A retail enterprise inventory collaborative management system based on intelligent order fulfillment and cross-channel demand prediction

Abstract

The application relates to the technical field of enterprise operation management, in particular to a retail enterprise inventory coordination management system based on intelligent order performance and cross-channel demand prediction, which comprises an order management module, an intelligent order performance module, a demand prediction module, an inventory coordination management module, a data analysis module and a user management module; compared with the simple scheme of directly using a historical logistics cycle as a predicted delivery time in the prior art, the scheme has the shortcoming that the current logistics progress and the actual situation cannot be accurately reflected, the scheme adopts a more refined prediction formula, comprehensively considers a logistics average cycle T, a current logistics progress P and respective corresponding coefficients beta and gamma, so that the delivery time can be more accurately predicted, more reliable logistics information is provided for customers, and customer experience and trust degree are improved.

Description

Technical Field

[0001] This invention relates to the field of enterprise operation management technology, and in particular to a collaborative inventory management system for retail enterprises based on intelligent order fulfillment and cross-channel demand forecasting. Background Technology

[0002] In today's retail businesses, inventory management and order fulfillment are crucial for ensuring smooth operations and customer satisfaction. However, traditional inventory management and order fulfillment methods often rely on historical data and experience-based judgments, making it difficult to accurately reflect real-time market changes and actual customer needs.

[0003] Especially in order fulfillment, existing technologies typically use historical logistics cycles as the basis for estimated delivery times. However, this method has significant limitations. On the one hand, it cannot accurately reflect the actual current logistics progress; unforeseen factors such as logistics congestion and weather conditions can lead to extensions or reductions in delivery times. On the other hand, it cannot provide personalized predictions based on the specific needs and characteristics of different orders, such as the type and quantity of goods, shipping address, and delivery address.

[0004] Furthermore, in terms of cross-channel demand forecasting, existing technologies are often based on simple weighted averages or single-factor forecasting models, which cannot fully consider the impact of channel characteristics and market dynamics on demand. This results in forecasts that are often inaccurate and cannot meet the needs of retail enterprises for refined operations.

[0005] Therefore, to overcome the shortcomings of existing technologies and improve the accuracy and efficiency of inventory management and order fulfillment for retail enterprises, this invention proposes a collaborative inventory management system for retail enterprises based on intelligent order fulfillment and cross-channel demand forecasting. This system, by comprehensively considering multiple factors, achieves accurate prediction of order delivery times and scientific prediction of cross-channel demand, providing strong support for operational optimization and competitiveness enhancement for retail enterprises. Summary of the Invention

[0006] To overcome the problems mentioned in the background art, this invention proposes a retail enterprise inventory collaborative management system based on intelligent order fulfillment and cross-channel demand forecasting.

[0007] The technical solution of this invention is: a retail enterprise inventory collaborative management system based on intelligent order fulfillment and cross-channel demand forecasting, comprising:

[0008] The order management module is used to track and manage customer orders throughout the entire process, including order receipt, processing, tracking, analysis, and optimization.

[0009] The intelligent order fulfillment module is used to manage the entire business process from receiving a sales order to delivering the goods to the customer;

[0010] The demand forecasting module is used to forecast demand across all channels based on historical sales data, market trends, and promotional activities.

[0011] The inventory collaborative management module is used to realize real-time sharing of inventory information and intelligent early warning, thereby optimizing inventory management;

[0012] The data analytics module is used to collect and analyze order data, sales data, and inventory data to provide decision support for retail businesses.

[0013] The user management module is used to manage system user information, including user registration, login, permission management, and personal information management.

[0014] As a preferred embodiment, the order management module, when implementing full-process tracking and management of customer orders, includes the following steps:

[0015] S11: Order Receiving. The system receives order information from various online and offline channels. The order information includes product details, quantity, shipping address, and payment method.

[0016] S12: Order review, automatically reviewing the completeness and accuracy of order information, including checking the validity of product inventory and delivery address;

[0017] S13: Order processing, based on the set shipping requirements and logistics strategies, splits, merges and reorders approved orders;

[0018] S14: Order tracking, real-time updates on order status, including product picking, packing, outbound, shipping, and receipt;

[0019] S15: Order analysis, collect order data and perform statistical analysis.

