Online shopping mall platform intelligent management method and system

Abstract

The invention relates to the technical field of information, and particularly discloses an online mall platform intelligent management method and system, and the method comprises the following steps: S1, constructing a data collection system, and obtaining platform operation data, user behavior data and external market data in real time; s2, acquiring historical sales data, analyzing the historical sales data by adopting a Prophet time sequence model, predicting a future sales trend and inventory requirements, and generating a dynamic replenishment suggestion; s3, optimizing inventory management through a dynamic programming algorithm, calculating an optimal inventory threshold value in combination with external market data, and performing automatic replenishment triggering; s4, establishing a user portrait according to the user behavior data, and generating a personalized coupon strategy based on a collaborative filtering algorithm; s5, dynamically matching the work order and the customer service according to a multi-attribute decision algorithm; and S6, storing quality assurance information, and ensuring non-tampering and traceability of construction time, material batches and technician ID data. Therefore, the operation efficiency and the user experience of the shopping mall platform are improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of information technology, in particular to an online mall platform intelligent management method and system. BACKGROUND

[0002] With the rapid development of e-commerce, online mall platforms are facing increasingly complex challenges in areas such as product sales, user service, and supply chain management. With the booming development of the automobile consumption market, car color film, as an important product for personalizing the appearance of cars, has seen increasing prosperity in its online mall business.

[0003] However, there are many problems in the management of current online mall platforms for car color film. In terms of inventory management, it is difficult to accurately assess complex factors such as market demand fluctuations and supply chain uncertainties. In terms of user marketing, general coupon distribution strategies are often used without deeply exploring user needs and preferences. In the work order processing link, existing allocation methods cannot dynamically and reasonably match work orders with customer service, resulting in low work order processing efficiency. In terms of warranty information management, traditional storage methods cannot guarantee the tamperability and traceability of data, and when quality disputes arise, it is difficult to quickly and accurately trace the source.

[0004] Therefore, there is an urgent need for an innovative management method that can effectively integrate multi-source data and use advanced algorithms and technologies to address the pain points in the management of online mall platforms for car color film, improving platform operation efficiency, user experience, and market competitiveness. SUMMARY

[0005] To overcome the above technical problems in the prior art, the present application provides an online mall platform intelligent management method and system, which integrates multi-dimensional data analysis, dynamic algorithm optimization, and reliable data tracing to improve platform operation efficiency and user experience.

[0006] In order to achieve the above object, the embodiment of the present application provides an online mall platform intelligent management method, comprising the following steps: S1: constructing a data acquisition system, acquiring platform operation data, user behavior data and external market data in real time, the external market data including delivery cycle and material delay probability; S2: acquiring historical sales data, analyzing the historical sales data by using a Prophet time series model, predicting future sales trend and inventory demand, and generating dynamic replenishment suggestions; S3: optimizing inventory management through a dynamic programming algorithm and the dynamic replenishment suggestions, calculating an optimal inventory threshold in combination with the delivery cycle and the material delay probability, and realizing automatic replenishment triggering; S4: establishing a user portrait according to the user behavior data, generating a personalized coupon strategy based on a collaborative filtering algorithm and the user portrait, and updating the user portrait in real time; S5: acquiring work order management module data, dynamically matching work orders and customer service according to a multi-attribute decision algorithm; and S6: storing warranty information, ensuring the non-tamperability and traceability of construction time, material batch and technician ID data.

[0007] Preferably, in the step S2, the generating of the dynamic replenishment suggestion specifically comprises: acquiring weather data and supply chain fluctuation information, integrating the weather data and the supply chain fluctuation information, and dynamically adjusting replenishment priority according to a gradient boosting tree; embedding a visual early warning interface in a data overview module of the online mall platform, acquiring inventory data in real time and generating an inventory health degree, acquiring replenishment logs in real time, and the visual early warning interface displaying the inventory health degree and the replenishment logs in real time.

[0008] Preferably, the step S5 specifically comprises: establishing a customer service information database, the customer service information database recording customer service professional skills, real-time load and historical satisfaction data; dynamically optimizing a work order distribution strategy in combination with a multi-attribute decision algorithm and a reinforcement learning model, balancing skill matching degree, response time and load balancing; acquiring work order texts and classifying the work order texts in semantics by using a BERT model, and identifying work order urgency and customer emotions.

