Supply chain management system based on big data technology

Abstract

The invention relates to the technical field of data analysis, in particular to a supply chain management system based on a big data technology, and the system comprises a data integration control module, a prediction analysis processing module, a risk assessment module and a response and optimization module. According to the invention, by integrating the data of the sales end, the storage end and the transportation end and analyzing the time series data by using the recurrent neural network and the long-short-term memory network, the sales trend can be identified more accurately, demand prediction can be carried out, a scientific basis is provided for decision making, and the response speed and flexibility of a supply chain are enhanced. Through real-time monitoring and risk assessment of key indexes of the supply chain, risk management is more accurate, potential problems can be recognized in advance and quickly coped, and the overall operation efficiency and cost efficiency of the supply chain are improved through dynamic adjustment of inventory and order quantity, optimization of a production plan and effective coordination of links of the supply chain.

Description

Technical Field

[0001] The present invention relates to the field of data analysis technology, and in particular to a supply chain management system based on big data technology. Background Art

[0002] The field of data analytics involves methods and techniques for collecting, processing, analyzing, and interpreting data from various data sources to extract useful information and insights. This field uses statistics, algorithms, and computer science techniques to efficiently process and analyze data through machine learning, artificial intelligence, data mining, and big data technologies. The goal of data analytics is to transform large amounts of data into actionable information, helping decision makers understand patterns and trends and make more informed decisions. This technology is widely used in business intelligence, market research, financial analysis, health informatics, and many other fields, providing organizations with the means to optimize operations, improve efficiency, and enhance market competitiveness.

[0003] Supply chain management systems (SCMs) use data analytics and information technology to optimize and control the flow of products from suppliers to end users. They primarily coordinate all supply chain participants, including suppliers, manufacturers, warehouses, and retailers, to ensure the efficient and timely flow of materials and information. These systems leverage real-time data analysis to forecast demand, optimize inventory, and reduce operating costs, while enhancing supply chain transparency and responsiveness. The goal of SCMs is to improve the efficiency and effectiveness of the overall supply chain, supporting businesses in maintaining their competitive advantage in a highly competitive market.

[0004] Traditional management systems rely on decentralized data processing and analysis methods, and cannot effectively predict market and inventory demands when processing complex data sets. This makes it difficult for supply chain systems to make timely adjustments under rapidly changing market conditions, increasing operating costs and the risk of missing market opportunities. Traditional systems have difficulty in real-time tracking and quantitatively assessing supply risks in terms of risk assessment, limiting their effectiveness in preventing supply disruptions and optimizing resource allocation, affecting the efficiency and stability of the entire supply chain. Risk assessments often rely on historical data and empirical judgments, which are insufficient for rapid responses to emergencies, leading to supply chain disruptions, inventory backlogs or out-of-stocks, and impacting the company's market competitiveness and customer satisfaction. Summary of the Invention

[0005] The purpose of the present invention is to solve the shortcomings of the existing technology and propose a supply chain management system based on big data technology.

[0006] In order to achieve the above objectives, the present invention adopts the following technical solution: a supply chain management system based on big data technology, the system comprising:

[0007] The data integration control module receives data from the sales, warehousing, and transportation ends through API interfaces based on the target supply chain, collects order data, synchronizes data based on timestamps, interpolates missing data, standardizes and scales data, unifies data encoding, and optimizes the consistency and integrity of data formats to obtain an integrated data set.

[0008] The forecasting analysis processing module analyzes the time series data based on the integrated data set through a recurrent neural network and a long short-term memory network, analyzes the changes in sales data over a period of time, identifies sales trends, and predicts sales volume for future periods based on current sales data to obtain demand forecast information;

[0009] Based on the demand forecast information, the risk assessment module monitors changes in key supply chain indicators, including inventory turnover rate, order delivery rate, order cycle time, and cost efficiency. The module analyzes the degree of change in key supply chain indicators within a predetermined period, tracks the key indicators in real time, quantitatively assesses the risk of supply disruption, and obtains risk assessment information.

[0010] The response and optimization module adjusts inventory and order quantities based on the demand forecast information and risk assessment information according to the current inventory level, optimizes production plans, and optimizes supply chain communication and collaboration by coordinating standard processes and communication protocols of upstream and downstream companies to obtain optimized execution information.

[0011] The present invention is improved in that the steps of obtaining the integrated data set are:

[0012] Based on the target supply chain, data from the sales, warehousing, and transportation ends are received through the API interface, and the data is synchronized and sorted according to the timestamp to obtain a synchronized and sorted data set;

[0013] Based on the synchronously collated data set, missing data are identified and interpolated using the formula:

[0014]

[0015] Calculate the standardized and scaled data points to obtain a standardized and scaled data set;

[0016] Among them, X j represents the original data point, X min and X max are the minimum and maximum values in the data, respectively, Y and b Y are the minimum and maximum values of the scaled range, Y j are the scaled data points;

[0017] Based on the standardized and scaled data set, data encoding and format conversion processing is performed to optimize the consistency and integrity of the data and obtain an integrated data set.