[0020] As a preferred option, the intelligent order fulfillment module manages the entire business process from receiving a sales order to delivering goods to the customer, including the following steps:

[0021] S21: Order Receipt and Confirmation: Receive order information from the order management module, and perform confirmation and preprocessing.

[0022] S22: Inventory pre-positioning: Based on the product information in the order, pre-position the corresponding inventory to ensure that the order can be shipped on time;

[0023] S23: Order splitting and dispatching: Based on product inventory, logistics strategy and customer needs, split and dispatch orders.

[0024] S24: Logistics tracking and updates, real-time tracking of order logistics status, updating order information, and providing customers with accurate logistics information and estimated delivery time;

[0025] S25: Exception handling, identify and handle exceptions during order fulfillment.

[0026] As a preferred option, the intelligent order fulfillment module predicts the estimated delivery time using the following formula when providing customers with accurate logistics information and estimated delivery time:

[0027]

[0028] Where S is the predicted delivery period, which is the time required to complete the delivery; T is the average logistics cycle, which is the time required for delivery to similar logistics addresses in historical data; P is the current logistics progress, expressed as a percentage; β is the coefficient of the average logistics cycle T; and γ is the coefficient of the current logistics progress P.

[0029] Preferably, the intelligent order fulfillment module includes the following steps when identifying and handling abnormal situations during the order fulfillment process:

[0030] S31: Establish a logistics model, divide the entire logistics process into multiple processes, and establish a logistics forecasting model;

[0031] S32: Parameter input. Determine the parameters for each process in the logistics prediction model based on the shipping address and delivery address, and input them into the logistics prediction model.

[0032] S33: Data comparison, comparing actual logistics information with logistics prediction models, and issuing a warning signal when the error between actual logistics information and logistics prediction models exceeds a threshold;

[0033] S34: Error analysis, which analyzes actual logistics information based on the logistics forecasting model to identify errors that may occur;

[0034] S35: Take corrective measures to address specific problems and resolve them.

[0035] As a preferred approach, when dividing the entire logistics process into multiple processes and establishing a logistics forecasting model, the following steps are included:

[0036] S41: Data acquisition, acquiring historical freight data, shipping information data, and receiving information data;

[0037] S42: Process prediction. Based on shipping and receiving information data, the entire logistics process is predicted. The predicted data includes logistics transit stations and key logistics nodes.

[0038] S43: Model building: Based on the acquired and predicted data, a logistics prediction model is built using neural network algorithms.

[0039] As a preferred approach, the demand forecasting module, when forecasting demand across all channels based on historical sales data, market trends, and promotional activities, includes the following steps:

[0040] S51: Data collection, collecting sales data and related data from all channels, including historical sales data, market trend data, and promotional activity data;

[0041] S52: Data cleaning and preprocessing, which involves identifying and processing duplicate, abnormal, and missing data in the data, and converting the data into a unified format;

[0042] S53: Model building and training. Select a suitable prediction model and train it using the collected data to build a demand prediction model. The selectable prediction models include exponential smoothing model, ARIMA model, support vector machine-based model, random forest model and neural network model.

[0043] S54: Demand forecasting, using a trained model to forecast demand across channels;

[0044] S55: Results Analysis. Analyze the prediction results and identify any problems that exist in the prediction results. These problems include duplicate channel data and abnormal data.

[0045] As a preferred option, when the demand forecasting module forecasts demand across all channels based on historical sales data, market trends, and promotional activities, the principle formula for forecasting demand across all channels is as follows:

[0046]

[0047] Where Y represents the demand across all channels, ω i Let X be the weight of the i-th channel, i.e., the importance of the i-th channel. i Let be the demand for goods in the i-th channel, where in, α represents the daily sales volume of this channel, α is the activity intensity coefficient, i.e. the degree of influence of promotional activities on sales volume, and Δ is the market trend coefficient, representing the degree of influence of market trends on sales volume.

[0048] As a preferred option, the inventory collaborative management module, in achieving real-time sharing of inventory information and intelligent early warning, and optimizing inventory management, includes the following steps:

[0049] S61: Inventory data collection, collecting inventory data from various channels, including product inventory quantity, inventory status, and inventory location;

[0050] S62: Sales volume and promotional activity analysis, analyze historical sales data and current trends for each channel, and assess the impact of promotional activities on sales volume;

[0051] S63: Channel weighting and priority ranking: Adjust the inventory allocation for each channel based on sales volume, promotional activity effectiveness, and sales volume trend.

