Inventory optimization and supply chain collaborative decision-making method for fast moving consumer goods trade industry

Abstract

The invention discloses a fast moving consumer goods trade industry-oriented inventory optimization and supply chain collaborative decision-making method, and relates to the technical field of supply chain management and inventory optimization. Store-warehouse-factory-logistics full-node real-time data are integrated through multi-source data acquisition, seasonal errors are eliminated through cross validation, and the supply chain collaborative decision-making method is applied to fast moving consumer goods trade industry-oriented inventory optimization and supply chain collaborative decision-making. The problems of data fragmentation and analysis lagging in the prior art are solved, and the accuracy of supply and demand state analysis is improved; the replenishment priority is adjusted based on a dynamic replenishment link model, and the distribution time sequence is regulated and controlled in combination with a salesman ability evaluation report, so that dynamic matching of demand-productivity-manpower is realized, and the problem of mismatching of replenishment machinery and resources in the prior art is solved; by comparing the commodity stock change rate and the vehicle transport capacity utilization rate before and after cargo transfer, a three-dimensional optimization distribution diagram is generated, so that subsequent correction of vehicle distribution and salesman scheduling is facilitated, and the cargo transfer path planning better fits the actual transport capacity.

Description

Technical Field

[0001] This invention relates to the field of supply chain management and inventory optimization technology, specifically to inventory optimization and supply chain collaborative decision-making methods for the fast-moving consumer goods (FMCG) trading industry. Background Technology

[0002] Inventory optimization and supply chain collaborative decision-making methods in the fast-moving consumer goods (FMCG) trading industry are widely used technologies in the retail and distribution sectors, particularly important when facing diverse needs such as store replenishment, promotional campaign execution, and regional inventory transfers. Its basic goal is to integrate salesperson store visit information, real-time warehouse status, and logistics capacity data to form a dynamic response mechanism, thereby improving inventory turnover efficiency, reducing stockout rates, and ensuring efficient collaborative operation across all links of the supply chain. However, some shortcomings still exist in practical operation, which will be detailed below with reference to the invention patent application.

[0003] Existing technologies, such as the supply and demand balance and inventory strategy optimization method disclosed in patent application CN113505908A, update inventory information through live streaming strategy information, historical return probabilities, and product sales sets, and generate replenishment data according to a preset replenishment strategy. While these also involve inventory optimization, their focus is on supply and demand matching in live streaming scenarios. Another example is the enterprise inventory optimization method based on an inventory optimization indicator tree disclosed in patent application CN116070775A. This invention improves performance by constructing an inventory cost reduction capability model and selecting optimization indicators to monitor abnormal indicators. Although it also emphasizes inventory optimization, its method leans more towards the construction of an indicator system and does not involve dynamic path optimization and intelligent control. Yet another example is the dynamic inventory optimization method disclosed in patent application CN119809009A, which improves inventory turnover through real-time data collection, accurate demand forecasting, and dynamic replenishment strategies. While there is some innovation in dynamic replenishment, there is a lack of in-depth discussion on logistics path optimization and salesperson capability assessment.

[0004] In summary, existing technologies suffer from several drawbacks. First, fragmented data collection leads to delayed supply and demand analysis, failing to achieve end-to-end data integration across stores, warehouses, factories, and logistics, resulting in a one-sided analysis of supply and demand. Second, low data update frequency prevents real-time capture of demand fluctuations, such as sudden inventory drops due to unexpected promotions, easily leading to untimely replenishment or overstocking. Third, replenishment decisions are often based on fixed rules, such as ranking by store sales, lacking dynamic adjustment mechanisms, resulting in resource misallocation. Fourth, the disconnect between inventory transfer routes and transportation capacity optimization leads to low logistics efficiency. Summary of the Invention

[0005] The purpose of this invention is to provide an inventory optimization and supply chain collaborative decision-making method for the fast-moving consumer goods (FMCG) trading industry, which solves the problems existing in the background technology.

