Article recommendation method and device based on user feedback and electronic equipment

• Main Authors: ZHENG JIANCHANG, WANG HONGJUAN
• Format: Patent
• Language: Chinese; English
• Published: 09.12.2022
• Subjects: CALCULATING; COMPUTING; COUNTING; DATA PROCESSING SYSTEMS OR METHODS, SPECIALLY ADAPTED FORADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORYOR FORECASTING PURPOSES; PHYSICS; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE,COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORY OR FORECASTINGPURPOSES, NOT OTHERWISE PROVIDED FOR

The invention provides an article recommendation method and device based on user feedback and electronic equipment, and relates to the technical field of computer recommendation, and the method comprises the steps: determining the weight of each implicit feedback behavior and the weighted implicit score of a target article based on implicit feedback data obtained in advance; the implicit feedback behaviors comprise searching, browsing, collecting, purchasing and purchasing; determining a prediction score matrix according to the weighted implicit score and a pre-acquired explicit score; according to the method, the problem that in the prior art, the recommendation accuracy is low can be relieved, and the effect of improving the item recommendation accuracy is achieved. 本发明提供了一种基于用户反馈的物品推荐方法、装置和电子设备，涉及计算机推荐技术领域，该方法包括：基于预先获取的隐式反馈数据确定每种隐式反馈行为的权重以及目标物品的加权隐式评分；隐式反馈行为包括：搜索、浏览、收藏、加购和购买；根据加权隐式评分和预先获取的显式评分，确定预测评分矩阵；基于预测评分矩阵向用户进行物品推荐，通过上述方法可以缓解现有技术中存在的推荐准确度较低的问题，实现了提高物品推荐准确的效果。