E-commerce commodity recommendation and inventory linkage system based on user behavior

Abstract

The application discloses an e-commerce commodity recommendation and inventory linkage system based on user behavior, and belongs to the technical field of e-commerce intelligent operation, comprising a user behavior acquisition module, a behavior characteristic analysis module, an intelligent commodity recommendation module, a real-time inventory monitoring module, a supply-demand linkage scheduling module and a data interaction storage module, wherein the behavior characteristic analysis module is connected with the user behavior acquisition module, the intelligent commodity recommendation module is connected with the behavior characteristic analysis module, the real-time inventory monitoring module is used for collecting and counting full-channel commodity inventory related data in real time, the supply-demand linkage scheduling module is connected with the intelligent commodity recommendation module and the real-time inventory monitoring module, and the data interaction storage module is connected with each module and used for completing full-system data unified storage, real-time interaction and synchronous calling. The application has the technical effects of real-time capturing of user consumption behavior, dynamic accurate pushing of commodities and realization of bidirectional collaborative regulation and control of recommendation and inventory.

Description

Technical Field

[0001] This invention belongs to the field of e-commerce intelligent operation technology, and in particular relates to an e-commerce product recommendation and inventory linkage system based on user behavior. Background Technology

[0002] With the rapid development of the e-commerce industry, the number of online shoppers continues to expand, and the variety of goods on platforms is becoming increasingly diverse. Personalized product recommendations have become a core means of improving platform traffic conversion, while warehouse inventory management directly affects order fulfillment efficiency and operating costs. Currently, most e-commerce platforms operate product recommendation and inventory management separately. Recommendation strategies often rely on fixed user tags and historical consumption data, making it difficult to accurately capture users' real-time consumption intentions. At the same time, inventory scheduling cannot be coordinated with front-end user consumption, easily leading to situations such as stockouts of popular products, stock shortages, and accumulation of slow-moving inventory, which seriously restricts the overall operational efficiency of e-commerce platforms and the user shopping experience.

[0003] In existing technologies, for example, patent number CN118365431B discloses a product recommendation system for e-commerce platforms based on big data. This solution mainly relies on product tags and historical consumption data to complete product recommendation matching. Although it can combine basic traffic data for simple inventory adaptation, it only focuses on the statistics of existing data and does not deeply mine dynamic behavioral information such as real-time browsing, abandonment, and price comparison of users. It cannot accurately grasp the users' immediate consumption needs and the recommendation flexibility is insufficient. For example, patent number CN120543081A discloses an intelligent product selection and dynamic inventory management solution for e-commerce. This solution can combine transaction data and competitor data to carry out product selection and inventory allocation. However, it only realizes one-way control of back-end inventory and does not establish a linkage mechanism between user behavior intentions, front-end recommendation traffic and warehouse inventory. Inventory adjustment has obvious lag and cannot adjust the supply of goods in advance according to the potential consumption trends of users. The collaborative control capability is weak. Summary of the Invention

[0004] To address the problems existing in the prior art, this invention provides an e-commerce product recommendation and inventory linkage system based on user behavior. It has the advantages of real-time capture of user consumption behavior, dynamic and accurate product push, and two-way collaborative control of recommendation and inventory. It solves the problems of rigid recommendation mode, lagging inventory scheduling, and supply and demand imbalance in the prior art.

[0005] This invention is implemented as follows: an e-commerce product recommendation and inventory linkage system based on user behavior, comprising a user behavior collection module, a behavior feature analysis module, an intelligent product recommendation module, a real-time inventory monitoring module, a supply and demand linkage scheduling module, and a data interaction and storage module. The user behavior collection module collects various real-time behavioral data of users within the e-commerce platform. The behavior feature analysis module, connected to the user behavior collection module, analyzes and processes the collected behavioral data to construct a dynamic user consumption profile. The intelligent product recommendation module, connected to the behavior feature analysis module, generates personalized product recommendations based on the dynamic user profile. The real-time inventory monitoring module collects and statistically analyzes inventory-related data across all channels in real time. The supply and demand linkage scheduling module is connected to both the intelligent product recommendation module and the real-time inventory monitoring module. The data interaction and storage module is connected to each module to achieve unified storage, real-time interaction, and synchronous access of data across the entire system.

