我的目标是编写一个查询,该查询将根据文档中字段的值重新排列文档.为了实现这一点,我使用了rescore查询,然后对结果进行排序.但是,对查询的解释显示,文档的排序是基于先前计算的分数而不是新分数完成的.
我看到以下内容解释了我无法使用rescore和排序.
“有时我们想要显示结果,其中页面上第一个文档的排序受到附加规则的影响.不幸的是,这不能通过rescore功能实现.第一个想法指向window_size参数,但实际上这个参数不是与结果列表中的第一个文档相关联,但每个分片上返回的结果数量.另外window_size不能小于页面大小.(如果它更少,ElasticSearch默默使用页面大小).另外,一个非常重要的事情 – 重新考虑不能与排序结合使用,因为排序是在重新安排引入的更改之后完成的.“
http://elasticsearchserverbook.com/elasticsearch-0-90-using-rescore/
我的查询是:
{
"query": {
"filtered": {
"query": {
"bool": {
"should": [
{
"constant_score": {
"query": {
"match": {
"question": {
"query": "diabetes"
}
}
},
"boost": 1
}
},
{
"dis_max": {
"queries": [
{
"constant_score": {
"query": {
"match": {
"question": {
"query": "diabetes"
}
}
},
"boost": 0.01
}
},
{
"constant_score": {
"query": {
"match": {
"answer_text": {
"query": "diabetes"
}
}
},
"boost": 0.0001
}
}
]
}
},
{
"dis_max": {
"queries": [
{
"constant_score": {
"query": {
"match_phrase": {
"question_phrase": {
"query": "what is diabetes",
"slop": 0
}
}
},
"boost": 100
}
},
{
"constant_score": {
"query": {
"match_phrase": {
"question_phrase": {
"query": "what is diabetes",
"slop": 1
}
}
},
"boost": 50
}
},
{
"constant_score": {
"query": {
"match_phrase": {
"question_phrase": {
"query": "what is diabetes",
"slop": 2
}
}
},
"boost": 33
}
},
{
"constant_score": {
"query": {
"match_phrase": {
"question_phrase": {
"query": "what is diabetes",
"slop": 3
}
}
},
"boost": 25
}
},
{
"constant_score": {
"query": {
"query_string": {
"default_field": "question_group_four",
"query": "what__is__diabetes"
}
},
"boost": 0.1
}
},
{
"constant_score": {
"query": {
"query_string": {
"default_field": "question_group_five",
"query": "what__is__diabetes"
}
},
"boost": 0.15
}
},
{
"constant_score": {
"query": {
"query_string": {
"default_field": "concept_words_no_synonyms_20",
"query": "what__is__diabetes"
}
},
"boost": 35
}
},
{
"constant_score": {
"query": {
"query_string": {
"default_field": "concept_words_no_synonyms_15",
"query": "what__is__diabetes"
}
},
"boost": 25
}
},
{
"constant_score": {
"query": {
"query_string": {
"default_field": "concept_words_no_synonyms_10",
"query": "what__is__diabetes"
}
},
"boost": 15
}
},
{
"constant_score": {
"query": {
"query_string": {
"default_field": "concept_words_20",
"query": "what__is__diabetes"
}
},
"boost": 28
}
},
{
"constant_score": {
"query": {
"query_string": {
"default_field": "concept_words_15",
"query": "what__is__diabetes"
}
},
"boost": 16
}
},
{
"constant_score": {
"query": {
"query_string": {
"default_field": "concept_words_10",
"query": "what__is__diabetes"
}
},
"boost": 13
}
},
{
"constant_score": {
"query": {
"query_string": {
"default_field": "concept_words_05",
"query": "what__is__diabetes"
}
},
"boost": 4
}
}
]
}
},
{
"dis_max": {
"queries": [
{
"constant_score": {
"query": {
"query_string": {
"default_field": "question_group_four",
"query": "diabetes"
}
},
"boost": 0.1
}
},
{
"constant_score": {
"query": {
"query_string": {
"default_field": "question_group_five",
"query": "diabetes"
}
},
"boost": 0.15
}
},
{
"constant_score": {
"query": {
"query_string": {
"default_field": "concept_words_no_synonyms_20",
"query": "diabetes"
}
},
"boost": 35
}
},
{
"constant_score": {
"query": {
"query_string": {
"default_field": "concept_words_no_synonyms_15",
"query": "diabetes"
}
},
"boost": 25
}
},
{
"constant_score": {
"query": {
"query_string": {
"default_field": "concept_words_no_synonyms_10",
"query": "diabetes"
}
},
"boost": 15
}
},
{
"constant_score": {
"query": {
"query_string": {
"default_field": "concept_words_20",
"query": "diabetes"
}
},
"boost": 28
}
},
{
"constant_score": {
"query": {
"query_string": {
"default_field": "concept_words_15",
"query": "diabetes"
}
},
"boost": 16
}
},
{
"constant_score": {
"query": {
"query_string": {
"default_field": "concept_words_10",
"query": "diabetes"
}
},
"boost": 13
}
},
{
"constant_score": {
"query": {
"query_string": {
"default_field": "concept_words_05",
"query": "diabetes"
}
},
"boost": 4
}
}
]
}
}
],
"disable_coord": true
}
},
"filter": {
"and": [
{
"term": {
"posted_by_expert": false
}
},
{
"term": {
"tip_question": false
}
},
{
"term": {
"show_in_work_queue": true
}
},
{
"range": {
"verified_answers_count": {
"gt": 0
}
}
}
]
}
}
},
"rescore": {
"window_size": 100,
"query": {
"rescore_query": {
"function_score": {
"functions": [
{
"script_score": {
"script": "_score * _source.concierge_boost"
}
}
]
}
}
}
},
"sort": [
"_score",
{
"count_words_with_high_concepts": {
"order": "asc"
}
},
{
"popularity": {
"order": "desc"
}
},
{
"length": {
"order": "asc"
}
}
],
"fields": [],
"size": 10,
"from": 0
}
任何帮助高度赞赏!
最佳答案 实际上,这是不可能的.
But this has been discussed并决定目前不值得实施.然而,关于github的讨论揭示了这方面的困难 – 需要对文档进行排序,选择前100(在您的情况下),然后应用rescore,然后再对它们进行排序.我建议阅读github问题中的评论,特别是来自simonw的评论.这个问题仍然是公开的,但似乎不会很快实施,如果它会的话.
关于你在另一个级别的评分后的排序,我理解只需要重新调整几个文档,但似乎是不可能的.如果您将查询包装在另一个function_score中,您可以在其中定义script_score函数来计算最终得分,该怎么办?像这样的东西:
{
"query": {
"function_score": {
"query": {
.......
},
"functions": [
{
"script_score": {
"script": "doc['concierge_boost'].value"
}
}
]
}
},
"sort": [
"_score",
{
"count_words_with_high_concepts": {
"order": "asc"
}
},
{
"popularity": {
"order": "desc"
}
},
{
"length": {
"order": "asc"
}
}
],
"fields": [],
"size": 10,
"from": 0
}