Intelligent inventory management system and method based on big data supply chain

Abstract

The invention discloses an intelligent inventory management system and method based on a big data supply chain, and relates to the technical field of big data processing, and the method comprises the steps: collecting inventory data, traffic condition data and weather data in a warehouse, and carrying out the preprocessing of the data; constructing a prediction model based on the pre-processed inventory data, and predicting the trend of the inventory; executing an inventory supplement plan according to a prediction result, automatically sending a replenishment request, and generating a replenishment task; according to the real-time traffic condition data and the weather data, utilizing a path optimization algorithm to generate an optimal path for the replenishment task; according to the method, the real-time traffic condition data and the weather data are combined, the optimal path is generated for each replenishment task, and the aim of delivering goods on time is achieved.

Description

Technical Field

[0001] This invention relates to the field of big data processing technology, and in particular to an intelligent inventory management system and method based on big data supply chain. Background Technology

[0002] With the rapid development of information technology and the increasing demand for supply chain management from enterprises, intelligent inventory management systems based on big data have become an important research direction in the field of modern warehousing and logistics. Traditional inventory management systems mainly rely on human experience and fixed rules for inventory control, which is not only inefficient but also easily affected by market fluctuations and unexpected events.

[0003] Existing intelligent inventory management in the supply chain often focuses only on the inventory data itself, ignoring the impact of traffic conditions and weather factors on inventory replenishment plans. Changes in external factors can lead to transportation delays or increased costs, which in turn affect the timely replenishment of inventory. Even if the system takes external factors into account, it is often optimized under static conditions and fails to update route planning in real time, making it unable to cope with emergencies. Summary of the Invention

[0004] In view of the aforementioned existing problems, the present invention is proposed.

[0005] Therefore, this invention provides an intelligent inventory management system and method based on big data supply chain to solve the problems of inaccurate inventory forecasting and untimely replenishment path optimization caused by the lack of comprehensive analysis of traffic conditions and weather data in existing inventory management systems.

[0006] To solve the above-mentioned technical problems, the present invention provides the following technical solution: In a first aspect, the present invention provides an intelligent inventory management method based on big data supply chain, comprising: Collect warehouse inventory data, real-time traffic data, and real-time weather data, and preprocess the data; Based on preprocessed inventory data, a predictive model is built to predict inventory trends; Based on the predicted inventory trends, an inventory replenishment plan is developed, and replenishment requests are automatically issued and replenishment tasks are generated based on the inventory replenishment plan. Based on real-time traffic and weather data, a route optimization algorithm is used to generate the optimal route for the replenishment task. Continuously monitor inventory data, vehicle location data for performing replenishment tasks, real-time traffic data, and real-time weather data to determine if there are any abnormalities in the replenishment path or inventory. When an abnormality is detected, regenerate the current optimal path or start the replenishment task. The management methods can be adjusted and optimized based on the feedback from the exception handling process.

[0007] As a preferred embodiment of the intelligent inventory management method based on big data supply chain described in this invention, the method involves collecting inventory data, real-time traffic data, and real-time weather data from the warehouse, and preprocessing the data, including the following steps: Collect warehouse inventory data, real-time traffic data, and real-time weather data, and then correct errors, fill in missing values, and handle outliers in the collected data.

[0008] As a preferred embodiment of the intelligent inventory management method based on big data supply chain described in this invention, the method includes the following steps: Based on preprocessed inventory data, a predictive model is constructed to predict inventory trends. The preprocessed inventory data is converted to time series format and divided into training, validation, and test sets. A prediction model is built, trained using the training set data, and then fed into the trained model using the test set data to obtain the predicted inventory value. The expression is as follows: ; in, for Inventory value at a given point in time. For time points Average inventory For the first The weight of each data point For time points Historical inventory value As a weighting factor, The length of the historical data window; Calculate the error between the predicted values ​​and the true values ​​in the validation set, adjust the model parameters based on the performance on the validation set, and find the optimal model configuration on the validation set. When the error is large, adjust the weighting factors and... Adjustments will be made.

[0009] As a preferred embodiment of the intelligent inventory management method based on big data supply chain described in this invention, the method includes the following steps: executing an inventory replenishment plan according to the predicted inventory trend, automatically issuing replenishment requests, and generating replenishment tasks. Based on the forecast results, an inventory replenishment plan is executed, setting a safety stock level and a reorder point. When inventory falls below the reorder point, a replenishment request is triggered, and a replenishment task is generated. An exponential smoothing model is used to predict demand over a future period; the formula is as follows. ; in, For time points The demand, To smooth the level, For trend volume, Based on current demand, It is a periodic component; Calculate the replenishment quantity based on the predicted demand; the expression for the replenishment quantity is as follows. ; in, To replenish the quantity, For time points Actual inventory levels This is the level of safety stock.

