehouse is calculated, and textile products with high similarity to the popular textile products with high demand are selected from the textile products in the warehouse for association. Then, the inventory cycle of the associated textile products is extracted to obtain the inventory cycle data of textile products in warehouse demand.

[0170] Optionally, step S4 specifically includes:

[0171] Step S41: performing textile warehouse inventory simulation according to warehouse demand textile product inventory cycle data and textile product forecast popular element data, thereby obtaining textile warehouse inventory simulation data;

[0172] In this embodiment, based on the inventory cycle data of textile products in warehouse demand (such as inventory turnover in the past period of time) and the predicted popular element data of textile products (for example, the popular trend analysis of textile product elements), and using time series analysis or regression model, an inventory simulation model is constructed to simulate the data, simulate the inventory level of the textile warehouse, and consider the influence of seasonal demand changes and popular elements. Assuming that the inventory cycle of a certain type of textile products in the warehouse is 30 days, the influence of different popular elements (such as color, material, etc.) on inventory changes is simulated and calculated to obtain textile warehouse inventory simulation data. The Monte Carlo simulation method can be used to predict inventory changes by randomly simulating multiple possible demand fluctuation scenarios.

[0173] Step S42: Calculate the inventory scheduling cycle of popular textile products on the textile warehouse inventory simulation data, so as to obtain the inventory scheduling cycle data of popular textile products;

[0174] In this embodiment, the scheduling cycle is calculated for the inventory data obtained through simulation to ensure that the supply of popular textile products in the warehouse can keep up with the changes in market demand. Specifically, firstly, it is identified which textile products are popular products (seasonal products or newly launched products) through the elements of the textile products. Then, the inventory replenishment cycle and scheduling cycle of different popular textile products are calculated based on the inventory simulation data.

[0175] Step S43: extracting the predicted popular cycle of textile elements from the predicted popular element data of textile products, thereby obtaining the predicted popular cycle data of textile elements;

[0176] In this embodiment, the popular element prediction data of textile products is combined to extract the popular cycle of elements. This step extracts the life cycle of popular elements in textile products by analyzing the market trends. For example, the popular trends of colors and materials usually have obvious seasonal patterns. By collecting and analyzing the sales data of various types of textile products in the past few years, combined with factors such as climate and festivals, the popular cycle of a certain type of textile products can be predicted and data can be extracted.

[0177] Step S44: Calculating the scheduling cycle error of the popular textile product inventory scheduling cycle data and the textile product element prediction popular cycle data, thereby obtaining the inventory textile product scheduling cycle error data;

[0178] In this embodiment, the scheduling cycle error is calculated to evaluate the deviation between the current inventory scheduling cycle and the popular element cycle. Specifically, the purpose of the error calculation is to evaluate the deviation between the actual inventory scheduling cycle and the forecast cycle so as to make adjustments. At this time, an error analysis method (such as mean square error MSE) can be used to measure the accuracy of the scheduling cycle.

[0179] Step S45: Perform a fitness evaluation of popular textile products based on the inventory textile product scheduling cycle error data, thereby obtaining fitness data of popular textile products.

[0180] In this embodiment, the fitness of popular textile products is evaluated based on the calculated inventory scheduling cycle error data. The fitness evaluation is mainly performed by calculating the matching degree between the scheduling cycle error and the predicted demand. If the scheduling cycle error is small, it means that the inventory scheduling of textile products is more accurate and the fitness is higher, otherwise the fitness is lower. For example, if a certain textile product has a high fitness, it means that its inventory scheduling cycle is highly matched with market demand, and inventory management is more accurate.

[0181] Optionally, the present invention further provides a textile warehouse intelligent management system based on popular element information monitoring, which is used to execute the textile warehouse intelligent management method based on popular element information monitoring as described above, and the textile warehouse intelligent management system based on popular element information monitoring includes:

[0182] The popular element trend analysis module is used to obtain the textile product transaction monitoring data of the e-commerce platform, and integrate the popular elements of the traded textile products according to the textile product transaction monitoring data of the e-commerce platform, so as to obtain the popular element data of the traded textile products; based on the popular element data of the traded textile products, the popular element trend analysis is performed to obtain the textile product popular trend data;