[0018] The present invention is improved in that the step of identifying sales trends is as follows:

[0019] Initializing a network model based on the integrated data set, loading the integrated data set into a recurrent neural network and a long short-term memory network, configuring training parameters including a learning rate and a batch size, and obtaining a model initialization state;

[0020] Based on the model initialization state, the time series data is processed through the recurrent neural network and the long short-term memory network, and the formula is used:

[0021]

[0022] Calculate the sales change rate, where V rate is the sales change rate, s t is the sales volume at time t, s t-1 is the sales at time t-1, α is the rate adjustment factor, and T is the total time period;

[0023] Based on the sales change rate, key trend changes in the sales data are analyzed, trend fluctuation points are calibrated, and sales trend identification results are obtained.

[0024] The present invention is improved in that the step of obtaining the demand forecast information is as follows:

[0025] Based on the sales trend identification result, extract the sales change rate, collect current sales data, set the baseline state of the prediction model, and obtain the prediction initialization state;

[0026] Based on the predicted initialization state, a statistical prediction model is used, using the formula:

[0027] P future =s current +V rate ×Δt+β P ×cos(2π×f P ×t P );

[0028] Calculate sales volume in future periods to obtain demand forecast information;

[0029] Among them, P future is the predicted sales volume for the future period, s current is the sales data at the current time point, V rate is the sales change rate, Δt is the length of the forecast period, β P is the periodic impact factor, fP is the periodic frequency, t P is the time variable and π is the circumference of a circle.

[0030] The present invention is improved in that the step of analyzing the degree of change of key indicators of the supply chain within a predetermined period is as follows:

[0031] Based on the demand forecast information, key supply chain indicators are summarized, including inventory turnover rate, order delivery rate, order cycle time and cost efficiency, and a time window for analysis is set to obtain a basic monitoring data set;

[0032] Based on the basic monitoring data set, using the statistical analysis model, the formula is adopted:

[0033]

[0034] Calculate the change ratio of each indicator within a predetermined period;

[0035] Among them, B is the change ratio of the key indicators of the supply chain, w i is the weight coefficient of the i-th indicator, Q c,i is the value of the i-th indicator in the current period c, Q c-1,i is the value of the ith indicator in the previous cycle c-1, and n is the total number of key indicators monitored;

[0036] Based on the proportion of the degree of change of each indicator within a predetermined period, the fluctuation of the indicator and the potential impact on supply chain efficiency are evaluated to obtain the supply chain change degree analysis results.

[0037] The present invention is improved in that the steps of obtaining the risk assessment information are:

[0038] Based on the analysis results of the degree of change in the supply chain, according to the change ratio of the key indicators of the supply chain, the formula is:

[0039]

[0040] Calculate a quantitative value for supply disruption risk;

[0041] Among them, R risk is the quantitative value of supply disruption risk, λ R is the risk sensitivity coefficient, B is the proportional value of the change degree of key indicators of the supply chain, and e is the base of the natural logarithm;

[0042] Based on the quantified value of the supply disruption risk, the supply disruption risk is assessed according to the magnitude of the quantified value to obtain risk assessment information.

[0043] The present invention is improved in that the steps of optimizing the production plan are:

[0044] Based on the demand forecast information and risk assessment information, and according to the current inventory level, the formula:

[0045] I new =I current +α Z ×(P future -I current )×(1+β Z ×R risk );

[0046] Calculate adjusted inventory levels;

[0047] Among them, I current is the current inventory, α Z and β Z is the inventory adjustment factor, P future To predict sales volume, R risk is a quantitative value for the risk of supply disruption;

[0048] Based on the adjusted inventory, combined with actual production capacity and supply chain conditions, the formula:

[0049] S opt =P future ×(1+γ Z ×R risk );

[0050] Calculate the adjusted production order quantity;

[0051] Among them, P future To predict sales volume, R risk is the quantitative value of supply disruption risk, S opt is the adjusted production order quantity, γ Z is the regulating factor;

[0052] Based on the adjusted inventory quantity and the adjusted production order quantity, they are applied to the target supply chain to optimize product supply, market demand and risk matching, and obtain optimized supply information.

[0053] The present invention is improved in that the step of obtaining the optimization execution information is as follows:

[0054] Based on the optimized supply information, evaluate the existing communication processes and protocols between upstream and downstream enterprises, identify existing inefficiencies and bottlenecks, and collect relevant data on communication and collaboration to obtain process and communication information;

[0055] Based on the above process and communication information, the formula:

[0056]

[0057] Calculate communication efficiency;

[0058] Among them, C eff is the communication efficiency, v f is the importance weight of process f, R f is the response rate of the fth process, d f is the communication delay of the fth process, T f is the communication time of the fth process, and F is the total number of processes;

[0059] Based on the communication efficiency, the standard processes and communication protocols of upstream and downstream enterprises are coordinated, and the changes in communication efficiency before and after coordination are analyzed, the coordination effect is evaluated, the communication and collaboration of the supply chain is optimized, and optimized execution information is obtained.

