elasticsearch查询之keyword字段的查询相关度评分控制

一、数据情况

purchase记录每个用户的购买信息;

PUT purchase
{
    "mappings":{
        "properties":{
            "id":{
                "type":"keyword"
            },
            "name":{
                "type":"text"
            },
            "goods":{
                "properties":{
                    "id":{
                        "type":"keyword"
                    },
                    "name":{
                        "type":"text"
                    }
                }
            }
        }
    }
}

index 三个document

PUT purchase/_doc/1
{
  "id":1,
  "name":"sam",
  "goods":[
    {"id":"g1","name":"ipad"},
    {"id":"g2","name":"iphone"}
  ]
}


PUT purchase/_doc/2
{
  "id":2,
  "name":"coco",
  "goods":[
    {"id":"g1","name":"ipad"},
    {"id":"g2","name":"iphone"},
    {"id":"g3","name":"ipod"}
  ]
}


PUT purchase/_doc/3
{
  "id":3,
  "name":"jim",
  "goods":[
    {"id":"g1","name":"ipad"},
    {"id":"g2","name":"iphone"},
    {"id":"g3","name":"ipod"},
    {"id":"g4","name":"TV"}
  ]
}

查看索引数据情况

POST purchase/_search
{
  "query": {
    "match_all": {}
  }
}

{
    "took":331,
    "timed_out":false,
    "_shards":{
        "total":1,
        "successful":1,
        "skipped":0,
        "failed":0
    },
    "hits":{
        "total":{
            "value":3,
            "relation":"eq"
        },
        "max_score":1,
        "hits":[
            {
                "_index":"purchase",
                "_id":"1",
                "_score":1,
                "_source":{
                    "id":1,
                    "name":"sam",
                    "goods":[
                        {
                            "id":"g1",
                            "name":"ipad"
                        },
                        {
                            "id":"g2",
                            "name":"iphone"
                        }
                    ]
                }
            },
            {
                "_index":"purchase",
                "_id":"2",
                "_score":1,
                "_source":{
                    "id":2,
                    "name":"coco",
                    "goods":[
                        {
                            "id":"g1",
                            "name":"ipad"
                        },
                        {
                            "id":"g2",
                            "name":"iphone"
                        },
                        {
                            "id":"g3",
                            "name":"ipod"
                        }
                    ]
                }
            },
            {
                "_index":"purchase",
                "_id":"3",
                "_score":1,
                "_source":{
                    "id":3,
                    "name":"jim",
                    "goods":[
                        {
                            "id":"g1",
                            "name":"ipad"
                        },
                        {
                            "id":"g2",
                            "name":"iphone"
                        },
                        {
                            "id":"g3",
                            "name":"ipod"
                        },
                        {
                            "id":"g4",
                            "name":"TV"
                        }
                    ]
                }
            }
        ]
    }
}

二、查询需求

我们需要查询购买过某种商品的顾客,一般我们可以通过ui的业务逻辑得到需要筛选的一些商品的id,由于id字段是一个不需要分词的keyword字段,所以我们会直接使用term级别的查询;


POST purchase/_search
{
  "query": {
    "terms": {
      "goods.id": [
        "g2",
        "g3",
        "g4"
      ]
    }
  }
}

我们可以看到查询结果中的三条记录的权重打分都是1;正常情况下购买商品越多的客户,相对来说价值更大即命中的权重得分越大;