[0006] As a preferred embodiment of the present invention, the user behavior collection module includes a browsing trajectory collection unit, an operation behavior collection unit, and a consumption intention collection unit, which are used to collect real-time behavior data of users in all dimensions, such as browsing path of products, page dwell time, product click frequency, adding to cart, canceling orders, and keyword search, within the e-commerce platform.

[0007] This setting allows for the comprehensive collection of various dynamic user behaviors within the platform, overcoming the limitations of only collecting historical transaction data. It fully reveals users' true shopping preferences and immediate consumption ideas, providing comprehensive raw data support for subsequent profile building.

[0008] As a preferred embodiment of the present invention, the behavior feature analysis module includes a data cleaning and classification unit, a behavior weight assignment unit, and a dynamic profile construction unit, which are used to organize and process the collected fragmented behavior data, divide the demand weights according to the behavior type, and construct a real-time updated dynamic user consumption behavior profile in combination with time-series behavior changes.

[0009] This setting allows for the elimination of invalid and redundant data, differentiation of the strength of consumption intentions corresponding to different behaviors, continuous iteration and updating of user profiles, avoidance of static and fixed profiles, and accurate matching of users' changing consumption needs at different times.

[0010] As a preferred embodiment of the present invention, the intelligent product recommendation module includes a preferred product matching unit, a hierarchical recommendation sorting unit, and a recommendation list generation unit, which are used to retrieve the user's dynamic consumption profile to match product categories that meet the user's current needs, sort them according to matching priority, and automatically generate a personalized product recommendation push list.

[0011] This setting enables personalized recommendations based on precise dynamic profiles, allowing for a more tailored approach to product recommendations. It also optimizes the order of recommended products, significantly improving the relevance of product recommendations and effectively increasing click-through rates and conversion rates on the platform.

[0012] As a preferred embodiment of the present invention, the real-time inventory monitoring module includes a spot inventory statistics unit, an in-transit inventory statistics unit, and an inventory threshold early warning unit, which are used to count the current inventory of goods at each warehousing node and the quantity of inventory transferred in transit in real time, while setting high and low inventory early warning thresholds and providing real-time feedback on the surplus and shortage status of goods inventory.

[0013] This setting allows for a comprehensive overview of the real-time inventory status of goods across all warehouse locations, enabling timely identification of inventory backlogs and shortages, proactive risk assessment of supply, and ensuring real-time control over the status of goods supply.

[0014] As a preferred embodiment of the present invention, the supply and demand linkage scheduling module includes a recommendation traffic analysis unit, an inventory allocation instruction unit, and a recommendation strategy control unit, which are used to count the front-end product recommendation exposure volume and the scale of potential users, predict the short-term product demand volume, simultaneously issue warehouse replenishment and inventory diversion instructions, and adjust the product recommendation exposure frequency and push intensity according to the real-time inventory status.

[0015] This setup breaks down the data barriers between front-end marketing and back-end warehousing, allowing for the prediction of market demand based on user intent traffic and enabling the advance coordination and allocation of goods.

[0016] As a preferred embodiment of the present invention, the data interaction storage module has a built-in data encryption storage unit and a high-speed data relay interaction unit.

[0017] This setting ensures the security of platform user behavior data and commercial inventory data storage, preventing data leaks, while also accelerating data transmission rates between modules, ensuring smooth and stable overall system operation.

[0018] As a preferred embodiment of the present invention, the supply and demand linkage scheduling module predicts consumer demand based on user behavior data and issues inventory scheduling instructions. At the same time, it dynamically adjusts the exposure level and push frequency of product recommendations based on the remaining inventory. The scheduling instructions specifically include: issuing replenishment / cross-warehouse transfer instructions to reduce product recommendation exposure when inventory is scarce; increasing targeted recommendations to accelerate product turnover when inventory is piling up; and maintaining the original recommendation and inventory preparation rhythm when inventory is normal.