[0010] As a preferred embodiment of the intelligent inventory management method based on big data supply chain described in this invention, the method involves generating an optimal route for replenishment tasks using a route optimization algorithm based on real-time traffic and weather data, including the following steps. By integrating real-time traffic and weather data into route planning, adjusting route costs, and selecting a route optimization algorithm, the optimal route is generated for each replenishment task, ensuring timely delivery of goods. The optimal route expression is as follows: ; in, The optimal path, For nodes To the node +1 distance, For nodes Distance to the target node For nodes Constraint factors, As a regulating factor, These are the weighting factors for the constraints. Let P be the total cost of all constraints on path P; As a preferred embodiment of the intelligent inventory management method based on big data supply chain described in this invention, the method includes: continuously monitoring inventory data, vehicle location information data for performing replenishment tasks, real-time traffic data, and weather data to determine whether the replenishment process is abnormal. When an abnormality is detected, the optimal path is regenerated, including the following steps. Collect location information data of vehicles performing replenishment tasks; Based on vehicle location information, real-time traffic data, and weather data, determine whether traffic congestion or sudden weather changes have occurred at the current vehicle's location or in its direction of travel. If the determination is yes, regenerate the current optimal route and automatically send an instruction to the vehicle terminal to adjust the route to the current optimal route. Real-time monitoring of warehouse inventory data; when the inventory level falls below the safety stock level, an abnormal alarm is automatically triggered, and a replenishment task is initiated after the abnormal alarm is triggered.

[0011] As a preferred embodiment of the intelligent inventory management method based on big data supply chain described in this invention, the method is adjusted and optimized using feedback from the handling of abnormal situations, including the following steps: Record the time, location, and details of each abnormal event; Record the handling methods and results of each exception to create a case database; Regularly analyze the above records and adjust and optimize the management methods accordingly.

[0012] Secondly, the present invention provides an intelligent inventory management system based on big data supply chain, including a data collection and preprocessing module, which is responsible for collecting inventory data, real-time traffic data and real-time weather data in the warehouse, and preprocessing the collected data. The inventory forecasting module builds a forecasting model based on preprocessed inventory data to predict inventory trends and provide a basis for inventory replenishment planning. The replenishment planning and request module formulates an inventory replenishment plan based on the inventory trend forecast and automatically issues replenishment requests to generate replenishment tasks. The route optimization module generates the optimal route for replenishment tasks based on real-time traffic and weather data using route optimization algorithms. The monitoring and anomaly handling module continuously monitors inventory data, the location of vehicles performing replenishment tasks, real-time traffic data, and real-time weather data to determine whether the replenishment path or inventory is abnormal. When an anomaly is detected, the module regenerates the current optimal path or restarts the replenishment task. The module also uses the feedback from the anomaly handling process to adjust and optimize the management methods.

[0013] Thirdly, the present invention provides a computer device including a memory and a processor, wherein the memory stores a computer program, wherein: when the computer program is executed by the processor, it implements any step of the intelligent inventory management method based on big data supply chain as described in the first aspect of the present invention.

[0014] Fourthly, the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein: when the computer program is executed by a processor, it implements any step of the intelligent inventory management method based on big data supply chain as described in the first aspect of the present invention.

[0015] The beneficial effects of this invention are as follows: By collecting inventory data, traffic data, and weather data from the warehouse, and preprocessing the data, the preprocessed inventory data is converted into a time series format. The test set is input into the trained prediction model to obtain the predicted inventory value. The model parameters are adjusted based on the performance on the validation set, improving the accuracy of inventory prediction and the ability to adapt to different scenarios. An inventory replenishment plan is executed based on the prediction results. When the inventory is lower than the reorder point, a replenishment request is triggered, and the replenishment quantity is calculated based on the predicted demand, achieving timely inventory replenishment. Real-time traffic data and weather data are integrated into the route planning. A route optimization algorithm is selected and combined with real-time traffic data and weather data to generate the optimal route for each replenishment task, achieving the goal of timely delivery of goods. By installing GPS devices on each transport vehicle, the route is replanned in the event of traffic congestion or sudden weather changes. Attached Figure Description

[0016] To more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the following description of the embodiments will be briefly introduced. 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.

[0017] Figure 1 This is a flowchart of the intelligent inventory management method based on big data supply chain in Example 1.

[0018] Figure 2 This is a system diagram of the intelligent inventory management system based on big data supply chain in Example 1.

[0019] Figures 3-7 This is a display of some basic data entry or query pages in some practical application scenarios of the intelligent inventory management system of this invention.