{
    "took":0,
    "timed_out":false,
    "_shards":{
        "total":1,
        "successful":1,
        "skipped":0,
        "failed":0
    },
    "hits":{
        "total":{
            "value":3,
            "relation":"eq"
        },
        "max_score":1,
        "hits":[
            {
                "_index":"purchase",
                "_id":"1",
                "_score":1,
                "_source":{
                    "id":1,
                    "name":"sam",
                    "goods":[
                        {
                            "id":"g1",
                            "name":"ipad"
                        },
                        {
                            "id":"g2",
                            "name":"iphone"
                        }
                    ]
                }
            },
            {
                "_index":"purchase",
                "_id":"2",
                "_score":1,
                "_source":{
                    "id":2,
                    "name":"coco",
                    "goods":[
                        {
                            "id":"g1",
                            "name":"ipad"
                        },
                        {
                            "id":"g2",
                            "name":"iphone"
                        },
                        {
                            "id":"g3",
                            "name":"ipod"
                        }
                    ]
                }
            },
            {
                "_index":"purchase",
                "_id":"3",
                "_score":1,
                "_source":{
                    "id":3,
                    "name":"jim",
                    "goods":[
                        {
                            "id":"g1",
                            "name":"ipad"
                        },
                        {
                            "id":"g2",
                            "name":"iphone"
                        },
                        {
                            "id":"g3",
                            "name":"ipod"
                        },
                        {
                            "id":"g4",
                            "name":"TV"
                        }
                    ]
                }
            }
        ]
    }
}

三、terms查询分析

我们使用_explain分析一下terms查询怎么打分的;

POST purchase/_explain/3
{
  "query": {
    "terms": {
      "goods.id": [
        "g2",
        "g3",
        "g4"
      ]
    }
  }
}

我们可以看到elasticsearch最终使用ConstantScore查询重写的terms查询,此查询默认权重打分为1;

{
  "_index" : "purchase",
  "_id" : "3",
  "matched" : true,
  "explanation" : {
    "value" : 1.0,
    "description" : "ConstantScore(goods.id:g2 goods.id:g3 goods.id:g4)",
    "details" : [ ]
  }
}

terms提供的查询参数十分有限,其中涉及权重的只有boost,但是这只是针对整个terms查询,而不是内部的子查询;

POST purchase/_explain/3
{
  "query": {
    "terms": {
      "goods.id": [
        "g2",
        "g3",
        "g4"
      ],
      "boost":2
    }
  }
}

{
  "_index" : "purchase",
  "_id" : "3",
  "matched" : true,
  "explanation" : {
    "value" : 2.0,
    "description" : "ConstantScore(goods.id:g2 goods.id:g3 goods.id:g4)^2.0",
    "details" : [ ]
  }
}

四、构建子查询打分

match是elasticsearch提供的一个跟terms类似的查询,由于goods.id的type是keyword,所以需要给match指定一个查询时的analyzer,才能保证输入的几个id分开作为不同的查询;

POST purchase/_search
{
  "query": {
    "match": {
      "goods.id": {
        "query": "g2 g3 g4",
        "analyzer":"standard"
      }
    }
  }
}


{
  "took" : 1,
  "timed_out" : false,
  "_shards" : {
    "total" : 1,
    "successful" : 1,
    "skipped" : 0,
    "failed" : 0
  },
  "hits" : {
    "total" : {
      "value" : 3,
      "relation" : "eq"
    },
    "max_score" : 2.178501,
    "hits" : [
      {
        "_index" : "purchase",
        "_id" : "3",
        "_score" : 2.178501,
        "_source" : {
          "id" : 3,
          "name" : "jim",
          "goods" : [
            {
              "id" : "g1",
              "name" : "ipad"
            },
            {
              "id" : "g2",
              "name" : "iphone"
            },
            {
              "id" : "g3",
              "name" : "ipod"
            },
            {
              "id" : "g4",
              "name" : "TV"
            }
          ]
        }
      },
      {
        "_index" : "purchase",
        "_id" : "2",
        "_score" : 0.8298607,
        "_source" : {
          "id" : 2,
          "name" : "coco",
          "goods" : [
            {
              "id" : "g1",
              "name" : "ipad"
            },
            {
              "id" : "g2",
              "name" : "iphone"
            },
            {
              "id" : "g3",
              "name" : "ipod"
            }
          ]
        }
      },
      {
        "_index" : "purchase",
        "_id" : "1",
        "_score" : 0.18360566,
        "_source" : {
          "id" : 1,
          "name" : "sam",
          "goods" : [
            {
              "id" : "g1",
              "name" : "ipad"
            },
            {
              "id" : "g2",
              "name" : "iphone"
            }
          ]
        }
      }
    ]
  }
}

