7

我正在努力在 Elastic Search 中按照我想要的方式进行提升工作。

假设我有一些包含性别、兴趣和年龄的个人资料索引，假设我发现性别匹配最相关，然后兴趣和最不重要的标准是用户的年龄。我期待下面的查询会根据刚才提到的原则对匹配的配置文件进行排序，但是当我执行它时，我先得到一些男性，然后在喜欢汽车的女性 Maria 之前得到 50 岁的女性 Anna ……为什么玛丽亚的分数没有比安娜高？？

{
    "query": {
        "bool" : {
            "should" : [
                { "term"  : { "gender" : { "term": "male", "boost": 10.0 } } },
                { "term"  : { "likes"  : { "term": "cars", "boost" : 5.0 } } },
                { "range" : { "age"    : { "from" : 50,    "boost" : 1.0 } } }
            ],
            "minimum_number_should_match" : 1
        }
    }    
}

提示将不胜感激，

斯廷

这些是执行的 curl 命令：

$ curl -XPUT http://localhost:9200/users/profile/1 -d '{
    "nickname" : "bob",
    "gender" : "male",
    "age" : 48,
    "likes" : "airplanes"
}'

$ curl -XPUT http://localhost:9200/users/profile/2 -d '{
    "nickname" : "carlos",
    "gender" : "male",
    "age" : 24,
    "likes" : "food"
}'

$ curl -XPUT http://localhost:9200/users/profile/3 -d '{
    "nickname" : "julio",
    "gender" : "male",
    "age" : 18,
    "likes" : "ladies"
}'

$ curl -XPUT http://localhost:9200/users/profile/4 -d '{
    "nickname" : "maria",
    "gender" : "female",
    "age" : 25,
    "likes" : "cars"
}'

$ curl -XPUT http://localhost:9200/users/profile/5 -d '{
    "nickname" : "anna",
    "gender" : "female",
    "age" : 50,
    "likes" : "clothes"
}'

$ curl -XGET http://localhost:9200/users/profile/_search -d '{
    "query": {
        "bool" : {
            "should" : [
                { "term" : { "gender" : { "term": "male", "boost": 10.0 } } },
                { "term" : { "likes" : { "term": "cars", "boost" : 5.0 } } },
                { "range" : { "age" : { "from" : 50, "boost" : 1.0 } } }
            ],
            "minimum_number_should_match" : 1
        }
    }    
}'
4

1 回答 1

14

该boost值不是绝对的 - 它与其他因素相结合来确定每个术语的相关性。

你有两个“性别”（我会假设），但有很多不同的“喜欢”。所以male被认为几乎无关紧要，因为它在您的数据中经常出现。然而，cars可能只出现几次，因此被认为更相关。

此逻辑对全文搜索很有用，但不适用于枚举，枚举本质上是用作过滤器。

omit_term_freq_and_positions幸运的是，您可以使用和在每个字段的基础上禁用此功能omit_norms。

尝试如下设置映射：

curl -XPUT 'http://127.0.0.1:9200/test/?pretty=1'  -d '
{
   "mappings" : {
      "test" : {
         "properties" : {
            "likes" : {
               "index" : "not_analyzed",
               "omit_term_freq_and_positions" : 1,
               "omit_norms" : 1,
               "type" : "string"
            },
            "gender" : {
               "index" : "not_analyzed",
               "omit_term_freq_and_positions" : 1,
               "omit_norms" : 1,
               "type" : "string"
            },
            "age" : {
               "type" : "integer"
            }
         }
      }
   }
}
'

更新：完整的工作示例：

删除现有索引：

curl -XDELETE 'http://127.0.0.1:9200/users/?pretty=1'

使用新映射创建索引：

curl -XPUT 'http://127.0.0.1:9200/users/?pretty=1'  -d '
{
   "mappings" : {
      "profile" : {
         "properties" : {
            "likes" : {
               "index" : "not_analyzed",
               "omit_term_freq_and_positions" : 1,
               "type" : "string",
               "omit_norms" : 1
            },
            "age" : {
               "type" : "integer"
            },
            "gender" : {
               "index" : "not_analyzed",
               "omit_term_freq_and_positions" : 1,
               "type" : "string",
               "omit_norms" : 1
            }
         }
      }
   }
}
'

索引测试文档：

curl -XPOST 'http://127.0.0.1:9200/users/profile/_bulk?pretty=1'  -d '
{"index" : {"_id" : 1}}
{"nickname" : "bob", "likes" : "airplanes", "age" : 48, "gender" : "male"}
{"index" : {"_id" : 2}}
{"nickname" : "carlos", "likes" : "food", "age" : 24, "gender" : "male"}
{"index" : {"_id" : 3}}
{"nickname" : "julio", "likes" : "ladies", "age" : 18, "gender" : "male"}
{"index" : {"_id" : 4}}
{"nickname" : "maria", "likes" : "cars", "age" : 25, "gender" : "female"}
{"index" : {"_id" : 5}}
{"nickname" : "anna", "likes" : "clothes", "age" : 50, "gender" : "female"}
'

刷新索引（以确保可以搜索到最新的文档）：

curl -XPOST 'http://127.0.0.1:9200/users/_refresh?pretty=1'

