Bulk commodity sales order management method and system based on cloud platform

Abstract

The invention discloses a bulk commodity sales order management method and system based on a cloud platform, and particularly relates to the technical field of data management. Stock batch information is acquired in real time through a stock management system, stock scheduling is optimized according to sales order demands and warehouse geographic positions, and meanwhile, the system is integrated with API interfaces of multiple logistics suppliers to realize real-time association of logistics states and sales order data; in combination with inventory scheduling abnormity and logistics state analysis, consistency abnormity of cross-platform data synchronization and inventory batch management can be predicted, and corresponding early warning signals and processing suggestions are generated, so that the stability and response efficiency of a supply chain are improved, and the system performance is improved. The problems of mismatching and supply chain interruption caused by inconsistent data or insufficient inventory management are reduced, and smooth execution of bulk commodity sales orders is ensured.

Description

Technical Field

[0001] The present invention relates to the technical field of data management, and particularly to a method and system for managing bulk commodity sales orders based on a cloud platform. Background Art

[0002] Managing bulk commodity sales orders based on a cloud platform refers to digitalizing, automating, and centralizing the order management link in the sales process of bulk commodities (such as raw materials, energy, agricultural products, etc.) through cloud computing technology. With the help of the cloud platform, enterprises can obtain order information in real time, track sales progress, handle customer needs, optimize inventory and logistics scheduling, thereby improving business efficiency and response speed.

[0003] Enterprise Resource Planning (ERP) systems are one of the most common technologies in current bulk commodity sales order management. Cloud ERP systems migrate traditional ERP functions to the cloud platform and utilize the advantages of cloud computing to provide comprehensive enterprise resource management solutions. It can integrate data from multiple departments such as procurement, inventory, sales, and finance, and help enterprises manage various links such as orders, supply chains, inventory, finance, and customer relationships of bulk commodities. The real-time data processing and big data analysis capabilities of cloud ERP systems can help enterprises track order status in real time, predict sales trends, optimize inventory management and order scheduling, and improve the operation efficiency and decision-making accuracy of enterprises.

[0004] The existing technologies have the following deficiencies:

[0005] In the management of bulk commodity sales orders based on a cloud platform, especially in cases involving multiple parties, multiple regions, and complex logistics links, the real-time synchronization and accurate tracking of sales order data become a major challenge. Since bulk commodities usually have a long delivery cycle and complex supply chains, information such as order status, inventory, and logistics progress often needs to be synchronized across multiple systems. In a cloud platform environment, cross-platform data exchange may cause problems such as delays, information loss, and data inconsistency. More seriously, when the inventory quantities of commodities involved in multiple sales orders in the warehouse are large, there are issues regarding the batch management of bulk commodities. For example, inconsistencies between inventory data in different warehouses in the cloud platform, or when purchase orders, sales orders, and production orders of a certain bulk commodity are scheduled across time dimensions, the system may produce incorrect matches or supply chain disruptions due to insufficient inventory batch management. Summary of the Invention

[0006] The purpose of the present invention is to provide a method and system for managing bulk commodity sales orders based on a cloud platform to solve the deficiencies in the background art.

[0007] To achieve the above object, the present invention provides the following technical solutions: A method for managing bulk commodity sales orders based on a cloud platform, comprising the following steps:

[0008] Generate a bulk commodity sales order on the cloud platform, and automatically transmit the order information to the inventory management system and the logistics management system through a real-time data synchronization mechanism;

[0009] The inventory management system, according to the inventory management rules, obtains the inventory batch information in real time, and matches the most suitable inventory batch according to the requirements of the sales order;

[0010] For a multi-warehouse environment, the inventory management system automatically schedules the commodity inventory among different warehouses according to the inventory status and the geographical location of the warehouses;

[0011] The logistics management system, by integrating with the API interfaces of multiple logistics suppliers, obtains the logistics progress information in real time, and associates the logistics status with the sales order data;

[0012] Analyze the scheduling anomalies of commodity inventory among different warehouses and the association status between the logistics status and the sales order data, predict the consistency anomalies of cross-platform data synchronization and inventory batch management, and give early warnings and generate corresponding handling suggestions.

[0013] Preferably, create a sales order for bulk commodities, the order includes commodity information, customer information, delivery information and payment information, generate a unique order number for each order, and synchronize the relevant data to the inventory management system and the logistics management system.

[0014] Preferably, after receiving the sales order, the inventory management system checks whether the inventory is sufficient according to the commodity number and quantity of the order; if the inventory is sufficient, the system will deduct the corresponding commodity inventory and arrange for outbound; if the inventory is insufficient, the system will trigger the procurement or production process.

[0015] Preferably, after analyzing the scheduling anomalies of commodity inventory among different warehouses, generate an abnormal index of warehouse inventory change rate. The method for obtaining the abnormal index of warehouse inventory change rate is as follows:

[0016] Calculate the change amount of inventory at each moment and convert it into a change rate: Through the EWMA algorithm, assign a weighted average value to the inventory change amount at each moment. The formula of EWMA is: μ t =α·ΔI t +(1 - α)·μ t-1 ; where: μ t is the smoothed value at time t, representing the long-term trend of the current inventory change, α is the smoothing factor, controlling the impact of recent inventory fluctuations on the model; ΔI tis the inventory change at time t. To measure the amplitude of inventory fluctuations, calculate the standard deviation of the inventory changes over the past N days: where N is the selected time window, and calculate the Warehouse Inventory Fluctuation Abnormal Index WIFAI. The expression is:

[0017] Preferably, after analyzing the correlation state between the logistics status and the sales order data, generate a logistics correlation risk change index. The method for obtaining the logistics correlation risk change index is:

