Supply chain data information analysis platform system

Abstract

The invention relates to the technical field of supply chain management, and discloses a supply chain data information analysis platform system, which comprises a dynamic data acquisition condition constraint module, an information analysis platform demand prediction module, a demand prediction mapping inventory optimization module and an information analysis platform management output module, and taking the first stage and the second stage of the time sequence period as constraint conditions of a conditional constraint layer, obtaining commodity delivery quantities of the first stage and the second stage in the time sequence period, and completing demand prediction of supply chain data through a time sequence prediction model. And comparing the difference value between the demand prediction result and the current inventory with a preset judgment threshold value, generating a single-stage optimization scheme based on the inventory redundancy risk and a multi-stage optimization scheme based on the inventory shortage risk, and sending an optimization instruction to ensure the continuity and stability of the supply chain.

Description

Technical Field

[0001] This invention relates to the field of supply chain management technology, and more specifically to a supply chain data information analysis platform system. Background Technology

[0002] In traditional supply chains, suppliers, manufacturers, logistics providers, and distributors often use independent information systems, resulting in fragmented data distribution across the entire chain. Furthermore, traditional management models relying on manual experience and scattered data struggle to meet the demands for real-time, accurate, and holistic optimization, necessitating more precise demand forecasting to optimize production planning and inventory management. Traditional forecasting models are ill-suited to adapting to non-linear and sudden changes in demand, and inventory management's reliance on experience-based judgment can easily lead to inventory buildup or shortages. Therefore, building dynamic and intelligent supply chain data analysis platforms that integrate big data, artificial intelligence, the Internet of Things, and cloud computing has become an industry trend.

[0003] With the advancement of big data technologies, such as distributed computing, cloud computing, and machine learning, it has become possible to process and analyze massive amounts of high-frequency and highly complex data from transactions, transportation, and inventory in the supply chain. This has improved the efficiency of data processing, enhanced the accuracy and real-time nature of data analysis, and provided stronger support for supply chain management.

[0004] However, with the continuous expansion of the supply chain and the rapid increase in data volume, the market changes rapidly. Enterprises need to be able to respond quickly to market changes and adjust production plans and supply chain strategies in a timely manner. However, existing supply chain data information analysis platforms lack the collaborative optimization of multi-level inventory structures, and information transmission delays lead to high inventory costs and slow response speeds. In the face of market changes, traditional supply chain data information analysis platforms cannot quickly adjust production plans and inventory strategies, resulting in resource waste or opportunity loss. Summary of the Invention

[0005] In order to overcome the above-mentioned defects of the prior art, the present invention provides a supply chain data information analysis platform system to solve the problems existing in the background art.

[0006] This invention provides the following technical solution: a supply chain data information analysis platform system, comprising: a dynamic data acquisition condition constraint module, an information analysis platform demand forecasting module, a demand forecasting mapping inventory optimization module, and an information analysis platform management output module; The dynamic data acquisition condition constraint module includes a dynamic data acquisition layer and a condition constraint layer. The dynamic data acquisition layer is used to collect demand forecast parameters in the supply chain in real time, and the condition constraint layer filters and selects the collected data according to preset rules and strategies. The demand forecasting module of the information analysis platform receives the filtered and screened demand forecasting parameters and inputs them into the supply chain data information analysis platform. The supply chain data information analysis platform completes the demand forecasting of supply chain data through a time series forecasting model. The demand forecasting and inventory optimization module receives the demand forecasting results output by the supply chain data information analysis platform, maps them to the inventory optimization analysis and judgment layer, and generates an inventory optimization plan, which includes single-level optimization and multi-level call optimization. The information analysis platform management output module receives inventory optimization plans through the supply chain data information analysis platform, issues optimization instructions based on the inventory optimization plans, and outputs the optimization results to the display terminal.