[0009] Preferably, the dynamically optimizing of the work order distribution strategy in combination with the multi-attribute decision algorithm and the reinforcement learning model further comprises: a state space defined by the reinforcement learning model being customer real-time load, work order backlog and customer emotion distribution, and an action space being work order distribution decision; a short-term reward function being set as work order solution time length and customer satisfaction score, and a long-term reward function being set as customer service skill improvement rate and overall work order solution rate; and a SHAP value explanation algorithm being used to distribute logic and generate an explainability distribution report.

[0010] Preferably, in the step S6, the storing of the warranty information specifically comprises: building a private chain node, associating Internet of Things equipment data of a construction store, and automatically uploading warranty operation records; providing a client-side blockchain query interface, and supporting code scanning to verify warranty information full link.

[0011] Preferably, the method further comprises: integrating AR augmented reality technology to provide a virtual color testing function to support users to upload vehicle photos and simulate the effect of color-changing films in real time; the virtual color testing function comprises: building a vehicle 3D model library to support the simulation of color-changing film effects for mainstream vehicle models; collecting user color testing interaction data and optimizing the priority of popular color recommendations through a clustering algorithm.

[0012] Preferably, the method further comprises: in the sensitive message record module of the online mall platform, using a natural language processing model to monitor work orders and chat records in real time, identifying sensitive keywords and customer emotions; generating a risk warning through an anomaly detection algorithm according to the sensitive keywords and the customer emotions; and classifying the work order processing priority according to the risk warning and triggering an automatic disposal process.

[0013] Correspondingly, the application also provides an online mall platform intelligent management system, which comprises the following modules: a data acquisition module for acquiring platform operation data, user behavior data and external market data; a sales prediction module connected with the data acquisition module, for receiving historical sales data, analyzing the historical sales data using a Prophet time series model, predicting future sales trends and inventory needs, and generating dynamic replenishment suggestions; an inventory management module connected with the sales prediction module, for optimizing inventory management through a dynamic programming algorithm, calculating the optimal inventory threshold in combination with the dynamic replenishment suggestions, delivery cycle and material delay probability, and triggering an automatic replenishment instruction; a user portrait module connected with the data acquisition module, for establishing a user portrait based on user behavior data and generating personalized coupon strategies based on a collaborative filtering algorithm, while updating the user portrait in real time; a work order management module for dynamically matching work orders and customer service according to a multi-attribute decision algorithm, the attributes including customer service professional skills, real-time load and historical processing efficiency, tracking work order status and feeding back processing results to the user portrait module; a quality assurance management module for storing quality assurance information, construction time, material batch and technician ID data, and ensuring data non-tamperability and traceability based on blockchain technology.

[0014] Preferably, the system further comprises: a virtual color testing module integrated with AR augmented reality technology to support users to upload vehicle photos and simulate the effect of color-changing films, while collecting color testing interaction data and optimizing the priority of popular color recommendations through a clustering algorithm; a sensitive message monitoring module using a natural language processing model to analyze work orders and chat records in real time, identify sensitive keywords and customer emotions, and trigger a risk warning through an anomaly detection algorithm.

[0015] Through the technical solutions provided by the application, the application has at least the following technical effects: The online mall platform management method provided by the application integrates external data such as delivery cycle, weather and logistics delay in inventory management, realizes dynamic adjustment of inventory threshold through dynamic programming algorithm, also increases a visual early warning interface, so that the management personnel can intuitively master the inventory state, and provides decision support, reduces the cost of manual intervention, and improves the platform operation efficiency; in the user marketing aspect, the user portrait is updated in real time, the user consumption behavior and preference are used for accurate marketing, personalized coupon strategies are generated, the coupon use rate and user repurchase rate are improved; in the work order processing link, the multi-attribute decision algorithm is used to match the work order and the customer service, the reinforcement learning model is used to optimize the distribution strategy, the BERT model is used to analyze the work order text, the work order processing efficiency and service quality are improved from multiple dimensions, and the distribution accuracy is improved, so as to improve the user experience; in the quality assurance information management aspect, the blockchain technology is used to store the quality assurance information, the blockchain and the internet of things equipment are linked, the private chain node is linked to the internet of things equipment to automatically upload records, the query interface is provided, the quality assurance information is guaranteed to be real and reliable, traceable, and the user trust is enhanced. BRIEF DESCRIPTION OF DRAWINGS