[0183] The textile product inventory cycle analysis module is used to obtain textile warehouse management data, and locate textile products based on the textile warehouse management data, thereby obtaining warehouse textile product location data; perform textile product inventory cycle analysis based on the warehouse textile product location data, thereby obtaining warehouse textile product inventory cycle data;

[0184] The textile product demand forecasting module is used to forecast the demand of popular textile products according to the textile product fashion trend data, so as to obtain the forecast data of the demand of popular textile products; based on the forecast data of the demand of popular textile products, the warehouse textile product inventory cycle data is associated with the demand textile product inventory, so as to obtain the warehouse demand textile product inventory cycle data;

[0185] A textile product fitness evaluation module is used to simulate the textile warehouse inventory according to the warehouse demand textile product inventory cycle data, thereby obtaining textile warehouse inventory simulation data, and to evaluate the fitness of popular textile products based on the textile warehouse inventory simulation data, thereby obtaining the fitness data of popular textile products;

[0186] The inventory cycle optimization module is used to optimize the inventory cycle of warehouse textile products based on the popular textile product suitability data, so as to obtain optimized popular textile product inventory cycle data; optimize the textile warehouse inventory structure of the textile warehouse management data according to the optimized popular textile product inventory cycle data, so as to obtain the textile warehouse optimized management data, and transmit it to the textile warehouse management platform to perform the inventory structure optimization task.

[0187] The intelligent management system for textile warehouses based on popular element information monitoring of the present invention can implement any one of the intelligent management methods for textile warehouses based on popular element information monitoring of the present invention, and is used to combine the medium for operation and signal transmission between various modules to complete the intelligent management method for textile warehouses based on popular element information monitoring. The internal modules of the system cooperate with each other to improve the overall efficiency of warehouse management.

[0188] Therefore, the embodiments should be regarded as illustrative and non-restrictive from all points, and the scope of the present invention is limited by the appended claims rather than the above description, and it is therefore intended that all changes falling within the meaning and range of equivalent elements of the application documents are included in the present invention.

[0189] The above description is only a specific embodiment of the present invention, so that those skilled in the art can understand or implement the present invention. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but should conform to the widest scope consistent with the principles and novel features invented herein.

