Inventory monitoring management system of silica gel material storage center

Abstract

The invention discloses an inventory monitoring management system for a silica gel material storage center, and relates to the technical field of intelligent storage management. According to the inventory monitoring and management system for the silica gel material storage center, real-time and historical inventory data of silica gel materials are collected and stored through the inventory data module, and the inventory shortage index is analyzed by utilizing the inventory detection module in combination with a Markov chain, so that the inventory risk is evaluated. The inventory prediction module predicts future inventory demand and a replenishment trend chart based on an LSTM neural network model, and optimizes a replenishment decision; the abnormity monitoring module generates an inventory abnormity index through the inventory shortage index and the future demand quantity, and early warns abnormal conditions in time. And the inventory distribution module dynamically distributes the inventory of each warehouse according to requirements by using an inventory optimization equation, so that reasonable allocation of resources is realized. The intelligent silica gel material inventory management is realized, and the monitoring efficiency and the response speed are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent warehouse management, and in particular to an inventory monitoring and management system for a silica gel material warehouse center. Background Art

[0002] With the development of modern industry, silicone materials are widely used in electronics, medical, automotive and other industries, and their usage and demand are increasing year by year. However, since silicone materials are easily affected by environmental humidity and temperature, if they are not strictly monitored during storage, product quality may decline or even become unusable. At the same time, companies are increasingly demanding efficiency, accuracy and cost control in inventory management, and traditional manual management methods can no longer meet the requirements of large-scale silicone material storage management. Therefore, building an intelligent storage system that can monitor the inventory status of silicone in real time to ensure inventory quality and stable supply has become an important demand in the industry.

[0003] The current storage monitoring system for silicone materials generally adopts the method of sensor monitoring plus manual management, which has the problems of insufficient real-time and accuracy. First, traditional monitoring systems mostly use independent sensors for decentralized deployment, which cannot form a unified data management platform, and it is difficult to achieve all-round real-time monitoring and comprehensive data analysis; second, these systems lack intelligent data analysis functions and cannot issue timely warnings when environmental parameters are abnormal, which increases the risk of material degradation; third, the existing system has low equipment compatibility, is difficult to interconnect with different equipment, has poor scalability, and is difficult to meet complex storage needs. Therefore, the existing system lacks the ability of overall coordination, intelligent response, and efficient expansion in technology. Summary of the invention

[0004] In view of the deficiencies in the prior art, the present invention provides an inventory monitoring and management system for a silica gel material storage center, which solves the problems of the above-mentioned background technology.

[0005] To achieve the above objectives, the present invention is implemented through the following technical solutions: an inventory monitoring and management system for a silicone material storage center, comprising the following modules: an inventory data module, an inventory detection module, an inventory prediction module, an abnormality monitoring module, and an inventory allocation module; the inventory data module is used to obtain and store silicone material inventory data, including current silicone material inventory data and historical silicone material inventory data; the inventory detection module is used to analyze silicone material inventory changes through a Markov chain based on the current silicone material inventory data to obtain an inventory shortage index; the inventory prediction module is used to analyze the fluctuation characteristics of historical silicone material inventory data through an LSTM neural network model based on historical silicone material inventory data, establish an inventory demand prediction model, and predict future inventory demand and replenishment trend charts; the abnormality monitoring module is used to analyze the inventory shortage index and future inventory demand, obtain the inventory abnormality index, and compare it with a set abnormality threshold. When the abnormality index exceeds the abnormality threshold, an early warning message is generated and sent to the inventory allocation module; the inventory allocation module is used to construct an inventory optimization equation based on the future inventory demand and inventory shortage index of each warehouse, and dynamically allocate inventory to each warehouse.

[0006] Furthermore, the current silicone material inventory information data includes the current inventory quantity, inventory status, warehousing time, outbound time, inventory batch number, inventory usage frequency and inventory change trend of each type of silicone material in each warehouse; the historical silicone material inventory information data includes the historical inventory quantity changes, inventory status change records, inventory turnover rate, past replenishment records, and inventory fluctuation characteristics in each warehouse.

[0007] Furthermore, based on the current silicone material inventory data, the specific process of analyzing the inventory changes of silicone materials through Markov chain is as follows: according to the current silicone material inventory data, the inventory status of each type of silicone material is classified, several states are set, and the transition probability of each state is evaluated; according to the inventory quantity and the transition probability of the inventory status, a Markov chain model is established to simulate the transition between different inventory states; the time distribution and frequency of inventory status changes are determined, and the transition probability matrix of the inventory status is calculated; the current inventory quantity is combined with the transition probability matrix to simulate the inventory change process of each silicone material in each warehouse, and the future inventory status change trend is evaluated.