通过查看文档3的打分情况,我们可以看到elasticsearch先针对每个关键字计算打分,然后将三项打分的和作为最终的打分;在这里我们也可以看到elasticsearch内部会自动将match查询rewrite为三个子查询;

POST purchase/_explain/3
{
  "query": {
    "match": {
      "goods.id": {
        "query": "g2 g3 g4",
        "analyzer":"standard"
      }
    }
  }
}

{
  "_index" : "purchase",
  "_id" : "3",
  "matched" : true,
  "explanation" : {
    "value" : 2.178501,
    "description" : "sum of:",
    "details" : [
      {
        "value" : 0.18360566,
        "description" : "weight(goods.id:g2 in 2) [PerFieldSimilarity], result of:",
        "details" : []
      },
      {
        "value" : 0.646255,
        "description" : "weight(goods.id:g3 in 2) [PerFieldSimilarity], result of:",
        "details" : []
      },
      {
        "value" : 1.3486402,
        "description" : "weight(goods.id:g4 in 2) [PerFieldSimilarity], result of:",
        "details" : []
      }
    ]
  }
}

我们也可以通过bool查询,使用它的should在查询之前手动组建多个子查询;

POST purchase/_search
{
  "query": {
    "bool": {
      "should": [
        {"term": {"goods.id": "g2"}},
        {"term": {"goods.id": "g3"}},
        {"term": {"goods.id": "g4"}}
      ],
      "minimum_should_match": 1
    }
  }
}

{
  "took" : 1,
  "timed_out" : false,
  "_shards" : {
    "total" : 1,
    "successful" : 1,
    "skipped" : 0,
    "failed" : 0
  },
  "hits" : {
    "total" : {
      "value" : 3,
      "relation" : "eq"
    },
    "max_score" : 2.178501,
    "hits" : [
      {
        "_index" : "purchase",
        "_id" : "3",
        "_score" : 2.178501,
        "_source" : {
          "id" : 3,
          "name" : "jim",
          "goods" : [
            {
              "id" : "g1",
              "name" : "ipad"
            },
            {
              "id" : "g2",
              "name" : "iphone"
            },
            {
              "id" : "g3",
              "name" : "ipod"
            },
            {
              "id" : "g4",
              "name" : "TV"
            }
          ]
        }
      },
      {
        "_index" : "purchase",
        "_id" : "2",
        "_score" : 0.8298607,
        "_source" : {
          "id" : 2,
          "name" : "coco",
          "goods" : [
            {
              "id" : "g1",
              "name" : "ipad"
            },
            {
              "id" : "g2",
              "name" : "iphone"
            },
            {
              "id" : "g3",
              "name" : "ipod"
            }
          ]
        }
      },
      {
        "_index" : "purchase",
        "_id" : "1",
        "_score" : 0.18360566,
        "_source" : {
          "id" : 1,
          "name" : "sam",
          "goods" : [
            {
              "id" : "g1",
              "name" : "ipad"
            },
            {
              "id" : "g2",
              "name" : "iphone"
            }
          ]
        }
      }
    ]
  }
}

在bool查询中,通过查看文档3的打分情况,我们可以看到elasticsearch也是先针对每个关键字计算打分,然后将三项打分的和作为最终的打分;

POST purchase/_explain/3
{
  "query": {
    "bool": {
      "should": [
        {"term": {"goods.id": "g2"}},
        {"term": {"goods.id": "g3"}},
        {"term": {"goods.id": "g4"}}
      ],
      "minimum_should_match": 1
    }
  }
}