[0020] Figures 8-9 This is a display of some inventory-related data pages in some practical application scenarios of the intelligent inventory management system of this invention.

[0021] Figure 10 This is a partial display of inventory replenishment plans in some practical application scenarios of the intelligent inventory management system of this invention. Detailed Implementation

[0022] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, the specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings.

[0023] Many specific details are set forth in the following description in order to provide a full understanding of the invention. However, the invention may also be practiced in other ways different from those described herein, and those skilled in the art can make similar extensions without departing from the spirit of the invention. Therefore, the invention is not limited to the specific embodiments disclosed below.

[0024] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The phrase "in one embodiment" appearing in different places in this specification does not necessarily refer to the same embodiment, nor is it a single or selective embodiment that is mutually exclusive with other embodiments.

[0025] Example 1, referring to Figure 1 and Figure 2 This is the first embodiment of the present invention, which provides an intelligent inventory management method based on big data supply chain, including the following steps: S1. Collect warehouse inventory data, real-time traffic data, and real-time weather data, and preprocess the data, including the following steps: Collect warehouse inventory data, real-time traffic data, and real-time weather data; then correct errors, fill in missing values, and handle outliers in the collected data. Furthermore, by collecting warehouse inventory data, traffic data, and weather data, and preprocessing the data, effective integration and cleaning of multi-source heterogeneous data was achieved, ensuring data quality. This allows subsequent forecasting and optimization processes to be based on accurate and reliable data. By collecting warehouse inventory quantity, traffic data, and weather data, and correcting errors, filling missing values, and handling outliers, the consistency and usability of the data are improved. This provides a rich source of information for subsequent forecasting, thereby improving the accuracy of inventory forecasting and providing a reliable basis for route optimization.

[0026] Specifically, collecting warehouse inventory data, traffic data, and weather data, and preprocessing the data, also includes the following steps: The data collection frequency for each data type (warehouse inventory data, traffic data, and weather data) is adjusted based on the amount of erroneous, missing, and abnormal data, including: The system acquires the amount of erroneous, missing, and abnormal data in each data type during data collection in real time; the data types include warehouse inventory quantity, traffic condition data, and weather condition data. By utilizing the amount of erroneous, missing, and outlier data collected for each data type, a data quality evaluation coefficient is obtained for each data type. The data quality evaluation coefficient for each data type is obtained using the following formula:

[0027] Where Q represents the data quality evaluation coefficient for each data type; n represents the number of data collections for each data type; C 01i C 02i and C 03i These represent the amounts of erroneous, missing, and outlier data collected during the i-th data collection for each data type, respectively; w 01 w 02 and w 03 These represent the preset weight values ​​for erroneous data, missing data, and abnormal data, respectively; T 01i T represents the error correction processing time for erroneous data during the i-th data collection for each data type; 02i T represents the time taken to fill in missing values ​​for missing data during the i-th data collection for each data type; 03i T represents the time taken to handle outliers during the i-th data collection for each data type; zi C represents the total preprocessing time for the i-th data collection of each data type; zi represents the total amount of data collected for each data type during the i-th data collection; s represents the adjustment coefficient, which is obtained using the following formula:

[0028] Where s represents the adjustment coefficient; n represents the number of data collections for each data type; C 01i C 02i and C 03i These represent the amounts of erroneous, missing, and outlier data collected during the i-th data collection for each data type, respectively; w 01 w 02 and w 03 These represent the preset weight values ​​for erroneous data, missing data, and abnormal data, respectively; T i express The corresponding data processing time (i.e., the time for correcting errors in erroneous data, the time for filling in missing values ​​for missing data, or the time for filling in missing values ​​for missing data); w i express The corresponding weight values ​​(i.e., the weight values ​​corresponding to erroneous data, missing data, or outlier data); C siThis represents the maximum amount of data processed per unit time during the i-th data collection of a certain data type, where the unit time is 1 second; The data quality evaluation coefficient corresponding to each data type is compared with a preset coefficient threshold. When the data quality evaluation coefficient for each data type exceeds a preset coefficient threshold, the data collection frequency for the data type whose data quality evaluation coefficient exceeds the preset coefficient threshold is adjusted. The adjusted data collection frequency is obtained using the following formula:

[0029] Where F represents the adjusted data collection frequency; F0 represents the adjusted data collection frequency; and Q represents the data quality evaluation coefficient corresponding to each data type.