[0016] The accompanying drawings are included to provide a further understanding of embodiments of the application, and constitute a part of the specification, and are used together with the specific embodiments described below to explain the embodiments of the application, but do not constitute a limitation on the embodiments of the application. In the drawings: Figure 1 is a flowchart of an online mall platform intelligent management method provided by the embodiments of the application; Figure 2 is a structural diagram of an online mall platform intelligent management system provided by the embodiments of the application. DETAILED DESCRIPTION

[0017] The specific embodiments of the embodiments of the application will be described in detail below with reference to the accompanying drawings. It should be understood that the specific embodiments described herein are only used to illustrate and explain the embodiments of the application, and do not limit the embodiments of the application.

[0018] The terms "system" and "network" in the embodiments of the application can be used interchangeably. "Multiple" means two or more, and in view of this, "multiple" can also be understood as "at least two" in the embodiments of the application. "And / or", which describes the association relationship of the associated objects, means that there can be three relationships, for example, A and / or B, which means that there are three cases of A alone, A and B together, and B alone. In addition, the character " / ", if not specially stated, generally represents that the associated objects before and after it are in an "or" relationship. In addition, it should be understood that in the description of the embodiments of the application, "first", "second", etc. are only used for the purpose of distinguishing the description, and cannot be understood as indicating or implying relative importance, nor can it be understood as indicating or implying order.

[0019] Referring to Figure 1 The embodiment of the present application provides an online mall platform intelligent management method, comprising the following steps: S1: Construct a data acquisition system to obtain platform operation data, user behavior data and external market data in real time, wherein the external market data comprises a delivery cycle and a material delay probability; S2: Obtain historical sales data, analyze the historical sales data by using a Prophet time series model, predict future sales trends and inventory demand, and generate dynamic replenishment suggestions; S3: Optimize inventory management through a dynamic programming algorithm and the dynamic replenishment suggestions, calculate an optimal inventory threshold in combination with the delivery cycle and the material delay probability, and realize automatic replenishment triggering; S4: Establish a user portrait according to the user behavior data, generate an individualized coupon strategy based on a collaborative filtering algorithm and the user portrait, and update the user portrait in real time; S5: Obtain work order management module data, and dynamically match work orders and customer service according to a multi-attribute decision algorithm; S6: Store warranty information to ensure the non-tamperability and traceability of construction time, material batch and technician ID data.

[0020] In the embodiment of the present application, the online mall platform intelligent management method provided by the embodiment of the present application is applicable to an online mall platform of car color film, and the online mall platform of car color film comprises the following functional modules: data overview, work order management, store management, short message group sending, commodity management, out-of-stock record, order management, quality assurance management, coupon management, sensitive message record, financial control center, color drawing business center, market business center and system operation and maintenance configuration; wherein, the data overview functional module counts the key data of the whole platform operation, helping the manager to comprehensively understand the sales performance of the platform; the work order management functional module is used for efficiently processing customer service demand and problems, and provides complete work order tracking and management functions, through which the detailed information of all work orders can be viewed and managed, helping the administrator to master the work order progress in real time, and ensuring timely response to customer demand; the out-of-stock record functional module is committed to optimizing inventory turnover and commodity supply efficiency, through real-time monitoring of commodity inventory state, helping the manager to quickly locate the specifications of out-of-stock commodities, and ensuring dynamic balance of inventory level and sales demand; the quality assurance management functional module provides comprehensive commodity quality assurance service support for customers, ensuring transparency and traceability of quality assurance information; the coupon management functional module provides comprehensive coupon issuance and use tracking functions; the sensitive message record functional module provides comprehensive customer communication monitoring and risk early warning functions, ensuring that sensitive information in the customer service process is identified and processed in time, optimizing the service process, and improving customer satisfaction and compliance. The online mall platform of car color film has many problems in use, therefore, the embodiment of the present application provides an online mall platform intelligent management method, so as to improve the platform operation efficiency, user experience and market competitiveness of the online mall platform.