[0060] Compared with the prior art, the advantages and positive effects of the present invention are:

[0061] In the present invention, by integrating data from the sales, warehousing and transportation ends, and using recurrent neural networks and long short-term memory networks to analyze time series data, sales trends can be identified more accurately, demand forecasts can be made, and a scientific basis for decision-making can be provided. The response speed and flexibility of the supply chain are enhanced, and real-time monitoring and risk assessment of key indicators of the supply chain make risk management more accurate, which helps to identify potential problems early and respond quickly. Through dynamic adjustment of inventory and order quantities, optimization of production plans, and effective coordination of various links in the supply chain, the overall operating efficiency and cost efficiency of the supply chain are improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0062] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. The drawings are only used to illustrate the implementation methods and are not to be considered as limiting the present invention.

[0063] Figure 1 is a system flow chart of the present invention;

[0064] Figure 2 A flow chart for obtaining an integrated data set for the present invention;

[0065] Figure 3 a flow chart for identifying sales trends for the present invention;

[0066] Figure 4 A flow chart for obtaining demand forecast information for the present invention;

[0067] Figure 5 A flow chart of analyzing the degree of change of key indicators of a supply chain within a predetermined period according to the present invention;

[0068] Figure 6 a flow chart for obtaining risk assessment information for the present invention;

[0069] Figure 7 A flow chart for optimizing the production plan of the present invention;

[0070] Figure 8 The flowchart of the present invention is to obtain the optimization execution information. DETAILED DESCRIPTION

[0071] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only some of the embodiments of the present invention, not all of them. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making any creative efforts shall fall within the scope of protection of the present invention.

[0072] Unless otherwise defined, all technical and scientific terms used in the present invention have the same meaning as commonly understood by those skilled in the art to which the present invention belongs; the terms used in the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention. The terms "including" and "having" and any variations thereof in the description and claims of the present invention and the above-mentioned drawings are intended to cover non-exclusive inclusions.

[0073] In the description of the embodiments of the present invention, technical terms such as "first" and "second" are used solely to distinguish between different objects and should not be understood to indicate or imply relative importance or to implicitly specify the quantity, specific order, or primary and secondary relationship of the technical features indicated. In the description of the embodiments of the present invention, "plurality" means more than two, unless otherwise specifically defined.

[0074] In the description of the embodiments of the present invention, the term "and / or" is simply a description of the association relationship between associated objects, indicating that three relationships can exist. For example, A and / or B can represent the following three situations: A exists alone, A and B exists simultaneously, and B exists alone. In addition, the character " / " in this document generally indicates that the associated objects are in an "or" relationship.

[0075] In the description of the embodiments of the present invention, the term "multiple" refers to more than two (including two). Similarly, "multiple groups" refers to more than two groups (including two groups), and "multiple pieces" refers to more than two pieces (including two pieces).

[0076] In the description of the embodiments of the present invention, the technical terms "center", "longitudinal", "lateral", "length", "width", "thickness", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", "clockwise", "counterclockwise", "axial", "radial", "circumferential", etc., indicating the orientation or position relationship, are based on the orientation or position relationship shown in the accompanying drawings, and are only for the convenience of describing the embodiments of the present invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operate in a specific orientation, and therefore cannot be understood as limiting the embodiments of the present invention.

[0077] In the description of the embodiments of the present invention, unless otherwise specified and limited, the technical terms "installed" and "connected" are used interchangeably.

[0078] Terms such as "connect" and "fixed" should be interpreted broadly. For example, they can refer to fixed connection, detachable connection, or integration; mechanical connection or electrical connection; direct connection or indirect connection through an intermediate medium; internal communication between two components or interaction between two components. Those skilled in the art will understand the specific meanings of the above terms in the examples of the present invention based on specific circumstances.

[0079] Example 1

[0080] See also Figure 1 The present invention provides a technical solution: a supply chain management system based on big data technology, the system comprising:

[0081] The data integration control module receives data from the sales, warehousing, and transportation ends through API interfaces based on the target supply chain, collects order data, synchronizes data based on timestamps, interpolates missing data, standardizes and scales data, unifies data encoding, and optimizes the consistency and integrity of data formats to obtain an integrated data set.

[0082] The forecasting and analysis processing module uses recurrent neural networks and long-short-term memory networks to analyze time series data based on the integrated data set, analyze changes in sales data over a period of time, identify sales trends, and predict sales volumes for future periods based on current sales data to obtain demand forecast information.

[0083] The risk assessment module monitors changes in key supply chain indicators based on demand forecast information, including inventory turnover, order delivery rate, order cycle time, and cost efficiency. It analyzes the degree of change in key supply chain indicators within a predetermined period, tracks key indicators in real time, and quantitatively assesses the risk of supply disruption to obtain risk assessment information.

[0084] The response and optimization module adjusts inventory and order quantities based on demand forecast information and risk assessment information according to current inventory levels, optimizes production plans, and optimizes supply chain communication and collaboration by coordinating standard processes and communication protocols of upstream and downstream companies to obtain optimized execution information.

[0085] The integrated data set specifically includes data consistency tables, data integrity tables and standardized data information. Demand forecast information includes sales trend information, cyclical change information and market demand forecast information. Risk assessment information includes key risk point marking information, risk factor quantification information and potential risk assessment information. Optimization execution information includes inventory adjustment measures, optimized production scheduling plans and resource coordination information.