[0030] This technical solution dynamically assesses data quality and adjusts the data collection frequency in real time based on changes in data quality. By collecting and analyzing the amount of erroneous, missing, and anomalous data for each data type (warehouse inventory data, traffic data, and weather data) during the data collection process, it ensures that data collection frequency is increased when data quality is low to obtain accurate data more promptly, while the collection frequency can be appropriately reduced when data quality is high to save resources and costs. By introducing a data quality evaluation coefficient, the solution comprehensively considers the amount of erroneous, missing, and anomalous data, as well as the corresponding processing time, thus enabling a more comprehensive and accurate assessment of data quality. Furthermore, by comparing the data quality evaluation coefficient with a preset threshold, substandard data quality can be identified promptly, allowing for appropriate adjustments to improve overall data quality. The adjustment coefficient formula in the solution considers the maximum data processing volume per unit time, which helps optimize the data processing workflow, ensuring full utilization of system resources and improving processing efficiency during data collection and processing. The solution's ability to dynamically adjust the data collection frequency based on real-time data quality feedback enhances the system's flexibility and adaptability. The system can automatically adjust its data collection strategy under different environments and conditions to meet the requirements for data accuracy and timeliness. By providing high-quality data, this technical solution can provide stronger support for decision-making in enterprises or organizations. Accurate and timely data can help decision-makers better understand the current situation and make more informed decisions.

[0031] In summary, this technical solution provides strong support for data management and decision-making for enterprises or organizations through various technical effects, such as dynamically adjusting the data collection frequency, improving data quality, optimizing data processing efficiency, enhancing system flexibility, and improving decision support capabilities.

[0032] S2. Based on the preprocessed inventory data, construct a predictive model to predict inventory trends, including the following steps: The preprocessed inventory data is converted to time series format and divided into training, validation, and test sets. A prediction model is built, trained using the training set data, and then fed into the trained model using the test set data to obtain the predicted inventory value. The expression is as follows: ; in, for Inventory value at a given point in time. For time points Average inventory For the first The weight of each data point For time points Historical inventory value As a weighting factor, This is the length of the historical data window.

[0033] Calculate the error between the predicted values ​​and the true values ​​in the validation set, adjust the model parameters based on the performance on the validation set, and find the optimal model configuration on the validation set. When the error is large, adjust the weighting factors and... Make adjustments; Furthermore, by building a predictive model based on preprocessed inventory data and predicting inventory trends, accurate predictions of future inventory levels were achieved, providing a scientific basis for inventory management and replenishment decisions. The preprocessed inventory data is converted into a time series format and divided into training, validation and test sets. A prediction model is built, the prediction model is trained using the training set data, and the test set is input into the trained prediction model to obtain the predicted inventory value. The model parameters were adjusted based on the performance on the validation set to find the optimal model configuration, which improved the accuracy and stability of inventory forecasting and provided reliable decision support for inventory management.

[0034] S3. Develop an inventory replenishment plan based on the predicted inventory trend, automatically issue replenishment requests based on the replenishment plan, and generate replenishment tasks, including the following steps. Based on the forecast results, an inventory replenishment plan is executed, setting a safety stock level and a reorder point. When inventory falls below the reorder point, a replenishment request is triggered, and a replenishment task is generated. An exponential smoothing model is used to predict demand over a future period; the formula is as follows. ; in, For time points The demand, To smooth the level, For trend volume, Based on current demand, It is a periodic component; Calculate the replenishment quantity based on the predicted demand; the expression for the replenishment quantity is as follows. ; in, To replenish the quantity, For time points Actual inventory levels To maintain a safety stock level; Furthermore, by setting safety stock levels and reorder points, safety stock is the amount of inventory held to prevent stockouts caused by demand fluctuations or supply delays. When the actual inventory level is lower than the reorder point, a replenishment request is automatically triggered, the specific replenishment quantity is calculated, a replenishment task is generated based on the calculated replenishment quantity, and the task is sent to the supply chain management system for processing the procurement process.

[0035] S4. Based on real-time traffic and weather data, generate the optimal route for the replenishment task using a route optimization algorithm, including the following steps. By integrating real-time traffic and weather data into route planning, adjusting route costs, and selecting a route optimization algorithm, the optimal route is generated for each replenishment task, ensuring timely delivery of goods. The optimal route expression is as follows: ; in, The optimal path, For nodes To the node +1 distance, For nodes Distance to the target node For nodes Constraint factors, As a regulating factor, These are the weighting factors for the constraints. Let P be the total cost of all constraints on path P; Furthermore, real-time traffic data and weather data both affect traffic conditions. The cost of adjusting routes based on integrated data includes distance, time delays caused by traffic conditions and weather conditions, or other factors. Based on specific needs, a route optimization algorithm is selected, and combined with real-time traffic and weather data, the optimal route is generated for each replenishment task. Once the optimal route is generated, the delivery task needs to be executed according to the route, and real-time traffic and weather changes are continuously monitored, and the route is recalculated when necessary.

