Technology Radar
Published : Apr 03, 2024
NOT ON THE CURRENT EDITION
This blip is not on the current edition of the Radar. If it was on one of the last few editions, it is likely that it is still relevant. If the blip is older, it might no longer be relevant and our assessment might be different today. Unfortunately, we simply don't have the bandwidth to continuously review blips from previous editions of the Radar.
Understand more
Apr 2024
Assess
由大语言模型（LLMs）支持的聊天机器人正变得非常流行，我们看到围绕这些机器人的产品化和生产化都涌现出了许多新技术。其中一个产品化挑战是理解用户如何与这类聊天机器人展开交流，毕竟这种对话有多个发展方向。了解对话流的实际情况对于改进产品和提高转化率至关重要。有一种技术对解决这一问题大有裨益，就是 对LLM对话进行图分析（graph analysis for LLM-backed chats） 。那些支持特定期望结果的聊天代理 — 如购物行为或成功解决客户问题 — 通常可以表示为一个期望的状态机。通过将所有对话加载到一个场景中，你可以分析它实际所处的模式，并寻找与预期状态机的偏差。这有助于发现错误和进行产品改进。
