利索-全球专利检索

  1. 登录
  2. 注册
发明公开
CN109993559A 模型训练方法和系统 无效 - 驳回

模型训练方法和系统
摘要：
本公开提供了一种模型训练方法，包括：获取至少一组数据，所述一组数据中包括媒体数据、广告数据、场景数据、用户数据中的至少一种数据；基于所述至少一组数据确定多个特征；根据所述至少一组数据计算所述多个特征的重要度，确定所述多个特征中的至少一个特征作为模型特征；使用所述至少一组数据中关于所述至少一个模型特征的相关数据训练至少一个模型。
摘要（英）：

The invention provides a model training method which comprises the steps that at least one group of data is acquired, and the group of data comprises at least one of media data, advertisement data, scene data and user data; a plurality of features are determined based on the at least one set of data; importance degrees of the plurality of features are calculated according to the at least one groupof data, and at least one feature is determined in the plurality of features as a model feature; at least one model is trained using relevant data about the at least one model feature in the at leastone set of data.

0/0