[0036] S5. Continuously monitor inventory data, vehicle location information data for replenishment tasks, real-time traffic data, and weather data to determine if the replenishment process is abnormal. When an abnormality is detected, regenerate the current optimal route, including the following steps. GPS devices are installed on each transport vehicle performing replenishment tasks to display the location information of all vehicles; Collect location information data of vehicles performing replenishment tasks; Based on vehicle location information, real-time traffic data, and weather data, determine whether traffic congestion or sudden weather changes have occurred at the current vehicle's location or in its direction of travel. If the determination is yes, regenerate the current optimal route and automatically send an instruction to the vehicle terminal to adjust the route to the current optimal route. Real-time monitoring of warehouse inventory data; when the inventory level falls below the safety stock level, an abnormal alarm is automatically triggered, and a replenishment task is initiated after the abnormal alarm is triggered. Furthermore, by accessing real-time traffic data streams, when severe congestion is detected on a certain route, route replanning is triggered. Using the previously mentioned route optimization algorithm, the shortest or fastest route is recalculated based on the new conditions, and the new route information is immediately sent to the driver via the vehicle terminal or other communication methods. Real-time monitoring of inventory status in the warehouse; when the inventory level is lower than the predetermined safety stock level, an abnormal alarm is automatically triggered; when an abnormal alarm is received that the inventory is lower than the safety level, a replenishment task is initiated automatically or manually. Based on the current order volume, transportation capacity, and inventory status, replenishment tasks are arranged, assigned to the corresponding transportation vehicles, and execution begins.

[0037] S6. Utilize the feedback from the abnormal situation handling to adjust and optimize the management method, including the following steps: Record the time, location, and details of each abnormal event; Record the handling methods and results of each exception to create a case database; Regularly analyze the above records and adjust and optimize the management methods accordingly; Furthermore, describe the specific circumstances of the anomaly, record the countermeasures taken, including rerouting, notifying drivers, and adjusting inventory, and record the results of the anomaly handling; Each exception, its handling method, and its result should be compiled into a document or electronic record to form a case database. The database should be easy to query and analyze. Regularly analyze the anomalies in the case database to identify common problems and potential risks, and develop improvement measures accordingly; Based on the analysis results, existing operating processes, emergency plans, and technical systems will be adjusted and optimized to reduce the probability and impact of anomalies.

[0038] This embodiment also provides an intelligent inventory management system based on big data supply chain, including: a data collection and preprocessing module, which is responsible for collecting inventory data, real-time traffic data and real-time weather data in the warehouse, and preprocessing the collected data; The inventory forecasting module builds a forecasting model based on preprocessed inventory data to predict inventory trends and provide a basis for inventory replenishment planning. The replenishment planning and request module formulates an inventory replenishment plan based on the inventory trend forecast and automatically issues replenishment requests to generate replenishment tasks. The route optimization module generates the optimal route for replenishment tasks based on real-time traffic and weather data using route optimization algorithms. The monitoring and anomaly handling module continuously monitors inventory data, the location of vehicles performing replenishment tasks, real-time traffic data, and real-time weather data to determine whether the replenishment path or inventory is abnormal. When an anomaly is detected, the module regenerates the current optimal path or restarts the replenishment task. The module also uses the feedback from the anomaly handling process to adjust and optimize the management methods.

[0039] This embodiment also provides a computer device applicable to the intelligent inventory management method based on big data supply chain, including: a memory and a processor; the memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions to realize the intelligent inventory management method based on big data supply chain proposed in the above embodiment. The computer device can be a terminal, comprising a processor, memory, communication interface, display screen, and input devices connected via a system bus. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, carrier networks, NFC (Near Field Communication), or other technologies. The display screen can be an LCD screen or an e-ink screen. The input devices can be a touch layer covering the display screen, buttons, a trackball, or a touchpad on the computer device's casing, or an external keyboard, touchpad, or mouse.

[0040] This embodiment also provides a storage medium storing a computer program, which, when executed by a processor, implements the intelligent inventory management method based on big data supply chain proposed in the above embodiments. The storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as Static Random Access Memory (SRAM), Electrically Erasable Programmable Read-Only Memory (EEPROM), Erasable Programmable Read Only Memory (EPROM), Programmable Red-Only Memory (PROM), Read-Only Memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk.

