{"title":"基于上下文感知特征交互的推荐系统","authors":"Pengcheng Ma, Qian Gao, Jun Fan","doi":"10.1109/IRC.2020.00092","DOIUrl":null,"url":null,"abstract":"Additional context information has strong support for all kinds of recommendation systems, so context aware recommendation systems have been widely concerned in recent years. The existing mainstream context aware recommendation model adopts the neural network method, which combines the user's long-term and short-term preferences with the input query to carry out personalized product recommendation.Based on the matrix factorization model, this paper proposes a new interaction mode network model, which consists of three modules: context user / item interaction module, attention mechanism module and context environment overall role module. In this model, we use bilinear function to establish the interaction between context and user / item, and add attention mechanism to distinguish the importance of different context information. Finally, we add user score bias and item score bias which are changed by context environment to the traditional matrix factorization method. Combined with the above methods, we set up a matrix factorization recommendation model based on context aware feature interaction, named “feature interactive network model” (FINM). Through experiments on data sets, it is shown that the algorithm proposed in this paper is superior to the general recommendation algorithm.","PeriodicalId":232817,"journal":{"name":"2020 Fourth IEEE International Conference on Robotic Computing (IRC)","volume":"227 2","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2020-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Context Aware Feature Interaction based Recommendation System\",\"authors\":\"Pengcheng Ma, Qian Gao, Jun Fan\",\"doi\":\"10.1109/IRC.2020.00092\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Additional context information has strong support for all kinds of recommendation systems, so context aware recommendation systems have been widely concerned in recent years. The existing mainstream context aware recommendation model adopts the neural network method, which combines the user's long-term and short-term preferences with the input query to carry out personalized product recommendation.Based on the matrix factorization model, this paper proposes a new interaction mode network model, which consists of three modules: context user / item interaction module, attention mechanism module and context environment overall role module. In this model, we use bilinear function to establish the interaction between context and user / item, and add attention mechanism to distinguish the importance of different context information. Finally, we add user score bias and item score bias which are changed by context environment to the traditional matrix factorization method. Combined with the above methods, we set up a matrix factorization recommendation model based on context aware feature interaction, named “feature interactive network model” (FINM). Through experiments on data sets, it is shown that the algorithm proposed in this paper is superior to the general recommendation algorithm.\",\"PeriodicalId\":232817,\"journal\":{\"name\":\"2020 Fourth IEEE International Conference on Robotic Computing (IRC)\",\"volume\":\"227 2\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2020-11-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2020 Fourth IEEE International Conference on Robotic Computing (IRC)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/IRC.2020.00092\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2020 Fourth IEEE International Conference on Robotic Computing (IRC)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/IRC.2020.00092","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Context Aware Feature Interaction based Recommendation System
Additional context information has strong support for all kinds of recommendation systems, so context aware recommendation systems have been widely concerned in recent years. The existing mainstream context aware recommendation model adopts the neural network method, which combines the user's long-term and short-term preferences with the input query to carry out personalized product recommendation.Based on the matrix factorization model, this paper proposes a new interaction mode network model, which consists of three modules: context user / item interaction module, attention mechanism module and context environment overall role module. In this model, we use bilinear function to establish the interaction between context and user / item, and add attention mechanism to distinguish the importance of different context information. Finally, we add user score bias and item score bias which are changed by context environment to the traditional matrix factorization method. Combined with the above methods, we set up a matrix factorization recommendation model based on context aware feature interaction, named “feature interactive network model” (FINM). Through experiments on data sets, it is shown that the algorithm proposed in this paper is superior to the general recommendation algorithm.