[0008] Furthermore, the specific process of obtaining the inventory shortage index is as follows: according to the analysis of the changes in the silicone material inventory by the Markov chain, the current inventory status, warehousing and outbound conditions of each type of silicone material are classified; according to the transition probability of each type of inventory status, the transition probability matrix of the inventory status is calculated; according to the transition probability matrix and the current inventory quantity, the future changes in the inventory status are simulated, and the inventory shortage index under each inventory status is calculated.

[0009] Furthermore, the specific process of analyzing the volatility characteristics of historical silicone material inventory data through the LSTM neural network model is as follows: according to the historical silicone material inventory data, the historical data is divided into a training set and a test set, and an LSTM neural network structure is constructed; the historical data is input into the trained LSTM model, and the key features are extracted according to the historical inventory fluctuations in the time series to identify the periodicity, regularity and abnormal fluctuation patterns of inventory changes; through the time series dependency, the predicted trend and fluctuation range of inventory changes are output to identify potential inventory risk points.

[0010] Furthermore, an inventory demand forecasting model is established to predict future inventory demand and replenishment trend chart. The specific process is as follows: based on the volatility characteristics of historical inventory data analyzed by the LSTM model, an inventory demand forecasting model is constructed; the current inventory status, inventory shortage index and historical inventory data are input, and the future inventory demand is predicted through the LSTM neural network, a time series of future inventory demand is generated, and a replenishment trend chart is drawn.

[0011] Furthermore, the specific process of analyzing the inventory shortage index and future inventory demand to obtain the inventory anomaly index is as follows: obtain the current inventory shortage index and future inventory demand for each type of silicone material; define the abnormal threshold of the inventory anomaly index according to the fluctuation characteristics of the inventory shortage index and future inventory demand; compare the current inventory quantity with the future demand to evaluate the degree of inventory anomaly in each warehouse and each type of silicone material; compare the difference between the inventory shortage index and the future inventory demand with the set threshold to obtain the inventory anomaly index.

[0012] Furthermore, an inventory optimization equation is constructed, and the specific process of dynamically allocating inventory to each warehouse is as follows: according to the inventory demand, inventory shortage index and inventory abnormality index of each warehouse, the inventory optimization goal is set; the future inventory demand, inventory shortage index and abnormality index of each warehouse are used as constraints and input into the inventory optimization equation; the optimal inventory allocation plan for each warehouse is analyzed through linear programming, and the inventory allocation plan is dynamically adjusted according to the real-time monitored inventory data.

[0013] The present invention has the following beneficial effects: (1) In this silicone material storage center inventory monitoring and management system, the inventory data module collects and stores the current inventory data and historical inventory data of silicone materials in real time to ensure that the inventory management system has accurate and complete basic data. The inventory detection module evaluates the current inventory status through Markov chain analysis, and obtains the inventory shortage index based on the inventory entry and exit. It can simulate the dynamic changes of inventory, identify the trend of inventory shortage or surplus in advance, and provide timely early warning information for inventory management, thereby realizing intelligent inventory monitoring. The inventory prediction module analyzes the fluctuation characteristics of historical silicone material inventory data through the LSTM neural network model, establishes an inventory demand prediction model, and predicts future inventory demand and replenishment trend charts. It effectively captures the regularity and periodicity of inventory fluctuations, and provides high-accuracy predictions for future inventory demand, avoiding management risks caused by inventory fluctuations.

[0014] (2) In the inventory monitoring and management system of the silicone material storage center, the abnormal monitoring module obtains the inventory abnormality index through comprehensive analysis based on the inventory shortage index and future inventory demand, and compares it with the set abnormal threshold. When the abnormal index exceeds the threshold, an early warning message is generated and automatically sent to the inventory allocation module to ensure the smooth operation of inventory management. The inventory allocation module dynamically adjusts the inventory allocation plan according to the future inventory demand and inventory shortage index of each warehouse through the inventory optimization equation. By accurately calculating the inventory demand of each warehouse, the allocation of inventory resources is optimized, and the inventory backlog and out-of-stock problems are reduced, thereby improving the efficiency of inventory management and resource utilization.

[0015] Of course, any product implementing the present invention does not necessarily need to achieve all of the advantages described above at the same time. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 This is a flow chart of an inventory monitoring and management system for a silica gel material storage center according to the present invention. DETAILED DESCRIPTION

[0017] The embodiment of the present application solves the problems of insufficient real-time performance, lack of accuracy and poor scalability of traditional warehouse management through an inventory monitoring and management system for a silicone material storage center. By combining intelligent sensor monitoring with deep learning algorithms, a unified data management platform is constructed to achieve real-time monitoring and intelligent analysis of the inventory status of silicone materials. It effectively reduces the risk of material degradation, supports equipment interconnection, and has high scalability to meet complex storage needs and ensure the quality and stable supply of silicone materials.