[0007] Preferably, the dynamic data acquisition condition constraint module includes the following specific contents of the dynamic data acquisition layer and the condition constraint layer: The dynamic data acquisition layer: uses lightweight data processing nodes deployed at the supply chain warehouse end to acquire dynamic data information of the supply chain; The condition constraint layer includes time condition constraints and data condition constraints. Time condition constraints are used to filter the collected data according to a preset time range; data condition constraints are used to filter the collected data according to preset data standards and rules.

[0008] Preferably, the specific content of the demand prediction module of the information analysis platform is as follows: Step S1: If the time series period is l days, then the first stage of the time series period is 1, 2, 3, ..., l, and the second stage of the time series period is l+1, l+2, l+3, ..., 2l; Step S2: Using the first phase of the time series period as a constraint condition in the conditional constraint layer, obtain the daily outbound volume of goods in the first phase of the time series period, and calculate the average outbound volume in the first phase of the time series period. The average outbound volume represents the first stage of the time series period, and l represents the length of the time series period, where i = 1, 2, 3, ..., l, and i represents the number of each day in the time series period. Step S3: Using the second phase of the time series period as a constraint condition in the condition constraint layer, obtain the daily outbound volume of goods in the second phase of the time series period, and calculate the average outbound volume in the second phase of the time series period. This represents the average outbound volume during the second phase of the time series period; Step S4: Perform incremental analysis on the average outbound volume of the first stage and the average outbound volume of the second stage of the time series cycle, and calculate the average daily increment within the two stages. This represents the average daily increment in the first and second phases of a time series period; Step S5: Perform fluctuation analysis on the average outbound volume in the first and second phases of the time series cycle, and calculate the average fluctuation index for the two phases. The calculation formula is as follows: ,in This represents the average volatility index of the first and second phases in a time series period. This represents the daily outbound volume within a time series period. This represents the change in outbound volume per unit time during the first phase of a time series period. This represents the unit-time change in outbound volume during the second phase of a time series period. Step S6: Input the average outbound volume of the first stage of the time series cycle, the average outbound volume of the second stage of the time series cycle, and the average fluctuation index of the first and second stages of the time series cycle into the time series forecasting model to complete the demand forecasting of supply chain data. The calculation formula of the time series forecasting model is as follows: ,in This represents the predicted outbound volume for the next stage based on the previous two stages within a time series period.

[0009] Preferably, the specific content of the demand forecasting-to-inventory optimization module is as follows: Receive demand forecast results from the supply chain data information analysis platform, map them to the inventory optimization analysis and judgment layer, and generate inventory optimization solutions; When the difference between the demand forecast output by the supply chain data information analysis platform and the current inventory level is less than a preset judgment threshold, it is determined as an inventory redundancy risk and a single-level optimization solution is generated; conversely, when the difference between the demand forecast output by the supply chain data information analysis platform and the current inventory level is greater than or equal to the preset judgment threshold, it is determined as an inventory shortage risk and a multi-level optimization solution is generated.

[0010] Preferably, the specific details of the single-level optimization scheme are as follows: When the demand forecast output by the supply chain data analysis platform exceeds twice the current inventory level, a promotional inventory clearance strategy is generated, and the discount rate of the inventory is automatically calculated using the following formula: ,in This indicates the discount rate for inventory items. This represents the preset base discount factor. This indicates the preset judgment threshold. Indicates the current inventory level. This represents the predicted outbound volume for the next stage based on the previous two stages within a time series period. Conversely, when the demand forecast output by the supply chain data analysis platform does not exceed twice the current inventory level, the supply chain will be dynamically adjusted to replenish the planned quantity. Adjusted to ,in This represents the minimum value.

[0011] Preferably, the specific details of the multi-level optimization scheme are as follows: When an inventory shortage risk is identified, a tiered optimization model is established to optimize the inventory items. The expression for the tiered optimization model is as follows: ,in This indicates the adjusted replenishment quantity. Indicates the elasticity replenishment coefficient. This indicates the preset judgment threshold. Indicates the current inventory level. This represents the predicted outbound volume for the next stage based on the previous two stages within a time series period. This indicates the maximum shipment volume in the supply chain.