[0018] Mark the correlation state between the logistics status and the sales order data as K, and establish a set K = [K1, K2, K3,..., K n , where n is a positive integer greater than 0; for the correlation risk factors between the logistics status and the sales order data, formulate the corresponding probability distribution and mark it as PK n , based on the formulated probability distribution, conduct Monte Carlo simulation and generate multiple simulation scenarios. For each scenario, calculate the logistics correlation risk before the change. The specific calculation expression is: Rnew = w1*K1 + w2*K2 +... + w n *K n ; in the formula, Rnew is the logistics correlation risk before the change, w1, w2,..., w n are the weights of each factor before the change, used to represent the importance of each factor to the material correlation risk; K1, K2,..., K n are the labels of the factors affecting the logistics correlation risk. According to the changed situation, calculate the logistics correlation risk after the change, denoted as Recr = r1*K1 + r2*K2 +... + r n *K n ; in the formula, Recr is the logistics correlation risk after the change, r1, r2,..., r n are the weights of each factor after the change. Calculate the logistics correlation risk change index. The specific calculation expression is: In the formula, erh df is the logistics correlation risk change index.

[0019] Preferably, convert the abnormal index of warehouse inventory change rate and the abnormal index of logistics-related risk change into a comprehensive feature vector, and use the comprehensive feature vector as the input of the machine learning model. The machine learning model takes predicting the consistency outlier label of cross-platform data synchronization and inventory batch management for each group of comprehensive feature vectors as the prediction target, and takes minimizing the sum of prediction errors for all consistency outlier labels of cross-platform data synchronization and inventory batch management as the training target. Train the machine learning model until the sum of prediction errors reaches convergence and then stop the model training. Determine the consistency outliers of cross-platform data synchronization and inventory batch management according to the model output results, where the machine learning model is a polynomial regression model.

[0020] Preferably, compare the obtained consistency outliers of cross-platform data synchronization and inventory batch management with the consistency reference threshold set according to historical data. If the consistency outliers of cross-platform data synchronization and inventory batch management are greater than or equal to the set consistency reference threshold, it indicates a high degree of consistency abnormality in cross-platform data synchronization and inventory batch management. At this time, generate a warning signal and generate corresponding handling suggestions; if the consistency outliers of cross-platform data synchronization and inventory batch management are less than the set consistency reference threshold, it indicates a low degree of consistency abnormality in cross-platform data synchronization and inventory batch management. At this time, do not generate a warning signal.

[0021] The present invention also provides a bulk commodity sales order management system based on a cloud platform, including an information transmission module, an inventory matching module, an inventory scheduling module, a logistics correlation module, and a prediction and warning module;

[0022] Information transmission module: Generate a bulk commodity sales order on the cloud platform, and automatically transmit the order information to the inventory management system and the logistics management system through a real-time data synchronization mechanism;

[0023] Inventory matching module: The inventory management system obtains inventory batch information in real time according to inventory management rules, and matches the most suitable inventory batch according to the sales order requirements;

[0024] Inventory scheduling module: For a multi-warehouse environment, the inventory management system automatically schedules commodity inventory among different warehouses according to the inventory status and the geographical location of the warehouses;

[0025] Logistics correlation module: The logistics management system integrates through the API interfaces of multiple logistics suppliers to obtain logistics progress information in real time, and correlates the logistics status with the sales order data;

[0026] Prediction and warning module: Analyze the scheduling abnormalities of commodity inventory among different warehouses and the correlation status between the logistics status and the sales order data, predict the consistency abnormalities of cross-platform data synchronization and inventory batch management, and give warnings and generate corresponding handling suggestions.

[0027] In the above technical solution, the technical effects and advantages provided by the present invention are as follows:

[0028] 1. Through the real-time data synchronization mechanism, the present invention can automatically transmit sales order information to the inventory management system and the logistics management system, ensuring the rapid circulation and synchronization of information. Through precise inventory batch matching and intelligent scheduling of multiple warehouses, the system greatly reduces the risk of inconsistency in inventory management and avoids supply chain interruption problems caused by unmatched inventory batches. At the same time, the logistics management system can obtain the logistics status in real time and, through the association with sales order data, can timely grasp the logistics progress of the order, thereby effectively reducing the impact of logistics delays and other problems on the delivery cycle.

[0029] 2. By calculating the abnormal index of warehouse inventory change rate and the change index of logistics-related risk, the present invention can monitor the consistency anomalies in cross-platform data synchronization and inventory batch management in real time. Combined with the machine learning model, this method can accurately predict potential abnormal situations and generate warning signals in a timely manner, providing data-driven decision support for enterprises, reducing the operational risks caused by information asymmetry or system delays, and improving the efficiency and accuracy of the entire sales order management. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings required for use in the embodiments. Obviously, the drawings described below are only some embodiments recorded in the present invention. For those of ordinary skill in the art, other drawings can also be obtained based on these drawings.

[0031] Figure 1 It is the flowchart of the method of the present invention.

[0032] Figure 2 It is the system module diagram of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0033] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the drawings in the embodiments of the present invention. Obviously, the described embodiments are some, but not all, of the embodiments of the present invention. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0034] Example 1. Please refer to Figure 1 As shown, a method for managing bulk commodity sales orders based on a cloud platform in this embodiment includes the following steps:

[0035] Generate a bulk commodity sales order on the cloud platform and automatically transmit the order information to the inventory management system and the logistics management system through a real-time data synchronization mechanism;

[0036] The inventory management system, according to the inventory management rules, obtains the inventory batch information in real time and matches the most suitable inventory batch according to the sales order requirements;

[0037] For a multi-warehouse environment, the inventory management system automatically schedules the commodity inventory among different warehouses according to the inventory status and the geographical location of the warehouses;

[0038] The logistics management system, through integration with the API interfaces of multiple logistics suppliers, obtains the logistics progress information in real time and associates the logistics status with the sales order data;

[0039] Analyze the scheduling anomalies of commodity inventory among different warehouses and the association status between the logistics status and the sales order data, predict the consistency anomalies of cross-platform data synchronization and inventory batch management, and give early warnings and generate corresponding handling suggestions.