[0018] The overall idea of ​​the problem in the embodiment of this application is as follows: Acquire and store silicone material inventory data, including current silicone material inventory data and historical silicone material inventory data.

[0019] Based on the current silicone material inventory data, the silicone material inventory changes are analyzed through Markov chain to obtain the inventory shortage index.

[0020] According to the historical silicone material inventory data, the volatility characteristics of the historical silicone material inventory data are analyzed through the LSTM neural network model, and an inventory demand forecasting model is established to predict future inventory demand and replenishment trend charts. Analyze the inventory shortage index and future inventory demand, obtain the inventory abnormality index, and compare it with the set abnormality threshold. When the abnormality index exceeds the abnormality threshold, generate and send an early warning message.

[0021] According to the future inventory demand and inventory shortage index of each warehouse, an inventory optimization equation is constructed to dynamically allocate inventory to each warehouse.

[0022] See also Figure 1 The embodiment of the present invention provides a technical solution: an inventory monitoring and management system for a silicone material storage center, comprising the following modules: an inventory data module, an inventory detection module, an inventory prediction module, an abnormality monitoring module, and an inventory allocation module; the inventory data module is used to obtain and store silicone material inventory data, including current silicone material inventory data and historical silicone material inventory data; the inventory detection module is used to analyze silicone material inventory changes through a Markov chain based on the current silicone material inventory data to obtain an inventory shortage index; the inventory prediction module is used to analyze the fluctuation characteristics of historical silicone material inventory data through an LSTM neural network model based on historical silicone material inventory data, establish an inventory demand prediction model, and predict future inventory demand and replenishment trend charts; the abnormality monitoring module is used to analyze the inventory shortage index and future inventory demand, obtain the inventory abnormality index, and compare it with the set abnormality threshold. When the abnormality index exceeds the abnormality threshold, an early warning message is generated and sent to the inventory allocation module; the inventory allocation module is used to construct an inventory optimization equation based on the future inventory demand and inventory shortage index of each warehouse, and dynamically allocate inventory to each warehouse.

[0023] In this implementation scheme, the inventory data module is responsible for collecting, storing and managing the inventory information of silicone materials, including current inventory data and historical inventory data. It helps to analyze inventory trends and demand changes. The core role of this module is to ensure the integrity and continuity of system data and provide basic data support for subsequent inventory forecasting and allocation. Inventory detection module: Based on the current inventory data, the Markov chain model is used to analyze the inventory change trend. Markov chain is a mathematical model used to predict state transitions, which is used here to calculate the inventory shortage index. This index can measure the adequacy of the current inventory status and predict the possibility of inventory shortages, thereby providing inventory warnings for warehouse managers. This method uses the transition probability of inventory status to more accurately assess inventory risks under random fluctuations. Inventory prediction module: Based on historical inventory data, the long short-term memory neural network model is used to predict future inventory demand. It can capture the periodicity, seasonality and sudden fluctuations of inventory data. The core role of this module is to establish an inventory demand forecasting model, generate a trend chart of future inventory demand, and help warehouse managers plan replenishment in advance. Abnormal monitoring module: Responsible for analyzing the inventory shortage index and future inventory demand, and calculating the "inventory abnormality index". The inventory anomaly index is used to reflect the deviation between the current inventory status and the predicted demand. When the index exceeds the preset anomaly threshold, the system generates an early warning message and passes the information to the inventory allocation module. The core purpose of this module is to achieve early warning monitoring of inventory status and avoid supply chain risks caused by abnormal inventory fluctuations. Inventory allocation module: According to the inventory shortage index and future demand of different warehouses, an inventory optimization equation is constructed to dynamically allocate inventory to each warehouse through linear programming and other methods. The inventory optimization equation takes into account conditions such as inventory, demand and anomaly index to form an optimal allocation plan to ensure the reasonable distribution and effective use of resources. Markov chain: A mathematical model based on state transition probability, which is used to predict the future state of the system. The Markov chain assumes that the future state of the system is only related to the current state, not to the past historical state. In the inventory detection module, the Markov chain is used to analyze the changing trend of the silicone material inventory, thereby calculating the inventory shortage index and evaluating the adequacy and urgency of the inventory. Inventory shortage index: An indicator to measure whether the inventory is in a shortage state. Through Markov chain calculation, the inventory shortage index can provide a reference for inventory management and help predict potential inventory shortages. The higher the shortage index value, the closer the inventory is to being insufficient, which prompts managers to consider replenishing. Long Short-Term Memory Neural Network: A special recursive neural network (RNN) model suitable for processing and predicting time series data. The LSTM network can avoid the gradient vanishing problem while learning long-term dependencies, so it is particularly suitable for capturing the periodicity and seasonality of historical data in inventory forecasting. Through the LSTM model, the system can accurately analyze the changing patterns of silicone material inventory data and predict future inventory demand.Inventory demand forecasting model: The inventory change forecasting model established by using algorithms such as LSTM generates a forecast curve for future inventory demand by analyzing historical inventory data. This model helps companies plan the time and quantity of inventory replenishment in advance to ensure the continuity of supply. Inventory anomaly index: An indicator that reflects the difference between the current inventory status and the predicted inventory demand. The calculation of the anomaly index is based on the inventory shortage index and the future inventory demand, and compares it with the set anomaly threshold. When the anomaly index exceeds the threshold, the system will generate an inventory anomaly warning to indicate the possible risk of supply and demand imbalance. Anomaly threshold: A preset value used to determine whether there is an inventory anomaly. When the inventory anomaly index exceeds the anomaly threshold, the system will automatically issue an alarm to prompt managers to pay attention to the inventory status and take measures. Linear programming: A mathematical optimization method that sets an objective function and constraints to find the best solution. In the inventory allocation module, linear programming is used to solve the optimal inventory allocation strategy, and realize the dynamic allocation and optimization of inventory according to the demand and shortage index of different warehouses.