[0012] Preferably, the specific content of the information analysis platform management output module is as follows: The inventory optimization plan is received through the supply chain data information analysis platform. The inventory optimization plan includes a single-level optimization plan generated based on inventory redundancy risk and a multi-level optimization plan generated based on inventory shortage risk. Based on the received inventory optimization plan, an optimization command is issued, the optimization task is executed, and the optimization results are output to the display terminal.

[0013] The technical effects and advantages of this invention are as follows: This invention achieves comprehensive collection, intelligent prediction, and optimized management of supply chain data by incorporating a dynamic data acquisition condition constraint module, an information analysis platform demand forecasting module, a demand forecasting-to-inventory optimization module, and an information analysis platform management output module.

[0014] Incremental and fluctuation analyses were performed on the average outbound volume in the first and second phases of the time series cycle to establish a time series forecasting model, which accurately predicted the demand of supply chain data, improving the accuracy and real-time performance of forecasts.

[0015] Inventory risk is assessed based on the difference between the forecast results and the current inventory level. When inventory redundancy risk is identified, a single-level optimization plan is generated. When inventory shortage risk is identified, a hierarchical optimization model is established to complete the hierarchical optimization of inventory items. This enables targeted optimization for different inventory risk conditions, effectively avoiding inventory backlog or stockouts, improving the efficiency and response speed of supply chain management, and further enhancing the intelligence level of supply chain management. Attached Figure Description

[0016] Figure 1 This is a schematic diagram of the structure of a supply chain data information analysis platform system.

[0017] Figure 2 This is a schematic diagram illustrating the steps involved in demand forecasting for an information analysis platform. Detailed Implementation

[0018] The technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings. In addition, the forms of the various structures described in the following embodiments are merely illustrative. The supply chain data information analysis platform system involved in the present invention is not limited to the structures described in the following embodiments. All other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0019] like Figure 1 As shown, the present invention provides a supply chain data information analysis platform system, including: a dynamic data acquisition condition constraint module, an information analysis platform demand forecasting module, a demand forecasting mapping inventory optimization module, and an information analysis platform management output module; The dynamic data acquisition condition constraint module includes a dynamic data acquisition layer and a condition constraint layer. The dynamic data acquisition layer is used to collect demand forecast parameters in the supply chain in real time, and the condition constraint layer filters and selects the collected data according to preset rules and strategies. The demand forecasting parameters include daily outbound volume of goods, current inventory of goods, planned replenishment volume of goods, and maximum shipment volume of the supply chain at different stages of the time series period. The conditional constraint layer uses different stages in the time series period as constraints to filter and screen the collected data. The demand forecasting module of the information analysis platform receives the filtered and screened demand forecasting parameters and inputs them into the supply chain data information analysis platform. The supply chain data information analysis platform completes the demand forecasting of supply chain data through a time series forecasting model. The demand forecasting and inventory optimization module receives the demand forecasting results output by the supply chain data information analysis platform, maps them to the inventory optimization analysis and judgment layer, and generates an inventory optimization plan, which includes single-level optimization and multi-level call optimization. The information analysis platform management output module receives inventory optimization plans through the supply chain data information analysis platform, issues optimization instructions based on the inventory optimization plans, and outputs the optimization results to the display terminal.

[0020] In this embodiment, it should be specifically explained that the dynamic data acquisition condition constraint module includes the following specific contents of the dynamic data acquisition layer and the condition constraint layer: The dynamic data acquisition layer: by deploying lightweight data processing nodes at the supply chain warehouse end, it is used to acquire dynamic supply chain data information. The dynamic supply chain data information represents demand forecasting parameters, namely, the daily outbound volume of goods, the current inventory of goods, the originally planned replenishment volume of goods, and the maximum shipment volume of the supply chain at different stages in the time series period. The condition constraint layer includes time condition constraints and data condition constraints. Time condition constraints are used to filter the collected data according to a preset time range to ensure that the analyzed data is timely. Data condition constraints are used to filter the collected data according to preset data standards and rules to remove abnormal or invalid data and improve data quality.