[0006] To solve the above-mentioned technical problems, the present invention adopts the following technical solution: The present invention provides an inventory optimization and supply chain collaborative decision-making method for the fast-moving consumer goods (FMCG) trading industry, including: S1, data collection and fusion analysis: stores, warehouses, factories and logistics nodes in the FMCG supply chain are recorded as target node areas, real-time operating data of multi-source data collection units arranged in the target node areas are obtained, and supply and demand status fusion analysis is performed based on this to generate a dynamic replenishment link model, and a salesperson capability assessment report is generated at the same time.

[0007] S2. Intelligent control of replenishment instructions: Based on the dynamic replenishment link model, the replenishment priority parameters of different store zones in the target node area are adjusted. At the same time, based on the dynamic replenishment link model and the salesperson's ability assessment report, the delivery time sequence parameters of different store zones in the target node area are dynamically controlled.

[0008] S3. Optimized transfer route generation: Real-time transportation capacity data of different logistics zones in the target node area are collected using a multi-source data acquisition unit, and an optimized transfer route distribution map is generated based on the comparison of transportation capacity data before and after the transfer.

[0009] The beneficial effects of the present invention are as follows: (1) The present invention integrates real-time data of the entire node of stores-warehouses-factories-logistics through multi-source data collection and eliminates seasonal errors through cross-validation, which solves the problems of data fragmentation and analysis lag in the prior art and improves the accuracy of supply and demand status analysis.

[0010] (2) This invention adjusts the replenishment priority based on the dynamic replenishment link model and controls the delivery sequence in conjunction with the salesperson's ability assessment report, so as to realize the dynamic matching of demand, capacity and manpower, and solve the problem of mismatch of replenishment machinery and resources in the existing technology.

[0011] (3) This invention generates a three-dimensional optimized distribution map by comparing the change rate of commodity inventory and the utilization rate of vehicle capacity before and after the transfer, which facilitates subsequent correction of vehicle allocation and salesperson scheduling, making the transfer route planning more in line with actual transportation capacity, and solving the problem of disconnect between existing technology route optimization and transportation capacity. Attached Figure Description

[0012] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0013] Figure 1 This is a flowchart of the method of the present invention. Detailed Implementation

[0014] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0015] Reference Figure 1 As shown, the present invention provides an inventory optimization and supply chain collaborative decision-making method for the fast-moving consumer goods (FMCG) trading industry, including: S1, data collection and fusion analysis: stores, warehouses, factories and logistics nodes in the FMCG supply chain are recorded as target node areas, real-time operating data of multi-source data collection units arranged in the target node areas are obtained, and supply and demand status fusion analysis is performed based on this to generate a dynamic replenishment link model, and a salesperson capability assessment report is generated at the same time.

[0016] In a specific embodiment of the present invention, the multi-source data acquisition unit includes a store inventory sensor, a warehouse outbound monitor, a factory production scheduling module, and a logistics capacity monitor.

[0017] It should be noted that the multi-source data acquisition units are distributed in the target node areas of the FMCG supply chain. The store inventory sensors are installed on the shelves or storage areas of each store, and acquire the product inventory fluctuation characteristics through radio frequency identification technology or barcode scanning technology. The warehouse outbound monitor is arranged at the outbound passage of the warehouse, and records the outbound rate characteristics using photoelectric sensing or weight detection technology. The factory production scheduling module is located inside the factory and extracts the capacity load characteristics through sensors and management systems on the production line. The logistics capacity monitor is installed on logistics vehicles and acquires vehicle availability characteristics using positioning systems and vehicle sensors. All of the above data acquisition devices are connected to the central processing unit through wired or wireless networks to form a complete data acquisition link. The central processing unit integrates the collected data and generates real-time operating data in a unified format, providing a foundation for subsequent supply and demand status fusion analysis.