[0052] S64: Inventory Warning and Adjustment. Based on the set inventory warning threshold, issue warnings about inventory levels and adjust inventory levels according to current demand and predicted changes.

[0053] As a preferred option, when adjusting the inventory allocation for each channel based on factors such as sales volume, promotional activity effectiveness, and sales volume trends, the following rules are adopted:

[0054] A11: When adjusting the inventory allocation for each channel, first set the priority. The inventory allocation for channels within the set priority is their predicted sales volume.

[0055] A12: Determine the weight of each channel based on channel type and historical sales data, and allocate inventory allocation for each channel from the inventory quantity outside the priority;

[0056] A13: The inventory allocation for each channel is updated at set time intervals.

[0057] The beneficial effects of this invention are:

[0058] 1. Compared with the simple solution of using historical logistics cycles as the estimated delivery time in the existing technology, which has the disadvantage of not being able to accurately reflect the current logistics progress and actual situation, this solution adopts a more refined prediction formula, which comprehensively considers the average logistics cycle T, the current logistics progress P and their corresponding coefficients β and γ, so as to more accurately predict the delivery time, provide customers with more reliable logistics information, and improve customer experience and trust.

[0059] 2. Compared with existing logistics forecasting schemes based on empirical rules or simple statistics, which suffer from low forecasting accuracy, poor adaptability, and inability to effectively cope with complex and ever-changing logistics environments, this solution adopts an intelligent logistics forecasting model establishment scheme that combines data acquisition, process prediction, and neural network algorithm modeling. It can make full use of historical freight, shipment, and receipt information data to accurately predict transit stations and key nodes in the entire logistics process, significantly improving the accuracy and flexibility of logistics forecasting and providing strong technical support for optimizing logistics management and improving customer experience.

[0060] 3. Compared to existing technologies that use a uniform standard or simple ratio to allocate inventory allocation, which has the disadvantage of being unable to flexibly respond to different channel characteristics and dynamic sales changes, this solution adopts an inventory allocation adjustment rule based on priority settings, channel weight ratio, and time cycle updates. This can more accurately match the actual needs and sales trends of each channel, achieving high efficiency and flexibility in inventory allocation. This solution not only significantly improves inventory turnover efficiency but also reduces inventory costs, enhances the retail enterprise's responsiveness to market changes, and provides a strong guarantee for the enterprise's operational optimization and competitiveness enhancement. Attached Figure Description

[0061] Figure 1 The diagram shown is a schematic representation of the structure of the retail enterprise inventory collaborative management system based on intelligent order fulfillment and cross-channel demand forecasting of the present invention.

[0062] Figure 2 The diagram illustrates the workflow of the smart order fulfillment module in the retail enterprise inventory collaborative management system based on smart order fulfillment and cross-channel demand forecasting of the present invention. Detailed Implementation

[0063] The present invention will be further described below with reference to the accompanying drawings and embodiments.

[0064] Please see Figure 1-2 This invention provides an embodiment: a retail enterprise inventory collaborative management system based on intelligent order fulfillment and cross-channel demand forecasting, comprising:

[0065] The order management module is used to track and manage customer orders throughout the entire process, including order receipt, processing, tracking, analysis, and optimization.

[0066] The intelligent order fulfillment module is used to manage the entire business process from receiving a sales order to delivering the goods to the customer;

[0067] The demand forecasting module is used to forecast demand across all channels based on historical sales data, market trends, and promotional activities.

[0068] The inventory collaborative management module is used to realize real-time sharing of inventory information and intelligent early warning, thereby optimizing inventory management;

[0069] The data analytics module is used to collect and analyze order data, sales data, and inventory data to provide decision support for retail businesses.

[0070] The user management module is used to manage system user information, including user registration, login, permission management, and personal information management.

[0071] As described above, this invention integrates modules for order management, intelligent order fulfillment, demand forecasting, collaborative inventory management, data analysis, and user management. This enables retail enterprises to track and optimize the entire order process, share inventory in real time, and receive intelligent early warnings. It also provides accurate demand forecasting based on multi-dimensional data, effectively improving operational efficiency, reducing inventory costs, and providing strong support for strategic decision-making. At the same time, it ensures system security and effective management of user information.

