微型电脑应用

由于用户行为数据量较大，并且具有实时性特征，因此当用户特征数据变化时，相应的用户兴趣标签同样会发生变化，进而影响标签权重，要想获取准确的用户分类识别结果，需要充分考虑上述因素。为了提升用户分类识别效果，提出一种基于画像标签特征重构与朴素贝叶斯算法的潜在用户递归分类识别方法。采用朴素贝叶斯算法改进逻辑递归分类结果，对潜在用户进行递归分类，计算最大后验概率，获取用户所属最佳类别。针对分类后的结果构建用户画像模型，并通过画像标签特征重构方法修改用户的兴趣标签及权重，完成潜在用户画像标签特征重构，实现潜在用户递归分类识别。实验结果表明，在准确率、召回率与F₁值方面，所提出的方法的优势十分明显，AUC值也保持在较高水平，说明所提出的方法的分类识别效果能够满足高精度需求。

Due to user behavior data have large amount and real-time feature,when the user feature data change,the corresponding user interest label will also change,which affects the label weight.To obtain accurate user classification and recognition results,it is necessary to fully consider the above factors.In order to improve the effectiveness of user classification and recognition,a recursive classification and recognition method for potential users based on image label feature reconstruction and naive Bayesian algorithm is proposed.The naive Bayesian algorithm is used to improve logical recursive classification results,potential users are recursively classified,and the maximum posterior probability is calculated to obtain the best category of users.A user image model is constructed based on the classification results,and the user's interest label and their weight are modified through the image label feature reconstruction algorithm,the feature reconstruction of potential user image label is completed,recursive classification and recognition of potential users are achieved.The experimental results show that the proposed method has significant advantages in terms of accuracy,recall,and F₁ value,and the AUC value remains at a high level,indicating that the classification and recognition results of the proposed method can meet the requirements of high accuracy.