[0021] In the embodiment of the present application, for step S1, first, a data acquisition system is constructed, after being constructed, the data acquisition system acquires platform operation data, user behavior data and external market data in real time through an application programming interface (API interface), wherein the acquired platform operation data comprises order quantity, sales data, commodity on-off shelf state, inventory data and daily user access quantity information; the user behavior data acquires user browsing path, click heat map, shopping cart adding behavior, browsing record, purchase record and search record through burying points, and can extract search keyword information in the search record; the delivery cycle and other external market data are acquired by connecting external suppliers and logistics companies, and the material delay probability is calculated in combination with historical logistics data; for example, an online mall of car color film in South China monitored by the data acquisition system finds that the probability of logistics delay rises to 35% due to typhoon weather, and the system automatically marks the region as a high-risk supply chain region.

[0022] Further, for step S2, the historical sales data is obtained by the data acquisition system and input into the Prophet time series model, the seasonal period is set to 12 months, the promotion node parameters include "Double 11" and "618", the Prophet time series model is used to analyze the historical sales data, and the future 3-month sales prediction curve and inventory demand are output, and the replenishment suggestion is generated; in another embodiment, when the Prophet model analyzes the historical sales data, the gradient boosting tree dynamically adjusts the replenishment priority in combination with the high-temperature weather prediction data and the supply chain fluctuation information of the recent frequent delayed delivery of the supplier, and the visualization early warning interface is embedded in the data overview module of the online mall platform, the visualization early warning interface obtains the inventory data and the replenishment log in real time, and generates the inventory health degree according to the inventory data and the preset inventory safety threshold, the inventory health degree is divided into green warning, yellow warning and red warning, the management personnel can see the inventory health degree through the visualization early warning interface, and can also check the detailed replenishment log, so as to grasp the inventory dynamics in time; further, for step S3, the inventory management is optimized by the dynamic programming algorithm and the replenishment suggestion, and the optimal inventory threshold is calculated by the dynamic programming algorithm considering the predicted sales, the delivery cycle and the material delay probability, and the automatic replenishment trigger is realized according to the optimal inventory threshold, so as to avoid the occurrence of out-of-stock situation; for example, taking an online mall of a certain car color film as an example, before the summer comes, the system obtains the following data through the data acquisition system: the sales data of the past three summers, the current inventory data, the delivery cycle of each supplier (such as A supplier delivery cycle is 15 days, B supplier is 20 days), the material delay probability (A supplier delay probability due to transportation problem is 10%, B supplier is 15%), and the high-temperature weather prediction data of the next two months released by the meteorological department; then, the Prophet time series model analyzes the historical sales data, and predicts that the sales of a certain light color color film in summer will increase by 40%; at the same time, the gradient boosting tree combines the high-temperature weather prediction data and the supply chain fluctuation information of the recent frequent delayed delivery of A supplier, and the replenishment priority of the color film is promoted to the highest; then, the dynamic programming algorithm is used to consider the predicted sales, the delivery cycle and the material delay probability, and the optimal inventory threshold is calculated as 800 rolls, but the current inventory is only 300 rolls, so the system automatically sends a replenishment order to A supplier, avoiding the occurrence of out-of-stock situation; on the visualization early warning interface, the management personnel can see the inventory health degree of the color film in the yellow warning state in real time, and can check the detailed replenishment log, so as to grasp the inventory dynamics in time.

[0023] In the embodiment of the present application, for step S4, according to the user portrait constructed by the data acquisition system, the user behavior data label system includes consumer frequency, price sensitivity, color preference, user browsing path, click heat map, shopping cart addition behavior, browsing record, purchase record, search record and other information to establish a detailed user portrait, generate personalized coupon strategies based on collaborative filtering algorithm and user portrait, and update the user portrait in real time according to the real-time changes of user behavior data; for example, a user A of the mall platform has browsed high-end color film with a price above 2000 yuan for many times in the past half year, but has only purchased a medium and low-end product once, and the system establishes a detailed user portrait according to the user behavior data such as browsing record and purchase history, labels that the user A has high interest in high-end color film but is cautious in purchase decision, and the collaborative filtering algorithm analysis finds that the user A has high similarity with other users who have purchased high-end color film in browsing preference, brand attention and other aspects, based on which the system generates personalized coupon strategies, pushes a high-end color film exclusive coupon with “full 2000 yuan minus 300 yuan” to the user A, and pushes the coupon through short message and APP message, after the user A receives the coupon, the user A completes the purchase of high-end color film within a week, realizes precise marketing, and improves the purchase conversion rate and the average single price of the user; or another user B has browsed electroplated blue color film for many times within 3 days but has not placed an order, the system updates the portrait of the user B in real time as “hesitant user”, and pushes “limited time 8% off + free construction coupon”, and finally promotes the conversion.