[0072] As a preferred embodiment, the order management module, when implementing full-process tracking and management of customer orders, includes the following steps:

[0073] S11: Order Receiving. The system receives order information from various online and offline channels. The order information includes product details, quantity, shipping address, and payment method.

[0074] S12: Order review, automatically reviewing the completeness and accuracy of order information, including checking the validity of product inventory and delivery address;

[0075] S13: Order processing, based on the set shipping requirements and logistics strategies, splits, merges and reorders approved orders;

[0076] S14: Order tracking, real-time updates on order status, including product picking, packing, outbound, shipping, and receipt;

[0077] S15: Order analysis, collect order data and perform statistical analysis.

[0078] As described above, this invention achieves comprehensive management from order receipt, review, processing, tracking to analysis through automated processes, ensuring the integrity and accuracy of order information, effectively improving the efficiency and flexibility of order processing, while updating order status in real time, enhancing customer experience, and providing valuable market insights and operational optimization basis for enterprises through statistical analysis of order data.

[0079] As a preferred option, the intelligent order fulfillment module manages the entire business process from receiving a sales order to delivering goods to the customer, including the following steps:

[0080] S21: Order Receipt and Confirmation: Receive order information from the order management module, and perform confirmation and preprocessing.

[0081] S22: Inventory pre-positioning: Based on the product information in the order, pre-position the corresponding inventory to ensure that the order can be shipped on time;

[0082] S23: Order splitting and dispatching: Based on product inventory, logistics strategy and customer needs, split and dispatch orders.

[0083] S24: Logistics tracking and updates, real-time tracking of order logistics status, updating order information, and providing customers with accurate logistics information and estimated delivery time;

[0084] S25: Exception handling, identify and handle exceptions during order fulfillment.

[0085] As described above, this invention ensures efficient operation of the entire order chain from receipt to delivery to the customer by automating order receiving, inventory pre-holding, order splitting and dispatching, logistics tracking and exception handling. This effectively improves order fulfillment efficiency, reduces inventory holding, and provides real-time logistics information and exception handling capabilities, significantly enhancing customer experience and satisfaction.

[0086] As a preferred option, the intelligent order fulfillment module predicts the estimated delivery time using the following formula when providing customers with accurate logistics information and estimated delivery time:

[0087]

[0088] Where S is the predicted delivery period, which is the time required to complete the delivery; T is the average logistics cycle, which is the time required for delivery to similar logistics addresses in historical data; P is the current logistics progress, expressed as a percentage; β is the coefficient of the average logistics cycle T; and γ is the coefficient of the current logistics progress P.

[0089] As mentioned above, compared to the simple solution of using historical logistics cycles as the estimated delivery time in existing technologies, this solution has the drawback of not being able to accurately reflect the current logistics progress and actual situation. This solution, however, uses a more refined prediction formula that comprehensively considers the average logistics cycle T, the current logistics progress P, and their corresponding coefficients β and γ. This allows for more accurate prediction of delivery time, providing customers with more reliable logistics information and improving customer experience and trust.

[0090] Preferably, the intelligent order fulfillment module includes the following steps when identifying and handling abnormal situations during the order fulfillment process:

[0091] S31: Establish a logistics model, divide the entire logistics process into multiple processes, and establish a logistics forecasting model;

[0092] S32: Parameter input. Determine the parameters for each process in the logistics prediction model based on the shipping address and delivery address, and input them into the logistics prediction model.

[0093] S33: Data comparison, comparing actual logistics information with logistics prediction models, and issuing a warning signal when the error between actual logistics information and logistics prediction models exceeds a threshold;

[0094] S34: Error analysis, which analyzes actual logistics information based on the logistics forecasting model to identify errors that may occur;

[0095] S35: Take corrective measures to address specific problems and resolve them.

[0096] As mentioned above, compared with existing anomaly handling solutions that rely directly on manual monitoring and processing, which suffer from slow response speed, low processing efficiency, and difficulty in preventing potential problems, this solution adopts an intelligent anomaly handling approach that establishes a logistics model, inputs parameters, compares data, analyzes errors, and takes corrective measures. This approach can monitor logistics information in real time, promptly detect and accurately locate anomalies, and quickly take targeted corrective measures, effectively improving the reliability and efficiency of order fulfillment, reducing anomaly handling costs, and significantly enhancing customer experience.