[0018] In a specific embodiment of the present invention, the specific process of acquiring real-time operating data of multi-source data acquisition units arranged within the target node area includes: synchronously acquiring the commodity inventory fluctuation characteristics output by the store inventory sensor, the outbound rate characteristics output by the warehouse outbound monitor, the capacity load characteristics output by the factory production scheduling module, and the vehicle availability characteristics output by the logistics capacity monitor, and integrating the commodity inventory fluctuation characteristics, outbound rate characteristics, capacity load characteristics, and vehicle availability characteristics into real-time operating data.

[0019] In a specific embodiment of the present invention, the specific process of performing supply and demand status fusion analysis to generate a dynamic replenishment link model includes: extracting the commodity inventory fluctuation characteristics, outbound rate characteristics and capacity load characteristics of the target node area from real-time operating data, and drawing the commodity inventory fluctuation curve and outbound rate curve for the current period.

[0020] Based on the commodity inventory fluctuation curve and outbound rate curve for the current period, cross-validate the overall commodity inventory fluctuation characteristics and overall outbound rate characteristics for the current period to eliminate seasonal demand fluctuation errors. Based on the verified mapping relationship between the commodity inventory fluctuation characteristics and outbound rate characteristics for the current period, divide the replenishment demand level regions.

[0021] It should be noted that the specific method for cross-validating the commodity inventory fluctuation characteristics and outbound rate characteristics to eliminate seasonal demand fluctuation errors is as follows: The correlation coefficient between the commodity inventory fluctuation curve and the outbound rate curve is calculated using the Pearson correlation coefficient. When the correlation coefficient is lower than a preset threshold, it is determined that a seasonal fluctuation error exists. Historical data matching the current period is retrieved from the data warehouse as benchmark normal data. The overall commodity inventory fluctuation characteristics of the current period are compared with the benchmark commodity inventory fluctuation characteristics in the benchmark normal data, and the difference ratio between the two is calculated to obtain the first seasonal fluctuation coefficient. Similarly, the overall outbound rate characteristics of the current period are compared with the benchmark outbound rate fluctuation characteristics in the benchmark normal data, and the difference ratio between the two is calculated to obtain the second seasonal fluctuation coefficient.

[0022] Divide the overall commodity inventory fluctuation characteristics and overall outbound rate characteristics of the current period by the first and second seasonal fluctuation coefficients, respectively, to obtain the commodity inventory fluctuation characteristics and outbound rate characteristics of the current period after removing seasonal effects.

[0023] The commodity inventory fluctuation curve specifically refers to the commodity inventory fluctuation characteristics under a time series, and the outbound rate curve specifically refers to the outbound rate characteristics under a time series.

[0024] It should also be noted that, based on the verified mapping relationship between the current period's commodity inventory fluctuation characteristics and outbound rate characteristics, replenishment demand level zones are divided. The specific method is as follows: Calculate the matching degree between the current period's commodity inventory fluctuation characteristics and outbound rate characteristics after verification, and based on the matching degree ranges corresponding to the pre-set high demand area, medium demand area, and low demand area in the data warehouse, map the target node area of ​​the current period to the high demand area, medium demand area, and low demand area.

[0025] The matching degree can be specifically represented by the synchronous fluctuation coefficient of the commodity inventory fluctuation characteristics and the outbound rate characteristics. For example, if the commodity inventory fluctuation characteristics are -10 and the outbound rate characteristics are +8, then the synchronous fluctuation coefficient can be expressed as 10 / 8.

[0026] By overlaying capacity load characteristics, risk correction is performed on replenishment demand level areas, and a dynamic replenishment link model labeled with high demand area, medium demand area and low demand area is output.

[0027] It should be noted that the specific method for risk correction of replenishment demand level areas by superimposing capacity load characteristics is as follows: for each high demand area, if the capacity load characteristics of a certain high demand area are within the range of capacity load characteristics corresponding to high risk, then the replenishment delay caused by the factory's inability to produce in time will result in the high demand area being downgraded to a medium demand area; otherwise, it will remain a high demand area. Similarly, risk correction will be performed on each medium demand area.

[0028] In a specific embodiment of the present invention, the specific process of generating the salesperson capability assessment report includes: extracting the commodity inventory fluctuation characteristics and vehicle availability characteristics of the target node area from real-time operating data. Specifically, the vehicle availability characteristics can be understood as the vehicle idle rate.