[0086] See also Figure 2 , the steps to obtain the integrated data set are:

[0087] Based on the target supply chain, data from the sales, warehousing, and transportation ends are received through the API interface, and the data is synchronized and sorted according to the timestamp to obtain a synchronized and sorted data set;

[0088] Data from the sales, warehousing, and transportation ends is received through the API interface, and data is synchronized and organized based on the core needs of the target supply chain to ensure the time consistency of the data. For example, through software tools such as ETL, the sales data of the most recent week, including sales revenue, sales volume, and timestamps, is first extracted from the sales end, inventory change records are obtained from the warehousing end, and logistics status data is obtained from the transportation end. All data are accompanied by detailed timestamp information to ensure time alignment during the organization process. After processing, a synchronized and organized data set is obtained based on the timestamp, including sales information, inventory status, and transportation status. The data set provides an accurate time benchmark for subsequent operations.

[0089] Based on the synchronous collation of the data set, missing data is identified and interpolated using the formula:

[0090]

[0091] Calculate the standardized and scaled data points to obtain a standardized and scaled data set;

[0092] Among them, X j represents the original data point, X min and X max are the minimum and maximum values in the data, respectively, Y and b Y are the minimum and maximum values of the scaled range, Y j are the scaled data points;

[0093] formula:

[0094]

[0095] The benefit of the formula is that it converts the data into values within a uniform range by standardizing and scaling the raw data, facilitating subsequent statistical analysis and the application of machine learning models.

[0096] Detailed explanation of the formula and the process of formula calculation and derivation:

[0097] In practical applications, it is necessary to determine the minimum value X in the original data set min and the maximum value X max , which can be obtained directly through database query or data analysis software, such as using SQL query or Python's Pandas library to calculate the minimum and maximum values. Let X min =10,X max =100, then determine the scaling range, set a Y =0 and b Y =1, each data point X j Substitute into the formula to calculate Y j , for example, for X j =55, substitute into the calculation to get The results show that the normalized data point Y j It is located in the middle of the new data range, consistent with the position in the original data set, and the new data range is more suitable for training and analysis of machine learning models.

[0098] Based on the standardized and scaled data set, perform data encoding and format conversion to optimize data consistency and integrity to obtain an integrated data set;

[0099] After the data set is integrated, data encoding and format conversion are performed to improve data consistency and integrity. All text data is encoded using a unified encoding format, such as UTF-8, to ensure error-free data exchange. At the same time, format conversion is performed on numerical data, such as unifying date and time data into the ISO8601 standard format. The data set is cleaned and verified to ensure that the data is correct and meets the standard format required for subsequent analysis. Through the data processing steps, the integrated data set obtained can be directly used for efficient data analysis and decision support.

[0100] See also Figure 3 , the steps to identify sales trends are:

[0101] Initialize the network model based on the integrated dataset, load the integrated dataset into the recurrent neural network and long short-term memory network, configure the training parameters, including the learning rate and batch size, and obtain the model initialization state;

[0102] Based on the integrated dataset, the network model is initialized and training parameters including the learning rate and batch size are configured. The learning rate is usually set between 0.01 and 0.1, and the optimal value is selected based on the results of the early small batch test. For example, the learning rate is adjusted by monitoring the training loss of early stopping to avoid overfitting. The batch size is adjusted according to the computing resources and the size of the dataset. Common settings are 32, 64, or 128. Obtaining the model initialization state indicates that the network is ready to load data for training, ensuring that the model can effectively process the input integrated dataset and learn effectively.

[0103] Based on the model initialization state, time series data is processed through recurrent neural networks and long short-term memory networks, and the formula is used:

[0104]

[0105] Calculate the sales change rate, where V rate is the sales change rate, s t is the sales volume at time t, s t-1 is the sales at time t-1, α is the rate adjustment factor, and T is the total time period;

[0106] formula:

[0107]

[0108] The benefit of the formula is that by calculating the rate of change of sales in a time series, sales dynamics can be accurately captured, thereby optimizing inventory management and sales strategies.

[0109] Detailed explanation of the formula and the process of formula calculation and derivation:

[0110] Settings t For the sales at a certain time point, the sales data of each time point in the past can be obtained from the database, for example, t For 100,000 yuan, t-1 The total time period 2 is 30 days, and the rate adjustment factor α is calculated based on the volatility analysis of historical data and is determined to be 0.05. Substituting the parameter value into the formula, we can get: The result shows that the sales change rate is 100, which reflects the average change rate of sales during this cycle and has direct guiding significance for sales strategy adjustments and inventory management.

[0111] Based on the sales change rate, analyze the key trend changes in sales data, calibrate trend fluctuation points, and obtain sales trend identification results;

[0112] Key trend changes in sales data are analyzed based on the sales change rate, and trend fluctuation points are calibrated by setting specific thresholds. For example, if the sales change rate exceeds 5%, it is marked as a key growth point, and if it decreases by more than 5%, it is marked as a key decline point. Through this method, the sales trend identification results obtained can be directly applied to marketing decisions and inventory adjustments, allowing companies to respond quickly to market dynamics, optimize inventory levels, and reduce the risk of oversupply or out-of-stock. The entire analysis process relies on precise data processing and efficient computing models to ensure the reliability and practicality of the results.

