我正在我的技能集中使用Microsoft.Skills.Text.EntityRecognitionSkill,该技能输出“人”,“位置”,“组织”。但是我只想输出置信水平> .5的Location有没有办法做到这一点?这是我的代码的快照
{
"@odata.type": "#Microsoft.Skills.Text.EntityRecognitionSkill",
"categories": [
"Person",
"Location",
"Organization"
],
"context": "/document/finalText/pages/*",
"inputs": [
{
"name": "text",
"source": "/document/finalText/pages/*"
},
{
"name": "languageCode",
"source": "/document/languageCode"
}
],
"outputs": [
{
"name": "persons",
"targetName": "people"
},
{
"name": "locations"
},
{
"name": "namedEntities",
"targetName": "entities"
}
]
},
[[根据Mick的评论编辑]
是,可以通过将实体识别技能的minimumPrecision
参数设置为0.5,这将导致返回置信度> = 0.5的实体。
实体识别技能的文档在这里:https://docs.microsoft.com/en-us/azure/search/cognitive-search-skill-entity-recognition
[正如Mick指出的,文档说minimumPrecision
尚未使用,但是该文档已过时,我会尽快修复。