[0029] The order completion rate of the target node area is calculated in real time within a unit of time. If a non-linear decline occurs within a unit of time, the target node area is identified as having an order execution bottleneck point within the corresponding unit of time. This allows us to extract the order execution bottleneck point from the product inventory fluctuation characteristics.

[0030] It should be noted that the specific identification process for the nonlinear decline characteristic within the preset time period is as follows: the order completion rate in each unit time is compared with the order completion rate in the previous unit time, the decline rate in each unit time is calculated, and if the decline rate in a certain unit time exceeds the preset decline rate threshold, then an order execution bottleneck point is identified in that unit time.

[0031] Simultaneously, the second derivative of the vehicle availability characteristics of the target node area within a unit of time is calculated to obtain the capacity acceleration of the target node area within a unit of time, and it is detected whether the capacity acceleration in each unit of time is a preset change characteristic.

[0032] When the bottleneck point of order execution coincides with the time area corresponding to the preset capacity acceleration change characteristic, an execution capability assessment report containing the salesperson's identifier is generated. The preset capacity acceleration change characteristic is a sharp increase. The execution capability assessment report records the execution capability characteristic parameters of the salespersons in the store division of the target node area.

[0033] The execution capability feature parameter mentioned above is specifically as follows: the execution efficiency feature value of the time region where the order execution bottleneck point coincides with the preset capacity acceleration change feature is recorded as -1, and vice versa, it is recorded as 1. The execution efficiency feature value of each unit time is averaged to obtain the execution capability feature parameter of the salesperson in the target node region.

[0034] It should be noted that the method for determining whether the capacity acceleration is a preset change feature in each unit of time is as follows: compare the capacity acceleration with the capacity acceleration range corresponding to the preset steep increase change feature in the data warehouse. If the capacity acceleration is within the capacity acceleration range corresponding to the steep increase change feature, then the capacity acceleration is determined to be a preset change feature.

[0035] This invention integrates real-time data from all nodes of the supply chain—stores, warehouses, factories, and logistics—through multi-source data collection and cross-validation to eliminate seasonal errors. This solves the problems of data fragmentation and delayed analysis in existing technologies and improves the accuracy of supply and demand status analysis.

[0036] This invention adjusts replenishment priorities based on a dynamic replenishment chain model and regulates delivery timing by combining salesperson capability assessment reports, thereby achieving dynamic matching of demand, production capacity, and manpower, and solving the problems of mechanical and resource mismatch in existing replenishment technologies.

[0037] S2. Intelligent control of replenishment instructions: Based on the dynamic replenishment link model, the replenishment priority parameters of different store zones in the target node area are adjusted. At the same time, based on the dynamic replenishment link model and the salesperson's ability assessment report, the delivery time sequence parameters of different store zones in the target node area are dynamically controlled.

[0038] In a specific embodiment of the present invention, the specific process of adjusting the replenishment priority parameters of different store zones in the target node area based on the dynamic replenishment link model includes: identifying the coordinates of high-demand areas marked in the dynamic replenishment link model, and controlling the intelligent sorting unit to deliver high-frequency replenishment batches to the high-demand areas.

[0039] Identify the coordinates of the medium demand zone marked in the dynamic replenishment chain model, and control the intelligent sorting unit to deliver standard replenishment batches to the medium demand zone.

[0040] Identify the coordinates of low-demand areas marked in the dynamic replenishment chain model, and control the intelligent sorting unit to deliver low-frequency replenishment batches to the low-demand areas.

[0041] In a specific embodiment of the present invention, the specific process of dynamically adjusting the delivery timing parameters of different store partitions in the target node area based on the dynamic replenishment link model and the salesperson capability assessment report includes: locating the store partition identified by the salesperson in the salesperson capability assessment report, denoted as the salesperson identification area, and querying the replenishment demand level of each salesperson identification area in the dynamic replenishment link model.