[0113] See also Figure 4 , the steps for obtaining demand forecast information are:

[0114] Based on the sales trend identification results, the sales change rate is extracted, and the current sales data is collected to set the baseline state of the forecast model and obtain the forecast initialization state;

[0115] Extract the sales change rate and collect current sales data to set a baseline state for the forecasting model. Ensure that the forecasting model is initialized with the latest and most accurate market data. For example, by analyzing the sales data of the past three months, identify the sales trends of major products, and use data analysis tools such as Tableau or Python for data visualization to ensure that the forecasting model is adjusted based on the current market situation and improve forecast accuracy. By integrating the latest sales data and market trends, the initial state of the forecasting model is obtained. The process involves data collection and analysis, as well as data cleaning and preparation before using the forecasting model to ensure data quality and relevance.

[0116] Based on the prediction initialization state, using the statistical prediction model, the formula is:

[0117] P future =s current +V rate ×Δt+β P ×cos(2π×f P ×t P );

[0118] Calculate sales volume in future periods to obtain demand forecast information;

[0119] Among them, P future is the predicted sales volume for the future period, s current is the sales data at the current time point, V rate is the sales change rate, Δt is the length of the forecast period, β P is the periodic impact factor, f P is the periodic frequency, defining the frequency of the periodic effect, t Pis the time variable, that is, the current periodic time point, used to represent the current time in the periodic function, and π is the pi;

[0120] formula:

[0121] P future =s current +V rate ×Δt+β P ×cos(2π×f P ×t P );

[0122] The benefit of the formula is that, by combining current sales data, sales change rate and cyclical influencing factors, it provides a comprehensive method for predicting future sales volume, which can adapt to changes in demand under different market conditions.

[0123] Detailed explanation of the formula and the process of formula calculation and derivation:

[0124] Assume the current sales data s current For 150,000 units, the sales change rate V rate is 200 units per day, the length of the forecast period Δt is 30 days, and the periodic impact factor β P is 500 units, the periodic frequency f P is once a month, the time variable t P The current cycle is on the 15th day, and the formula is used to calculate: The results show that the predicted sales volume in the next 30 days is 155,500 units, which shows that the forecast model can take into account the impact of cyclical factors and provide data support for sales strategies.

[0125] See also Figure 5 ,The steps to analyze the degree of change of key indicators of the supply chain within a predetermined period are:

[0126] Based on demand forecast information, key supply chain indicators are summarized, including inventory turnover rate, order delivery rate, order cycle time and cost efficiency, and the analysis time window is set to obtain the basic monitoring data set;

[0127] Based on demand forecast information, key supply chain indicators are summarized, including inventory turnover rate, order delivery rate, order cycle time and cost efficiency. The summary of indicators helps monitor the operating efficiency of the entire supply chain. For example, inventory turnover rate is calculated by analyzing inventory inbound and outbound records within a specific time window. Data analysis tools are used to sample and analyze inventory data from the past three months to determine inventory liquidity. Order delivery rate is evaluated by tracking and comparing the number of planned and actually completed orders. This can provide a basic monitoring data set that reflects the current supply chain operation efficiency and provides data support for analysis.

[0128] Based on the basic monitoring data set, using the statistical analysis model, the formula is:

[0129]

[0130] Calculate the change ratio of each indicator within a predetermined period;

[0131] Among them, B is the change ratio of the key indicators of the supply chain, w i is the weight coefficient of the i-th indicator, Q c,i is the value of the i-th indicator in the current period c, Q c-1,i is the value of the ith indicator in the previous cycle c-1, and n is the total number of key indicators monitored;

[0132] formula:

[0133]

[0134] The benefit of the formula is that it provides a method to quantify changes in key supply chain indicators, which can be used to evaluate the effectiveness of improvement measures and the fluctuations of indicators during the monitoring period.

[0135] Detailed explanation of the formula and the process of formula calculation and derivation:

[0136] For example, suppose there are three indicators: inventory turnover rate, order delivery rate, and cost efficiency. Their corresponding weights are w1=0.3, w2=0.5, and w3=0.2. The indicator values in the current cycle c are 100, 95, and 90 respectively, and the indicator values in the previous cycle c-1 are 95, 90, and 85 respectively. Substitute them into the formula to calculate, The results show that, taking into account the weight of each indicator, the overall key indicator change ratio is 5.6%. This result can be used to evaluate the overall health of the supply chain and the fluctuation of various indicators.

[0137] Based on the change ratio of each indicator within a predetermined period, the fluctuation of the indicator and the potential impact on supply chain efficiency are evaluated to obtain the supply chain change degree analysis results;

[0138] Based on the proportion of changes in each indicator within a predetermined period, an in-depth assessment of the potential impact on supply chain efficiency is conducted. For example, by comparing the fluctuations of key indicators within the period, possible areas of efficiency improvement or reduction are identified. Combined with industry standards and past performance data, data analysis software is used to depict trend charts of these changes. Through trend charts and fluctuation data, the supply chain management team can conduct cost-benefit analysis, evaluate which improvement measures are likely to bring the greatest benefits, and obtain comprehensive analysis results of the degree of change in the supply chain, which will help to formulate more effective strategies to optimize supply chain operations.