[0024] Specifically, the current silicone material inventory information data includes the current inventory quantity, inventory status, warehousing time, outbound time, inventory batch number, inventory usage frequency and inventory change trend of each type of silicone material in each warehouse; the historical silicone material inventory information data includes the historical inventory quantity changes, inventory status change records, inventory turnover rate, past replenishment records, and inventory fluctuation characteristics in each warehouse.

[0025] In this implementation scheme, the current inventory quantity of each type of silicone material: the existing quantity of each type of silicone material in each warehouse, to ensure the reasonable allocation of inventory under different demand scenarios. Inventory status: indicates the quality and availability of the current inventory, such as normal, pending inspection, pending processing, etc., to facilitate monitoring and management of inventory quality. Inbound time: the timestamp when the silicone material enters the warehouse, used to track the storage time and historical management records of the material in the warehouse. Outbound time: the time when the silicone material is removed or shipped from the warehouse, used to calculate the inventory turnover cycle and usage frequency. Inventory batch number: the unique identifier of each batch of inventory materials, used for traceability and batch management, to ensure quality control and information traceability. Inventory usage frequency: indicates the frequency with which the inventory is used or shipped out of the warehouse, to help predict future inventory demand and optimize replenishment strategies. Inventory change trend: through the increase and decrease trend of the current inventory quantity, the possibility and trend of future inventory changes are judged, providing a basis for intelligent replenishment and inventory optimization. Historical silicone material inventory information data: historical inventory quantity changes in each warehouse: records the changes in the inventory quantity of silicone materials in each warehouse, used to identify seasonal fluctuations or long-term trends in inventory. Inventory status change records: historical changes in inventory status, including switching from normal to damaged, pending inspection and other different states, providing a reference for quality and reliability data. Inventory turnover rate: used to indicate the efficiency of inventory turnover, that is, the frequency of use or outbound delivery of inventory materials over a period of time, to help optimize inventory levels and liquidity. Past replenishment records: information such as the quantity, time, and frequency of historical replenishment, to provide a basis for establishing replenishment models and predicting future demand. Inventory fluctuation characteristics: historical inventory fluctuation patterns and characteristics, to help identify demand cycles and inventory safety levels, and to provide support for inventory forecasting and early warning systems.

[0026] Specifically, based on the current silicone material inventory data, the specific process of analyzing the inventory changes of silicone materials through Markov chain is as follows: according to the current silicone material inventory data, the inventory status of each type of silicone material is classified, several states are set, and the transition probability of each state is evaluated; according to the inventory quantity and the transition probability of the inventory status, a Markov chain model is established to simulate the transition between different inventory states; the time distribution and frequency of inventory status changes are determined, and the transition probability matrix of the inventory status is calculated; the current inventory quantity is combined with the transition probability matrix to simulate the inventory change process of each silicone material in each warehouse, and the future inventory status change trend is evaluated.