[0097] As a preferred approach, when dividing the entire logistics process into multiple processes and establishing a logistics forecasting model, the following steps are included:

[0098] S41: Data acquisition, acquiring historical freight data, shipping information data, and receiving information data;

[0099] S42: Process prediction. Based on shipping and receiving information data, the entire logistics process is predicted. The predicted data includes logistics transit stations and key logistics nodes.

[0100] S43: Model building: Based on the acquired and predicted data, a logistics prediction model is built using neural network algorithms.

[0101] As mentioned above, compared to existing logistics forecasting schemes based on empirical rules or simple statistics, which suffer from low forecasting accuracy, poor adaptability, and inability to effectively cope with complex and ever-changing logistics environments, this solution adopts an intelligent logistics forecasting model establishment scheme that combines data acquisition, process prediction, and neural network algorithm modeling. This scheme can make full use of historical freight, shipment, and receipt information data to accurately predict transit stations and key nodes throughout the entire logistics process, significantly improving the accuracy and flexibility of logistics forecasting and providing strong technical support for optimizing logistics management and enhancing customer experience.

[0102] As a preferred approach, the demand forecasting module, when forecasting demand across all channels based on historical sales data, market trends, and promotional activities, includes the following steps:

[0103] S51: Data collection, collecting sales data and related data from all channels, including historical sales data, market trend data, and promotional activity data;

[0104] S52: Data cleaning and preprocessing, which involves identifying and processing duplicate, abnormal, and missing data in the data, and converting the data into a unified format;

[0105] S53: Model building and training. Select a suitable prediction model and train it using the collected data to build a demand prediction model. The selectable prediction models include exponential smoothing model, ARIMA model, support vector machine-based model, random forest model and neural network model.

[0106] S54: Demand forecasting, using a trained model to forecast demand across channels;

[0107] S55: Results Analysis. Analyze the prediction results and identify any problems that exist in the prediction results. These problems include duplicate channel data and abnormal data.

[0108] As described above, this invention comprehensively collects omnichannel sales and related data, undergoes rigorous data cleaning and preprocessing to ensure data quality, and then employs various advanced predictive models for construction and training to achieve accurate predictions of cross-channel demand. This solution not only improves the accuracy of predictions but also promptly identifies and addresses problems in the prediction process through results analysis, such as duplicate channel data and abnormal data, providing strong data support for retail enterprises' inventory management and market strategies.

[0109] As a preferred option, when the demand forecasting module forecasts demand across all channels based on historical sales data, market trends, and promotional activities, the principle formula for forecasting demand across all channels is as follows:

[0110]

[0111] Where Y represents the demand across all channels, ω i Let X be the weight of the i-th channel, i.e., the importance of the i-th channel. i Let be the demand for goods in the i-th channel, where in, α represents the daily sales volume of this channel, α is the activity intensity coefficient, i.e. the degree of influence of promotional activities on sales volume, and Δ is the market trend coefficient, representing the degree of influence of market trends on sales volume.

[0112] As mentioned above, compared to existing technologies that use simple weighted averages or single-factor methods to predict omnichannel demand, these methods suffer from insufficient prediction accuracy and an inability to fully consider the characteristics of each channel and the impact of market dynamics. This solution, however, employs an omnichannel demand forecasting formula that comprehensively considers channel weights, daily sales volume, activity intensity coefficients, and market trend coefficients. This formula more accurately reflects the actual demand and market changes across each channel, thus providing more precise demand forecast results. This solution not only improves the accuracy and reliability of forecasts but also provides a more scientific basis for retail enterprises' inventory management and market strategy formulation.

[0113] As a preferred option, the inventory collaborative management module, in achieving real-time sharing of inventory information and intelligent early warning, and optimizing inventory management, includes the following steps:

[0114] S61: Inventory data collection, collecting inventory data from various channels, including product inventory quantity, inventory status, and inventory location;

[0115] S62: Sales volume and promotional activity analysis, analyze historical sales data and current trends for each channel, and assess the impact of promotional activities on sales volume;

[0116] S63: Channel weighting and priority ranking: Adjust the inventory allocation for each channel based on sales volume, promotional activity effectiveness, and sales volume trend.

[0117] S64: Inventory Warning and Adjustment. Based on the set inventory warning threshold, issue warnings about inventory levels and adjust inventory levels according to current demand and predicted changes.