[0139] See also Figure 6 , the steps for obtaining risk assessment information are:

[0140] Based on the analysis results of the degree of change in the supply chain and the proportion of the degree of change in the key indicators of the supply chain, the formula is:

[0141]

[0142] Calculate a quantitative value for supply disruption risk;

[0143] Among them, R risk is the quantitative value of supply disruption risk, λ R is the risk sensitivity coefficient, B is the proportional value of the change degree of key indicators of the supply chain, and e is the base of the natural logarithm;

[0144] formula:

[0145]

[0146] The benefit of the formula is that it provides a method for quantifying the risk of supply disruption through calculation, allowing risk management decisions to be made based on specific numerical values.

[0147] Detailed explanation of the formula and the process of formula calculation and derivation:

[0148] Assume that the change ratio value B of the key indicator is 0.056 (as calculated above), and the risk sensitivity coefficient λ R According to historical data analysis, it is set to 3 and then put into the formula to calculate R risk =1-e -3×0.056 =1-e -0.168 ≈1-0.845=0.155. The results show that the quantitative value of the supply disruption risk is 0.155, which indicates that there is a moderate risk in the current supply chain status. The management team should pay attention to this and consider corresponding risk mitigation strategies based on this risk level.

[0149] Based on the quantitative value of the supply disruption risk, the supply disruption risk is evaluated according to the magnitude of the quantitative value to obtain risk assessment information;

[0150] Based on the quantitative value of supply disruption risk, a comprehensive assessment of the overall risk status of the supply chain is conducted, including comparing the quantitative value with industry standards or preset risk thresholds. For example, if the quantitative value exceeds 0.2, the supply chain is considered to be in a high-risk state and emergency measures such as multi-source procurement strategies or increased inventory are required. The risk assessment information obtained can help decision makers understand the current risk level of the supply chain and formulate corresponding risk management strategies accordingly, which helps to ensure the continuity and efficiency of corporate operations.

[0151] See also Figure 7 , the steps to optimize the production plan are:

[0152] Based on demand forecast information and risk assessment information, according to the current inventory level, the formula:

[0153] I new =I current +α Z ×(P future -I current )×(1+β Z ×R risk );

[0154] Calculate adjusted inventory levels;

[0155] Among them, I current is the current inventory, α Z and β Z is the inventory adjustment factor, P future To predict sales volume, R risk is a quantitative value for the risk of supply disruption;

[0156] formula:

[0157] I new =I current +α Z ×(P future -I current )×(1+β Z ×R risk );

[0158] The benefit of the formula is that by combining current inventory levels, forecast sales, and risk assessment, it calculates adjusted inventory levels, optimizing inventory management to adapt to market demand and potential risks.

[0159] Detailed explanation of the formula and the process of formula calculation and derivation:

[0160] Assume the current inventory I current For 1000 units, the predicted sales volume is P future is 1200 units, and the inventory adjustment factor α ZSet to 0.3, the risk adjustment factor β Z Set to 0.1, the quantitative value of supply disruption risk R risk is 0.155 (as shown in the previous calculation), and we can get it by substituting it into the formula. new =1000+0.3×(1200-1000)×(1+0.1×0.155)

[0161] =1000+60×1.0155≈1061. This result indicates that the adjusted inventory level is 1061 units, which shows how to adjust inventory based on forecast sales and risk level to avoid over-inventory or under-inventory.

[0162] Based on the adjusted inventory, combined with actual production capacity and supply chain conditions, the formula:

[0163] S opt =P future ×(1+γ Z ×R risk );

[0164] Calculate the adjusted production order quantity;

[0165] Among them, P future To predict sales volume, R risk is the quantitative value of supply disruption risk, S opt is the adjusted production order quantity, γ Z is the regulating factor;

[0166] formula:

[0167] S opt =P future ×(1+γ Z ×R risk );

[0168] The formula is beneficial in that it adjusts production order quantities based on forecast sales and supply disruption risks, ensuring that production plans are aligned with market demand and potential risks.

[0169] Detailed explanation of the formula and the process of formula calculation and derivation:

[0170] Set the forecast sales volume P future The quantitative value of supply interruption risk is 1200 units, R risk is 0.155, and the adjustment factor γ Z Set it to 0.2 and substitute it into the formula to calculate, S opt=1200×(1+0.2×0.155)=1200×1.031=1237.2. The result shows that the adjusted production order quantity is 1237.2 units. This quantity reflects the response to market forecasts and risks, ensuring that production volume can meet the expected market demand while taking into account potential supply risks.

[0171] Based on the adjusted inventory and production order quantities, the data is applied to the target supply chain to optimize product supply, market demand, and risk matching, thus obtaining optimized supply information.

[0172] Apply the adjusted inventory and production order quantities to the target supply chain to optimize product supply, match market demand and risk. For example, adjust raw material procurement plans and production scheduling based on the adjusted production order quantities, consider supply disruption risks, and increase backup suppliers of key raw materials. These measures can effectively reduce risks caused by market fluctuations or supply problems. The optimized supply information helps companies respond to market changes more flexibly and maintain the stability and efficient operation of the supply chain.