[0024] In the embodiment of the present application, for step S5, the work order data of the work order management module is acquired, and the work order and the customer service are dynamically matched according to the multi-attribute decision algorithm. Specifically, first, a customer service information database is established, which records the professional skills, real-time load and historical satisfaction data of the customer service, and combines the multi-attribute decision algorithm and the reinforcement learning model, so as to dynamically optimize the work order distribution strategy, balance the skill matching degree, response time and load balancing, and thus improve the work order processing efficiency and customer experience. When optimizing the work order distribution strategy, the work order text needs to be acquired and the BERT model is used for semantic classification of the work order text, so as to identify the work order urgency and customer emotion through semantic classification, and the work order urgency and customer emotion need to be combined in the work order distribution strategy. As for the combination of the multi-attribute decision algorithm and the reinforcement learning model, the state space defined in the reinforcement learning model is the real-time load of the customer service, the work order backlog and the customer emotion distribution, and the action space defined is the work order distribution decision. The short-term reward function set in the reinforcement learning model is the work order solution time and the customer satisfaction score, and the long-term reward function set is the customer service skill improvement rate and the overall work order solution rate. Further, in addition to the multi-attribute decision algorithm and the reinforcement learning model, the SHAP value explanation algorithm distribution logic can also be used to generate an explainable distribution report. That is, after the reinforcement learning model outputs the work order distribution decision, for each distribution decision, the SHAP value of each feature is calculated, for example: the skill matching degree of customer A contributes +0.4 (positive influence), the current load of customer B contributes -0.3 (negative influence), and the work order urgency contributes +0.2. The total SHAP value is equal to the difference of the final decision score of the model (for example, the score of customer A is 0.3 higher than that of customer B). Then an explainable report is generated, which includes feature importance ranking (listing the top 3 factors that have the greatest impact on this distribution), contribution value visualization (showing the SHAP value of each feature through a column chart or waterfall chart), and decision logic summary (for example, the skill matching degree of customer A (+0.4) is significantly higher than that of customer B (+0.1), and the current load of customer B is high (-0.3)). In order to realize algorithm transparency and management intelligence.

[0025] Further, for the work order allocation optimization strategy provided by the present embodiment, taking an example, the work order management module of the online mall platform receives three work orders at the same time: work order 1: the user feedbacks that the edge of the new post film appears slight warping, and the text content is relatively mild; work order 2: the user claims that the color film falls off in a large area, and the tone is very excited, requiring immediate solution; work order 3: inquires about the warranty period of a certain color film, and the attitude is friendly. At this time, the BERT model first classifies the semantics of the work order text, identifies that work order 2 is urgent and the customer is excited, work order 1 is a normal problem, and work order 3 is a consultation problem; then the customer service information database shows that customer service A is good at handling after-sales problems and the current load is low, customer service B is good at answering consultation problems and the work is not saturated, and customer service C is processing other urgent work orders; then the multi-attribute decision algorithm combines the reinforcement learning model, and work order 2 is allocated to customer service A, work order 3 is allocated to customer service B, and work order 1 is temporarily queued for processing; after receiving the work order, customer service A quickly communicates with the user, arranges professional personnel to check and re-paste the film, and the user's satisfaction score reaches 4.8 points (full score 5 points); customer service B answers the user's consultation in time, and the user gives good comments; finally, the system generates a work order allocation report through the SHAP value explanation algorithm, which clearly shows the reason for allocating work order 2 to customer service A, facilitating managers to evaluate and optimize the allocation strategy.