[0021] like Figure 2 As shown in this embodiment, the specific content of the information analysis platform demand prediction module is as follows: Step S1: If the time series period length is l days, then the first stage of the time series period is 1, 2, 3, ..., l, the second stage of the time series period is l+1, l+2, l+3, ..., 2l, and so on. The period length of different stages in the time series is l days. Step S2: Using the first phase of the time series period as the constraint condition of the constraint layer, obtain the daily outbound volume of goods in the first phase of the time series period, and calculate the average outbound volume in the first phase of the time series period. The calculation formula is as follows: ,in The average outbound volume represents the first stage of the time series period, and l represents the length of the time series period, where i = 1, 2, 3, ..., l, and i represents the number of each day in the time series period. Step S3: Using the second phase of the time series period as a constraint condition in the condition constraint layer, obtain the daily outbound volume of goods in the second phase of the time series period, and calculate the average outbound volume in the second phase of the time series period. The calculation formula is as follows: ,in The average outbound volume represents the second phase of the time series period, and l represents the length of the time series period, where i = 1, 2, 3, ..., l, and i represents the number of each day in the time series period. Step S4: Perform incremental analysis on the average outbound volume of the first stage and the average outbound volume of the second stage of the time series cycle, and calculate the average daily increment within the two stages. The calculation formula is as follows: ,in This represents the average daily increment in the first and second phases of a time series period; Step S5: Perform fluctuation analysis on the average outbound volume in the first and second phases of the time series cycle, and calculate the average fluctuation index for the two phases. The calculation formula is as follows: ,in This represents the average volatility index of the first and second phases in a time series period. This represents the daily outbound volume within a time series period. This represents the change in outbound volume per unit time during the first phase of a time series period. This represents the unit-time change in outbound volume during the second phase of a time series period. Step S6: Input the average outbound volume of the first stage of the time series cycle, the average outbound volume of the second stage of the time series cycle, and the average fluctuation index of the first and second stages of the time series cycle into the time series forecasting model to complete the demand forecasting of supply chain data. The calculation formula of the time series forecasting model is as follows: ,in This represents the predicted outbound volume for the next stage based on the previous two stages within a time series period.

[0022] In this embodiment, it should be specifically explained that the specific content of the demand forecasting mapping inventory optimization module is as follows: Receive demand forecast results from the supply chain data information analysis platform, map them to the inventory optimization analysis and judgment layer, and generate inventory optimization solutions; When the difference between the demand forecast output by the supply chain data information analysis platform and the current inventory level is less than a preset judgment threshold, it is determined as an inventory redundancy risk and a single-level optimization solution is generated; conversely, when the difference between the demand forecast output by the supply chain data information analysis platform and the current inventory level is greater than or equal to the preset judgment threshold, it is determined as an inventory shortage risk and a multi-level optimization solution is generated.

[0023] In this embodiment, it should be specifically explained that the specific content of the single-level optimization scheme is as follows: When the demand forecast output by the supply chain data analysis platform exceeds twice the current inventory level, a promotional inventory clearance strategy is generated, and the discount rate of the inventory is automatically calculated using the following formula: ,in This indicates the discount rate for inventory items. This represents the preset base discount factor. This indicates the preset judgment threshold. Indicates the current inventory level. This represents the predicted outbound volume for the next stage based on the previous two stages within a time series period. Conversely, when the demand forecast output by the supply chain data analysis platform does not exceed twice the current inventory level, the supply chain will be dynamically adjusted to replenish the planned quantity. Adjusted to ,in This represents the minimum value.

[0024] In this embodiment, it should be specifically explained that the details of the multi-level optimization scheme are as follows: When an inventory shortage risk is identified, a tiered optimization model is established to optimize the inventory items. The expression for the tiered optimization model is as follows: ,in This indicates the adjusted replenishment quantity. Indicates the elasticity replenishment coefficient. This indicates the preset judgment threshold. Indicates the current inventory level. This represents the predicted outbound volume for the next stage based on the previous two stages within a time series period. This indicates the maximum shipment volume in the supply chain.

