Elasticsearch 不会匹配确切的字符串

Rob*_*cia 2 autosuggest elasticsearch

我创建了一个带有完成提示的类别索引,但它的行为并不符合我的预期。

curl -XPUT http://localhost:9200/categories/category/_mapping -d '{
    "category" : {
        "properties" : {
            "categoryDescription" : {
                "type" : "string"
            },
            "suggest" : {
                "type" : "completion",
                "analyzer" : "simple",
                "search_analyzer" : "simple",
                "payloads" : true
            }
        }
    }
}'
Run Code Online (Sandbox Code Playgroud)

我有一个为“墨西哥杂货店”编入索引的类别,当我搜索该字符串时,我得到的点击次数为零,只有一个建议结果:

{
    "query":{
        "fuzzy":{
            "categoryDescription":{
                "value":"mexican grocery store"
            }
        }
    },
    "from":0,
    "size":20,
    "suggest":{
        "category-suggest":{
            "text":"mexican grocery store",
            "completion":{
                "field":"suggest","fuzzy":{"fuzziness":2}
            }
        }
    }
}

{
    "took":19,
    "timed_out":false,
    "_shards":{"total":5,"successful":5,"failed":0},
    "hits":{
        "total":0,"max_score":null,"hits":[]
    },
    "suggest":{
        "category-suggest":[
            {
                "text":"mexican grocery store",
                "offset":0,
                "length":21,
                "options":[
                    {
                        "text":"Mexican Grocery Store",
                        "score":1.0,
                        "payload":{"id":5915028960051200}
                    }
                ]
            }
        ]
    }
}
Run Code Online (Sandbox Code Playgroud)

我不仅得到了完全匹配的零点击率,而且当我输入字符串“墨西哥”时,一堆带有“医疗”一词的类别列在“墨西哥”类别之前,这对我来说没有任何意义任何一个。

{
    "query":{
        "fuzzy":{
            "categoryDescription":{
                "value":"mexican"
            }
        }
    },
    "from":0,
    "size":20,
    "suggest":{
        "category-suggest":{
            "text":"mexican",
            "completion":{
                "field":"suggest","fuzzy":{"fuzziness":2}
            }
        }
    }
}