[0026] In the embodiment of the present application, for step S6, the quality assurance information is stored, specifically, first, a private chain is built, that is, an alliance chain is built based on Hyperledger Fabric, the nodes of the private chain include the headquarters, the construction store, and the logistics company; the Internet of Things equipment (hereinafter referred to as IOT equipment) data associated with the construction store is automatically uploaded to the quality assurance operation record, that is, after the construction is completed, the IOT equipment of the store automatically uploads the construction time, the material batch, and the technician ID to the blockchain; a client-side blockchain query interface is provided, which supports scanning the code to verify the quality assurance information full link, that is, the customer scans the two-dimensional code on the quality assurance card, and the full link information (such as material batch source, construction video hash value) can be queried to ensure the non-tamperability and traceability of the construction time, material batch, and technician ID data. For example, after a user purchases a color-changing film and completes the construction, the IOT equipment (such as a camera and an electronic tag reader) of the construction store automatically records the construction time (such as 2024-06-01 14:30), the batch of the material used (such as NO.20240601A identified by the electronic tag), and the technician ID (such as TECH-001 recorded by the work card punching), and these quality assurance operation records are automatically uploaded to the blockchain system through the private chain node to form a non-tamperable record; one month later, the user finds that the color-changing film has a fading problem, and can use the client-side blockchain query interface to view the full-link quality assurance information of the color-changing film, including the construction process video clip (recorded and uploaded by the camera), material batch detailed information, and technician qualification certificate, by scanning the two-dimensional code on the product packaging. According to the blockchain record, the merchant can quickly trace the material supplier and the construction link problem, and timely solve the dispute for the user, protect the user's rights and interests, and also maintain its own reputation.

[0027] In still another embodiment, the online mall platform intelligent management method provided by the present application further comprises integrating AR augmented reality technology to provide a virtual color testing function, supporting users to upload vehicle photos and simulate the effect of color film in real time; wherein the virtual color testing function comprises: building a vehicle 3D model library to support the simulation of color film effect for mainstream vehicle models; and further collecting user color testing interaction data to optimize the priority of popular color recommendations through clustering algorithms. For example, the online mall platform builds a vehicle 3D model library, and when the user selects and purchases color film in the mall, uses the AR virtual color testing function to upload the user's own vehicle photos, the system matches the vehicle model from the vehicle 3D model library and simulates the color film effect in real time through AR technology, displays the real-time simulation effect of different color films, and the user tries red, blue, gray and other colors in turn, and stays longer on the color testing operation of the blue color film and repeatedly adjusts the viewing angle to view the effect; after the system collects the user color testing interaction data, it is found through clustering algorithm analysis that the number of users browsing and testing blue color film has increased significantly in recent period, and the conversion rate of this group is high, and the mall can embed the color testing data heat map in the color painting business center module according to this data, and in the color testing data heat map of the color painting business center module, mark the blue color film as a popular product, and adjust the inventory strategy to increase the inventory of blue color film; at the same time, the promotion of blue color film is increased on the home page and product recommendation page, so as to improve the sales of the mall.

[0028] In still another embodiment, the online mall platform intelligent management method provided by the present application further comprises first using a natural language processing model (hereinafter referred to as NLP model) to monitor work orders and chat records in real time in the sensitive message recording module of the online mall platform, and identifying sensitive keywords and customer emotions. Specifically, the NLP model detects sensitive keywords such as "complaint" and "fake goods" appearing in the chat record, and analyzes the customer emotions; then generates a risk warning through an anomaly detection algorithm according to the sensitive keywords and customer emotions; finally, the risk warning classifies the work order processing priority and triggers an automatic disposal process, that is, the system automatically marks it as a high-risk work order and notifies the supervisor to intervene. For example, the chat record between the customer service and the user contains the message "your color film is fake, I want to complain to the consumer association", the NLP model identifies the sensitive keywords "fake goods" and "complaint" in real time, and judges that the customer emotion is angry, then uses the anomaly detection algorithm to generate a high-risk warning, the system immediately raises the work order processing priority to the highest, and triggers the automatic disposal process. At the same time, the system also automatically notifies the customer service supervisor to intervene and handles, and immediately sends a soothing message to the user, promising to provide a solution within 24 hours. After the customer service supervisor communicates and negotiates with the user, a professional detection personnel is arranged to detect the color film, and finally confirms that the problem is caused by improper construction, and re-provides free construction for the user, successfully solving the user's problem.

[0029] This invention provides an intelligent management method for online shopping mall platforms. Through steps such as constructing a data collection system, employing advanced data analysis and prediction models, optimizing inventory management, generating personalized marketing strategies, dynamically matching work orders and customer service, and storing warranty information, it achieves intelligent management of the online shopping mall platform. This significantly improves inventory turnover, increases work order response speed and customer satisfaction, and greatly enhances the efficiency of warranty dispute resolution. Furthermore, automated decision-making reduces manual intervention, leading to more accurate resource allocation and improved efficiency. AR color try-on, personalized recommendations, and rapid work order response further enhance customer satisfaction. Blockchain-based warranty traceability and sensitive message monitoring ensure data transparency and compliance, increasing customer trust. Reinforced learning and dynamic optimization capabilities support continuous business iteration. Overall, this method improves the operational efficiency and user experience of the shopping mall platform.

