Intelligent management system for number of commodities in shopping mall
Through the mall product quantity intelligent management system, data modeling and time series analysis are used to automatically generate replenishment orders, which solves the problem that traditional inventory management cannot effectively respond to dynamic market demand, and improves the accuracy and response speed of inventory management.
Patent Information
- Application Number
- CN202411461268.5
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-10-18
- Publication Date
- 2025-02-07
AI Technical Summary
Traditional inventory management is based on experience and simple statistical prediction methods, and cannot effectively respond to dynamic market demand and real-time data prediction. It lacks the ability to automatically adjust inventory levels and place replenishment orders, and has poor adaptability.
An intelligent management system for the quantity of shopping malls is proposed. By collecting key product data, data modeling and time series analysis, replenishment orders are automatically generated, and inventory thresholds are dynamically adjusted according to market demand to achieve real-time inventory management and prediction.
Improve the accuracy and response speed of inventory management, reduce the risk of oversupply and out of stock, ensure that the inventory level meets market demand, reduces operating costs, and improves customer satisfaction.
Smart Images
Figure CN119398665A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to an intelligent management system for the quantity of goods in a shopping mall, and in particular to the field of goods management. Background Art
[0002] Inventory management of goods is a crucial component, especially in a rapidly changing market environment. In order to meet these challenges, the industry has developed a variety of inventory management technologies, but there are still shortcomings in handling dynamic market demands and the accuracy of real-time data forecasting.
[0003] Traditional inventory management is usually based on experience (such as commodity order quantity) and simple statistical forecasting methods to manage inventory; these analyses of historical sales data lack the ability to respond quickly to real-time market data, and perform poorly when dealing with nonlinear trends and sudden market events; in addition, they are unable to automatically adjust inventory levels and place replenishment orders, and have poor adaptability to changes in commodities or markets.
[0004] The market demand for smarter, more flexible and more predictive inventory management systems continues to grow. Companies need such systems to help them reduce operating costs, improve customer satisfaction and quickly adapt to market changes. In addition, with the increase in personalization and customization needs, companies also need more refined inventory management strategies to meet these needs. Summary of the invention
[0005] Purpose of the invention: To propose an intelligent management system for the number of goods in a shopping mall to solve the above problems existing in the prior art;
[0006] Technical solution: An intelligent management system for the number of goods in a shopping mall, comprising the following steps:
[0007] Step 1: Collect key data of the goods sold, including sales data, inventory quantity, customer purchase quantity and purchase time period;
[0008] Step 2: Use the graph database to perform data modeling on the collected key data. The data modeling creates entity nodes for sales data, inventory quantity, customer purchase quantity, and purchase time period, as well as the spatiotemporal relationships between entities.
[0009] Step 3: Analyze the data modeling through time series, calculate the quantity and scheduled time of future demand forecast of the goods according to the total number of goods set by the store on the goods management platform, and according to the real-time sales quantity and inventory quantity;
[0010] Step 4: Convert the predicted results of the analysis into specific operation instructions. The operation instructions automatically generate replenishment orders and feed back the order information to the supplier. After the supplier formulates the order, it feeds back to the product management platform and confirms the order with the store.
[0011] Step 5: The product management platform automatically updates product inventory data based on the store's confirmation of order information, internal inventory status, and supplier feedback; it also displays real-time inventory and estimated replenishment time, and dynamically adjusts inventory thresholds based on market demand.
[0012] In a further embodiment, in the key data collection process, a data collection vector is defined to obtain the sales volume of each commodity, and the number of orders for the commodity is determined according to the sales volume, which is specifically expressed as follows:
[0013] Data(t)=[s(t),k(t),b(t),e(t)]
[0014] In the formula, Data(t) represents the set of all key data collected within time t; s(t) represents the sales volume of each commodity at time t, and each s(t) corresponds to the sales quantity of a specific commodity at time point t; k(t) represents the inventory quantity of each commodity at time t, and each k(t) is the inventory quantity of a specified commodity at time point t; b(t) represents the purchase quantity of different users at time t; e(t) represents the purchase information of users within a specific time t.
[0015] In a further embodiment, entity nodes and spatiotemporal relationships are defined according to the data modeling process, and the specific expressions are as follows:
[0016] E=[e1,e2,e3,e4]
[0017] R=[(e1,e2,t)]
[0018] Where E represents the set of all entity nodes, e1, e2, e3, and e4 represent the entity nodes of sales data, inventory quantity, customer purchase quantity, and purchase time period, respectively; R represents the set of relationships between entity nodes; and (e1, e2, t) represents the relationship between entity nodes e1 and e2 within time t.