[0118] As described above, this invention comprehensively collects inventory data from various channels, deeply analyzes the impact of sales trends and promotional activities, and flexibly adjusts channel weighting and inventory allocation priorities, achieving real-time sharing and intelligent early warning of inventory information. This solution not only significantly improves the precision of inventory management but also dynamically adjusts inventory based on actual demand and forecast changes, effectively avoiding inventory backlog and stockout risks, ensuring efficient and balanced inventory turnover, and providing strong support for operational optimization and cost control for retail enterprises.

[0119] As a preferred option, when adjusting the inventory allocation for each channel based on factors such as sales volume, promotional activity effectiveness, and sales volume trends, the following rules are adopted:

[0120] A11: When adjusting the inventory allocation for each channel, first set the priority. The inventory allocation for channels within the set priority is their predicted sales volume.

[0121] A12: Determine the weight of each channel based on channel type and historical sales data, and allocate inventory allocation for each channel from the inventory quantity outside the priority;

[0122] A13: The inventory allocation for each channel is updated at set time intervals.

[0123] As mentioned above, compared to existing technologies that use a uniform standard or simple proportional allocation of inventory, this approach suffers from a lack of flexibility in responding to different channel characteristics and dynamic sales changes. This solution, however, employs an inventory allocation adjustment rule based on priority settings, channel weighting, and time-cycle updates. This allows for a more precise match between the actual needs and sales trends of each channel, achieving efficient and flexible inventory allocation. This solution not only significantly improves inventory turnover efficiency but also reduces inventory costs, enhances the retail enterprise's responsiveness to market changes, and provides strong support for operational optimization and competitiveness enhancement.

[0124] The embodiments of the present invention have been described in detail above with reference to the accompanying drawings. However, the present invention is not limited to the above embodiments. Within the scope of knowledge possessed by those skilled in the art, various changes can be made without departing from the spirit of the present invention.

Claims

1. A collaborative inventory management system for retail enterprises based on intelligent order fulfillment and cross-channel demand forecasting; characterized in that: Including: The order management module is used to track and manage customer orders throughout the entire process, including order receipt, processing, tracking, analysis, and optimization. The intelligent order fulfillment module is used to manage the entire business process from receiving a sales order to delivering the goods to the customer; The demand forecasting module is used to forecast demand across all channels based on historical sales data, market trends, and promotional activities. The inventory collaborative management module is used to realize real-time sharing of inventory information and intelligent early warning, thereby optimizing inventory management; The data analytics module is used to collect and analyze order data, sales data, and inventory data to provide decision support for retail businesses. The user management module is used to manage the system's user information, including user registration, login, permission management, and personal information management. The intelligent order fulfillment module provides customers with accurate logistics information and estimated delivery times by predicting the estimated delivery time using the following formula: ; Where S is the predicted delivery period, which is the time required to complete the delivery; T is the average logistics cycle, which is the time required for delivery to similar logistics addresses in historical data; P is the current logistics progress, expressed as a percentage; β is the coefficient of the average logistics cycle T; and γ is the coefficient of the current logistics progress P. When the demand forecasting module forecasts demand across all channels based on historical sales data, market trends, and promotional activities, the underlying formula for forecasting demand across all channels is as follows: ; in, To meet the needs of all channels, Let be the weight of the i-th channel, i.e., the importance of the i-th channel. Let be the demand for goods in the i-th channel, where in, This represents the daily sales volume of this channel. This is the activity intensity coefficient, which represents the degree of impact of promotional activities on sales volume. This is the market trend coefficient, representing the degree to which market trends affect sales volume. The inventory collaborative management module optimizes inventory management by achieving real-time sharing of inventory information and intelligent early warning, and includes the following steps: S61: Inventory data collection, collecting inventory data from various channels, including product inventory quantity, inventory status, and inventory location; S62: Sales volume and promotional activity analysis, analyze historical sales data and current trends for each channel, and assess the impact of promotional activities on sales volume; S63: Channel weighting and priority ranking: Adjust the inventory allocation for each channel based on sales volume, promotional activity effectiveness, and sales volume trend. S64: Inventory Warning and Adjustment. Based on the set inventory warning threshold, issue warnings about inventory levels and adjust inventory levels according to current demand and predicted changes.