[0019] This setting enables proactive demand forecasting and inventory preparation, while simultaneously leveraging inventory status to optimize product recommendations. It increases promotional efforts for slow-moving products and reduces exposure for out-of-stock items, thus balancing supply and demand in the market from the source.

[0020] Compared with the prior art, the beneficial effects of the present invention are as follows: This invention comprehensively collects real-time dynamic user behavior data to construct a dynamic user consumption profile that can be updated in real time. It is no longer limited to historical consumption and product tags for recommendations, but can accurately capture users' temporary consumption needs and instantaneous shopping intentions, effectively improving the accuracy and flexibility of product recommendations. This invention establishes a two-way linkage architecture between front-end product recommendation and back-end warehousing and inventory, breaking the pattern of independent operation of the two businesses. It no longer relies on lagging sales data to adjust inventory, but can predict market demand in advance based on user consumption behavior trends, complete the allocation and restocking of goods in advance, and at the same time adjust the recommendation strategy in reverse based on the actual inventory status. This system can effectively reduce problems such as inventory backlog and stockouts of popular products, reduce warehousing and operation costs and inventory losses for e-commerce platforms, improve platform operation efficiency, optimize the overall online shopping experience for users, and effectively enhance practicality and market application value. Attached Figure Description

[0021] Figure 1 This is a schematic diagram of the overall system flow provided in an embodiment of the present invention; Figure 2 These are partial structural schematic diagrams provided in embodiments of the present invention; Figure 3 This is a schematic diagram of the supply and demand linkage scheduling module provided in an embodiment of the present invention. Detailed Implementation

[0022] To further understand the invention's content, features, and effects, the following embodiments are provided, and detailed descriptions are given in conjunction with the accompanying drawings.

[0023] The structure of the present invention will now be described in detail with reference to the accompanying drawings.

[0024] refer to Figures 1 to 3 As shown in the figure, the e-commerce product recommendation and inventory linkage system based on user behavior provided in this embodiment of the invention includes a user behavior collection module, a behavior feature analysis module, an intelligent product recommendation module, a real-time inventory monitoring module, a supply and demand linkage scheduling module, and a data interaction and storage module. The user behavior collection module is used to collect various real-time behavior data of users within the e-commerce platform. The behavior feature analysis module is connected to the user behavior collection module and is used to analyze and process the collected behavior data and construct a dynamic user consumption profile. The intelligent product recommendation module is connected to the behavior feature analysis module and generates personalized product recommendation content based on the dynamic user profile. The real-time inventory monitoring module is used to collect and statistically analyze product inventory-related data across all channels in real time. The supply and demand linkage scheduling module is connected to the intelligent product recommendation module and the real-time inventory monitoring module respectively. The data interaction and storage module is connected to each module respectively and is used to complete the unified storage, real-time interaction, and synchronous calling of data across the entire system.

[0025] Specifically, the user behavior collection module includes a browsing trajectory collection unit, an operation behavior collection unit, and a consumption intention collection unit, which are used to collect real-time behavioral data of users in all dimensions within the e-commerce platform, such as product browsing path, page dwell time, product click frequency, add-to-cart operations, order cancellation, and keyword search.

[0026] By adopting the above solution, we can collect all kinds of dynamic operation behaviors of users within the platform in an all-round way, get rid of the limitation of only collecting historical transaction data, fully restore users' true shopping preferences and real consumption ideas, and provide comprehensive raw data support for subsequent profile building.

[0027] Specifically, the behavioral feature analysis module includes a data cleaning and classification unit, a behavior weight assignment unit, and a dynamic profile construction unit, which are used to organize and process the collected fragmented behavioral data, divide the demand weights according to the behavior type, and construct a real-time updated dynamic user consumption behavior profile in combination with time-series behavior changes.

[0028] By adopting the above solution, invalid and redundant data can be eliminated, the strength of consumption intention corresponding to different behaviors can be distinguished, user profiles can be continuously updated, static profiles can be avoided, and user consumption needs can be accurately matched to changes in different time periods.

