Movement prediction method, intelligent terminal and storage medium

Abstract

The invention discloses a movement prediction method, an intelligent terminal and a storage medium, and the method comprises the steps: obtaining newly-added movement data and historical movement data, carrying out the clustering of the newly-added movement data and the historical movement data, and generating a corresponding newly-added region of interest; when the similarity value between the newly added region of interest and a preset historical region of interest conforms to a preset similarity rule, updating the historical mobile data according to the newly added mobile data to obtain updated mobile data; training a preset initial movement prediction model according to the updated movement data to generate a target movement prediction model; and when a to-be-predicted specified momentis detected, inputting the specified moment into the target movement prediction model, generating a target area corresponding to the specified moment, and outputting the target area. When movement prediction is carried out, the region of interest is updated in real time in combination with new and old data, so that the accuracy of a subsequent prediction result is improved. 本发明公开了一种移动预测方法、智能终端及存储介质，所述方法包括：获取新增移动数据和历史移动数据，并对所述新增移动数据和所述历史移动数据进行聚类处理，生成对应的新增兴趣区域；当所述新增兴趣区域与预设的历史兴趣区域之间的相似度值符合预设的相似度规则时，根据所述新增移动数据，对所述历史移动数据进行更新，得到更新移动数据；根据所述更新移动数据，对预设的初始移动预测模型进行训练，生成目标移动预测模型；当检测到待预测的指定时刻时，将所述指定时刻输入所述目标移动预测模型中，生成所述指定时刻对应的目标区域并输出。本发明在进行移动预测时，结合新旧数据，对兴趣区域进行实时更新，以提高后续预测结果的准确性。