[0027] In this implementation scheme, the inventory status is classified: first, the inventory status of each type of silicone material is classified and set as "sufficient", "moderate", and "shortage". In this way, the inventory status can be concretized for subsequent analysis and calculation. The transition probability of the set state is calculated by analyzing historical data. What is the probability of the inventory changing from "sufficient" to "moderate" within a certain period of time. These probabilities help predict the change pattern of the inventory status. Establish a Markov chain model: According to each inventory state and its transition probability, a Markov chain model is constructed to simulate the transition process between inventory states. Through the model, the transition path and possibility between each state can be predicted, so as to grasp the overall trend of inventory status changes. Calculate the transition probability matrix: In the Markov chain model, a transition probability matrix is ​​generated. Each element in the matrix represents the probability of going from one inventory state to another, so as to fully describe the changes in the inventory state. Simulate the inventory change process: Combine the current inventory quantity data with the transition probability matrix to simulate the inventory changes of each silicone material in each warehouse. Through simulation, the possible changes in inventory status in a certain period of time in the future can be predicted to understand whether there will be shortages in inventory and other problems. Evaluate inventory change trends: Based on the simulation results, evaluate the future inventory status change trends to facilitate the formulation of reasonable replenishment strategies and warehousing plans. This trend analysis can help companies make inventory management plans in advance to prevent inventory shortages or excesses.

[0028] Specifically, the specific process of obtaining the inventory shortage index is as follows: based on the analysis of the changes in silicone material inventory by the Markov chain, the current inventory status, warehousing and outbound conditions of each type of silicone material are classified; based on the transition probability of each type of inventory status, the transition probability matrix of the inventory status is calculated; based on the transition probability matrix and the current inventory quantity, the future changes in the inventory status are simulated, and the inventory shortage index under each inventory status is calculated.

[0029] In this implementation plan, the inventory status is classified: First, the current inventory status, warehousing and outbound status of each type of silicone material are classified according to the Markov chain analysis of the changes in the silicone material inventory. It is assumed that the inventory status is divided into three categories: "sufficient", "moderate" and "shortage". Calculate the transition probability matrix: Through historical data analysis, calculate the transition probability between each inventory status and construct the transition probability matrix , where the elements in the matrix Indicates from inventory status Transfer to Inventory Status The probability of . The structure of the matrix is ​​as follows: ;in, Represents the state Transfer to state The probability of Corresponding to the states of "sufficient", "moderate" and "scarce". Inventory status simulation: combined with the current inventory quantity of silicone materials (“sufficient”, “moderate” and “scarce” inventory quantities), simulate the future changes in inventory status. Assume that at time When , the quantity of a certain inventory state is , then in time When , the change of inventory status can be simulated by the transition probability matrix: ;in, is the quantity vector of the current inventory status, Is the inventory state vector predicted at the next moment. Calculate the inventory shortage index: Inventory shortage index Used to measure the degree of inventory shortage, the shortage index formula is: ;in, Indicates from the state The probability of transitioning to the "shortage" state, Is the current state The inventory quantity. From stock status The probability of moving to the "shortage" state represents the potential risk of inventory shortage. It is the inventory quantity in a certain state at the current moment, indicating the contribution of the inventory quantity in each state to the degree of shortage.

[0030] Specifically, the specific process of analyzing the volatility characteristics of historical silicone material inventory data through the LSTM neural network model is as follows: according to the historical silicone material inventory data, the historical data is divided into a training set and a test set, and an LSTM neural network structure is constructed; the historical data is input into the trained LSTM model, and the key features are extracted according to the historical inventory fluctuations in the time series to identify the periodicity, regularity and abnormal fluctuation patterns of inventory changes; through the time series dependency relationship, the predicted trend and fluctuation range of inventory changes are output to identify potential inventory risk points.

[0031] In this implementation scheme, historical data division: historical silicone material inventory data is obtained, which includes the time series of inventory quantity. In order to train the neural network, the historical data needs to be divided into a training set and a test set. The training set is used to train the model, and the test set is used to evaluate the performance of the model. The ratio of data division is generally 80% (training set and 20% (test set). Constructing the LSTM neural network structure: LSTM is a commonly used recurrent neural network (RNN) variant, which is particularly suitable for time series data. LSTM uses its special gating mechanism (input gate, forget gate and output gate) to memorize long-term dependencies, which can effectively solve the gradient vanishing problem of traditional RNN in long sequences. When constructing an LSTM neural network, it is necessary to design a suitable number of network layers and the number of neurons in each layer. Common structures include input layer, LSTM layer, and fully connected layer (output layer). The input layer receives historical inventory data, the LSTM layer processes the dependencies in the time series, and the output layer predicts future inventory change trends. Training the LSTM model: historical data is input into the LSTM network for training. Through training, the LSTM model can learn the regularity, periodicity and potential abnormal fluctuation patterns of inventory fluctuations from historical inventory data. During the training process, the model The network weights are automatically adjusted according to historical inventory fluctuations to minimize the prediction error. During the training process, the LSTM model extracts key features based on the time series characteristics of historical inventory data and learns the patterns of inventory changes, such as periodic ups and downs and irregular abnormal fluctuations. Output predicted inventory change trends: After training, the LSTM model can output predictions of future inventory change trends based on the time series of historical inventory data. The model predicts the future inventory fluctuation range based on the temporal dependencies of historical data and identifies potential inventory risk points. Identify inventory risk points: Through the analysis of historical data by the LSTM model, abnormal patterns of inventory fluctuations can be identified. For example, if the model predicts that the inventory quantity will drop significantly in the future, an early warning can be issued at this time to prompt inventory managers to take action. Inventory risk points usually include that the inventory quantity may be close to a "shortage" state, or certain inventory fluctuation patterns indicate potential risks in the future.