[0030] Please see Figure 2 Based on the same inventive concept, embodiments of the present invention provide an intelligent management system for an online shopping mall platform, the system comprising the following modules: Data acquisition module: used to collect platform operation data, user behavior data, and external market data; Sales forecasting module: connected to the data acquisition module, used to receive historical sales data, analyze the historical sales data using the Prophet time series model, predict future sales trends and inventory demand, and generate dynamic replenishment suggestions; Inventory Management Module: Connected to the sales forecasting module, it is used to optimize inventory management through dynamic programming algorithms, calculate the optimal inventory threshold by combining the dynamic replenishment suggestions, delivery cycle and material delay probability, and trigger automatic replenishment instructions; User profiling module: connected to the data acquisition module, used to build user profiles based on user behavior data, generate personalized coupon strategies based on collaborative filtering algorithms, and update the user profiles in real time. Work order management module: used to dynamically match work orders with customer service representatives based on a multi-attribute decision algorithm. The attributes include customer service representative professional skills, real-time load, and historical processing efficiency. It tracks the status of work orders and feeds back the processing results to the user profile module. Quality Assurance Management Module: Used to store quality assurance information, construction time, material batches, and technician ID data. Based on blockchain technology, it ensures the immutability and traceability of the data.

[0031] In another embodiment, the online shopping platform intelligent management system provided by this invention further includes: Virtual color try-on module: Integrates AR augmented reality technology, supports users to upload vehicle photos and simulate the effect of color change film, and collects color try-on interaction data, and optimizes the recommendation priority of popular colors through clustering algorithms; Sensitive message monitoring module: using natural language processing model to analyze the ticket and chat records in real time, identify sensitive keywords and customer emotions, and trigger risk warning through anomaly detection algorithm.

[0032] The above describes the optional implementation of the embodiments of the present application in detail in combination with the drawings, but the embodiments of the present application are not limited to the specific details in the above implementation, and various simple modifications can be made to the technical solutions of the embodiments of the present application within the technical concept of the embodiments of the present application, and these simple modifications all belong to the protection scope of the embodiments of the present application.

[0033] In addition, it should be noted that various specific technical features described in the above specific implementation can be combined in any appropriate manner without contradiction. In order to avoid unnecessary repetition, various possible combinations are not described again in the embodiments of the present application.

[0034] Those skilled in the art can understand that all or part of the steps of the above-mentioned embodiment methods can be completed by programs instructing related hardware, the programs are stored in a storage medium, and the programs include a plurality of instructions for making a single-chip microcomputer, a chip or a processor execute all or part of the steps of the methods described in various embodiments of the present application. The foregoing storage medium includes: a U disk, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk and various program code storage media.

[0035] In addition, various different implementations of the embodiments of the present application can also be combined in any manner, as long as they do not deviate from the idea of the embodiments of the present application, and should be considered as disclosed by the embodiments of the present application.

Claims

1. A method for intelligent management of an online shopping mall platform, characterized in that, Includes the following steps: S1: Build a data acquisition system to acquire platform operation data, user behavior data and external market data in real time. The external market data includes delivery cycle and material delay probability. S2: Obtain historical sales data, analyze the historical sales data using the Prophet time series model, predict future sales trends and inventory demand, and generate dynamic replenishment suggestions; S3: Optimize inventory management through dynamic programming algorithm and the dynamic replenishment suggestion, and calculate the optimal inventory threshold by combining the delivery cycle and the material delay probability to achieve automatic replenishment triggering; S4: Establish a user profile based on the user behavior data, generate a personalized coupon strategy based on the collaborative filtering algorithm and the user profile, and update the user profile in real time; S5: Obtain data from the work order management module and dynamically match work orders with customer service representatives based on a multi-attribute decision algorithm; S6: Store quality assurance information to ensure the immutability and traceability of construction time, material batches, and technician ID data.