[0173] See also Figure 8 , the steps to obtain the optimized execution information are:

[0174] Based on the optimized supply information, evaluate the existing communication processes and protocols between upstream and downstream companies, identify existing inefficiencies and bottlenecks, and collect relevant data on communication and collaboration to obtain process and communication information;

[0175] The existing communication processes and protocols between upstream and downstream companies were evaluated. Through on-site visits and internal software log analysis, the main bottlenecks in the demand forecast information exchange and order processing processes were identified. For example, the long response time of some suppliers resulted in insufficient response speed of the entire supply chain. Communication delays and data inconsistencies in the process were archived and summarized. Through actual operation scenario comparisons, such as using the data export function of the ERP system, the order processing time between different suppliers was compared to identify inefficient links. The collected communication and collaboration related data showed that some suppliers were slow to process specific order types, affecting the efficiency of the overall supply chain. The preliminary analysis results helped identify key areas for improvement.

[0176] Based on process and communication information, the formula:

[0177]

[0178] Calculate communication efficiency;

[0179] Among them, C eff is the communication efficiency, v f is the importance weight of process f, R fis the response rate of the fth process, d f is the communication delay of the fth process, T f is the communication time of the fth process, and F is the total number of processes;

[0180] formula:

[0181]

[0182] The usefulness of the formula is that by considering the importance, response rate and communication time of each process, the overall communication efficiency is calculated, providing a quantitative tool to evaluate the efficiency of the communication process.

[0183] Detailed explanation of the formula and the process of formula calculation and derivation:

[0184] Set the total number of processes F to 3 and the importance weight of each process v f are 0.5, 0.3, and 0.2 respectively, and the response rate R f They are 100, 80, and 60 respectively, and the communication delay d f They are 0.3, 0.5, and 0.2 respectively, and the communication time T f They are 1, 10, and 100 respectively. Substitute them into the formula to calculate: The results show that the communication efficiency is 71.07, which shows the improvement potential in reducing communication delay and increasing response speed.

[0185] Based on communication efficiency, coordinate the standard processes and communication protocols of upstream and downstream enterprises, analyze the changes in communication efficiency before and after coordination, evaluate the coordination effect, optimize supply chain communication and collaboration, and obtain optimized execution information;

[0186] Coordinate the standard processes and communication protocols of upstream and downstream enterprises, standardize the improved processes, such as adopting a unified data exchange format and a faster response mechanism, and re-evaluate the adjusted communication efficiency through implementation measures. Analysis shows that after adopting the new protocol, the overall communication delay is reduced, the response rate is improved, and the coordination effect is significant. For example, after implementing the new communication protocol, through simulation testing and actual operation comparison, it was found that the average processing time was reduced from the original 48 hours to 30 hours, which improved efficiency. The standardized measures effectively improved the communication and collaboration level of the supply chain, and the optimized execution information showed that the new protocol and process improvements brought practical benefits, such as cost savings and shortened response time, which brought higher adaptability and competitiveness to the entire supply chain.

[0187] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, not to limit them. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some or all of the technical features therein. These modifications or replacements do not deviate the essence of the corresponding technical solutions from the scope of the technical solutions of the embodiments of the present invention, and they should all be included in the scope of the claims and description of the present invention. In particular, as long as there is no structural conflict, the various technical features mentioned in the various embodiments can be combined in any way. The present invention is not limited to the specific embodiments disclosed herein, but includes all technical solutions that fall within the scope of the claims.

Claims

1. A supply chain management system based on big data technology, characterized in that: The system comprises: The data integration control module receives data from the sales, warehousing, and transportation ends through API interfaces based on the target supply chain, collects order data, synchronizes data based on timestamps, interpolates missing data, standardizes and scales data, unifies data encoding, and optimizes the consistency and integrity of data formats to obtain an integrated data set. The forecasting analysis processing module analyzes the time series data based on the integrated data set through a recurrent neural network and a long short-term memory network, analyzes the changes in sales data over a period of time, identifies sales trends, and predicts sales volume for future periods based on current sales data to obtain demand forecast information; Based on the demand forecast information, the risk assessment module monitors changes in key supply chain indicators, including inventory turnover rate, order delivery rate, order cycle time, and cost efficiency. The module analyzes the degree of change in key supply chain indicators within a predetermined period, tracks the key indicators in real time, quantitatively assesses the risk of supply disruption, and obtains risk assessment information. The response and optimization module adjusts inventory and order quantities based on the demand forecast information and risk assessment information according to the current inventory level, optimizes production plans, and optimizes supply chain communication and collaboration by coordinating standard processes and communication protocols of upstream and downstream companies to obtain optimized execution information.

2. The supply chain management system based on big data technology according to claim 1 is characterized in that: The steps for obtaining the integrated data set are: Based on the target supply chain, data from the sales, warehousing, and transportation ends are received through the API interface, and the data is synchronized and sorted according to the timestamp to obtain a synchronized and sorted data set; Based on the synchronously collated data set, missing data are identified and interpolated using the formula: Calculate the standardized and scaled data points to obtain a standardized and scaled data set; Among them, X j represents the original data point, X min and X max are the minimum and maximum values in the data, respectively, Y and b Y are the minimum and maximum values of the scaled range, Y j are the scaled data points; Based on the standardized and scaled data set, data encoding and format conversion processing is performed to optimize the consistency and integrity of the data and obtain an integrated data set.