[0040] First, create a sales order for bulk commodities on the cloud platform. Usually, the order is entered through an enterprise resource planning (ERP) system, a customer relationship management (CRM) system, or a dedicated order management module. The content of the sales order generally includes the following key information:

[0041] Commodity information: including commodity number, name, specification, quantity, unit price, etc. Customer information: including customer name, address, contact information, tax information, etc. Delivery information: including delivery location, delivery time requirement, transportation method, etc. Payment information: including payment method, payment period, etc. Salesperson information: including the salesperson and team responsible for this order. After the order is created, the system generates a unique order number and automatically enters it into the cloud platform database for subsequent operations and data synchronization.

[0042] On the cloud platform, the data synchronization mechanism ensures seamless connection between the sales order and other systems (such as the inventory management system, the logistics management system, etc.), ensuring information consistency and real-time update. This mechanism mainly includes the following parts:

[0043] Through the API interface, the cloud platform can conduct real-time data interaction with the inventory management system and the logistics management system. The cloud platform automatically transmits the key information of the sales order (such as commodity number, quantity, delivery time, etc.) to the inventory management system to ensure that the inventory information can be updated quickly. At the same time, data such as the delivery information and customer requirements of the sales order are also transmitted to the logistics management system so that the logistics company can plan the transportation route and arrange the distribution according to the order requirements.

[0044] The cloud platform not only pushes sales order information to the inventory management system and the logistics management system, but also synchronizes the response data (such as inventory status, outbound time, logistics status, etc.) of these two systems back to the cloud platform.

[0045] For example, after receiving a sales order, the inventory management system will confirm whether it can meet the order requirements based on the inventory quantity. If the inventory is insufficient, the system will feedback the situation of insufficient inventory to the cloud platform, and the cloud platform will then trigger the procurement or production process. The logistics management system will automatically update the logistics progress according to the delivery time requirement of the order and synchronize the information back to the cloud platform to ensure that the order status and transportation progress are completely transparent to customers and salespersons.

[0046] To ensure data consistency, the cloud platform usually adopts distributed transaction management or event-driven architecture to ensure that the order information transmitted between systems will not be lost or conflict. At the same time, the data synchronization mechanism will implement real-time verification. For example, it checks whether the quantity of goods in the sales order matches the existing inventory in the inventory system to avoid order errors caused by data asynchronization.

[0047] In some cases, especially in high-concurrency situations, the cloud platform will adopt an asynchronous processing mechanism. When a sales order information is created, the system will not immediately wait for the response from the inventory or logistics, but first save the order information to the database and push it to the inventory and logistics management systems asynchronously. Asynchronous processing can also use a message queue system (such as Kafka, RabbitMQ, etc.) to transmit the sales order information to ensure efficient and reliable data transmission. Once the inventory management system or the logistics management system has processed the relevant information, they will update the feedback result back to the cloud platform through synchronization or callback to complete the final confirmation of the order status.

[0048] Once the inventory or logistics system has completed the processing of the order-related information, the cloud platform will update the status of the sales order in real time based on the inventory data and logistics progress to ensure that salespersons, customers, and relevant systems can all obtain the latest information. For example, the system will send a notification of order status update to the salesperson, and customers can also view the order progress through the self-service portal. If the order has changed (such as insufficient inventory, delivery delay, etc.), the cloud platform will update the order information in a timely manner and push relevant notifications to all relevant parties.

[0049] When a sales order is generated, the cloud platform automatically transmits the order information to the inventory management system, and the inventory management system will perform the following operations:

[0050] Inventory Check: The inventory system looks up whether there is sufficient inventory to meet the order requirements based on the product numbers and quantities in the sales order. Inventory Deduction: If the inventory is sufficient, the system will deduct the corresponding quantity of products from the inventory according to the order information and mark them as pending shipment; if the inventory is insufficient, the system will trigger the procurement or production process through automated rules or manually. Inventory Scheduling: In a multi-warehouse environment, the inventory management system will also select the most suitable warehouse for product scheduling based on the delivery location of the sales order and the warehouse location.

[0051] Meanwhile, the delivery information of the sales order will be transmitted to the logistics management system, and the logistics system will perform the following operations according to the delivery requirements of the order (such as delivery date, transportation method, delivery address, etc.):

[0052] Transportation Plan Planning: The logistics management system will automatically select the best logistics plan and transportation method (such as express delivery, freight, etc.) according to the delivery requirements and cooperate with logistics suppliers. Shipping Arrangement: Once the inventory is confirmed, the logistics system will arrange the shipment of the products and automatically update the logistics status of the order. Tracking and Feedback: The logistics system integrates with the logistics supplier system to track the transportation status of the products in real time and feedback the logistics information back to the cloud platform and the customer.

[0053] In the inventory management of bulk commodities, an inventory batch refers to the products of the same production or procurement batch, usually having the same production date, expiration date, production location or other identical characteristics. For bulk commodities such as chemical raw materials, minerals, etc., the management of batch information is particularly important because it involves the shelf life, source, transportation conditions, etc. of the products.