[0041] In summary, this invention achieves timely inventory replenishment by: collecting warehouse inventory data, traffic data, and weather data; preprocessing the data; converting the preprocessed inventory data into a time series format; inputting the test set into a trained prediction model to obtain predicted inventory values; adjusting model parameters based on performance on the validation set to improve inventory prediction accuracy and adaptability to different scenarios; executing an inventory replenishment plan based on the prediction results; triggering a replenishment request when inventory falls below the reorder point; and calculating the replenishment quantity based on predicted demand. Furthermore, by integrating real-time traffic and weather data into route planning and using a route optimization algorithm, the optimal route is generated for each replenishment task, ensuring timely delivery of goods. Finally, by installing GPS devices on each transport vehicle and replanning routes in case of traffic congestion or sudden weather changes, the invention ensures timely inventory replenishment.

[0042] Example 2, referring to Table 1, is the second embodiment of the present invention. To further verify the technical solution of the present invention, experimental simulation data of the intelligent inventory management method based on big data supply chain are given.

[0043] First, sensors were installed in four warehouses to collect real-time inventory data, traffic data, and weather data. The data was transmitted to a central server via a wireless network, where it was cleaned and standardized to ensure data quality and consistency. The exponential smoothing model is used to predict demand over a future period. The model parameters include the smoothing level, trend amount, and period fraction, which are adjusted based on historical sales data. Set safety stock levels and reorder points based on forecast results. When inventory falls below the reorder point, trigger a replenishment request and generate a replenishment task. Calculate the replenishment quantity based on the predicted demand to ensure that each replenishment can meet the predicted demand without causing excessive inventory backlog. Automatically issue replenishment requests and generate replenishment tasks, with task information including replenishment quantity and replenishment time; By combining real-time traffic data and real-time weather data, a route optimization algorithm is used to generate the optimal route for each replenishment task; When traffic congestion or sudden weather changes are detected, the system will automatically replan the route and notify the driver to adjust the driving route. GPS devices were installed on each transport vehicle to display the real-time location information of all vehicles; Real-time monitoring of warehouse inventory status; when inventory levels fall below safety stock levels, an abnormal alarm is automatically triggered. Upon receiving an anomaly alert, immediately initiate a replenishment task and replan the route if necessary; Record the time, location, and specific details of each anomaly, as well as the handling method and result of each anomaly, to form a case database; Regularly analyze abnormal situations and make adjustments and optimizations based on the analysis results; The details are shown in Table 1 below: Table 1 Experimental Data Experimental subjects Current inventory (units) Forecast demand (units) Replenishment quantity (pieces) Actual replenishment time (minutes) Warehouse A 2500 3000 1000 120 Warehouse B 3000 3500 1500 150 Warehouse C 2000 2500 800 90 Warehouse D 1500 2000 700 80 Based on demand forecasts, replenishment quantities are set to avoid inventory backlog. For example, if warehouse A currently has 2,500 units in stock and forecasts a demand of 3,000 units, it will replenish 1,000 units to ensure that the inventory is at a reasonable level. By optimizing the routes, replenishment time has been significantly reduced. For example, the actual replenishment time for warehouse B is 150 minutes, which is significantly shorter than the traditional method. The system monitors inventory status and vehicle location in real time. When inventory falls below a safe level, the system can promptly trigger an alarm and quickly initiate a replenishment task, ensuring the continuity and stability of the supply chain.

[0044] Furthermore, as an example, the code of the intelligent inventory management system provided by this invention includes SQL Server stored procedure code for synchronizing and updating data related to inventory management. This code implements a stored procedure named distDailyInventorySync for synchronizing daily inventory data, and its specific functions and logic are as follows: Purpose: The main purpose of this stored procedure is to extract and summarize inventory data from multiple source tables and insert the results into a target table named dist_daily_inventory_sync. This provides daily inventory status updates for inventory management.

[0045] Data Extraction and Transformation: Inventory data is extracted from relevant tables, including dist_group_data_mdmud, product_uom_data, product_sn, product_none, dist_whhouse, and dist_agent. Multiple UNION ALL statements are used to combine different inventory source types. The CASE WHEN statement is used to select the appropriate distributor code and name to ensure data accuracy and consistency. Unit conversion is performed using b.rate to uniformly convert inventory quantities to the basic unit EA.

[0046] Data filtering and conditional application: Select only inventory records with a status of "In Stock". Apply multiple conditional filters, such as whether the user is a warehouse manager or the warehouse type, to ensure the accuracy of the selected data.

[0047] Data aggregation and calculation: The GROUP BY statement is used to group and summarize the data, calculating the total inventory for each material. A left join with the price table asp_product_price is performed to obtain the price information for each material and calculate the total price.

[0048] Result Insertion: The processed and calculated inventory data, including distributor information, material number, unit, quantity, date, and price information, is inserted into the dist_daily_inventory_sync table.

[0049] Dynamic SQL execution: Queries are constructed and executed using dynamic SQL. This design provides greater flexibility and scalability, enabling the dynamic adjustment and execution of complex SQL operations as needed.