[0042] If the salesperson's identified area is a high-demand area, and the salesperson's execution capability characteristic parameter is greater than or equal to the preset execution capability characteristic parameter threshold, then the first delivery instruction is triggered and the high-frequency replenishment batch is switched.

[0043] If the salesperson's identified area is a medium or low demand area, or if the salesperson's execution capability characteristic parameter is less than the execution capability characteristic parameter threshold, then a second delivery instruction is triggered and the current replenishment batch is maintained.

[0044] The time requirement for the first delivery instruction is less than the time requirement for the second delivery instruction.

[0045] S3. Optimized transfer route generation: Real-time transportation capacity data of different logistics zones in the target node area are collected using a multi-source data acquisition unit, and an optimized transfer route distribution map is generated based on the comparison of transportation capacity data before and after the transfer.

[0046] In a specific embodiment of the present invention, the specific process of collecting real-time transportation capacity data of different logistics zones in the target node area using a multi-source data acquisition unit includes: collecting the reconstructed features of commodity inventory updated by the store inventory sensor and the reconstructed features of vehicle transportation capacity updated by the logistics transportation capacity monitor during the logistics interval, and combining the reconstructed features of commodity inventory and vehicle transportation capacity into real-time transportation capacity data.

[0047] In a specific embodiment of the present invention, the specific process of generating the optimized distribution map of the transfer route based on the comparison of transportation capacity data before and after the transfer includes: extracting the baseline commodity inventory reconstruction features and baseline vehicle transportation capacity reconstruction features of different logistics zones in the target node area before the transfer from the database, and extracting the commodity inventory reconstruction features and vehicle transportation capacity reconstruction features of different logistics zones in the target node area after the transfer.

[0048] Specifically, the baseline commodity inventory reconstruction feature before the transfer represents the initial inventory status before the transfer, such as the total inventory and the proportion of slow-moving and fast-moving products. The baseline vehicle capacity reconstruction feature represents the vehicle resource status before the transfer, such as the number of available vehicles and the average load rate. When applying this invention, these can be customized according to the needs, and no specific restrictions are imposed here.

[0049] By comparing the baseline commodity inventory characteristics and commodity inventory reconstruction characteristics of different logistics zones in the target node area before and after the transfer, the commodity inventory change rate of different logistics zones in the target node area is calculated. The commodity inventory change rate is specifically calculated as (commodity inventory reconstruction characteristics after transfer - baseline commodity inventory characteristics before transfer) / baseline commodity inventory characteristics before transfer * 100%. The inventory change rates of all logistics zones are arranged according to the regional coordinates to obtain the commodity inventory change rate matrix of different logistics zones in the target node area.

[0050] By comparing the baseline vehicle capacity characteristics and vehicle capacity reconstruction characteristics of different logistics zones in the target node area before and after cargo transfer, the vehicle capacity utilization rate of different logistics zones in the target node area is calculated. The vehicle capacity utilization rate is specifically calculated as: (actual number of vehicles used after cargo transfer / total number of vehicles available after cargo transfer) * 100%. The capacity utilization rates of all logistics zones are arranged according to regional coordinates to obtain the vehicle capacity utilization rate matrix of different logistics zones in the target node area.

[0051] By integrating the commodity inventory change rate matrix and the vehicle capacity utilization rate matrix, a three-dimensional distribution map of the optimized distribution of cargo transfer routes in different logistics zones of the target node area is generated.

[0052] It should be added that, with the region as the horizontal axis, the inventory change rate as the vertical axis, and the transportation capacity utilization rate as the height, a visualized distribution map of optimized freight routes is generated. The following regions are marked on the optimized freight route distribution map: High-efficiency route areas with reasonable changes in existing capacity and high capacity utilization.

[0053] Inefficient routes with excess capacity or wasted transport capacity.

[0054] Bottleneck routes with insufficient stock or saturated capacity.