[0054] Each inventory batch usually contains the following key information:

[0055] Batch Number: A unique number that identifies a certain batch. Production Date: The production or receipt date of the batch. Expiration Date / Shelf Life: The expiration period of the product, which is particularly important in the fields of bulk commodities such as food and medicine. Inventory Quantity: The current inventory quantity of the products in this batch. Warehouse Location: The specific location where the batch is stored. Quality Inspection Result: Whether the products in this batch have passed the quality inspection or certification.

[0056] The inventory management system obtains the inventory batch information in real time, usually relying on the following technical means:

[0057] RFID technology: Through radio frequency identification (RFID) tags, the batch information of goods is combined with RFID reading devices to achieve automated tracking and real-time updating of inventory. Internet of Things (IoT) devices: Through sensors and IoT devices, the environmental conditions (such as temperature, humidity, etc.) of inventory batches and the storage locations of goods can be monitored in real time. Database synchronization: The inventory management system synchronizes data with ERP systems, production systems, procurement systems, etc., to obtain information such as inbound, outbound, and inventory changes of batches in real time. These technologies ensure that the inventory management system can accurately grasp the specific information of inventory batches at any time point and monitor them in real time.

[0058] To match the most suitable inventory batches according to the requirements of sales orders, the inventory management system will automatically screen inventory batches according to a series of matching rules. Common inventory matching rules include:

[0059] (1) First In, First Out (FIFO): This rule requires the earliest received batches to be used first. This is particularly important for large commodities with shelf life requirements. For example, for large commodities such as chemicals or food, the earlier produced batches should be used first to ensure that the goods are delivered within the shelf life.

[0060] (2) Batch quality priority: If the sales order has specific quality requirements for the goods (such as the purity of chemicals or the grade of ores), the inventory management system will preferentially select batches whose quality inspection results meet the requirements.

[0061] (3) Geographic location priority: If the inventory management system supports a multi-warehouse mode, the nearest warehouse and batches to the customer can be selected according to the delivery location of the sales order. This can effectively shorten the transportation time and cost and improve the delivery efficiency.

[0062] (4) Inventory sufficiency matching: The inventory management system will check the inventory quantity of each inventory batch and compare it with the demand in the sales order to ensure that the quantity of the selected batch is sufficient to meet the order demand. If the inventory of a certain batch is insufficient, the system will supplement the inventory from other batches according to the rules, or trigger the procurement or production process.

[0063] (5) Customer priority: If there is a priority setting for specific customers (such as long-term cooperative VIP customers or high-value orders), the inventory management system can allocate inventory according to the needs of the customers first to ensure customer satisfaction.

[0064] Based on the above rules, the specific process of the inventory management system for inventory batch matching is as follows:

[0065] When a sales order is generated and transmitted to the inventory management system, the system first analyzes information such as the type of goods, quantity, and delivery time requirements in the order. The system will automatically compare this information with the current inventory.

[0066] The inventory management system automatically filters eligible inventory batches according to order requirements (such as product type, quantity, delivery date, etc.). For example, if a sales order requests a specific batch of products, the system will first search for that batch.

[0067] If the order requests multiple products, the system will match batches according to the quantity requirements to ensure that there is sufficient inventory of each product to fulfill the order.

[0068] After the system filters out eligible inventory batches, it will sort these batches according to inventory matching rules (such as FIFO, quality priority, geographical location priority, etc.), and finally select the most suitable inventory batch.

[0069] If the system finds that a certain batch cannot meet the order requirements (such as insufficient quantity, substandard quality, etc.), it will automatically select the next priority batch until the order requirements are met.

[0070] Once a suitable batch is matched, the inventory management system will automatically update the inventory records, reduce the inventory quantity, and mark this batch as "allocated".

[0071] The system will synchronize the batch allocation results and inventory update information back to the cloud platform, sales management system, or other relevant systems through a real-time data synchronization mechanism to ensure that the processing process of sales orders is completely transparent.

[0072] Once the inventory batch is confirmed and allocated to a sales order, the inventory management system will also arrange the distribution and logistics plan through integration with the logistics management system to ensure the timely delivery of products.

[0073] In a multi-warehouse environment, the process of the inventory management system automatically scheduling the inventory of products according to the inventory status and warehouse geographical location is the key to achieving supply chain optimization. Through intelligent scheduling, the system can automatically allocate the inventory of products between different warehouses according to demand forecasting, order requirements, inventory status, and geographical location, ensuring that products can be delivered to customers in a timely manner, improving the overall operation efficiency, and reducing inventory costs.

[0074] The basic process of automatically scheduling the inventory of products generally consists of the following steps:

[0075] The inventory management system monitors the inventory status of each warehouse in real time through data synchronization with each warehouse. Inventory information includes but is not limited to: product name, specification, quantity; remaining inventory in the warehouse; shelf life, batch information, storage conditions, etc. of the product; storage capacity and available space of the warehouse.

[0076] When a sales order or other business requirements (such as production orders, internal transfers, etc.) enter the system, the inventory management system analyzes the requirements to identify whether inventory needs to be allocated from different warehouses. Demand forecasting generally relies on the following information:

[0077] The types and quantities of goods in the sales order, the delivery location and time requirements of the customer, the geographical location and transportation capacity of the warehouse, possible seasonal demand fluctuations, promotional activities, and other factors.

[0078] The inventory management system determines the most suitable scheduling plan according to the preset scheduling rules. Scheduling decisions usually depend on the following factors:

[0079] Inventory status: Check whether the inventory in each warehouse is sufficient to meet the demand. If the inventory in a certain warehouse is insufficient, the system will automatically select other warehouses for replenishment allocation.

