Design And Implementation Of Personalized Shopping WeChat Applets Based On Micro Services

With the rapid growth of mobile phone users and the rapid improvement of mobile phone performance in China,most users tend to use mobile phones for shopping.The functional requirements of the shopping system are constantly increasing,and its complexity is also increasing.The old monolithic architecture is not enough to deal with frequent changes in the shopping system.Therefore,there is an urgent need for a flexible and flexible architecture that is easy to extend and maintain.The microservice architecture was born in this context.The microservice architecture is highly available,fast to deploy,and easy to scale and maintain.Personalized shopping based on microservices WeChat Mini Program is a personalized shopping system built with a microservices architecture.The functional modules of the shopping system are divided into user modules,product modules,and order modules.These small functional modules are independently deployed and independent of each other.,By calling the API interface of other modules to achieve their own functions.The main functions of the user module include user registration,account management,refunds,and shopping carts.The main functions of the product module include personalized recommendations,product search,and product management.Due to the small screen of the mobile phone,personalized recommendation is particularly important.It can help users find the products they need in a limited screen,and it can also give users a pleasant surprise.The personalized recommendation function is to extract the user's feature matrix based on the user's use history,use the least squares(ALS)method to decompose the user's feature vector and the product feature vector,and then use the modified cosine similarity to calculate the similarity of the product.The weighted sum formula calculates the recommendation coefficient of the product to be recommended,and generates a recommendation list according to the recommendation coefficient.Product search mainly provides users with a way to actively find products,integrates Elastic Search into the system,uses the API provided by Elastic Search to complete searches,and then enters the results of product search into the personalized recommendation algorithm as products to be predicted,based on the analyzed results.The user feature vector calculates a recommendation coefficient for the searched product,sorts the searched product according to the size of the recommendation coefficient,and displays it on a page by page.The main functions of the order module include placing orders,querying orders,deleting orders,and canceling orders.Personalized WeChat mini-programs based on WeChat services take advantage of the fact that WeChat Mini-programs do not need to be downloaded,providing users with a more convenient and quick way to shop.In addition,the system adopts a distributed deployment method,and uses a load balancing server to distribute requests to ensure high concurrency and scalability of the system.The personalized recommendation function can improve the platform's revenue and user experience,and can well meet the needs of current users and merchants.