[0025] In this embodiment, it should be specifically explained that the specific content of the information analysis platform management output module is as follows: The inventory optimization plan is received through the supply chain data information analysis platform. The inventory optimization plan includes a single-level optimization plan generated based on inventory redundancy risk and a multi-level optimization plan generated based on inventory shortage risk. Based on the received inventory optimization plan, an optimization command is issued, the optimization task is executed, and the optimization results are output to the display terminal.

[0026] In this embodiment, it should be specifically noted that to complete the demand forecasting of supply chain data in the time series forecasting model, the average volatility index of the two stages preceding the forecasting stage needs to be input. That is, the supply chain demand of the third stage is predicted based on the average volatility index of the first and second stages; the supply chain demand of the fourth stage is predicted based on the average volatility index of the second and third stages; and the supply chain demand of the fifth stage is predicted based on the average volatility index of the third and fourth stages. The demand forecasting of supply chain data is completed based on this.

[0027] In this embodiment, it should be specifically noted that the main difference between this embodiment and the prior art is that this embodiment achieves comprehensive collection, intelligent prediction and optimized management of supply chain data by including a dynamic data acquisition condition constraint module, an information analysis platform demand forecasting module, a demand forecasting mapping inventory optimization module and an information analysis platform management output module.

[0028] Incremental and fluctuation analyses were performed on the average outbound volume in the first and second phases of the time series cycle to establish a time series forecasting model, which accurately predicted the demand of supply chain data, improving the accuracy and real-time performance of forecasts.

[0029] Inventory risk is assessed based on the difference between the forecast results and the current inventory level. When inventory redundancy risk is identified, a single-level optimization plan is generated. When inventory shortage risk is identified, a hierarchical optimization model is established to complete the hierarchical optimization of inventory items. This enables targeted optimization for different inventory risk conditions, effectively avoiding inventory backlog or stockouts, improving the efficiency and response speed of supply chain management, and further enhancing the intelligence level of supply chain management.

[0030] In conclusion, the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

[0031] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A supply chain data information analysis platform system, characterized in that: include: The system includes a dynamic data acquisition constraint module, an information analysis platform demand forecasting module, a demand forecasting mapping inventory optimization module, and an information analysis platform management output module. The dynamic data acquisition condition constraint module includes a dynamic data acquisition layer and a condition constraint layer. The dynamic data acquisition layer is used to collect demand forecast parameters in the supply chain in real time, and the condition constraint layer filters and selects the collected data according to preset rules and strategies. The demand forecasting module of the information analysis platform receives the filtered and screened demand forecasting parameters and inputs them into the supply chain data information analysis platform. The supply chain data information analysis platform completes the demand forecasting of supply chain data through a time series forecasting model. The demand forecasting and inventory optimization module receives the demand forecasting results output by the supply chain data information analysis platform, maps them to the inventory optimization analysis and judgment layer, and generates an inventory optimization plan, which includes single-level optimization and multi-level call optimization. The information analysis platform management output module receives inventory optimization plans through the supply chain data information analysis platform, issues optimization instructions based on the inventory optimization plans, and outputs the optimization results to the display terminal.

2. The supply chain data information analysis platform system according to claim 1, characterized in that: The dynamic data acquisition condition constraint module includes the dynamic data acquisition layer and the condition constraint layer, the specific contents of which are as follows: The dynamic data acquisition layer: uses lightweight data processing nodes deployed at the supply chain warehouse end to acquire dynamic data information of the supply chain; The condition constraint layer includes time condition constraints and data condition constraints. The time condition constraints are used to filter the collected data according to a preset time range. Data condition constraints are used to filter the collected data according to preset data standards and rules.