[0080] Geographical location: Consider the geographical location of the customer and the transportation distance from each warehouse to the customer. The system usually selects the warehouse closest to the customer to reduce transportation time and costs. For example, if the customer is located in the east and the inventory in the eastern warehouse is sufficient, the system will give priority to selecting the eastern warehouse for shipment.

[0081] Warehouse priority and transportation capacity: If multiple warehouses have inventory, the system may select the scheduling warehouse according to the warehouse priority (for example, some warehouses are used as the main shipping warehouses), or give priority to selecting warehouses with strong transportation capacity and fast shipping speed.

[0082] Once the scheduling plan is determined, the inventory management system triggers the inventory transfer action and automatically arranges to transfer inventory from one warehouse to another. The transfer usually includes the following operations:

[0083] Inventory change: Deduct the inventory of goods from the warehouse being transferred out and mark the transferred goods as "in transit" status.

[0084] Inventory receipt: After the target warehouse receives the transferred goods, the system updates the inventory record and marks the goods as "received" status.

[0085] Logistics arrangement: According to the distance and urgency of the transfer, the system generates an automatic transportation plan. The logistics management system or a third-party logistics company will arrange transportation according to this plan to complete the transfer of goods.

[0086] The inventory management system synchronizes all data during the transfer process in real time, including: the quantity and batch information of the goods transferred, the changes in the inventory status during the transfer process, and the order update situation in the client or sales system. At the same time, the system checks whether the transfer is successful through a feedback mechanism. If the transfer fails (such as insufficient inventory, transportation delays, etc.), the system will automatically handle the error and notify the relevant personnel.

[0087] The logistics management system can obtain real-time logistics progress information by integrating with the API interfaces of different logistics providers (such as express companies, freight companies, etc.). API (Application Programming Interface) is a standardized way that allows the system to interact with external services. Logistics providers usually offer API interfaces that allow third-party systems to query information such as the status, location, and estimated arrival time during transportation.

[0088] Supplier API: Different logistics providers may offer different API interfaces. For example, some provide interfaces based on tracking numbers. After users provide the tracking number of an order through the API, they can query the transportation status. Some suppliers may offer more comprehensive interfaces that allow querying detailed information such as the real-time location of goods, transportation delays, and estimated delivery times.

[0089] Multi-supplier support: To avoid relying on a single logistics provider, the system usually supports integrating with multiple logistics companies through API interfaces, enabling intelligent scheduling among multiple options to find the optimal logistics solution.

[0090] The API interfaces of logistics providers allow the system to query real-time information such as transportation routes, the current location of goods, and transportation delays. Based on the real-time data during transportation, the system can dynamically update the estimated delivery time, providing accurate delivery information to customers and the sales team. Once the transportation status changes (e.g., the package has been shipped, the package has reached a transfer station, the package has been delivered, etc.), the API of the logistics provider can automatically transmit these update notifications to the management system.

[0091] The logistics management system can not only obtain logistics progress information but also associate this information with sales order data in real time. After association, the status of the order can reflect the change in the logistics status in the sales-end system, timely reminding customers and the sales team. Each sales order is assigned a unique order ID and a related logistics tracking number. Through the API interface, the logistics management system updates the logistics status of the order in real time and maps it to the corresponding sales order. When the logistics status changes, the system automatically updates the status of the sales order. For example, the order status is updated from "awaiting shipment" to "shipped", then to "in transit" or "delivered", and each update reflects the logistics process.

[0092] After associating the logistics status with sales order data, the system can provide a visual display of the order progress for customers, the sales team, and supply chain managers. For example:

[0093] Client interface: Customers can view the current logistics status of each sales order in their own accounts and even view a real-time map of the location of the goods. Sales team interface: Sales personnel can check the transportation progress of a certain order at any time, timely track logistics delays, and handle customer inquiries or complaints.

[0094] By integrating with the API interfaces of logistics suppliers, the logistics management system can promptly identify anomalies during transportation (such as delays, incorrect deliveries, losses, etc.) and feed this information back into the sales orders. The system can issue alerts to relevant personnel through a delay warning mechanism to prompt the timely handling of anomalies. When a logistics supplier reports a transportation delay or other issues, the system can automatically update the status of the sales order and generate warning messages to notify customers and relevant management personnel. If there is a logistics delay for an order, the system can automatically notify the customer via text message, email, etc., providing an estimated update or solution.

[0095] Through the API, the logistics management system automatically synchronizes the real-time transportation data obtained from multiple logistics suppliers to the sales order management system. The entire process is automated and requires no manual intervention.

[0096] The system will automatically synchronize each logistics status update (such as "in transit", "out of warehouse", "arrived at the distribution center", etc.) obtained from the logistics supplier API to the order management system.

[0097] In addition to the transportation status, the system will also automatically record and synchronize additional information such as transportation time and transportation costs to form complete sales order information.

[0098] The system can automatically associate orders with logistics data in the following ways:

[0099] Each sales order will be assigned a unique logistics tracking number, and through the API, this tracking number will be docked with the data of the logistics supplier to automatically query and update the logistics status.

[0100] Each sales order will be associated with a specific transportation task or cargo scheduling. In this way, even in the case of complex multi-commodity orders or partial shipments, it can ensure that the logistics information corresponds one-to-one with the order information, avoiding information confusion.

[0101] The inventory of bulk commodities may fluctuate due to factors such as market demand, procurement plans, and transportation delays. Abnormal fluctuations in the inventory change rate often indicate problems in inventory management, such as slow-moving goods, mismatches between procurement and demand, inventory backlogs, etc., which may all lead to significant changes in the inventory levels of a certain warehouse.