2. The retail enterprise inventory collaborative management system based on intelligent order fulfillment and cross-channel demand forecasting as described in claim 1, characterized in that: The order management module, in implementing full-process tracking and management of customer orders, includes the following steps: S11: Order Receiving. The system receives order information from various online and offline channels. The order information includes product details, quantity, shipping address, and payment method. S12: Order review, automatically reviewing the completeness and accuracy of order information, including checking the validity of product inventory and delivery address; S13: Order processing, based on the set shipping requirements and logistics strategies, splits, merges and reorders approved orders; S14: Order tracking, real-time updates on order status, including product picking, packing, outbound, shipping, and receipt; S15: Order analysis, collect order data and perform statistical analysis.

3. The retail enterprise inventory collaborative management system based on intelligent order fulfillment and cross-channel demand forecasting as described in claim 2, characterized in that: The intelligent order fulfillment module manages the entire business process from receiving a sales order to delivering goods to the customer, including the following steps: S21: Order Receipt and Confirmation: Receive order information from the order management module, and perform confirmation and preprocessing. S22: Inventory pre-positioning: Based on the product information in the order, pre-position the corresponding inventory to ensure that the order can be shipped on time; S23: Order splitting and dispatching: Based on product inventory, logistics strategy and customer needs, split and dispatch orders. S24: Logistics tracking and updates, real-time tracking of order logistics status, updating order information, and providing customers with accurate logistics information and estimated delivery time; S25: Exception handling, identify and handle exceptions during order fulfillment.

4. The retail enterprise inventory collaborative management system based on intelligent order fulfillment and cross-channel demand forecasting as described in claim 3, characterized in that: The intelligent order fulfillment module includes the following steps when identifying and handling abnormal situations during the order fulfillment process: S31: Establish a logistics model, divide the entire logistics process into multiple processes, and establish a logistics forecasting model; S32: Parameter input. Determine the parameters for each process in the logistics prediction model based on the shipping address and delivery address, and input them into the logistics prediction model. S33: Data comparison, comparing actual logistics information with logistics prediction models, and issuing a warning signal when the error between actual logistics information and logistics prediction models exceeds a threshold; S34: Error analysis, which analyzes actual logistics information based on the logistics forecasting model to identify errors that may occur; S35: Take corrective measures to address specific problems and resolve them.

5. A retail enterprise inventory collaborative management system based on intelligent order fulfillment and cross-channel demand forecasting as described in claim 4, characterized in that: When dividing the entire logistics process into multiple processes and establishing a logistics forecasting model, the following steps are included: S41: Data acquisition, acquiring historical freight data, shipping information data, and receiving information data; S42: Process prediction. Based on shipping and receiving information data, the entire logistics process is predicted. The predicted data includes logistics transit stations and key logistics nodes. S43: Model building: Based on the acquired and predicted data, a logistics prediction model is built using neural network algorithms.

6. The retail enterprise inventory collaborative management system based on intelligent order fulfillment and cross-channel demand forecasting as described in claim 5, characterized in that: When forecasting demand across all channels based on historical sales data, market trends, and promotional activities, the demand forecasting module includes the following steps: S51: Data collection, collecting sales data and related data from all channels, including historical sales data, market trend data, and promotional activity data; S52: Data cleaning and preprocessing, which involves identifying and processing duplicate, abnormal, and missing data in the data, and converting the data into a unified format; S53: Model building and training. Select a suitable prediction model and train it using the collected data to build a demand prediction model. The selectable prediction models include exponential smoothing model, ARIMA model, support vector machine-based model, random forest model and neural network model. S54: Demand forecasting, using a trained model to forecast demand across channels; S55: Results Analysis. Analyze the prediction results and identify any problems that exist in the prediction results. These problems include duplicate channel data and abnormal data.

7. A retail enterprise inventory collaborative management system based on intelligent order fulfillment and cross-channel demand forecasting as described in claim 6, characterized in that: When adjusting inventory allocation for each channel based on sales volume, promotional activity effectiveness, and sales volume trends, the following rules apply: A11: When adjusting the inventory allocation for each channel, first set the priority. The inventory allocation for channels within the set priority is their predicted sales volume. A12: Determine the weight of each channel based on channel type and historical sales data, and allocate inventory allocation for each channel from the inventory quantity outside the priority; A13: The inventory allocation for each channel is updated at set time intervals.

Images