[0032] Specifically, the specific process of establishing an inventory demand forecasting model and predicting future inventory demand and replenishment trend chart is as follows: construct an inventory demand forecasting model based on the volatility characteristics of historical inventory data analyzed by the LSTM model; input the current inventory status, inventory shortage index and historical inventory data, predict future inventory demand through the LSTM neural network, generate a time series of future inventory demand, and draw a replenishment trend chart.

[0033] In this implementation scheme, historical inventory data fluctuation characteristics analysis: based on the LSTM neural network, the fluctuation characteristics of historical inventory data are analyzed, and key characteristics such as periodicity, trend and abnormal fluctuation of inventory are first extracted. These characteristics will be used to build an inventory demand forecasting model. By training the LSTM model, the system can grasp the law of inventory changes. Building an inventory demand forecasting model: after obtaining the fluctuation characteristics of historical inventory data, a LSTM-based inventory demand forecasting model is built. The model needs to consider the following inputs: current inventory status: including current inventory quantity, inventory status (normal, too low, too high), inventory turnover rate, etc. Inventory shortage index: according to the inventory status change trend analyzed by the Markov chain model, the current inventory shortage is evaluated. Historical inventory data: including historical inventory quantity, replenishment records, warehousing and outbound conditions, etc. These input data will be used to predict future inventory demand. Based on these inputs, the LSTM model captures the dependencies in the time series and combines historical fluctuation characteristics to predict future inventory demand. Input data to the LSTM model for prediction: the current inventory status, inventory shortage index and historical inventory data are passed as input to the trained LSTM neural network. The LSTM network automatically learns and remembers the long-term dependencies of historical data through its gating mechanism. Based on the input data, the LSTM model will output the inventory demand in the future and generate a time series, which represents the predicted future inventory demand. Generate a replenishment trend chart: Based on the inventory demand time series output by the LSTM model, draw a replenishment trend chart. This chart shows the future period of time. The replenishment trend chart reflects the increase or decrease in inventory demand, helping warehouse managers determine whether they need to prepare for replenishment in advance, as well as the time and amount of replenishment. The trend chart can be drawn based on the following formula: in: It's in time Forecasted inventory requirements. Represents input features such as current inventory status, historical inventory data, and inventory shortage index. are the weights and biases of the LSTM model. is the prediction function of the LSTM neural network and represents the output calculated by the network.

[0034] Specifically, the specific process of analyzing the inventory shortage index and future inventory demand to obtain the inventory anomaly index is as follows: obtain the current inventory shortage index and future inventory demand for each type of silicone material; define the abnormal threshold of the inventory anomaly index according to the fluctuation characteristics of the inventory shortage index and future inventory demand; compare the current inventory quantity with the future demand, and evaluate the degree of inventory anomaly in each warehouse and each type of silicone material; compare the difference between the inventory shortage index and the future inventory demand with the set threshold to obtain the inventory anomaly index.

[0035] In this implementation plan, the inventory shortage index : After analyzing the current inventory status of each type of silicone material, the index obtained is used to measure the shortage of a certain type of material under the current inventory level. The higher the shortage index, the tighter the inventory of this type of material. Future inventory demand : Based on historical data, the demand for each type of silicone material in the future time period is predicted through the LSTM neural network, and the predicted value is the time series data of future demand. Abnormal threshold : To distinguish between normal and abnormal inventory status, a threshold is defined based on the fluctuation characteristics of the inventory shortage index and future demand. The threshold can be determined based on the statistical results of historical inventory data and demand data. The calculation formula for the inventory abnormality index is established based on the difference between the inventory shortage index and future demand. The inventory abnormality index is used to evaluate the inventory tightness of each type of silicone material and determine whether the current inventory status exceeds the range allowed by the business. The formula for the inventory abnormality index is: ;in: : Inventory abnormality index, used to reflect the abnormality of the overall inventory :No. Stock shortage index of silicone-like materials. :No. Future inventory demand for silicone-like materials. :The weight coefficient of each type of silicone material is used to reflect the relative importance of this type of material in the overall inventory : Smoothing coefficient, used to adjust the proportional relationship between the inventory shortage index and future demand, to ensure the stability of the index under specific demand fluctuations. : Adjustment term used to avoid the denominator being zero and to ensure numerical stability of the calculation. : Indicates the number of silica gel material types currently analyzed.