[0102] After analyzing the abnormal situations of commodity inventory scheduling between different warehouses, an abnormal index of warehouse inventory change rate is generated. The method for obtaining the abnormal index of warehouse inventory change rate is as follows:

[0103] Calculate the change amount of inventory at each moment and convert it into a change rate: A measure of the percentage fluctuation in inventory at a warehouse during a specific period of time.

[0104] Through the EWMA algorithm, a weighted average is assigned to the inventory change at each moment. The formula for EWMA is: t =α·ΔI t +(1-α)·μ t-1 ; Among them: μ t It is the smoothed value (i.e. weighted average) at time t, which indicates the long-term trend of current inventory changes. α is the smoothing factor, which controls the impact of recent inventory fluctuations on the model. t is the inventory change at time t. In order to measure the magnitude of inventory fluctuations, the standard deviation of inventory changes (i.e., degree of fluctuation) over the past N days is calculated: Where N is the selected time window (for example, the past 7 days, the past 30 days, etc.). The warehouse inventory change rate abnormality index WIFAI is calculated as follows: WIFAI indicates the degree of deviation between the current inventory change rate and the smoothed value. If the WIFAI value is high, it means that the inventory change is abnormal. The level of the abnormal index will reflect the abnormal degree of inventory fluctuation. The higher the value, the more drastic the inventory fluctuation and the higher the abnormal degree.

[0105] After analyzing the association status between the logistics status and the sales order data, the logistics association risk change index is generated. The method for obtaining the logistics association risk change index is as follows:

[0106] The association status between logistics status and sales order data is marked as K, and a set K = [K1, K2, K3, ..., K n ], where n is a positive integer greater than 0; for the associated risk factors between logistics status and sales order data, a corresponding probability distribution is formulated and marked as PK n Based on the established probability distribution, Monte Carlo simulation is performed and multiple simulation scenarios are generated. For each scenario, the logistics-related risk before the change is calculated. The specific calculation expression is: Rnew=w1*K1+w2*K2+...+w n *K n ; where Rnew is the logistics-related risk before the change, w1, w2, ..., w n It is the weight of each factor before the change, which is used to indicate the importance of each factor to the material-related risk; K1, K2, ..., K n It is the label of the factors affecting logistics-related risk. According to the changed situation, the changed logistics-related risk is calculated, which is recorded as Recr = r1*K1+r2*K2+...r n *K n ; In the formula, Recr is the modified logistics-related risk, r1, r2, ..., rn is the weight of each factor after the change, and the logistics correlation risk change index is calculated. The specific calculation expression is: In the formula, erh df is the logistics correlation risk change index.

[0107] The logistics correlation risk change index is an important indicator to measure the correlation between the logistics status and the sales order data. The fluctuation of the value of this index reflects the matching degree between the logistics progress and the order demand. When the logistics correlation risk change index increases, it means that the correlation between the logistics status and the sales order data becomes more unstable or inconsistent, and risks such as delays, incorrect deliveries, and information asymmetry may occur, resulting in the failure to deliver sales orders on time or abnormal situations. At this time, the system needs to promptly detect potential logistics problems and give early warnings to reduce possible customer complaints or inventory backlogs.

[0108] On the contrary, when the logistics correlation risk change index is small, it indicates that the correlation between the logistics status and the sales order data is relatively stable, the logistics progress usually highly matches the order demand, the delivery route is smooth, the information is updated in a timely manner, and the order can be delivered smoothly as expected. At this time, the operation of the logistics management system is usually in a healthy state, and both inventory management and customer satisfaction can be well guaranteed. Therefore, a low index usually represents good logistics scheduling and supply chain operation efficiency.

[0109] Convert the warehouse inventory change rate anomaly index and the logistics correlation risk change index into a comprehensive feature vector, and use the comprehensive feature vector as the input of the machine learning model. The machine learning model takes predicting the consistency outlier label of cross-platform data synchronization and inventory batch management for each group of comprehensive feature vectors as the prediction target, and takes minimizing the sum of the prediction errors for all consistency outlier labels of cross-platform data synchronization and inventory batch management as the training target to train the machine learning model until the sum of the prediction errors reaches convergence and then stop the model training. Determine the consistency outlier of cross-platform data synchronization and inventory batch management according to the model output result, where the machine learning model is a polynomial regression model.

[0110] The method for obtaining the consistency outlier of cross-platform data synchronization and inventory batch management is: obtain the corresponding function expression from the comprehensive feature vector training data of the trained machine learning model: La = F(WIFAI, erh df ); in the formula, F is the output function of the model, WIFAI is the warehouse inventory change rate anomaly index, erh df is the logistics correlation risk change index, and La is the consistency outlier of cross-platform data synchronization and inventory batch management.

[0111] Compare the obtained consistency outliers in cross-platform data synchronization and inventory batch management with the consistency reference threshold set according to historical data. If the consistency outliers in cross-platform data synchronization and inventory batch management are greater than or equal to the set consistency reference threshold, it indicates a high degree of consistency anomaly in cross-platform data synchronization and inventory batch management. At this time, generate a warning signal and generate corresponding handling suggestions; if the consistency outliers in cross-platform data synchronization and inventory batch management are less than the set consistency reference threshold, it indicates a low degree of consistency anomaly in cross-platform data synchronization and inventory batch management. At this time, no warning signal is generated.

[0112] The content of the handling suggestions includes the following aspects:

[0113] Optimize the inventory management strategy: For abnormal situations in inventory batch management, propose to optimize inventory data synchronization and batch selection rules. It is recommended to further adjust the inventory scheduling algorithm to ensure more accurate inventory matching and batch management, and avoid supply chain disruptions caused by inconsistent inventory.