[0050] This code provides a comprehensive snapshot of daily inventory status by integrating data from different sources. This design helps manage and analyze real-time inventory data, supporting subsequent decision-making, and is especially suitable for large-scale supply chain systems that require granular inventory control.

[0051] To further illustrate, let's take an example. Figures 3-10The invention demonstrates some of the working pages of the system in some practical application scenarios. The intelligent inventory management system provided by this invention can realize basic data collection (including sensor collection or manual input collection), data processing, data conversion, data prediction, provide inventory replenishment suggestions, and optimize paths, thereby realizing intelligent inventory management based on big data supply chain.

[0052] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention, and all such modifications or substitutions should be covered within the scope of the claims of the present invention.

Claims

1. An intelligent inventory management method based on big data supply chain, characterized by: include, Collect inventory data, real-time traffic data, and real-time weather data in the warehouse, and pre-process the data; Based on the pre-processed inventory data, a forecasting model is built to predict inventory trends; Formulate an inventory replenishment plan based on the forecast results of the inventory trend, automatically issue replenishment requests based on the inventory replenishment plan, and generate replenishment tasks; Based on real-time traffic data and real-time weather data, the path optimization algorithm is used to generate the optimal path for the replenishment task; Continuously monitor inventory data, vehicle location data for replenishment tasks, real-time traffic conditions data, and real-time weather data to determine whether the replenishment path or inventory is abnormal. When an abnormality is detected, regenerate the current optimal path or start the replenishment task; Using feedback from the exception handling to adjust and optimize management methods; The collection of warehouse inventory data, real-time traffic data and real-time weather data, and pre-processing of the data also include the following steps: Adjust the data collection frequency for each data type (warehouse inventory data, traffic data, and weather data) based on the amount of erroneous data, missing data, and abnormal data in each data type, including: Acquire in real time the amount of data corresponding to erroneous data, missing data and abnormal data in data collection for each data type; wherein the data types include inventory quantity in the warehouse, traffic condition data and weather condition corresponding data; The data quality evaluation coefficient corresponding to each data type is obtained by using the data amount corresponding to the erroneous data, missing data and abnormal data in the data collection of each data type; The data quality evaluation coefficient corresponding to each data type is obtained by the following formula: Among them, Q represents the data quality evaluation coefficient corresponding to each data type; n represents the number of data collection times corresponding to each data type; C 01i , C 02i and C 03i represents the amount of erroneous data, missing data, and abnormal data corresponding to the i-th data collection for each data type; w 01 、w 02 and w 03 Respectively represent the weight values ​​corresponding to the preset erroneous data, missing data and abnormal data; T 01i represents the error correction processing time corresponding to the error data during the i-th data collection of each data type; T 02i T represents the time required to fill missing values ​​in the i-th data collection for each data type; 03i T represents the time it takes to process abnormal values ​​when collecting the i-th data for each data type; zi represents the total preprocessing time corresponding to the i-th data collection of each data type; C zi represents the total amount of collected data corresponding to the i-th data collection of each data type; s represents the adjustment coefficient, and the adjustment coefficient is obtained by the following formula: Among them, s represents the adjustment coefficient; n represents the number of data collection times corresponding to each data type; C 01i , C 02i and C 03i represents the amount of erroneous data, missing data, and abnormal data corresponding to the i-th data collection for each data type; w 01 、w 02 and w 03 Respectively represent the weight values ​​corresponding to the preset erroneous data, missing data and abnormal data; T i express The corresponding data processing time (i.e., the processing time for correcting errors corresponding to erroneous data, the processing time for filling missing values ​​for missing data, or the processing time for filling missing values ​​for missing data); w i express The corresponding weight value (i.e., the weight value corresponding to the wrong data, missing data or abnormal data); C si represents the maximum data processing amount per unit time during the i-th data collection of the data type, and the unit time is 1s; Compare the data quality evaluation coefficient corresponding to each data type with a preset coefficient threshold; When the data quality evaluation coefficient corresponding to each data type exceeds the preset coefficient threshold, the data collection frequency of the data type corresponding to the data quality evaluation coefficient exceeding the preset coefficient threshold is adjusted, wherein the adjusted data collection frequency is obtained by the following formula: Among them, F represents the adjusted data collection frequency; F0 represents the adjusted data collection frequency; Q represents the data quality evaluation coefficient corresponding to each data type.

2. The intelligent inventory management method based on big data supply chain according to claim 1, characterized in that: Collect inventory data, real-time traffic data, and real-time weather data in the warehouse, and pre-process the data. The following steps are included: Collect inventory quantities in warehouses, collect real-time traffic conditions data, collect real-time weather conditions data, and correct errors, fill missing values, and process outliers in the collected data.