{
    "took":11,
    "timed_out":false,
    "_shards":{
        "total":5,
        "successful":5,
        "failed":0
    },
    "hits":{
        "total":25,
        "max_score":3.8085938,
        "hits":[
            {
                "_index":"categories",
                "_type":"category",
                "_id":"4993638215974912",
                "_score":3.8085938,
                "_source":{
                    "id":4993638215974912,
                    "categoryDescription":"Medical Spa",
                    "suggest":{
                        "input":["Medical Spa"],
                        "output":"Medical Spa",
                        "payload":{"id":4993638215974912}}}},
{"_index":"categories","_type":"category","_id":"6401013099528192","_score":3.8085938,"_source":{"id":6401013099528192,"categoryDescription":"Medical School","suggest":{"input":["Medical School"],"output":"Medical School","payload":{"id":6401013099528192}}}},{"_index":"categories","_type":"category","_id":"4712163239264256","_score":3.4429123,"_source":{"id":4712163239264256,"categoryDescription":"Medical Examiner","suggest":{"input":["Medical Examiner"],"output":"Medical Examiner","payload":{"id":4712163239264256}}}},{"_index":"categories","_type":"category","_id":"5978800634462208","_score":3.4429123,"_source":{"id":5978800634462208,"categoryDescription":"Medical Center","suggest":{"input":["Medical Center"],"output":"Medical Center","payload":{"id":5978800634462208}}}},{"_index":"categories","_type":"category","_id":"5415850681040896","_score":3.4429123,"_source":{"id":5415850681040896,"categoryDescription":"Medical Clinic","suggest":{"input":["Medical Clinic"],"output":"Medical Clinic","payload":{"id":5415850681040896}}}},{"_index":"categories","_type":"category","_id":"4852900727619584","_score":2.75433,"_source":{"id":4852900727619584,"categoryDescription":"Medical Billing Service","suggest":{"input":["Medical Billing Service"],"output":"Medical Billing Service","payload":{"id":4852900727619584}}}},{"_index":"categories","_type":"category","_id":"5352079006629888","_score":2.4411354,"_source":{"id":5352079006629888,"categoryDescription":"Mexican Restaurant","suggest":{"input":["Mexican Restaurant"],"output":"Mexican Restaurant","payload":{"id":5352079006629888}}}},{"_index":"categories","_type":"category","_id":"5915028960051200","_score":2.143557,"_source":{"id":5915028960051200,"categoryDescription":"Mexican Grocery Store","suggest":{"input":["Mexican Grocery Store","shop"],"output":"Mexican Grocery Store","payload":{"id":5915028960051200}}}},{"_index":"categories","_type":"category","_id":"6392217006505984","_score":2.0527549,"_source":{"id":6392217006505984,"categoryDescription":"Latin American Restaurant","suggest":{"input":["Latin American Restaurant"],"output":"Latin American Restaurant","payload":{"id":6392217006505984}}}},{"_index":"categories","_type":"category","_id":"5149768867119104","_score":2.0527549,"_source":{"id":5149768867119104,"categoryDescription":"Occupational Medical Physician","suggest":{"input":["Occupational Medical Physician"],"output":"Occupational Medical Physician","payload":{"id":5149768867119104}}}},{"_index":"categories","_type":"category","_id":"5157465448513536","_score":2.0527549,"_source":{"id":5157465448513536,"categoryDescription":"Central American Restaurant","suggest":{"input":["Central American Restaurant"],"output":"Central American Restaurant","payload":{"id":5157465448513536}}}},{"_index":"categories","_type":"category","_id":"6479078425100288","_score":2.0527549,"_source":{"id":6479078425100288,"categoryDescription":"American Football Field","suggest":{"input":["American Football Field"],"output":"American Football Field","payload":{"id":6479078425100288}}}},{"_index":"categories","_type":"category","_id":"4789129053208576","_score":1.9529084,"_source":{"id":4789129053208576,"categoryDescription":"Mexican Goods Store","suggest":{"input":["Mexican Goods Store","shop"],"output":"Mexican Goods Store","payload":{"id":4789129053208576}}}},{"_index":"categories","_type":"category","_id":"5275113192685568","_score":1.9138902,"_source":{"id":5275113192685568,"categoryDescription":"Medical Laboratory","suggest":{"input":["Medical Laboratory"],"output":"Medical Laboratory","payload":{"id":5275113192685568}}}},{"_index":"categories","_type":"category","_id":"5838063146106880","_score":1.7436681,"_source":{"id":5838063146106880,"categoryDescription":"Medical Group","suggest":{"input":["Medical Group"],"output":"Medical Group","payload":{"id":5838063146106880}}}},{"_index":"categories","_type":"category","_id":"4649491076481024","_score":1.7436681,"_source":{"id":4649491076481024,"categoryDescription":"American Restaurant","suggest":{"input":["American Restaurant"],"output":"American Restaurant","payload":{"id":4649491076481024}}}},{"_index":"categories","_type":"category","_id":"5458456756617216","_score":1.5311122,"_source":{"id":5458456756617216,"categoryDescription":"Traditional American Restaurant","suggest":{"input":["Traditional American Restaurant"],"output":"Traditional American Restaurant","payload":{"id":5458456756617216}}}},{"_index":"categories","_type":"category","_id":"6183309797228544","_score":1.5311122,"_source":{"id":6183309797228544,"categoryDescription":"Public Medical Center","suggest":{"input":["Public Medical Center"],"output":"Public Medical Center","payload":{"id":6183309797228544}}}},{"_index":"categories","_type":"category","_id":"6706677332049920","_score":1.5311122,"_source":{"id":6706677332049920,"categoryDescription":"Native American Goods Store","suggest":{"input":["Native American Goods Store","shop"],"output":"Native American Goods Store","payload":{"id":6706677332049920}}}},{"_index":"categories","_type":"category","_id":"6119538122817536","_score":1.3949344,"_source":{"id":6119538122817536,"categoryDescription":"Medical Supply Store","suggest":{"input":["Medical Supply Store","shop"],"output":"Medical Supply Store","payload":{"id":6119538122817536}}}}]},"suggest":{"category-suggest":[{"text":"mexican","offset":0,"length":7,"options":[{"text":"Medical Billing Service","score":1.0,"payload":{"id":4852900727619584}},{"text":"Medical Center","score":1.0,"payload":{"id":5978800634462208}},{"text":"Medical Clinic","score":1.0,"payload":{"id":5415850681040896}},{"text":"Medical Examiner","score":1.0,"payload":{"id":4712163239264256}},{"text":"Medical Group","score":1.0,"payload":{"id":5838063146106880}}]}]}}
Run Code Online (Sandbox Code Playgroud)

knu*_*ker 6

您将该字段索引categoryDescriptionstring,因此 Elasticsearch 会在您的输入上运行其标准分析器并Mexican Grocery Store转换为三个标记[mexican, grocery, store]

fuzzy查询属于术语查询系列,也就是说,它在术语级别上运行并且不通过任何分析器运行。带有输入的模糊查询Mexican Grocery Store将尝试将这些词匹配为一个词,而不是 3 个不同的词。它没有找到任何内容,因为完整的短语不作为索引中的一个术语存在。您可以向categoryDescription未分析的子字段添加子字段或仅使用小写标记过滤器并在该字段上运行模糊查询以生成“完全匹配”。

对于第二部分,模糊查询不区分修改后的匹配(应用模糊性)和精确匹配。在执行实际搜索之前,模糊术语在内部与给定字段中的所有术语列表进行匹配并展开。在你的例子中,它变成了类似的东西

"boolean": {
  "should": [
    {
      "term": {
        "categoryDescription": "medical"
      }
    },
    {
      "term": {
        "categoryDescription": "mexican"
      }
    }
  ]
}
Run Code Online (Sandbox Code Playgroud)

由此,很明显为什么Medical Spa会返回类似的东西。这些命中的分数也高于Mexican Grocery Store,因此首先返回它们。我怀疑这是由于术语频率(医疗出现的频率高于墨西哥),但应该再次运行查询并explain启用以查看分数较高的确切原因。

如果要对模糊匹配应用惩罚,可以将模糊查询和术语查询包装到布尔查询中:

{
  "query": {
    "boolean": {
      "should": [
        {
          "fuzzy": {
            "categoryDescription": "mexican"
          }
        },
        {
          "term": {
            "categoryDescription": "mexican"
          }
        }
      ]
    }
  }
}
Run Code Online (Sandbox Code Playgroud)

这会将只有fuzzy部分匹配的文档的分数减半(由于布尔查询的协调因素)。