[0055] This invention generates a three-dimensional optimized distribution map by comparing the change rate of commodity inventory and vehicle capacity utilization rate before and after the transfer, which facilitates subsequent correction of vehicle allocation and salesperson scheduling, making the transfer route planning more in line with actual transportation capacity, and solving the problem of disconnect between route optimization and transportation capacity in existing technologies.

[0056] The above content is merely an example and illustration of the concept of the present invention. Those skilled in the art can make various modifications or additions to the specific embodiments described, or use similar methods to replace them, as long as they do not deviate from the concept of the invention or exceed the scope defined by the present invention, and all such modifications and additions should fall within the protection scope of the present invention.

Claims

1. A method for inventory optimization and supply chain collaborative decision-making in the fast-moving consumer goods (FMCG) trading industry, characterized by: include: S1. Data Acquisition and Fusion Analysis: Stores, warehouses, factories and logistics nodes in the FMCG supply chain are designated as target node areas. Real-time operating data of multi-source data acquisition units deployed within the target node areas are acquired. Based on this, supply and demand status fusion analysis is performed to generate a dynamic replenishment link model, and a salesperson capability assessment report is generated. S2. Intelligent control of replenishment instructions: Based on the dynamic replenishment link model, the replenishment priority parameters of different store zones in the target node area are adjusted. At the same time, based on the dynamic replenishment link model and the salesperson's ability assessment report, the delivery time sequence parameters of different store zones in the target node area are dynamically controlled. S3. Optimized transfer route generation: Real-time transportation capacity data of different logistics zones in the target node area are collected using a multi-source data acquisition unit, and an optimized transfer route distribution map is generated based on the comparison of transportation capacity data before and after the transfer.

2. The inventory optimization and supply chain collaborative decision-making method for the fast-moving consumer goods (FMCG) trading industry according to claim 1, characterized in that, The multi-source data acquisition unit includes a store inventory sensor, a warehouse outbound monitoring device, a factory production scheduling module, and a logistics capacity monitoring device.

3. The inventory optimization and supply chain collaborative decision-making method for the fast-moving consumer goods (FMCG) trading industry according to claim 1, characterized in that, The specific process of acquiring real-time operational data from multi-source data acquisition units deployed within the target node area includes: synchronously acquiring the commodity inventory fluctuation characteristics output by the store inventory sensor, the outbound rate characteristics output by the warehouse outbound monitor, the capacity load characteristics output by the factory production scheduling module, and the vehicle availability characteristics output by the logistics capacity monitor, and integrating the commodity inventory fluctuation characteristics, outbound rate characteristics, capacity load characteristics, and vehicle availability characteristics into real-time operational data.

4. The inventory optimization and supply chain collaborative decision-making method for the fast-moving consumer goods (FMCG) trading industry according to claim 3, characterized in that, The specific process of generating a dynamic replenishment link model through supply and demand status fusion analysis includes: Extract the commodity inventory fluctuation characteristics, outbound rate characteristics, and capacity load characteristics of the target node area from real-time operational data, and plot the commodity inventory fluctuation curve and outbound rate curve for the current period. Based on the commodity inventory fluctuation curve and outbound rate curve of the current period, cross-validate the overall commodity inventory fluctuation characteristics and overall outbound rate characteristics of the current period to eliminate seasonal demand fluctuation errors. Based on the verified mapping relationship between the commodity inventory fluctuation characteristics and outbound rate characteristics of the current period, divide the replenishment demand level regions. By overlaying capacity load characteristics, risk correction is performed on replenishment demand level areas, and a dynamic replenishment link model labeled with high demand area, medium demand area and low demand area is output.