[0019] In a further embodiment, the demand for goods is predicted based on the time series, which is specifically expressed as follows:
[0020] D(d,t)=h(d,t)+trend(d,t)
[0021] Where D(d,t) represents the demand for commodity d within the forecast time t; h(d,t) represents the historical average sales volume of commodity d at time t, which is usually calculated as the average sales volume within a certain time window in the past; trend(d,t) represents the sales trend of commodity d within time t.
[0022] In a further embodiment, by automatically generating a purchase order to a supplier, tracking the status of the order in real time, and receiving feedback from the supplier, the order quantity and replenishment frequency are adjusted according to the feedback.
[0023] The calculation formula for automatically generating replenishment order quantity is as follows:
[0024] Order(d,t)=max(0,ceil((D(d,t)-k(t))*factor))
[0025] In the formula, Order(d,t) represents the number of orders generated for commodity d at time t; D(d,t) represents the demand for commodity d within the predicted time t; k(t) represents the inventory quantity of each commodity at time t; factor represents the adjustment factor, which is used to adjust the order quantity according to market response, seasonal demand changes or special events; ceil represents the function to ensure that the order quantity is an integer, because in actual operation, non-integer quantities of commodities cannot be ordered; max(0) represents ensuring that the order quantity will not be negative. If the calculated result is negative, the order quantity is set to 0, indicating that no replenishment is required;
[0026] The number of orders that need to be replenished is automatically calculated, taking into account the current inventory, using a formula that automatically generates the replenishment order quantity. If there is a gap between the current inventory and the forecasted demand, feedback received from suppliers adjusts future orders. If suppliers expect delays, place orders in advance or increase the order quantity.
[0027] In a further embodiment, the product management platform also includes store areas, product content, user login and registration pages and personal center pages after login, members, product order information statistics, product management and pre-order management. The backend management is divided into different account permissions, and the account permissions are controlled by the store; users use the search function to search for products and store information, which involves operations on the product database, so they need to register or log in; the store obtains all functions in product management.
[0028] In a further embodiment, whether the user is logged in to the product management platform, if logged in, the user will be directed to the login page;
[0029] After logging in, the user will be prompted to filter the stores and make judgments on the products the user has inquired about;
[0030] After the inventory inquiry is completed, the reservation order management notifies the user of the successful inquiry by sending an email. After receiving the user's email inquiring about inventory, the product management replies to the user with the inventory status of the product. Finally, the user makes a reservation in the product reservation operation in the personal center.
[0031] Beneficial effects: The present invention proposes an intelligent management system for the quantity of goods in a shopping mall. By collecting key data of goods sold and performing data modeling on the key data, the data modeling is analyzed through time series, and the prediction results of the analysis are converted into specific operation instructions. The commodity management platform automatically updates the commodity inventory data according to the store's confirmation of order information and the internal inventory status and the feedback from the supplier; and displays the real-time inventory and the estimated replenishment time, and dynamically adjusts the inventory threshold according to market demand to adapt to changes in market demand, thereby realizing accurate prediction of commodity sales trends and real-time adjustment of inventory levels;
[0032] Updating product quantities to match forecasted demand and market feedback ensures that inventory levels can both meet customer needs and avoid overstocking. The mall product quantity intelligent management system improves the accuracy and responsiveness of inventory management, bringing significant operational efficiency improvements and cost savings to the e-commerce platform. BRIEF DESCRIPTION OF THE DRAWINGS
[0033] Figure 1 It is a schematic diagram of the process of the present invention. DETAILED DESCRIPTION
[0034] The applicant believes that traditional inventory management is usually based on experience and simple statistical forecasting methods to manage goods, commodity quantities and inventory quantities, and is unable to automatically adjust inventory levels and place replenishment orders.
[0035] In order to solve the problems existing in the prior art, the present invention realizes real-time control of the quantity of goods through an intelligent management system for the quantity of goods in a mall.
[0036] The present invention will be further described in detail below through embodiments and in conjunction with the accompanying drawings.
[0037] In this application, we propose an intelligent management system for the number of goods in a mall, which includes the following steps:
[0038] Step 1: Collect key data of the goods sold, including sales data, inventory quantity, customer purchase quantity and purchase time period; key data provides basic information for the entire intelligent management system to better understand market dynamics and consumer behavior.
[0039] In the key data collection process, define the data collection vector, and then obtain the sales volume of each product. According to the sales volume, formulate the number of orders for the product. The specific expression is as follows:
[0040] Data(t)=[s(t),k(t),b(t),e(t)]
[0041] In the formula, Data(t) represents the set of all key data collected within time t; s(t) represents the sales volume of each commodity at time t, and each s(t) corresponds to the sales quantity of a specific commodity at time point t; k(t) represents the inventory quantity of each commodity at time t, and each k(t) is the inventory quantity of a specified commodity at time point t; b(t) represents the purchase quantity of different users at time t; e(t) represents the purchase information of users within a specific time t.