[0029] Specifically, the intelligent product recommendation module includes a preferred product matching unit, a hierarchical recommendation sorting unit, and a recommendation list generation unit. It is used to retrieve the user's dynamic consumption profile, match product categories that meet the user's current needs, sort them according to matching priority, and automatically generate a personalized product recommendation push list.

[0030] By adopting the above solution, personalized recommendations can be achieved based on accurate dynamic profiles, and the order of recommended products can be reasonably arranged to greatly improve the relevance of product push and effectively increase the platform's product click-through rate and conversion rate.

[0031] Specifically, the real-time inventory monitoring module includes a spot inventory statistics unit, an in-transit inventory statistics unit, and an inventory threshold early warning unit. It is used to count the current inventory of goods at each warehousing node and the quantity of inventory transferred in transit in real time, while setting high and low inventory early warning thresholds and providing real-time feedback on the surplus and shortage status of goods inventory.

[0032] By adopting the above solution, we can have a comprehensive understanding of the actual inventory status of goods at all warehouse locations, promptly identify inventory backlogs and shortages, proactively identify supply risks, and ensure that the status of goods supply is controllable in real time.

[0033] Specifically, the supply and demand linkage scheduling module includes a recommendation traffic analysis unit, an inventory allocation instruction unit, and a recommendation strategy control unit. It is used to count the front-end product recommendation exposure volume and the scale of potential users, predict the short-term product demand volume, simultaneously issue warehouse replenishment and inventory diversion instructions, and adjust the product recommendation exposure frequency and push intensity according to the real-time inventory status.

[0034] By adopting the above solution, the data barriers between front-end marketing and back-end warehousing are broken down, and market demand can be predicted based on user intention traffic, enabling advance coordination and allocation of goods.

[0035] Specifically, the data interaction storage module has a built-in data encryption storage unit and a high-speed data relay interaction unit.

[0036] By adopting the above solution, we can not only ensure the security of platform user behavior data and commercial inventory data storage and prevent data leakage, but also accelerate the data transmission rate between modules and ensure the smooth and stable operation of the system as a whole.

[0037] Specifically, the supply and demand linkage scheduling module predicts consumer demand based on user behavior data and issues inventory scheduling instructions. At the same time, it dynamically adjusts the exposure level and push frequency of product recommendations based on the remaining inventory. The scheduling instructions specifically include: issuing replenishment / cross-warehouse transfer instructions to reduce product recommendation exposure when inventory is scarce; increasing targeted recommendations to accelerate product turnover when inventory is piling up; and maintaining the original recommendation and inventory preparation rhythm when inventory is normal.

[0038] By adopting the above approach, we can anticipate demand and prepare inventory in advance. At the same time, we can optimize the recommendation layout by using inventory status, increase promotion efforts for slow-moving products, and reduce the recommendation exposure for out-of-stock products, thus balancing the supply and demand relationship in the commodity market from the source.

[0039] Working principle of the invention: In use, the user behavior collection module comprehensively collects real-time user behavior data across all dimensions, including browsing, clicking, adding to cart, abandoning purchases, and searching. This data is then transmitted to the behavior feature analysis module, which cleans, filters, and weights the raw data. Combined with time-series changes, it continuously builds and updates dynamic user consumption profiles. Subsequently, the intelligent product recommendation module retrieves user profiles, accurately matches corresponding products, prioritizes them, and generates personalized recommendation lists for platform push. Simultaneously, the real-time inventory monitoring module aggregates the quantities of goods in stock and in transit in each warehouse, monitors abnormal inventory status in real time based on preset thresholds, and issues timely warnings, linking supply and demand. The dynamic scheduling module serves as the core hub, synchronously connecting with front-end recommendation traffic data and back-end inventory data. On one hand, it predicts consumer demand based on user behavior trends and issues cross-warehouse transfer and emergency replenishment instructions in advance. On the other hand, it dynamically adjusts the exposure and push frequency of product recommendations based on the surplus or shortage status of product inventory, realizing the promotion of slow-moving products and the control and limiting of traffic for scarce products. Finally, all business data is uniformly collected in the data interaction and storage module for encrypted storage and high-speed circulation, ensuring real-time data communication and collaborative operation of each module, effectively realizing the integrated linkage of user behavior analysis, intelligent product recommendation, and warehouse inventory scheduling.

