公开(公告)号：US20250013658A1

公开(公告)日：2025-01-09

申请号：US18749131

申请日：2024-06-20

Applicant: Beijing Baidu Netcom Science Technology Co., Ltd.

Inventor： Weixu CHEN ,  Li LI ,  Qing YE

IPC: G06F16/25

Abstract: A method for storing data and a method for processing data, for a large model scenario, and corresponding apparatus are provided, relating to the field of artificial intelligence such as data processing, data storage, cloud platforms, cloud services, deep learning, large models, and large language models. An implementation of the method includes: in response to receiving to-be-stored data to be stored into a target data lake, detecting a data type of the to-be-stored data; in response to the data type of the to-be-stored data being an unstructured data type, generating a feature vector of the to-be-stored data; and storing the feature vector, as a substitute of the to-be-stored data, into the target data lake.