Unverified50% confidenceFactExact time
注意力机制计算当前token与历史token相关性的时间复杂度为O(n²)
1
Sources
50%
Confidence
Long-term
Relevance
7/11/2026
First Seen
Sources
Related Claims
Unverified注意力机制计算当前 token 与所有历史 token 相关性的时间复杂度为 O(n²)，其中 n 为序列长度84% similarUnverifiedThe memory retrieval of Generative Agents extracts key memories based on importance, recency, and relevance scores.65% similarUnverified胡塞尔在《内在时间意识现象学》中将意识时间流分为原印象、滞留与前摄三个共时维度62% similarUnverified记忆增强型智能体通过持续读取用户历史交互数据来识别高频关注点，技术实现通常需对原始对话数据做向量化处理再通过相似度检索或关键词抽取筛选62% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/488191API
curl https://kongchang.com/api/v1/knowledge/claims/488191MCP
get_claim(id=488191)