3. The supply chain data information analysis platform system according to claim 1, characterized in that: The specific content of the demand forecasting module of the information analysis platform is as follows: Step S1: If the time series period is l days, then the first stage of the time series period is 1, 2, 3, ..., l, and the second stage of the time series period is l+1, l+2, l+3, ..., 2l; Step S2: Using the first phase of the time series period as a constraint condition in the conditional constraint layer, obtain the daily outbound volume of goods in the first phase of the time series period, and calculate the average outbound volume in the first phase of the time series period. The value represents the average outbound volume in the first phase of the time series period, l represents the length of the time series period, and i = 1, 2, 3, ..., l, where i represents the number of each day in the time series period. Step S3: Using the second phase of the time series period as a constraint condition in the condition constraint layer, obtain the daily outbound volume of goods in the second phase of the time series period, and calculate the average outbound volume in the second phase of the time series period. This represents the average outbound volume during the second phase of the time series period; Step S4: Perform incremental analysis on the average outbound volume of the first stage and the average outbound volume of the second stage of the time series cycle, and calculate the average daily increment within the two stages. This represents the average daily increment in the first and second phases of a time series period; Step S5: Perform fluctuation analysis on the average outbound volume in the first and second phases of the time series cycle, and calculate the average fluctuation index for the two phases. The calculation formula is as follows: ,in This represents the average volatility index of the first and second phases in a time series period. This represents the daily outbound volume within a time series period. This represents the change in outbound volume per unit time during the first phase of a time series period. This represents the unit-time change in outbound volume during the second phase of a time series period. Step S6: Input the average outbound volume of the first stage of the time series cycle, the average outbound volume of the second stage of the time series cycle, and the average fluctuation index of the first and second stages of the time series cycle into the time series forecasting model to complete the demand forecasting of supply chain data. The calculation formula of the time series forecasting model is as follows: ,in This represents the predicted outbound volume for the next stage based on the previous two stages within a time series period.

4. The supply chain data information analysis platform system according to claim 1, characterized in that: The specific content of the demand forecasting-to-inventory optimization module is as follows: Receive demand forecast results from the supply chain data information analysis platform, map them to the inventory optimization analysis and judgment layer, and generate inventory optimization solutions; When the difference between the demand forecast result output by the supply chain data information analysis platform and the current inventory level is less than the preset judgment threshold, it is judged as an inventory redundancy risk and a single-level optimization solution is generated. Conversely, when the difference between the demand forecast output by the supply chain data information analysis platform and the current inventory level is greater than or equal to the preset judgment threshold, it is determined to be an inventory shortage risk and a multi-level optimization plan is generated.

5. The supply chain data information analysis platform system according to claim 4, characterized in that: The specific details of the single-level optimization scheme are as follows: When the demand forecast output by the supply chain data analysis platform exceeds twice the current inventory level, a promotional inventory clearance strategy is generated, and the discount rate of the inventory is automatically calculated using the following formula: ,in This indicates the discount rate for inventory items. This represents the preset base discount factor. This indicates the preset judgment threshold. Indicates the current inventory level. This represents the predicted outbound volume for the next stage based on the previous two stages within a time series period. Conversely, when the demand forecast output by the supply chain data analysis platform does not exceed twice the current inventory level, the supply chain will be dynamically adjusted to replenish the planned quantity. Adjusted to ,in This represents the minimum value.

6. The supply chain data information analysis platform system according to claim 4, characterized in that: The specific details of the multi-level optimization scheme are as follows: When an inventory shortage risk is identified, a tiered optimization model is established to optimize the inventory items. The expression for the tiered optimization model is as follows: ,in This indicates the adjusted replenishment quantity. Indicates the elasticity replenishment coefficient. This indicates the preset judgment threshold. Indicates the current inventory level. This represents the predicted outbound volume for the next stage based on the previous two stages within a time series period. This indicates the maximum shipment volume in the supply chain.

7. The supply chain data information analysis platform system according to claim 1, characterized in that: The specific contents of the information analysis platform management output module are as follows: The inventory optimization plan is received through the supply chain data information analysis platform. The inventory optimization plan includes a single-level optimization plan generated based on inventory redundancy risk and a multi-level optimization plan generated based on inventory shortage risk. Based on the received inventory optimization plan, an optimization command is issued, the optimization task is executed, and the optimization results are output to the display terminal.

Images