[0036] Specifically, the inventory optimization equation is constructed, and the specific process of dynamically allocating inventory to each warehouse is as follows: according to the inventory demand, inventory shortage index and inventory abnormality index of each warehouse, the inventory optimization goal is set; the future inventory demand, inventory shortage index and abnormality index of each warehouse are used as constraints and input into the inventory optimization equation; the optimal inventory allocation plan for each warehouse is analyzed through linear programming, and the inventory allocation plan is dynamically adjusted according to the real-time monitored inventory data.

[0037] In this implementation scheme, the goal of inventory optimization is to meet the inventory needs of each warehouse, maximize the utilization of inventory resources, and minimize the operational risks caused by insufficient or excessive inventory. The goal of the present invention is to minimize warehousing costs and inventory shortage risks and achieve efficient inventory configuration. The inventory demand, inventory shortage index and inventory abnormality index of each warehouse are used as constraints for inventory optimization: Inventory demand: the expected demand for a certain type of silicone material in each warehouse in the future. Inventory shortage index: an index value that reflects the current level of inventory tension, used to determine whether the warehouse has potential inventory shortages. Inventory abnormality index: indicates whether the current inventory status meets the reasonable inventory level, and is used to determine inventory abnormalities. Enter the inventory optimization equation: During the inventory optimization process, construct an optimization equation to integrate the needs and risk conditions of each warehouse to ensure the rationality of inventory allocation. The objective function of the inventory optimization equation is expressed as: ;in: : Indicates the number of warehouses. :No. Inventory shortage index of warehouses. : No. The future inventory requirements for a warehouse. : The weight coefficient used to adjust the difference between the inventory shortage index and future inventory demand. : The weight coefficient used to balance the impact of the abnormal index on inventory allocation. Adjust the importance of inventory shortages and abnormal situations in the optimization objectives. Analyze the optimal inventory allocation through linear programming: After setting the objective function and constraints, the system analyzes the inventory allocation plan through linear programming. Specifically: Use the linear programming algorithm to optimize the inventory allocation of each warehouse and solve the inventory allocation plan that minimizes the objective function. Based on real-time inventory monitoring data, the system uses the inventory demand, inventory shortage index and inventory abnormality index of each warehouse as constraint inputs to optimize the dynamic allocation plan of inventory. Dynamic adjustment: The system recalculates the inventory optimization equation regularly or according to changes in monitoring data to cope with demand fluctuations or changes in inventory status. Automatic execution: The system automatically allocates the inventory quantity of each warehouse based on the optimization results to ensure that the inventory level matches the actual demand.

[0038] In summary, this application has at least the following effects: An inventory monitoring and management system for a silicone material storage center can dynamically track the inventory status through real-time monitoring of the current inventory data, inventory shortage index, and future inventory demand of silicone materials, thereby avoiding material degradation or supply interruption caused by delayed inventory management. By analyzing the fluctuation characteristics of historical inventory data with the help of the LSTM neural network model, it can accurately predict future inventory demand, generate a replenishment trend chart, make inventory replenishment plans in advance, and ensure the continuous supply of silicone materials. Through the inventory optimization equation, the inventory shortage index and inventory abnormality index are comprehensively considered to dynamically adjust the inventory allocation of each warehouse, improve the utilization efficiency of inventory resources, and effectively control inventory costs. Through the abnormal monitoring module, early warning information is generated in time when the inventory status is abnormal, helping enterprises to respond quickly to inventory risks and reduce operational risks caused by inventory abnormalities. Intelligent and automated processing of inventory data is realized, the errors of manual management are reduced, and the efficiency and accuracy of warehouse management are improved.

[0039] It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0040] The present invention is described with reference to flowcharts and / or block diagrams of systems, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0041] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0042] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process in the computer or other programmable device. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0043] Although the preferred embodiments of the present invention have been described, those skilled in the art may make other changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention.