2. The intelligent management method for an online shopping mall platform according to claim 1, characterized in that, In step S2, generating dynamic replenishment suggestions specifically includes: Acquire weather data and supply chain fluctuation information, integrate the weather data and supply chain fluctuation information, and dynamically adjust replenishment priority according to the gradient boosting tree; A visual alert interface is embedded in the data overview module of the online shopping platform to obtain inventory data in real time and generate inventory health status, and to obtain replenishment logs in real time. The visual alert interface displays the inventory health status and the replenishment logs in real time.

3. The intelligent management method for an online shopping mall platform according to claim 2, characterized in that, Step S5 specifically includes: Establish a customer service information database that records customer service professional skills, real-time workload, and historical satisfaction data. By combining multi-attribute decision-making algorithms and reinforcement learning models, the work order allocation strategy is dynamically optimized to balance skill matching, response time and load balancing. The system acquires work order texts and performs semantic classification on them using the BERT model to identify the urgency of the work order and the customer's emotions.

4. The intelligent management method for an online shopping mall platform according to claim 3, characterized in that, The dynamic optimization strategy for work order allocation, which combines multi-attribute decision-making algorithms and reinforcement learning models, further includes: The state space defined by the reinforcement learning model is the real-time customer service load, the backlog of work orders, and the distribution of customer sentiment, while the action space is the work order allocation decision. Set the short-term reward function as work order resolution time and customer satisfaction score, and the long-term reward function as customer service skill improvement rate and overall work order resolution rate; The SHAP value interpretation algorithm is used to allocate the logic and generate an interpretable allocation report.

5. The intelligent management method for an online shopping mall platform according to claim 1, characterized in that, In step S6, storing the warranty information specifically includes: Set up private chain nodes, link them to IoT device data at construction sites, and automatically upload warranty operation records; Provides a client-side blockchain query interface, supporting QR code verification of quality assurance information across the entire process.

6. The intelligent management method for an online shopping mall platform according to claim 1, characterized in that, The method further includes: It integrates AR augmented reality technology, provides a virtual color try-on function, and supports users to upload vehicle photos and simulate the effect of color change film in real time; The virtual color matching function includes: building a 3D vehicle model library to support the simulation of color-changing film effects for mainstream vehicle models; Collect user color trial interaction data and optimize the recommendation priority of popular colors through clustering algorithms.

7. The intelligent management method for an online shopping mall platform according to claim 1, characterized in that, The method also includes: in the sensitive message recording module of the online shopping mall platform, using a natural language processing model to monitor work orders and chat records in real time, and identify sensitive keywords and customer emotions; Risk warnings are generated based on the sensitive keywords and customer sentiment using an anomaly detection algorithm. Based on the risk warning, the work order processing priority is classified and an automatic handling process is triggered.

8. An intelligent management system for an online shopping mall platform, characterized in that, The system includes the following modules: Data acquisition module: used to collect platform operation data, user behavior data, and external market data; Sales forecasting module: Connected to the data acquisition module, it receives historical sales data, analyzes the historical sales data using the Prophet time series model, predicts future sales trends and inventory demand, and generates dynamic replenishment suggestions; Inventory Management Module: Connected to the sales forecasting module, it is used to optimize inventory management through dynamic programming algorithms, calculate the optimal inventory threshold by combining the dynamic replenishment suggestions, delivery cycle and material delay probability, and trigger automatic replenishment instructions; User profiling module: connected to the data acquisition module, used to build user profiles based on user behavior data, generate personalized coupon strategies based on collaborative filtering algorithms, and update the user profiles in real time; Work order management module: used to dynamically match work orders with customer service representatives based on a multi-attribute decision algorithm. The attributes include customer service representative professional skills, real-time load, and historical processing efficiency. It tracks the status of work orders and feeds back the processing results to the user profile module. Quality Assurance Management Module: Used to store quality assurance information, construction time, material batches, and technician ID data. Based on blockchain technology, it ensures the immutability and traceability of the data.

9. The intelligent management system for an online shopping mall platform according to claim 8, characterized in that, The system also includes: Virtual color try-on module: Integrates AR augmented reality technology, supports users to upload vehicle photos and simulate the effect of color change film, and collects color try-on interaction data, and optimizes the recommendation priority of popular colors through clustering algorithms; Sensitive message monitoring module: It uses a natural language processing model to analyze work orders and chat records in real time, identify sensitive keywords and customer sentiments, and trigger risk warnings through anomaly detection algorithms.

Images