一种面向磨矿过程溢流浓度的模型训练方法、装置、设备及介质
By constructing labeled and unlabeled datasets and generating pseudo-labels to expand the training set, a semi-supervised learning strategy is used to solve the problem of time-consuming and labor-intensive traditional supervised learning methods, thereby improving the efficiency and performance of model training.
CN120670852BActive Publication Date: 2026-07-17NORTH MINE ZHIYUN TECH (BEIJING) CO LTD +1
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- NORTH MINE ZHIYUN TECH (BEIJING) CO LTD
- Filing Date
- 2025-06-18
- Publication Date
- 2026-07-17
Smart Images

Figure CN120670852B_ABST
Abstract
本申请提供了一种面向磨矿过程溢流浓度的模型训练方法、装置、设备及介质,其中,基于各标记数据的输入变量和输出变量以及各未标记数据的输入变量构建标记数据集和未标记数据集;基于所述标记数据集和所述未标记数据集构建候选列表;利用所述标记数据集对第一初始模型进行训练得到第一目标模型,利用所述候选列表对所述未标记数据集进行扩充得到目标数据集;利用所述第一目标模型确定出所述目标数据集中各目标数据的第一伪标签,根据各目标数据的第一伪标签构建扩展训练集;利用所述扩展训练集对第二初始模型进行训练得到第二目标模型。采用上述方法,以减少模型训练所需耗费的时间和资源,提高模型训练的效率。
Need to check novelty before this filing date? Find Prior Art