[0044] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. A silica gel material storage center inventory monitoring and management system, characterized in that: It includes the following modules: inventory data module, inventory detection module, inventory forecasting module, abnormal monitoring module, inventory allocation module; The inventory data module is used to obtain and store silicone material inventory data, including current silicone material inventory data and historical silicone material inventory data; The inventory detection module is used to analyze the inventory changes of silicone materials through Markov chain based on the current silicone material inventory data to obtain the inventory shortage index; The inventory forecasting module is used to analyze the fluctuation characteristics of historical silicone material inventory data through the LSTM neural network model, establish an inventory demand forecasting model, and predict future inventory demand and replenishment trend charts; The abnormality monitoring module is used to analyze the inventory shortage index and future inventory demand, obtain the inventory abnormality index, and compare it with the set abnormality threshold. When the abnormality index exceeds the abnormality threshold, an early warning message is generated and sent to the inventory allocation module; The inventory allocation module is used to construct an inventory optimization equation based on the future inventory demand and inventory shortage index of each warehouse, and dynamically allocate inventory to each warehouse.

2. The inventory monitoring and management system for a silica gel material storage center according to claim 1 is characterized by: The current silicone material inventory information data includes the current inventory quantity, inventory status, storage time, storage time, inventory batch number, inventory usage frequency and inventory change trend of each type of silicone material in each warehouse; Historical silicone material inventory information data includes historical inventory quantity changes in each warehouse, inventory status change records, inventory turnover rate, past replenishment records, and inventory fluctuation characteristics.

3. The inventory monitoring and management system for a silica gel material storage center according to claim 2 is characterized by: Based on the current silicone material inventory data, the specific process of analyzing silicone material inventory changes through Markov chain is as follows: According to the current silicone material inventory data, the inventory status of each type of silicone material is classified, several states are set, and the transition probability of each state is evaluated; According to the inventory quantity and the transition probability of inventory status, a Markov chain model is established to simulate the transition between different inventory status; Determine the time distribution and frequency of inventory status changes and calculate the transition probability matrix of inventory status; The current inventory quantity is combined with the transition probability matrix to simulate the inventory change process of each silicone material in each warehouse and evaluate the changing trend of future inventory status.

4. The inventory monitoring and management system for a silica gel material storage center according to claim 3 is characterized by: The specific process of obtaining the inventory shortage index is as follows: Based on the Markov chain analysis of silicone material inventory changes, the current inventory status, inbound and outbound conditions of each type of silicone material are classified; According to the transition probability of each type of inventory status, calculate the transition probability matrix of inventory status; According to the transition probability matrix and the current inventory quantity, the future changes of inventory status are simulated and the inventory shortage index under each inventory status is calculated.

5. The inventory monitoring and management system for a silica gel material storage center according to claim 4 is characterized by: The specific process of analyzing the volatility characteristics of historical silicone material inventory data through the LSTM neural network model is as follows: According to the historical silicone material inventory data, the historical data is divided into training set and test set, and the LSTM neural network structure is constructed; Input historical data into the trained LSTM model, extract key features based on historical inventory fluctuations in the time series, and identify the periodicity, regularity, and abnormal fluctuation patterns of inventory changes; Through time-series dependencies, the trend and fluctuation range of inventory changes are predicted and potential inventory risk points are identified.

6. The inventory monitoring and management system for a silica gel material storage center according to claim 5 is characterized by: The specific process of establishing an inventory demand forecasting model and predicting future inventory demand and replenishment trend chart is as follows: Based on the fluctuation characteristics of historical inventory data analyzed by the LSTM model, an inventory demand forecasting model is constructed; Input the current inventory status, inventory shortage index and historical inventory data, predict the future inventory demand through LSTM neural network, generate the time series of future inventory demand, and draw a replenishment trend chart.

7. The inventory monitoring and management system for a silica gel material storage center according to claim 6 is characterized by: The specific process of analyzing the inventory shortage index and future inventory demand and obtaining the inventory abnormality index is as follows: Get the current inventory shortage index and future inventory demand for each type of silicone material; According to the inventory shortage index and the fluctuation characteristics of future inventory demand, define the abnormal threshold of the inventory abnormality index; Compare current inventory quantities with future demand and assess the degree of inventory anomalies in each warehouse and for each type of silicone material; The difference between the inventory shortage index and the future inventory demand is compared with the set threshold to obtain the inventory abnormality index.

8. The inventory monitoring and management system for a silica gel material storage center according to claim 7 is characterized by: The specific process of constructing the inventory optimization equation and dynamically allocating inventory to each warehouse is as follows: Set inventory optimization goals based on the inventory demand, inventory shortage index, and inventory abnormality index of each warehouse; The future inventory demand, inventory shortage index and abnormal index of each warehouse are used as constraints and input into the inventory optimization equation; The optimal inventory allocation plan for each warehouse is analyzed through linear programming, and the inventory allocation plan is dynamically adjusted based on real-time monitored inventory data.

Images