微调

AI Center includes the capability of fine-tuning ML models using data that has been validated by a human using Validation Station.

当 RPA 工作流使用现有 ML 模型处理文档时，某些文档可能需要使用“呈现验证站点”活动（在有人值守机器人上或使用 Orchestrator Action Center 的浏览器中提供）进行人工验证。

The validated data generated in Validation Station can be exported using Machine Learning Extractor Trainer activity, and can be used to fine-tune ML models in AI Center.

我们不建议使用来自验证站点的数据从头开始训练 ML 模型（即 DocumentUnderstanding ML 包），而仅用于微调现有 ML 模型（包括开箱即用模型）。

For the detailed steps involved in fine-tuning an ML model see the Import Documents section of the Data Manager documentation.

For more details about how to build a dataset for fine-tuning, go here.

重要提示：

It if often wrongly assumed that the way to use Validation Station data is to iteratively retrain the previous model version, so the current batch is used to train package X.1 to obtain X.2. Then the next batch trains on X.2 to obtain X.3 and so on. This is the wrong way to use the product. Each Validation Station batch needs to be imported into the same Data Manager session as the original manually labeled data making a larger dataset, which must be used to train always on the X.0 ML Package version.