3. The intelligent inventory management method based on big data supply chain according to claim 1, characterized in that: Based on the preprocessed inventory data, a forecasting model is constructed to predict the inventory trend. The following steps are included: The preprocessed inventory data is converted into a time series format and divided into a training set, a validation set, and a test set. A prediction model is constructed. The prediction model is trained using the training set data. The test set is input into the trained prediction model to obtain the predicted inventory value. The expression is: ； in, For time point The inventory value, For time point The average inventory For the The weight of the data point, For time point Historical inventory values, is the weighting factor, is the length of the historical data window; Calculate the error between the predicted value and the true value in the validation set, adjust the model parameters according to the performance on the validation set, find the optimal model configuration on the validation set, and adjust the weighting factors and weights when the error is large.

4. The intelligent inventory management method based on big data supply chain according to claim 1, characterized in that: Execute the inventory replenishment plan according to the forecast results of the forecast inventory trend, automatically issue replenishment requests, and generate replenishment tasks, including the following steps: Execute the inventory replenishment plan based on the forecast results, set the safety stock level and reorder point, trigger the replenishment request when the inventory is lower than the reorder point, and generate the replenishment task. Use the exponential smoothing model to predict the demand for a period of time in the future. The formula is: ； in, For time point The demand, is the smoothing level, is the trend quantity, is the current demand, is the periodic component; Calculate the replenishment quantity based on the predicted demand, the replenishment quantity expression, ； in, is the replenishment quantity, For time point The actual inventory level, is the safety stock level.

5. The intelligent inventory management method based on big data supply chain according to claim 1, characterized in that: Based on real-time traffic data and real-time weather data, the path optimization algorithm is used to generate the optimal path for the replenishment task, including the following steps: Integrate real-time traffic data and real-time weather data into path planning, adjust the path cost, and choose to use the path optimization algorithm. Combine real-time traffic data and real-time weather data to generate the optimal path for each replenishment task, and the goods are delivered on time. The optimal path expression is: ； in, is the optimal path, For Node To Node +1 distance, For Node The distance to the target node, For Node The constraint factor, is the regulating factor, is the weight factor of the constraint condition, is the total cost of all constraints on path P.

6. The intelligent inventory management method based on big data supply chain according to claim 1, characterized in that: Continuously monitor inventory data, vehicle location information data for replenishment tasks, real-time traffic conditions data, and weather data to determine whether the replenishment process is abnormal. When an abnormality is detected, regenerate the current optimal path. The following steps are included: Collect location information data of vehicles performing replenishment tasks; Based on the vehicle location information data, real-time traffic status data and weather data, determine whether there is traffic congestion or sudden weather changes at the current vehicle location or travel direction. If so, regenerate the current optimal path and automatically send an instruction to the vehicle terminal to adjust the path to the current optimal path; Monitor warehouse inventory data in real time. When the inventory level is lower than the safety stock level, an abnormal alarm is automatically triggered. After the abnormal alarm is triggered, the replenishment task is initiated.

7. The intelligent inventory management method based on big data supply chain according to claim 1, characterized in that: Using the feedback from the abnormal situation handling, the management method is adjusted and optimized, including the following steps: Record the time, location and specific circumstances of each abnormal situation; Record the method and results of handling each abnormal situation to form a case database; Regularly analyze the above records and make adjustments and optimizations to the management methods.

8. An intelligent inventory management system based on a big data supply chain, based on the intelligent inventory management method based on a big data supply chain according to any one of claims 1 to 7, characterized in that: include, The data collection and preprocessing module is responsible for collecting inventory data, real-time traffic data, and real-time weather data in the warehouse, and preprocessing the collected data; The inventory forecasting module builds a forecasting model based on pre-processed inventory data to predict inventory trends and provide a basis for inventory replenishment planning; The replenishment plan and request module formulates inventory replenishment plans based on the forecast results of inventory trends, and automatically issues replenishment requests and generates replenishment tasks; The route optimization module generates the optimal route for the replenishment task using the route optimization algorithm based on real-time traffic condition data and real-time weather data; The monitoring and exception handling module continuously monitors inventory data, the location of vehicles performing replenishment tasks, real-time traffic conditions and weather data, and determines whether the replenishment path or inventory is abnormal. When an abnormality is detected, the current optimal path is regenerated or the replenishment task is started; The feedback from the exception handling is used to adjust and optimize the management method.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the intelligent inventory management method based on big data supply chain described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the intelligent inventory management method based on big data supply chain described in any one of claims 1 to 7 are implemented.

Images