[0114] Enhance the data synchronization mechanism: If the consistency outlier value is high, it is recommended to reduce the latency and loss of cross-platform data transmission by optimizing the data synchronization mechanism. An incremental update mechanism can be considered to calibrate system data regularly or in real time to ensure information consistency among systems.

[0115] Enhance the system fault tolerance ability: For example, if cross-platform data synchronization problems occur frequently, increase the fault tolerance mechanism, such as redundant storage, system retry mechanism or more intelligent data error correction technology, to ensure that the system can automatically recover and ensure consistency when data loss or errors occur.

[0116] Adjust the cross-platform data coordination strategy: For problems in collaborative operations between systems, propose to improve the data collaboration mechanism, such as setting more accurate cross-platform data exchange rules, using a distributed database for off-site backup, or adjusting the data exchange interface to ensure seamless connection and efficient synchronization between systems.

[0117] Regularly review and optimize the prediction accuracy of the model: For the prediction results of machine learning models, it is recommended to regularly train and validate the model, adjust the selection strategy of feature vectors, and optimize the algorithm to ensure that the system can maintain high-precision prediction ability in a changing market and supply chain environment.

[0118] Example 2, please refer to Figure 2 As shown, the commodity sales order management system based on the cloud platform in this embodiment includes an information transmission module, an inventory matching module, an inventory scheduling module, a logistics association module, and a prediction and warning module;

[0119] Information Transmission Module: Generate bulk commodity sales orders on the cloud platform and automatically transmit order information to the inventory management system and logistics management system through a real-time data synchronization mechanism;

[0120] Inventory Matching Module: The inventory management system obtains inventory batch information in real time according to inventory management rules and matches the most suitable inventory batch according to the requirements of the sales order;

[0121] Inventory Scheduling Module: For a multi-warehouse environment, the inventory management system automatically schedules commodity inventory among different warehouses according to the inventory status and the geographical location of the warehouses;

[0122] Logistics Association Module: The logistics management system integrates with the API interfaces of multiple logistics suppliers to obtain logistics progress information in real time and associate the logistics status with the sales order data;

[0123] Prediction and Warning Module: Analyze the scheduling anomalies of commodity inventory among different warehouses and the association status between the logistics status and the sales order data, predict the consistency anomalies in cross-platform data synchronization and inventory batch management, issue warnings and generate corresponding handling suggestions.

[0124] The above formulas are all dimensionless and take their numerical values for calculation. The formulas are obtained by collecting a large amount of data for software simulation to get a formula that is closest to the actual situation, and the preset parameters in the formulas are set by those skilled in the art according to the actual situation.

[0125] It should be understood that the term "and / or" in this article is only a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist simultaneously, and B exists alone. Here, A and B can be singular or plural. In addition, the character " / " in this article generally represents an "or" relationship between the associated objects before and after, but it may also represent an "and / or" relationship, which can be specifically understood by referring to the context before and after.

[0126] Those of ordinary skill in the art can realize that the units and algorithm steps of each example described in combination with the embodiments disclosed in this article can be implemented by electronic hardware, or by a combination of computer software and electronic hardware. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. Professional technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of this application.

[0127] As described above, it is only the specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present application can easily think of changes or substitutions, which should all be covered within the protection scope of the present application.

Claims

1. A management method for bulk commodity sales orders based on a cloud platform, characterized in that: Including: Generate a bulk commodity sales order on the cloud platform and automatically transmit the order information to the inventory management system and the logistics management system through a real-time data synchronization mechanism; The inventory management system obtains the inventory batch information in real time according to the inventory management rules and matches the most suitable inventory batch according to the requirements of the sales order; For a multi-warehouse environment, the inventory management system automatically schedules the commodity inventory among different warehouses according to the inventory status and the geographical location of the warehouses; The logistics management system integrates with the API interfaces of multiple logistics suppliers to obtain the logistics progress information in real time and associate the logistics status with the sales order data; Analyze the scheduling anomalies of the commodity inventory among different warehouses and the association status between the logistics status and the sales order data, predict the consistency anomalies of cross-platform data synchronization and inventory batch management, and issue warnings and generate corresponding handling suggestions.

2. The method for managing bulk commodity sales orders based on a cloud platform according to claim 1, characterized in that: Create a sales order for bulk commodities. The order includes commodity information, customer information, delivery information, and payment information. Generate a unique order number for each order and synchronize the relevant data to the inventory management system and the logistics management system.

3. A method for managing bulk commodity sales orders based on a cloud platform according to claim 2, characterized in that: After receiving the sales order, the inventory management system checks whether the inventory is sufficient according to the commodity number and quantity of the order; If the inventory is sufficient, the system will deduct the corresponding commodity inventory and arrange for outbound; If the inventory is insufficient, the system will trigger the procurement or production process.

