gpt4 book ai didi

search - 有关搜索结果的Elasticsearch相关性的问题

转载 作者:行者123 更新时间:2023-12-02 22:49:18 25 4
gpt4 key购买 nike

我正在尝试使用Elasticsearch for Chinese实现一个简单的演示。
但是,有关搜索结果的相关性存在一些问题。

我使用映射创建了一个新索引:

{
"tag": {
"mappings": {
"tag": {
"properties": {
"name": {
"type": "text",
"analyzer": "standard"
},
"note": {
"type": "text",
"analyzer": "standard"
},
"status": {
"type": "integer"
},
"synonyms": {
"type": "text",
"analyzer": "standard"
}
}
}
}
}
}

以及带有查询“美国”的请求正文:
{
"query" : {
"bool" : {
"must" : {
"multi_match" : {
"query" : "美国",
"fields" : [ "name", "synonyms" ]
}
},
"filter" : {
"term" : {
"status" : 2
}
}
}
}
}

有两个与查询匹配的记录“中国”和“美国”。但是唱片“中国”的得分更高。响应JSON如下:
{
"took": 2,
"timed_out": false,
"_shards": {
"total": 5,
"successful": 5,
"failed": 0
},
"hits": {
"total": 2,
"max_score": 0.7373906,
"hits": [ {
"_index": "tag",
"_type": "tag",
"_id": "5482361185636870",
"_score": 0.7373906,
"_source": {
"status": 2,
"name": "中国",
"note": "",
"synonyms": []
}
}, {
"_index": "tag",
"_type": "tag",
"_id": "5474649504748034",
"_score": 0.53484553,
"_source": {
"status": 2,
"name": "美国",
"note": "",
"synonyms": []
}
} ]
}
}

“中国”的记录为0.7373906,而“美国”的记录仅为0.53484553。

结果说明:
{
"hits": [
{
"_shard": "[tag][0]",
"_node": "Wh9qH0bcTAaVNrsP1Aiyxg",
"_index": "tag",
"_type": "tag",
"_id": "5482361185636870",
"_score": 0.7373906,
"_source": {
"status": 2,
"name": "中国",
"note": "",
"synonyms": []
},
"_explanation": {
"value": 0.73739064,
"description": "sum of:",
"details": [
{
"value": 0.73739064,
"description": "sum of:",
"details": [
{
"value": 0.73739064,
"description": "max of:",
"details": [
{
"value": 0.73739064,
"description": "sum of:",
"details": [
{
"value": 0.73739064,
"description": "weight(name:国 in 0) [PerFieldSimilarity], result of:",
"details": [
{
"value": 0.73739064,
"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": 1.0638298,
"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": 2.56,
"description": "fieldLength",
"details": []
}
]
}
]
}
]
}
]
}
]
},
{
"value": 0,
"description": "match on required clause, product of:",
"details": [
{
"value": 0,
"description": "# clause",
"details": []
},
{
"value": 1,
"description": "status:[2 TO 2], product of:",
"details": [
{
"value": 1,
"description": "boost",
"details": []
},
{
"value": 1,
"description": "queryNorm",
"details": []
}
]
}
]
}
]
},
{
"value": 0,
"description": "match on required clause, product of:",
"details": [
{
"value": 0,
"description": "# clause",
"details": []
},
{
"value": 1,
"description": "*:*, product of:",
"details": [
{
"value": 1,
"description": "boost",
"details": []
},
{
"value": 1,
"description": "queryNorm",
"details": []
}
]
}
]
}
]
}
},
{
"_shard": "[tag][4]",
"_node": "Wh9qH0bcTAaVNrsP1Aiyxg",
"_index": "tag",
"_type": "tag",
"_id": "5474649504748034",
"_score": 0.51623213,
"_source": {
"status": 2,
"name": "美国",
"note": "",
"synonyms": []
},
"_explanation": {
"value": 0.51623213,
"description": "sum of:",
"details": [
{
"value": 0.51623213,
"description": "sum of:",
"details": [
{
"value": 0.51623213,
"description": "max of:",
"details": [
{
"value": 0.51623213,
"description": "sum of:",
"details": [
{
"value": 0.25811607,
"description": "weight(name:美 in 0) [PerFieldSimilarity], result of:",
"details": [
{
"value": 0.25811607,
"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": 0.89722675,
"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": 2.56,
"description": "fieldLength",
"details": []
}
]
}
]
}
]
},
{
"value": 0.25811607,
"description": "weight(name:国 in 0) [PerFieldSimilarity], result of:",
"details": [
{
"value": 0.25811607,
"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": 0.89722675,
"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": 2.56,
"description": "fieldLength",
"details": []
}
]
}
]
}
]
}
]
}
]
},
{
"value": 0,
"description": "match on required clause, product of:",
"details": [
{
"value": 0,
"description": "# clause",
"details": []
},
{
"value": 1,
"description": "status:[2 TO 2], product of:",
"details": [
{
"value": 1,
"description": "boost",
"details": []
},
{
"value": 1,
"description": "queryNorm",
"details": []
}
]
}
]
}
]
},
{
"value": 0,
"description": "match on required clause, product of:",
"details": [
{
"value": 0,
"description": "# clause",
"details": []
},
{
"value": 1,
"description": "*:*, product of:",
"details": [
{
"value": 1,
"description": "boost",
"details": []
},
{
"value": 1,
"description": "queryNorm",
"details": []
}
]
}
]
}
]
}
}
]
}

最佳答案

您的索引似乎只包含几个文档,它们属于不同的碎片。每个shrad都有其自己的术语频率。默认情况下,ElasticSearch使用这些本地值。但是您可以通过指定search_type=dfs_query_then_fetch querystring参数来更改此行为,或添加类似这样的正文字段

{
"search_type": "dfs_query_then_fetch",
"query": {
"bool": {
"must": {
"multi_match": {
"query": "美国",
"fields": [
"name",
"synonyms"
]
}
},
"filter": {
"term": {
"status": 2
}
}
}
}
}

看看这篇文章 https://www.elastic.co/blog/understanding-query-then-fetch-vs-dfs-query-then-fetch

关于search - 有关搜索结果的Elasticsearch相关性的问题,我们在Stack Overflow上找到一个类似的问题: https://stackoverflow.com/questions/43332039/

25 4 0
Copyright 2021 - 2024 cfsdn All Rights Reserved 蜀ICP备2022000587号
广告合作:1813099741@qq.com 6ren.com