5. The inventory optimization and supply chain collaborative decision-making method for the fast-moving consumer goods (FMCG) trading industry according to claim 3, characterized in that, The specific process for generating the salesperson competency assessment report includes: Extract the commodity inventory fluctuation characteristics and vehicle availability characteristics of the target node area from real-time operational data; The order completion rate of the target node area is calculated in real time within a unit of time. If a non-linear decline occurs within a unit of time, the target node area is identified as having an order execution bottleneck point within the corresponding unit of time. This allows us to extract the order execution bottleneck point from the product inventory fluctuation characteristics. Simultaneously, the second derivative of the vehicle availability characteristics of the target node area within a unit of time is calculated to obtain the capacity acceleration of the target node area within a unit of time, and it is detected whether the capacity acceleration in each unit of time is a preset change characteristic. When the bottleneck point of order execution coincides with the time region corresponding to the preset capacity acceleration change characteristics, an execution capability assessment report containing the salesperson's identifier is generated. The execution capability assessment report records the execution capability characteristic parameters of the salespersons in the store division of the target node area.

6. The inventory optimization and supply chain collaborative decision-making method for the fast-moving consumer goods (FMCG) trading industry according to claim 4, characterized in that, The specific process of adjusting the replenishment priority parameters for different store zones in the target node area based on the dynamic replenishment link model includes: Identify the coordinates of high-demand areas marked in the dynamic replenishment chain model, and control the intelligent sorting unit to deliver high-frequency replenishment batches to the high-demand areas. Identify the coordinates of the medium demand zone marked in the dynamic replenishment chain model, and control the intelligent sorting unit to deliver standard replenishment batches to the medium demand zone; Identify the coordinates of low-demand areas marked in the dynamic replenishment chain model, and control the intelligent sorting unit to deliver low-frequency replenishment batches to the low-demand areas.

7. The inventory optimization and supply chain collaborative decision-making method for the fast-moving consumer goods (FMCG) trading industry according to claim 5, characterized in that, The specific process of dynamically adjusting the delivery timing parameters of different store zones in the target node area based on the dynamic replenishment link model and salesperson capability assessment report includes: Locate the store area marked by the salesperson in the salesperson capability assessment report, record it as the salesperson marked area, and query the replenishment demand level of each salesperson marked area in the dynamic replenishment link model; If the salesperson's identified area is a high-demand area, and the salesperson's execution capability characteristic parameter is greater than or equal to the preset execution capability characteristic parameter threshold, then the first delivery instruction is triggered and the high-frequency replenishment batch is switched. If the salesperson's identified area is a medium or low demand area, or if the salesperson's execution capability characteristic parameter is less than the execution capability characteristic parameter threshold, then a second delivery instruction is triggered and the current replenishment batch is maintained. The time requirement for the first delivery instruction is less than the time requirement for the second delivery instruction.

8. The inventory optimization and supply chain collaborative decision-making method for the fast-moving consumer goods (FMCG) trading industry according to claim 1, characterized in that, The specific process of collecting real-time transportation capacity data of different logistics zones in the target node area using a multi-source data acquisition unit includes: During logistics downtime, the system collects product inventory reconstruction features updated by store inventory sensors and vehicle capacity reconstruction features updated by logistics capacity monitors, and combines these product inventory reconstruction features and vehicle capacity reconstruction features into real-time capacity data.

9. The inventory optimization and supply chain collaborative decision-making method for the fast-moving consumer goods (FMCG) trading industry according to claim 8, characterized in that, The specific process of generating the optimized distribution map of the freight transfer route based on the comparison of transportation capacity data before and after the transfer includes: Extract the baseline commodity inventory reconstruction features and baseline vehicle capacity reconstruction features of different logistics zones in the target node area before the transfer of goods from the database, and extract the commodity inventory reconstruction features and vehicle capacity reconstruction features of different logistics zones in the target node area after the transfer of goods. By comparing the baseline commodity inventory characteristics and commodity inventory reconstruction characteristics of different logistics zones in the target node area before and after the transfer, the commodity inventory change rate matrix of different logistics zones in the target node area is calculated. By comparing the baseline vehicle capacity characteristics and vehicle capacity reconstruction characteristics of different logistics zones in the target node area before and after cargo transfer, the vehicle capacity utilization matrix of different logistics zones in the target node area is calculated. By integrating the commodity inventory change rate matrix and the vehicle capacity utilization rate matrix, a three-dimensional distribution map of the optimized distribution of cargo transfer routes in different logistics zones of the target node area is generated.

Images