3. The supply chain management system based on big data technology according to claim 1 is characterized in that: The steps for identifying sales trends are: Initializing a network model based on the integrated data set, loading the integrated data set into a recurrent neural network and a long short-term memory network, configuring training parameters including a learning rate and a batch size, and obtaining a model initialization state; Based on the model initialization state, the time series data is processed through the recurrent neural network and the long short-term memory network, and the formula is used: Calculate the sales change rate, where V rate is the sales change rate, s t is the sales volume at time t, s t-1 is the sales at time t-1, α is the rate adjustment factor, and T is the total time period; Based on the sales change rate, key trend changes in the sales data are analyzed, trend fluctuation points are calibrated, and sales trend identification results are obtained.

4. The supply chain management system based on big data technology according to claim 3 is characterized in that: The steps for obtaining the demand forecast information are as follows: Based on the sales trend identification result, extract the sales change rate, collect current sales data, set the baseline state of the prediction model, and obtain the prediction initialization state; Based on the predicted initialization state, a statistical prediction model is used, using the formula: P future =s current +V rate ×Δt+β P ×cos(2π×f P ×t P ); Calculate sales volume in future periods to obtain demand forecast information; Among them, P future is the predicted sales volume for the future period, s current is the sales data at the current time point, V rate is the sales change rate, Δt is the length of the forecast period, β P is the periodic impact factor, f P is the periodic frequency, t P is the time variable, and π is the circumference of a circle.

5. The supply chain management system based on big data technology according to claim 1 is characterized in that: The steps of analyzing the degree of change of key supply chain indicators within a predetermined period are as follows: Based on the demand forecast information, key supply chain indicators are summarized, including inventory turnover rate, order delivery rate, order cycle time and cost efficiency, and a time window for analysis is set to obtain a basic monitoring data set; Based on the basic monitoring data set, using the statistical analysis model, the formula is adopted: Calculate the change ratio of each indicator within a predetermined period; Among them, B is the change ratio of the key indicators of the supply chain, w i is the weight coefficient of the i-th indicator, Q c,i is the value of the i-th indicator in the current period c, Q c-1,i is the value of the ith indicator in the previous cycle c-1, and n is the total number of key indicators monitored; Based on the proportion of the degree of change of each indicator within a predetermined period, the fluctuation of the indicator and the potential impact on supply chain efficiency are evaluated to obtain the supply chain change degree analysis results.

6. The supply chain management system based on big data technology according to claim 5 is characterized in that: The steps for obtaining the risk assessment information are: Based on the analysis results of the degree of change in the supply chain, according to the change ratio of the key indicators of the supply chain, the formula is: Calculate a quantitative value for supply disruption risk; Among them, R risk is the quantitative value of supply disruption risk, λ R is the risk sensitivity coefficient, B is the proportional value of the change degree of key indicators of the supply chain, and e is the base of the natural logarithm; Based on the quantified value of the supply disruption risk, the supply disruption risk is assessed according to the magnitude of the quantified value to obtain risk assessment information.

7. The supply chain management system based on big data technology according to claim 1 is characterized in that: The steps of optimizing the production plan are: Based on the demand forecast information and risk assessment information, and according to the current inventory level, the formula: I new =I current +α Z ×(P future -I current )×(1+β Z ×R risk ); Calculate adjusted inventory levels; Among them, I current is the current inventory, α Z and β Z is the inventory adjustment factor, P future To predict sales volume, R risk is a quantitative value for the risk of supply disruption; Based on the adjusted inventory, combined with actual production capacity and supply chain conditions, the formula: S opt =P future ×(1+γ Z ×R risk ); Calculate the adjusted production order quantity; Among them, P future To predict sales volume, R risk is the quantitative value of supply disruption risk, S opt is the adjusted production order quantity, γ Z is the regulating factor; Based on the adjusted inventory quantity and the adjusted production order quantity, they are applied to the target supply chain to optimize product supply, market demand and risk matching, and obtain optimized supply information.

8. The supply chain management system based on big data technology according to claim 7 is characterized in that: The steps for obtaining the optimization execution information are as follows: Based on the optimized supply information, evaluate the existing communication processes and protocols between upstream and downstream enterprises, identify existing inefficiencies and bottlenecks, and collect relevant data on communication and collaboration to obtain process and communication information; Based on the above process and communication information, the formula: Calculate communication efficiency; Among them, C eff is the communication efficiency, v f is the importance weight of process f, R f is the response rate of the fth process, d f is the communication delay of the fth process, T f is the communication time of the fth process, and F is the total number of processes; Based on the communication efficiency, the standard processes and communication protocols of upstream and downstream enterprises are coordinated, and the changes in communication efficiency before and after coordination are analyzed, the coordination effect is evaluated, the communication and collaboration of the supply chain is optimized, and optimized execution information is obtained.

Images