4. The method for managing bulk commodity sales orders based on a cloud platform according to claim 3, characterized in that: After analyzing the scheduling anomalies of the commodity inventory among different warehouses, generate an abnormal index of the warehouse inventory change rate. The method for obtaining the abnormal index of the warehouse inventory change rate is: Calculate the change in inventory at each moment and convert it into a change rate: change rate Through the EWMA algorithm, assign a weighted average to the inventory change at each moment. The formula for EWMA is: μ t = α · ΔI t + (1 - α) · μ t-1 ; where: μ t is the smoothed value at time t, representing the long-term trend of the current inventory change. α is the smoothing factor, controlling the impact of recent inventory fluctuations on the model; ΔI t is the inventory change at time t. To measure the amplitude of inventory fluctuations, calculate the standard deviation of the inventory changes in the past N days: Among them, N is the selected time window. Calculate the warehouse inventory change rate anomaly index WIFAI, and the expression is:

5. The method for managing bulk commodity sales orders based on a cloud platform according to claim 4, characterized in that: After analyzing the association status between the logistics status and the sales order data, generate a logistics association risk change index. The method for obtaining the logistics association risk change index is: Mark the association status between the logistics status and the sales order data as K, and establish a set K = [K1, K2, K3, ..., Kn], where n is a positive integer greater than 0; for the risk factors associated with the logistics status and the sales order data, formulate the corresponding probability distribution and mark it as PK n Based on the formulated probability distribution, perform Monte Carlo simulation and generate multiple simulation scenarios. For each scenario, calculate the logistics association risk before the change. The specific calculation formula is: Rnew = w1*K1 + w2*K2 +... + wn*Kn; where Rnew is the logistics association risk before the change, w1, w2,..., wn are the weights of each factor before the change, representing the importance of each factor to the material association risk; K1, K2,..., Kn are the labels of the factors affecting the logistics association risk. Calculate the logistics association risk after the change according to the changed situation, denoted as Recr = r1*K1 + r2*K2 +... + rn*Kn; where Recr is the logistics association risk after the change, r1, r2,..., rn are the weights of each factor after the change. Calculate the logistics association risk change index. The specific calculation formula is: n In the formula, erh n *K n ; where Rnew is the logistics association risk before the change, w1, w2,..., wn are the weights of each factor before the change, used to represent the importance of each factor to the material association risk; K1, K2,..., Kn are the labels of the factors affecting the logistics association risk. According to the changed situation, calculate the logistics association risk after the change, denoted as Recr = r1*K1 + r2*K2 +... + rn*Kn; where Recr is the logistics association risk after the change, r1, r2,..., rn are the weights of each factor after the change. Calculate the logistics association risk change index. The specific calculation formula is: n is the weight of each factor before the change, used to represent the importance of each factor to the material association risk; K1, K2,..., Kn are the labels of the factors affecting the logistics association risk. According to the changed situation, calculate the logistics association risk after the change, denoted as Recr = r1*K1 + r2*K2 +... + rn*Kn; where Recr is the logistics association risk after the change, r1, r2,..., rn are the weights of each factor after the change. Calculate the logistics association risk change index. The specific calculation formula is: n is the label of the factor affecting the logistics association risk. According to the changed situation, calculate the logistics association risk after the change, denoted as Recr = r1*K1 + r2*K2 +... + rn*Kn; where Recr is the logistics association risk after the change, r1, r2,..., rn are the weights of each factor after the change. Calculate the logistics association risk change index. The specific calculation formula is: n *K n ; where Recr is the logistics association risk after the change, r1, r2,..., rn are the weights of each factor after the change. Calculate the logistics association risk change index. The specific calculation formula is: n In the formula, erh In the formula, erh df is the logistics association risk change index.

6. The method for managing bulk commodity sales orders based on a cloud platform according to claim 5, characterized in that: Convert the abnormal index of the warehouse inventory change rate and the logistics association risk change index into a comprehensive feature vector. Use the comprehensive feature vector as the input of the machine learning model. The machine learning model takes predicting the consistency outlier label of cross-platform data synchronization and inventory batch management for each group of comprehensive feature vectors as the prediction target, and takes minimizing the sum of the prediction errors of all the consistency outlier labels of cross-platform data synchronization and inventory batch management as the training target. Train the machine learning model until the sum of the prediction errors reaches convergence and then stop the model training. Determine the consistency outlier of cross-platform data synchronization and inventory batch management according to the model output result. Among them, the machine learning model is a polynomial regression model.

7. A method for managing bulk commodity sales orders based on a cloud platform according to claim 6, characterized in that: Compare the obtained consistency outlier of cross-platform data synchronization and inventory batch management with the set consistency reference threshold based on historical data. If the consistency outlier of cross-platform data synchronization and inventory batch management is greater than or equal to the set consistency reference threshold, it indicates a high degree of consistency anomaly in cross-platform data synchronization and inventory batch management. At this time, generate a warning signal and generate corresponding handling suggestions; If the consistency outlier of cross-platform data synchronization and inventory batch management is less than the set consistency reference threshold, it indicates a low degree of consistency anomaly in cross-platform data synchronization and inventory batch management. At this time, no warning signal is generated.

8. A bulk commodity sales order management system based on a cloud platform, which is used to implement a bulk commodity sales order management method based on a cloud platform described in any one of claims 1-7, and is characterized in that: It includes an information transmission module, an inventory matching module, an inventory scheduling module, a logistics association module, and a prediction and early warning module; Information transmission module: Generate a bulk commodity sales order on the cloud platform and automatically transmit the order information to the inventory management system and the logistics management system through a real-time data synchronization mechanism; Inventory matching module: The inventory management system obtains the inventory batch information in real time according to the inventory management rules and matches the most suitable inventory batch according to the sales order requirements; Inventory scheduling module: For a multi-warehouse environment, the inventory management system automatically schedules the commodity inventory among different warehouses according to the inventory status and the geographical location of the warehouses; Logistics association module: The logistics management system integrates through the API interfaces of multiple logistics suppliers, obtains the logistics progress information in real time, and associates the logistics status with the sales order data; Prediction and early warning module: Analyze the scheduling anomalies of the commodity inventory among different warehouses and the association status between the logistics status and the sales order data, predict the consistency anomalies of cross-platform data synchronization and inventory batch management, and give early warnings and generate corresponding handling suggestions.

Images