[0040] It should be noted that, in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus.

[0041] Although embodiments of the invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the appended claims and their equivalents.

Claims

1. An e-commerce product recommendation and inventory linkage system based on user behavior, characterized by: The system includes a user behavior collection module, a behavior feature analysis module, an intelligent product recommendation module, a real-time inventory monitoring module, a supply and demand linkage scheduling module, and a data interaction and storage module. The user behavior collection module collects various real-time behavioral data of users within the e-commerce platform. The behavior feature analysis module is connected to the user behavior collection module and is used to analyze and process the collected behavioral data to build a dynamic user consumption profile. The intelligent product recommendation module is connected to the behavior feature analysis module and generates personalized product recommendation content based on the dynamic user profile. The real-time inventory monitoring module collects and statistically analyzes relevant data on product inventory across all channels in real time. The supply and demand linkage scheduling module is connected to both the intelligent product recommendation module and the real-time inventory monitoring module. The data interaction and storage module is connected to each module and is used to achieve unified storage, real-time interaction, and synchronous access of data across the entire system.

2. The e-commerce product recommendation and inventory linkage system based on user behavior as described in claim 1, characterized in that: The user behavior collection module includes a browsing trajectory collection unit, an operation behavior collection unit, and a consumption intention collection unit, which are used to collect real-time behavioral data of users in all dimensions within the e-commerce platform, such as product browsing path, page dwell time, product click frequency, add-to-cart actions, order cancellation, and keyword search.

3. The e-commerce product recommendation and inventory linkage system based on user behavior as described in claim 1, characterized in that: The behavioral feature analysis module includes a data cleaning and classification unit, a behavior weight assignment unit, and a dynamic profile construction unit. It is used to organize and process the collected fragmented behavioral data, divide the demand weights according to the behavior type, and construct a real-time updated dynamic user consumption behavior profile based on temporal behavior changes.

4. The e-commerce product recommendation and inventory linkage system based on user behavior as described in claim 1, characterized in that: The intelligent product recommendation module includes a preferred product matching unit, a hierarchical recommendation sorting unit, and a recommendation list generation unit. It is used to retrieve the user's dynamic consumption profile, match product categories that meet the user's current needs, sort them according to matching priority, and automatically generate a personalized product recommendation push list.

5. The e-commerce product recommendation and inventory linkage system based on user behavior as described in claim 1, characterized in that: The real-time inventory monitoring module includes a spot inventory statistics unit, an in-transit inventory statistics unit, and an inventory threshold early warning unit. It is used to count the current inventory of goods at each warehousing node and the quantity of inventory transferred in transit in real time. At the same time, it sets high and low inventory early warning thresholds and provides real-time feedback on the surplus and shortage status of goods inventory.

6. The e-commerce product recommendation and inventory linkage system based on user behavior as described in claim 1, characterized in that: The supply and demand linkage scheduling module includes a recommendation traffic analysis unit, an inventory allocation instruction unit, and a recommendation strategy control unit. It is used to count the front-end product recommendation exposure volume and the scale of potential users, predict the short-term product demand volume, simultaneously issue warehouse replenishment and inventory diversion instructions, and adjust the product recommendation exposure frequency and push intensity based on the real-time inventory status.

7. The e-commerce product recommendation and inventory linkage system based on user behavior as described in claim 1, characterized in that: The data interaction and storage module has a built-in data encryption storage unit and a high-speed data relay and interaction unit.

8. The e-commerce product recommendation and inventory linkage system based on user behavior as described in claim 1, characterized in that: The supply and demand linkage scheduling module predicts consumer demand based on user behavior data and issues inventory scheduling instructions. At the same time, it dynamically adjusts the exposure level and push frequency of product recommendations based on the remaining inventory.

Images