搜索：

curl -XGET 'http://127.0.0.1:9200/users/profile/_search?pretty=1'  -d '
{
   "query" : {
      "bool" : {
         "minimum_number_should_match" : 1,
         "should" : [
            {
               "term" : {
                  "gender" : {
                     "boost" : 10,
                     "term" : "male"
                  }
               }
            },
            {
               "term" : {
                  "likes" : {
                     "boost" : 5,
                     "term" : "cars"
                  }
               }
            },
            {
               "range" : {
                  "age" : {
                     "boost" : 1,
                     "from" : 50
                  }
               }
            }
         ]
      }
   }
}
'

结果：

# {
#    "hits" : {
#       "hits" : [
#          {
#             "_source" : {
#                "nickname" : "bob",
#                "likes" : "airplanes",
#                "age" : 48,
#                "gender" : "male"
#             },
#             "_score" : 0.053500723,
#             "_index" : "users",
#             "_id" : "1",
#             "_type" : "profile"
#          },
#          {
#             "_source" : {
#                "nickname" : "carlos",
#                "likes" : "food",
#                "age" : 24,
#                "gender" : "male"
#             },
#             "_score" : 0.053500723,
#             "_index" : "users",
#             "_id" : "2",
#             "_type" : "profile"
#          },
#          {
#             "_source" : {
#                "nickname" : "julio",
#                "likes" : "ladies",
#                "age" : 18,
#                "gender" : "male"
#             },
#             "_score" : 0.053500723,
#             "_index" : "users",
#             "_id" : "3",
#             "_type" : "profile"
#          },
#          {
#             "_source" : {
#                "nickname" : "anna",
#                "likes" : "clothes",
#                "age" : 50,
#                "gender" : "female"
#             },
#             "_score" : 0.029695695,
#             "_index" : "users",
#             "_id" : "5",
#             "_type" : "profile"
#          },
#          {
#             "_source" : {
#                "nickname" : "maria",
#                "likes" : "cars",
#                "age" : 25,
#                "gender" : "female"
#             },
#             "_score" : 0.015511602,
#             "_index" : "users",
#             "_id" : "4",
#             "_type" : "profile"
#          }
#       ],
#       "max_score" : 0.053500723,
#       "total" : 5
#    },
#    "timed_out" : false,
#    "_shards" : {
#       "failed" : 0,
#       "successful" : 5,
#       "total" : 5
#    },
#    "took" : 4
# }

更新：替代方法

在这里，我提出了一个替代查询，它虽然更详细，但可以为您提供更可预测的结果。它涉及使用自定义过滤器得分查询。首先，我们将文档过滤为至少匹配一个条件的文档。因为我们使用恒定分数查询，所以所有文档的初始分数都是 1。

自定义过滤器分数允许我们在每个文档匹配过滤器时提升它：

curl -XGET 'http://127.0.0.1:9200/_all/_search?pretty=1'  -d '
{
   "query" : {
      "custom_filters_score" : {
         "query" : {
            "constant_score" : {
               "filter" : {
                  "or" : [
                     {
                        "term" : {
                           "gender" : "male"
                        }
                     },
                     {
                        "term" : {
                           "likes" : "cars"
                        }
                     },
                     {
                        "range" : {
                           "age" : {
                              "gte" : 50
                           }
                        }
                     }
                  ]
               }
            }
         },
         "score_mode" : "total",
         "filters" : [
            {
               "boost" : "10",
               "filter" : {
                  "term" : {
                     "gender" : "male"
                  }
               }
            },
            {
               "boost" : "5",
               "filter" : {
                  "term" : {
                     "likes" : "cars"
                  }
               }
            },
            {
               "boost" : "1",
               "filter" : {
                  "range" : {
                     "age" : {
                        "gte" : 50
                     }
                  }
               }
            }
         ]
      }
   }
}
'

您会看到与每个文档相关的分数都是很好的整数，很容易追溯到匹配的子句：

# [Fri Jun  8 21:30:24 2012] Response:
# {
#    "hits" : {
#       "hits" : [
#          {
#             "_source" : {
#                "nickname" : "bob",
#                "likes" : "airplanes",
#                "age" : 48,
#                "gender" : "male"
#             },
#             "_score" : 10,
#             "_index" : "users",
#             "_id" : "1",
#             "_type" : "profile"
#          },
#          {
#             "_source" : {
#                "nickname" : "carlos",
#                "likes" : "food",
#                "age" : 24,
#                "gender" : "male"
#             },
#             "_score" : 10,
#             "_index" : "users",
#             "_id" : "2",
#             "_type" : "profile"
#          },
#          {
#             "_source" : {
#                "nickname" : "julio",
#                "likes" : "ladies",
#                "age" : 18,
#                "gender" : "male"
#             },
#             "_score" : 10,
#             "_index" : "users",
#             "_id" : "3",
#             "_type" : "profile"
#          },
#          {
#             "_source" : {
#                "nickname" : "maria",
#                "likes" : "cars",
#                "age" : 25,
#                "gender" : "female"
#             },
#             "_score" : 5,
#             "_index" : "users",
#             "_id" : "4",
#             "_type" : "profile"
#          },
#          {
#             "_source" : {
#                "nickname" : "anna",
#                "likes" : "clothes",
#                "age" : 50,
#                "gender" : "female"
#             },
#             "_score" : 1,
#             "_index" : "users",
#             "_id" : "5",
#             "_type" : "profile"
#          }
#       ],
#       "max_score" : 10,
#       "total" : 5
#    },
#    "timed_out" : false,
#    "_shards" : {
#       "failed" : 0,
#       "successful" : 20,
#       "total" : 20
#    },
#    "took" : 6
# }
于 2012-06-08T11:08:20.917 回答