[0042] Step 2: Use the graph database to perform data modeling on the collected key data. Data modeling creates entity nodes for sales data, inventory quantity, customer purchase quantity, and purchase time period, as well as the spatiotemporal relationship between entities. Through the data expression of entity nodes, the sales path and user behavior pattern of each product can be tracked, and the flow of products and consumer purchase trends can be observed.
[0043] According to the data modeling process, entity nodes and spatiotemporal relationships are defined. The specific expressions are as follows:
[0044] E=[e1,e2,e3,e4]
[0045] R=[(e1,e2,t)]
[0046] Where E represents the set of all entity nodes, e1, e2, e3, and e4 represent the entity nodes of sales data, inventory quantity, customer purchase quantity, and purchase time period, respectively; R represents the set of relationships between entity nodes; and (e1, e2, t) represents the relationship between entity nodes e1 and e2 within time t.
[0047] Step 3: Analyze data modeling through time series, calculate the quantity and reservation time of future demand forecast of goods according to the total number of goods set by the store on the product management platform, and according to the real-time sales quantity and inventory quantity, provide reference data for inventory management and replenishment strategy, and ensure the reasonable allocation and utilization of item reservation resources;
[0048] The demand for commodities is predicted based on time series, which is specifically expressed as follows:
[0049] D(d,t)=h(d,t)+trend(d,t)
[0050] Where D(d,t) represents the demand for commodity d within the forecast time t; h(d,t) represents the historical average sales volume of commodity d at time t, which is usually calculated as the average sales volume within a certain time window in the past; trend(d,t) represents the sales trend of commodity d within time t.
[0051] Step 4: Convert the predicted results of the analysis into specific operation instructions.
[0052] Operation instructions automatically generate replenishment orders and feed back order information to suppliers. After the supplier formulates the order, it feeds back to the product management platform and confirms the order with the store, reducing the possibility of manual errors and delays, making inventory management more accurate and responsive, and preventing operational efficiency from being affected by out-of-stock or excess inventory.
[0053] By automatically generating purchase orders to suppliers, tracking order status in real time, and receiving feedback from suppliers, the order quantity and replenishment frequency can be adjusted based on the feedback to respond to changes in market demand and supply conditions.
[0054] The calculation formula for automatically generating replenishment order quantity is as follows:
[0055] Order(d,t)=max(0,ceil((D(d,t)-k(t))*factor))
[0056] In the formula, Order(d,t) represents the number of orders generated for commodity d at time t; D(d,t) represents the demand for commodity d within the predicted time t; k(t) represents the inventory quantity of each commodity at time t; factor represents the adjustment factor, which is used to adjust the order quantity according to market reaction, seasonal demand changes or special events; ceil represents the function to ensure that the order quantity is an integer, because in actual operation, non-integer quantities of commodities cannot be ordered; max(0) represents to ensure that the order quantity will not be negative. If the calculated result is negative, the order quantity is set to 0, indicating that no replenishment is required.
[0057] The order quantity that needs to be replenished is automatically calculated, taking into account the current inventory, using a formula that automatically generates the replenishment order quantity. If there is a gap between the current inventory and the forecasted demand, feedback received from suppliers adjusts future orders. If suppliers expect delays, orders are placed in advance or the order quantity is increased to ensure sufficient inventory.
[0058] Step 5: The product management platform automatically updates product inventory data based on the store’s confirmation of order information, internal inventory status, and supplier feedback; it also displays real-time inventory and estimated replenishment time, and dynamically adjusts inventory thresholds based on market demand to adapt to changes in market demand.
[0059] Inventory optimization reduces the risk of overstocking and out-of-stocks, ensuring that merchandise in a mall or marketplace can efficiently meet consumer demand while controlling operating costs.
[0060] The product management platform also includes store areas, product content, user login and registration pages and personal center pages after login, members, product order information statistics, product management and pre-order management. The backend management is divided into different account permissions, and the account permissions are controlled by the store. Users use the search function to search for products and store information, which involves operations on the product database (for example: collection and reservation). In this case, they need to register or log in. The store obtains all functions in product management.
[0061] Whether the user has logged in to the product management platform. If logged in, the user will be directed to the login page;
[0062] After logging in, the user will be prompted to filter the stores and make judgments on the products the user has inquired about;
[0063] After the inventory inquiry is completed, the reservation order management notifies the user of the successful inquiry by sending an email. After receiving the user's email inquiring about inventory, the product management replies to the user with the inventory status of the product. Finally, the user makes a reservation in the product reservation operation in the personal center.
[0064] As described above, although the present invention has been shown and described with reference to specific preferred embodiments, it should not be construed as limiting the present invention itself. Various changes in form and details may be made without departing from the spirit and scope of the present invention as defined in the appended claims.
