Simulation Modeling and Analysis of Ocean Transportation System under Sea Ice Condition
The traditional use of mobile phone for information query,restaurant ordering,commodity purchase need mobile phone download APP or iPad for the use of related functions,cumbersome process,occupy too much memory of the phone.In order to enable customers to easily and quickly obtain effective information from a large amount of data,the Mvc development mode and Node.js technolo-gy were adopted to design the wechat small program.The architecture of the wechat small program was mainly included interaction layer,data access layer,control layer and database layer.The product recommendation was carried out by combining user-based collaborative filtering recommendation algorithm and feature-based collaborative filtering recommendation algorithm.For the user-based algorithm,the IG feature selection algorithm was used to select the commodity features,and then the improved Pearson correlation coefficient was used for similarity calculation to obtain the recommended commodities.For the feature-based algorithm,the improved cosine similarity was used to calculate the user similarity,and products were recommended according to the similarity.Combine the recommended goods ac-cording the proportion,and finally carry out the product recommendation.In order to verify the performance of the wechat small program,the wechat recommendation small program operation test and commodity recommendation test were carried out.The test results show that all mobile terminals of wechat small program could operate normally,all function could be operated,and the effective information recom-mended to users meets the design requirements.
wechat small programcollaborative filtering algorithminformation gain characteristicscommodity characteristicsPear-son correlation
NETL
NSTL
万方数据
