1、算法介绍
relevance score算法，简单来说，就是计算出，一个索引中的文本，与搜索文本，他们之间的关联匹配程度
Elasticsearch使用的是 term frequency/inverse document frequency算法，简称为TF/IDF算法
1)Term frequency：搜索文本中的各个词条在field文本中出现了多少次，出现次数越多，就越相关
搜索请求：hello world
doc1：hello you, and world is very good doc2：hello, how are you
doc1更相关
2)Inverse document frequency：搜索文本中的各个词条在整个索引的所有文档中出现了多少次，出现的次数越多，就越不相关
搜索请求：hello world
doc1：hello, today is very good doc2：hi world, how are you
比如说，在index中有1万条document，hello这个单词在所有的document中，一共出现了1000次；world这个单词在所有的document中，一共出现了100次
doc2更相关
3)Field-length norm：field长度，field越长，相关度越弱
搜索请求：hello world
doc1：{ “title”: “hello article”, “content”: “babaaba 1万个单词” } doc2：{ “title”: “my article”, “content”: “blablabala 1万个单词，hi world” }
hello world在整个index中出现的次数是一样多的，但是doc1的hello是在title中，doc2的world是在content中。
doc1更相关，title field比content field短
2、_score是如何被计算出来的GET /test_index/test_type/_search?explain
{
"query": {
"match": {
"test_field": "test hello"
}
}
}
响应结果
{
"took": 195,
"timed_out": false,
"_shards": {
"total": 5,
"successful": 5,
"skipped": 0,
"failed": 0
},
"hits": {
"total": 3,
"max_score": 0.8835016,
"hits": [
{
"_shard": "[test_index][2]",
"_node": "x0QR1D02RkmUyQw6uG_ayQ",
"_index": "test_index",
"_type": "test_type",
"_id": "6",
"_score": 0.8835016,
"_source": {
"test_field": "test test"
},
"_explanation": {
"value": 0.8835016,
"description": "sum of:",
"details": [
{
"value": 0.8835016,
"description": "weight(test_field:test in 0) [PerFieldSimilarity], result of:",
"details": [
{
"value": 0.8835016,
"description": "score(doc=0,freq=2.0 = termFreq=2.0\n), product of:",
"details": [
{
"value": 0.6931472,
"description": "idf, computed as log(1 + (docCount - docFreq + 0.5) / (docFreq + 0.5)) from:",
"details": [
{
"value": 1,
"description": "docFreq",
"details": []
},
{
"value": 2,
"description": "docCount",
"details": []
}
]
},
{
"value": 1.2746234,
"description": "tfNorm, computed as (freq * (k1 + 1)) / (freq + k1 * (1 - b + b * fieldLength / avgFieldLength)) from:",
"details": [
{
"value": 2,
"description": "termFreq=2.0",
"details": []
},
{
"value": 1.2,
"description": "parameter k1",
"details": []
},
{
"value": 0.75,
"description": "parameter b",
"details": []
},
{
"value": 2,
"description": "avgFieldLength",
"details": []
},
{
"value": 2.56,
"description": "fieldLength",
"details": []
}
]
}
]
}
]
}
]
}
},
{
"_shard": "[test_index][1]",
"_node": "x0QR1D02RkmUyQw6uG_ayQ",
"_index": "test_index",
"_type": "test_type",
"_id": "8",
"_score": 0.49191087,
"_source": {
"test_field": "test client 2"
},
"_explanation": {
"value": 0.49191087,
"description": "sum of:",
"details": [
{
"value": 0.49191087,
"description": "weight(test_field:test in 0) [PerFieldSimilarity], result of:",
"details": [
{
"value": 0.49191087,
"description": "score(doc=0,freq=1.0 = termFreq=1.0\n), product of:",
"details": [
{
"value": 0.6931472,
"description": "idf, computed as log(1 + (docCount - docFreq + 0.5) / (docFreq + 0.5)) from:",
"details": [
{
"value": 1,
"description": "docFreq",
"details": []
},
{
"value": 2,
"description": "docCount",
"details": []
}
]
},
{
"value": 0.7096774,
"description": "tfNorm, computed as (freq * (k1 + 1)) / (freq + k1 * (1 - b + b * fieldLength / avgFieldLength)) from:",
"details": [
{
"value": 1,
"description": "termFreq=1.0",
"details": []
},
{
"value": 1.2,
"description": "parameter k1",
"details": []
},
{
"value": 0.75,
"description": "parameter b",
"details": []
},
{
"value": 2,
"description": "avgFieldLength",
"details": []
},
{
"value": 4,
"description": "fieldLength",
"details": []
}
]
}
]
}
]
}
]
}
},
{
"_shard": "[test_index][3]",
"_node": "x0QR1D02RkmUyQw6uG_ayQ",
"_index": "test_index",
"_type": "test_type",
"_id": "7",
"_score": 0.25316024,
"_source": {
"test_field": "test client 2"
},
"_explanation": {
"value": 0.25316024,
"description": "sum of:",
"details": [
{
"value": 0.25316024,
"description": "weight(test_field:test in 0) [PerFieldSimilarity], result of:",
"details": [
{
"value": 0.25316024,
"description": "score(doc=0,freq=1.0 = termFreq=1.0\n), product of:",
"details": [
{
"value": 0.2876821,
"description": "idf, computed as log(1 + (docCount - docFreq + 0.5) / (docFreq + 0.5)) from:",
"details": [
{
"value": 1,
"description": "docFreq",
"details": []
},
{
"value": 1,
"description": "docCount",
"details": []
}
]
},
{
"value": 0.88,
"description": "tfNorm, computed as (freq * (k1 + 1)) / (freq + k1 * (1 - b + b * fieldLength / avgFieldLength)) from:",
"details": [
{
"value": 1,
"description": "termFreq=1.0",
"details": []
},
{
"value": 1.2,
"description": "parameter k1",
"details": []
},
{
"value": 0.75,
"description": "parameter b",
"details": []
},
{
"value": 3,
"description": "avgFieldLength",
"details": []
},
{
"value": 4,
"description": "fieldLength",
"details": []
}
]
}
]
}
]
}
]
}
}
]
}
}
GET /test_index/test_type/6/_explain
{
"query": {
"match": {
"test_field": "test hello"
}
}
}
响应结果
{
"_index": "test_index",
"_type": "test_type",
"_id": "7",
"matched": true,
"explanation": {
"value": 0.25316024,
"description": "sum of:",
"details": [
{
"value": 0.25316024,
"description": "weight(test_field:test in 0) [PerFieldSimilarity], result of:",
"details": [
{
"value": 0.25316024,
"description": "score(doc=0,freq=1.0 = termFreq=1.0\n), product of:",
"details": [
{
"value": 0.2876821,
"description": "idf, computed as log(1 + (docCount - docFreq + 0.5) / (docFreq + 0.5)) from:",
"details": [
{
"value": 1,
"description": "docFreq",
"details": []
},
{
"value": 1,
"description": "docCount",
"details": []
}
]
},
{
"value": 0.88,
"description": "tfNorm, computed as (freq * (k1 + 1)) / (freq + k1 * (1 - b + b * fieldLength / avgFieldLength)) from:",
"details": [
{
"value": 1,
"description": "termFreq=1.0",
"details": []
},
{
"value": 1.2,
"description": "parameter k1",
"details": []
},
{
"value": 0.75,
"description": "parameter b",
"details": []
},
{
"value": 3,
"description": "avgFieldLength",
"details": []
},
{
"value": 4,
"description": "fieldLength",
"details": []
}
]
}
]
}
]
}
]
}
}
