首页> 外国专利> ANTICIPATORY LEARNING METHOD AND SYSTEM ORIENTED TOWARDS SHORT-TERM TIME SERIES PREDICTION

ANTICIPATORY LEARNING METHOD AND SYSTEM ORIENTED TOWARDS SHORT-TERM TIME SERIES PREDICTION

机译:以短期时间序列预测导向的预期学习方法和系统

摘要

Disclosed are an anticipatory learning method and system oriented towards short-term time-series prediction, which solves the problem of predicting a short-term high-dimensional time series, and achieves the precise multi-step prediction of short-term high-dimensional data. The technical solution therefor is: selecting a variable used for prediction from among time-series data; on the basis of two trained neural network models, performing anticipatory learning oriented towards short-term time-series prediction, and finally outputting a portion of the selected prediction variable that needs to be predicted.
机译:公开了一种预期的学习方法和系统以短期时间序列预测导向,其解决了预测短期高维时间序列的问题,并实现了短期高维数据的精确多步预测。其中技术解决方案是:选择用于从时序数据中预测的变量;在两个训练有素的神经网络模型的基础上,对短期时间序列预测进行预期学习,并且最终输出需要预测的选定预测变量的一部分。

著录项

相似文献

  • 专利
  • 外文文献
  • 中文文献
获取专利

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号