Claims

1. A textile warehouse intelligent management method based on popular element information monitoring, characterized in that: The following steps are involved: Step S1: obtaining textile product transaction monitoring data from an e-commerce platform, and integrating popular elements of traded textile products according to the textile product transaction monitoring data from the e-commerce platform, thereby obtaining popular element data of traded textile products; Performing a trend analysis of popular elements based on the popular element data of traded textile products, thereby obtaining the popular trend data of textile products; step S1 specifically comprises: Step S11: acquiring textile product transaction monitoring data on the e-commerce platform, and performing data preprocessing on the textile product transaction monitoring data on the e-commerce platform, thereby obtaining textile product transaction monitoring data to be processed; Step S12: extracting features of traded textile products according to the textile product transaction monitoring data to be processed, thereby obtaining fabric data of traded textile products and color data of traded textile products; Step S13: Analyze the popular elements of textile fabrics based on the traded textile fabric data, so as to obtain the popular elements data of textile fabrics; Step S13 is specifically as follows: Step S131: performing textile fabric transaction volume statistics based on the textile fabric transaction data, thereby obtaining high-frequency transaction fabric data and low-frequency transaction fabric data; Step S132: performing fabric transaction periodicity identification on the high-frequency transaction fabric data, thereby obtaining transaction periodic fabric data and non-transaction periodic fabric data; Step S133: seasonal fabric element integration is performed according to the transaction periodic fabric data, thereby obtaining seasonal fabric element data; Step S134: integrating non-periodic fabric elements according to the low-frequency transaction fabric data and the non-transaction periodic fabric data, thereby obtaining non-periodic fabric element data; Step S135: performing fabric element popular time series merging on seasonal fabric element data and non-periodic fabric element data, thereby obtaining fabric popular element data for textile products; Step S14: integrating the color data of traded textile products with the popular elements of traded textile products according to the popular elements data of textile product fabrics, thereby obtaining the popular elements data of traded textile products; Step S14 is specifically as follows: Step S141: performing color combination frequency statistics on the traded textile product color data, thereby obtaining high-frequency traded textile product color combination data; Step S142: classifying the high-frequency traded textile product color combination data by textile product size, thereby obtaining high-frequency traded large-size textile product color combination data and high-frequency traded small-size textile product color combination data; Step S143: performing large-size textile element matching frequency calculation on textile fabric popular element data and high-frequency large-size textile color combination data, thereby obtaining large-size textile element-color combination matching frequency data, and performing large-size textile element integration according to the large-size textile element-color combination matching frequency data, thereby obtaining large-size textile element data; Step S144: performing small-size textile element matching frequency calculation on textile fabric popular element data and high-frequency trading small-size textile color combination data, thereby obtaining small-size textile element-color combination matching frequency data, and performing small-size textile element integration according to the small-size textile element-color combination matching frequency data, thereby obtaining small-size textile element data; Step S145: performing intersection screening of popular textile product elements according to the large-size textile product element data and the small-size textile product element data, thereby obtaining popular textile product element data for transactions; Step S15: performing a trend analysis of popular elements based on the popular element data of traded textile products, thereby obtaining popular trend data of textile products; Step S2: obtaining textile warehouse management data, and locating textile products based on the textile warehouse management data, thereby obtaining warehouse textile product positioning data; Perform textile inventory cycle analysis based on warehouse textile location data to obtain warehouse textile inventory cycle data; Step S3: forecasting the demand for popular textile products according to the textile product fashion trend data, thereby obtaining forecast data for the demand for popular textile products; Based on the forecast data of the demand for popular textile products, the inventory cycle data of warehouse textile products is associated with the inventory cycle data of demand textile products, so as to obtain the inventory cycle data of warehouse demand textile products; Step S4: performing a textile warehouse inventory simulation according to the warehouse demand textile product inventory cycle data, thereby obtaining textile warehouse inventory simulation data, and performing a popular textile product fitness evaluation based on the textile warehouse inventory simulation data, thereby obtaining the popular textile product fitness data; Step S5: optimizing the inventory cycle of popular textile products on the warehouse textile product inventory cycle data based on the popular textile product fitness data, thereby obtaining optimized inventory cycle data of popular textile products; The textile warehouse inventory structure is optimized based on the optimized inventory cycle data of popular textile products, so as to obtain the textile warehouse optimization management data and transmit it to the textile warehouse management platform to perform the inventory structure optimization task.

2. The intelligent management method for textile warehouses based on popular element information monitoring according to claim 1 is characterized in that: Step S134 is specifically as follows: According to the seasonal fabric element data, the low-frequency transaction fabric data is seasonally eliminated, so as to obtain the low-frequency transaction fabric data to be analyzed; Integrate the low-frequency transaction fabric data to be analyzed into fabric elements, so as to obtain low-frequency transaction fabric element data; Perform fabric element integration on non-trading periodic fabric data, thereby obtaining non-trading periodic fabric element data; Fabric element similarity calculation is performed based on low-frequency transaction fabric element data and non-transaction periodic fabric element data, thereby obtaining fabric element similarity data; Based on the fabric element similarity data, the non-transaction periodic fabric data is subjected to high similarity fabric element elimination to obtain non-periodic fabric element data.

3. The intelligent management method for textile warehouses based on popular element information monitoring according to claim 1 is characterized in that: Step S2 is specifically as follows: Step S21: obtaining textile warehouse management data, and dividing the textile warehouse management data into time windows, thereby obtaining textile warehouse time window management data; Step S22: extracting RFID read-write records of the textile warehouse time window management data, thereby obtaining RFID read-write data of the textile warehouse window; Step S23: performing textile product RFID tag identification according to the textile warehouse window RFID reading and writing data, thereby obtaining textile product window RFID tag data; Step S24: locating the warehouse textile products based on the textile product window RFID tag data, thereby obtaining warehouse textile product positioning data; Step S25: Performing inventory cycle analysis of textile products according to the warehouse textile product location data, thereby obtaining warehouse textile product inventory cycle data.

