- 专利标题: Observation-based training of artificial intelligence character models
-
申请号: US18530245申请日: 2023-12-06
-
公开(公告)号: US11954451B1公开(公告)日: 2024-04-09
- 发明人: Ilya Gelfenbeyn , Mikhail Ermolenko , Kylan Gibbs
- 申请人: Theai, Inc.
- 申请人地址: US CA Mountain View
- 专利权人: Theai, Inc.
- 当前专利权人: Theai, Inc.
- 当前专利权人地址: US CA Mountain View
- 代理商 Georgiy L. Khayet
- 主分类号: G10L15/22
- IPC分类号: G10L15/22 ; G06F40/40 ; G06N20/00
摘要:
Systems and methods for observation-based training of an Artificial Intelligence (AI) character model are provided. An example method includes receiving log data including interactions of a user and a first AI character model, receiving internal parameters of a second AI character model including a first plurality of heuristic machine learning models and a second plurality of primary machine learning models, pre-processing the log data to obtain one or more data streams including behavioral characteristics of the user, running the one or more data streams through the first plurality of heuristic machine learning models to produce intermediate outputs, composing the intermediate outputs into templated formats, and providing the templated formats to the second plurality of primary machine learning models. The internal parameters of the second AI character model are adjusted based on the templated formats such that the second AI character model mimics the behavioral characteristics of the user.
公开/授权文献
信息查询