{
  "_index" : "purchase",
  "_id" : "3",
  "matched" : true,
  "explanation" : {
    "value" : 2.178501,
    "description" : "sum of:",
    "details" : [
      {
        "value" : 0.18360566,
        "description" : "weight(goods.id:g2 in 2) [PerFieldSimilarity], result of:",
        "details" : []
      },
      {
        "value" : 0.646255,
        "description" : "weight(goods.id:g3 in 2) [PerFieldSimilarity], result of:",
        "details" : []
      },
      {
        "value" : 1.3486402,
        "description" : "weight(goods.id:g4 in 2) [PerFieldSimilarity], result of:",
        "details" : []
      }
    ]
  }
}

五、控制子查询的打分

不管是elasticsearch自动组建子查询,还是我们自己手动构建子查询,elasticsearch都会针对每个查询做相关性的打分计算,这对于一般的语义化关键字搜索是没有问题的;

我们这里的搜索条件goods.id一般是没有任何语义的,不同的值打分应该是一样的;这样我们只能使用bool+constant_score+term来手动构建查询语句;

POST purchase/_search
{
  "query": {
    "bool": {
      "should": [
        {"constant_score": {"filter": {"term": {"goods.id": "g2"}}}},
        {"constant_score": {"filter": {"term": {"goods.id": "g3"}}}},
        {"constant_score": {"filter": {"term": {"goods.id": "g4"}}}}
      ],
      "minimum_should_match": 1
    }
  }
}


{
  "took" : 0,
  "timed_out" : false,
  "_shards" : {
    "total" : 1,
    "successful" : 1,
    "skipped" : 0,
    "failed" : 0
  },
  "hits" : {
    "total" : {
      "value" : 3,
      "relation" : "eq"
    },
    "max_score" : 3.0,
    "hits" : [
      {
        "_index" : "purchase",
        "_id" : "3",
        "_score" : 3.0,
        "_source" : {
          "id" : 3,
          "name" : "jim",
          "goods" : [
            {
              "id" : "g1",
              "name" : "ipad"
            },
            {
              "id" : "g2",
              "name" : "iphone"
            },
            {
              "id" : "g3",
              "name" : "ipod"
            },
            {
              "id" : "g4",
              "name" : "TV"
            }
          ]
        }
      },
      {
        "_index" : "purchase",
        "_id" : "2",
        "_score" : 2.0,
        "_source" : {
          "id" : 2,
          "name" : "coco",
          "goods" : [
            {
              "id" : "g1",
              "name" : "ipad"
            },
            {
              "id" : "g2",
              "name" : "iphone"
            },
            {
              "id" : "g3",
              "name" : "ipod"
            }
          ]
        }
      },
      {
        "_index" : "purchase",
        "_id" : "1",
        "_score" : 1.0,
        "_source" : {
          "id" : 1,
          "name" : "sam",
          "goods" : [
            {
              "id" : "g1",
              "name" : "ipad"
            },
            {
              "id" : "g2",
              "name" : "iphone"
            }
          ]
        }
      }
    ]
  }
}

我们看下文档3的打分情况,每一个命中项的打分都是固定的1,最终的打分命中项的和;

POST purchase/_explain/3
{
  "query": {
    "bool": {
      "should": [
        {"constant_score": {"filter": {"term": {"goods.id": "g2"}}}},
        {"constant_score": {"filter": {"term": {"goods.id": "g3"}}}},
        {"constant_score": {"filter": {"term": {"goods.id": "g4"}}}}
      ],
      "minimum_should_match": 1
    }
  }
}

{
  "_index" : "purchase",
  "_id" : "3",
  "matched" : true,
  "explanation" : {
    "value" : 3.0,
    "description" : "sum of:",
    "details" : [
      {
        "value" : 1.0,
        "description" : "ConstantScore(goods.id:g2)",
        "details" : [ ]
      },
      {
        "value" : 1.0,
        "description" : "ConstantScore(goods.id:g3)",
        "details" : [ ]
      },
      {
        "value" : 1.0,
        "description" : "ConstantScore(goods.id:g4)",
        "details" : [ ]
      }
    ]
  }
}

文章来源于互联网:elasticsearch查询之keyword字段的查询相关度评分控制

THE END
分享
二维码