基于TFIDF算法的家庭关系识别模型构建及其应用

STUDY ON CONSTRUCTION AND APPLICATION OF THE FAMILY RELATIONSHIP RECOGNITION MODEL BASED ON THE TFIDF ALGORITHM

基于TFIDF(Term Frequency Inverse Document Frequency)算法,结合用户通话圈运用呼叫指纹方法分析用户的交往圈、呼叫特征、短信特征、位置特征、客服特征、终端特征等特征,构建家庭关系识别模型,进而挖掘家庭关联关系的手机与固话在呼叫圈相似度、平均每天通话次数、平均每次通话时长等变量上的相关性,为发现手机号码与家庭固定电话之间的关联关系提供了有效的技术手段,并有效地应用于固移捆绑套餐和可选套餐的目标客户的识别。从实际营销效果来看,该模型的使用有利于帮助市场营销人员快速、方便、有效地开展融合套餐的销售,在降低营销成本的同时提高了营销效果。

We construct the family relationship recognition model based on the TFIDF algorithm, which would be used to characterize the distinctive features of contacts circle, call, SMS, site, customer service and terminal based on the fingerprint method. Furthermore, the recognition model provides an effective technology to discover the relationship between cell phone and domestic telephone, such as the similarity of call behavior, the average number of calls behavior per day, the average time of calls behavior per turn, which could be used to recognition the bundled packages and optional packages of target customer. The actual marketing effect shows that the model can be used to help marketers to promote the combination the package sales, which reduce marketing costs and increase the marketing effect.