4. The intelligent management method for textile warehouses based on popular element information monitoring according to claim 3 is characterized in that: Step S25 is specifically as follows: Step S251: performing textile product positioning time distribution statistics according to the textile product positioning data in the warehouse, thereby obtaining textile product positioning time distribution data; Step S252: classifying the textile product positioning time distribution data according to the positioning time, thereby obtaining short-term textile product positioning data and long-term textile product positioning data; Step S253: Calculating the short-term positioning cycle of the textile product tag according to the short-term textile product positioning data, thereby obtaining the textile product scheduling cycle data; Step S254: Calculating the long-term positioning period of the textile product tag according to the long-term textile product positioning data, thereby obtaining textile product storage period data; Step S255: performing periodic time series merging of the textile product scheduling cycle data and the textile product storage cycle data, thereby obtaining warehouse textile product inventory cycle data.

5. The intelligent management method for textile warehouses based on popular element information monitoring according to claim 1 is characterized in that: Step S3 is specifically as follows: Step S31: constructing a textile product popular element prediction model according to textile product popular trend data, and predicting textile product popular elements according to the textile product popular element prediction model, thereby obtaining textile product predicted popular element data; Step S32: Associating the textile product transaction monitoring data with the textile product predicted popular element data to be processed, thereby obtaining textile product transaction data associated with the predicted popular element; Step S33: forecasting the demand of associated popular textile products based on the predicted transaction data of textile products associated with popular elements, thereby obtaining forecast data of the demand of popular textile products; Step S34: performing statistics on high-demand textile products according to the popular textile product demand forecast data, thereby obtaining high-demand popular textile product data; Step S35: Associating the warehouse textile product inventory cycle data with the high-demand popular textile product inventory based on the high-demand popular textile product data, thereby obtaining the warehouse demand textile product inventory cycle data.

6. The intelligent management method for textile warehouses based on popular element information monitoring according to claim 1 is characterized in that: Step S4 is specifically as follows: Step S41: performing textile warehouse inventory simulation according to warehouse demand textile product inventory cycle data and textile product forecast popular element data, thereby obtaining textile warehouse inventory simulation data; Step S42: Calculate the inventory scheduling cycle of popular textile products on the textile warehouse inventory simulation data, so as to obtain the inventory scheduling cycle data of popular textile products; Step S43: extracting the predicted popular cycle of textile elements from the predicted popular element data of textile products, thereby obtaining the predicted popular cycle data of textile elements; Step S44: Calculating the scheduling cycle error of the popular textile product inventory scheduling cycle data and the textile product element prediction popular cycle data, thereby obtaining the inventory textile product scheduling cycle error data; Step S45: Perform a fitness evaluation of popular textile products based on the inventory textile product scheduling cycle error data, thereby obtaining fitness data of popular textile products.

7. A textile warehouse intelligent management system based on popular element information monitoring, characterized in that: Used to execute the textile warehouse intelligent management method based on popular element information monitoring as claimed in claim 1, the textile warehouse intelligent management system based on popular element information monitoring comprises: The popular element trend analysis module is used to obtain the textile product transaction monitoring data of the e-commerce platform, and integrate the popular elements of the traded textile products according to the textile product transaction monitoring data of the e-commerce platform, so as to obtain the popular element data of the traded textile products; based on the popular element data of the traded textile products, the popular element trend analysis is performed to obtain the textile product popular trend data; The textile product inventory cycle analysis module is used to obtain textile warehouse management data, and locate textile products based on the textile warehouse management data, thereby obtaining warehouse textile product location data; perform textile product inventory cycle analysis based on the warehouse textile product location data, thereby obtaining warehouse textile product inventory cycle data; The textile product demand forecasting module is used to forecast the demand of popular textile products according to the textile product fashion trend data, so as to obtain the forecast data of the demand of popular textile products; based on the forecast data of the demand of popular textile products, the warehouse textile product inventory cycle data is associated with the demand textile product inventory, so as to obtain the warehouse demand textile product inventory cycle data; A textile product fitness evaluation module is used to simulate the textile warehouse inventory according to the warehouse demand textile product inventory cycle data, thereby obtaining textile warehouse inventory simulation data, and to evaluate the fitness of popular textile products based on the textile warehouse inventory simulation data, thereby obtaining the fitness data of popular textile products; The inventory cycle optimization module is used to optimize the inventory cycle of warehouse textile products based on the popular textile product suitability data, so as to obtain optimized popular textile product inventory cycle data; optimize the textile warehouse inventory structure of the textile warehouse management data according to the optimized popular textile product inventory cycle data, so as to obtain the textile warehouse optimized management data, and transmit it to the textile warehouse management platform to perform the inventory structure optimization task.

Images