Claims
1. An intelligent management system for the number of goods in a shopping mall, characterized in that: The steps include: Step 1: Collect key data of the goods sold, including sales data, inventory quantity, customer purchase quantity and purchase time period; Step 2: Use the graph database to perform data modeling on the collected key data. The data modeling creates entity nodes for sales data, inventory quantity, customer purchase quantity, and purchase time period, as well as the spatiotemporal relationships between entities. Step 3: Analyze the data modeling through time series, calculate the quantity and scheduled time of future demand forecast of the goods according to the total number of goods set by the store on the goods management platform, and according to the real-time sales quantity and inventory quantity; Step 4: Convert the predicted results of the analysis into specific operation instructions. The operation instructions automatically generate replenishment orders and feed back the order information to the supplier. After the supplier formulates the order, it feeds back to the product management platform and confirms the order with the store. Step 5: The product management platform automatically updates product inventory data based on the store's confirmation of order information, internal inventory status, and supplier feedback; it also displays real-time inventory and estimated replenishment time, and dynamically adjusts inventory thresholds based on market demand.
2. According to claim 1, the intelligent management system for the number of goods in a shopping mall is characterized in that: In the key data collection process, define the data collection vector, and then obtain the sales volume of each product. According to the sales volume, formulate the number of orders for the product. The specific expression is as follows: Data(t)=[s(t),k(t),b(t),e(t)] In the formula, Data(t) represents the set of all key data collected within time t; s(t) represents the sales volume of each commodity at time t, and each s(t) corresponds to the sales quantity of a specific commodity at time point t; k(t) represents the inventory quantity of each commodity at time t, and each k(t) is the inventory quantity of a specified commodity at time point t; b(t) represents the purchase quantity of different users at time t; e(t) represents the purchase information of users within a specific time t.
3. According to claim 1, the intelligent management system for the number of goods in a shopping mall is characterized in that: According to the data modeling process, entity nodes and spatiotemporal relationships are defined. The specific expressions are as follows: E=[e1,e2,e3,e4] R=[(e1,e2,t)] Where E represents the set of all entity nodes, e1, e2, e3, and e4 represent the entity nodes of sales data, inventory quantity, customer purchase quantity, and purchase time period, respectively; R represents the set of relationships between entity nodes; and (e1, e2, t) represents the relationship between entity nodes e1 and e2 within time t.
4. The intelligent management system for the number of goods in a shopping mall according to claim 1, characterized in that: The demand for commodities is predicted based on time series, which is specifically expressed as follows: D(d,t)=h(d,t)+trend(d,t) Where D(d,t) represents the demand for commodity d within the forecast time t; h(d,t) represents the historical average sales volume of commodity d at time t, which is usually calculated as the average sales volume within a certain time window in the past; trend(d,t) represents the sales trend of commodity d within time t.
5. The intelligent management system for the number of goods in a shopping mall according to claim 1, characterized in that: By automatically generating purchase orders to suppliers, tracking order status in real time, and receiving feedback from suppliers, we can adjust order quantity and replenishment frequency based on feedback. The calculation formula for automatically generating replenishment order quantity is as follows: Order(d,t)=max(0,ceil((D(d,t)-k(t))*factor)) In the formula, Order(d,t) represents the number of orders generated for commodity d at time t; D(d,t) represents the demand for commodity d within the predicted time t; k(t) represents the inventory quantity of each commodity at time t; factor represents the adjustment factor, which is used to adjust the order quantity according to market response, seasonal demand changes or special events; ceil represents the function to ensure that the order quantity is an integer, because in actual operation, non-integer quantities of commodities cannot be ordered; max(0) represents ensuring that the order quantity will not be negative. If the calculated result is negative, the order quantity is set to 0, indicating that no replenishment is required; The number of orders that need to be replenished is automatically calculated, taking into account the current inventory, using a formula that automatically generates the replenishment order quantity. If there is a gap between the current inventory and the forecasted demand, feedback received from suppliers adjusts future orders. If suppliers expect delays, place orders in advance or increase the order quantity.
6. The intelligent management system for the number of goods in a shopping mall according to claim 1, characterized in that: The product management platform also includes store areas, product content, user login and registration pages and personal center pages after login, members, product order information statistics, product management and pre-order management. The backend management is divided into different account permissions, and the account permissions are controlled by the store; Users use the search function to search for products and store information. If this involves operations on the product database, they need to register or log in. Store owners obtain all functions in product management.
7. The intelligent management system for the number of goods in a shopping mall according to claim 6, characterized in that: Whether the user has logged in to the product management platform. If logged in, the user will be directed to the login page; After logging in, the user will be prompted to filter the stores and make judgments on the products the user has inquired about; After the inventory inquiry is completed, the reservation order management notifies the user of the successful inquiry by sending an email. After receiving the user's email inquiring about inventory, the product management replies to the user with the inventory status of the product. Finally, the user makes a reservation in the product reservation operation in the personal center.