Verified80% confidenceFactExact time
余弦相似度是衡量两个向量方向接近程度的指标，值域在-1到1之间，越接近1表示语义越相似
7
Sources
80%
Confidence
Long-term
Relevance
7/13/2026
First Seen
Sources
零基础理解RAG：检索增强生成原理与应用场景详解
Related Claims
UnverifiedSemantic matching is based on the semantic vector representation of text and uses metrics such as cosine similarity to determine the degree of semantic proximity.74% similarUnverifiedSemantic retrieval is based on mathematical metrics such as cosine similarity rather than simple keyword matching.73% similarUnverifiedSynonym normalization can be achieved by using sentence embedding models such as Sentence-BERT to map words into dense vectors, and then computing semantic proximity via cosine similarity.67% similarUnverified嵌入相似度方案将请求编码为向量后与预定义类别的代表向量计算余弦相似度，延迟约10-50毫秒，准确率中等66% similarUnverified向量化通常将文本映射为 768 维或 1536 维的浮点数向量，相似度检索采用余弦相似度或近似最近邻算法如 HNSW、IVF-PQ64% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/502201API
curl https://kongchang.com/api/v1/knowledge/claims/502201MCP
get_claim(id=502201)