实时分析输出 - Amazon Comprehend

本文属于机器翻译版本。若本译文内容与英语原文存在差异,则一律以英文原文为准。

实时分析输出

文本输入的输出

如果使用 Text 参数输入文本,输出将由分析检测到的实体数组组成。以下示例显示了检测到两个 JUDGE 实体的分析。

{ "Entities": [ { "BeginOffset": 0, "EndOffset": 22, "Score": 0.9763959646224976, "Text": "John Johnson", "Type": "JUDGE" }, { "BeginOffset": 11, "EndOffset": 15, "Score": 0.9615424871444702, "Text": "Thomas Kincaid", "Type": "JUDGE" } ] }

半结构化输入的输出

对于半结构化输入文档或文本文件,输出可以包括以下附加字段:

  • DocumentMetadata — 提取有关文档的信息。元数据包括文档中的页面列表,以及从每页中提取的字符数。如果请求包含 Byte 参数,则响应中会显示此字段。

  • DocumentType -输入文档中每页的文档类型。此字段出现在包含该 Byte 参数的请求的响应中。

  • 块:有关输入文档中每个文本块的信息。块是嵌套的。页面块包含每行文本的块,其中每个单词都包含一个块。此字段出现在包含该 Byte 参数的请求的响应中。

  • BlockReferences — 对该实体的每个区块的引用。此字段出现在包含该 Byte 参数的请求的响应中。文本文件中不存在该字段。

  • 错误:系统在处理输入文档时检测到的页面级错误。如果系统未遇到任何错误,则该字段为空。

有关这些输出字段的描述,请参阅DetectEntitiesAmazon Comprehend API 参考》。有关布局元素的更多信息,请参阅《Amazon Textract 开发人员指南》中的 Amazon Textract 分析对象

以下示例显示了单页扫描的 PDF 输入文档的输出。

{ "Entities": [{ "Score": 0.9984670877456665, "Type": "DATE-TIME", "Text": "September 4,", "BlockReferences": [{ "BlockId": "42dcaaee-c484-4b5d-9e3f-ae0be928b3e1", "BeginOffset": 0, "EndOffset": 12, "ChildBlocks": [{ "ChildBlockId": "6e9cbb43-f8be-4da0-9a4b-ff9a6c350a14", "BeginOffset": 0, "EndOffset": 9 }, { "ChildBlockId": "599e0d53-ae9f-491b-a762-459b22c79ff5", "BeginOffset": 0, "EndOffset": 2 }, { "ChildBlockId": "599e0d53-ae9f-491b-a762-459b22c79ff5", "BeginOffset": 0, "EndOffset": 2 } ] }] }], "DocumentMetadata": { "Pages": 1, "ExtractedCharacters": [{ "Page": 1, "Count": 609 }] }, "DocumentType": [{ "Page": 1, "Type": "SCANNED_PDF" }], "Blocks": [{ "Id": "ee82edf3-28de-4d63-8883-40e2e4938ccb", "BlockType": "LINE", "Text": "Your Band", "Page": 1, "Geometry": { "BoundingBox": { "Height": 0.024125460535287857, "Left": 0.11745482683181763, "Top": 0.06821706146001816, "Width": 0.12074867635965347 }, "Polygon": [{ "X": 0.11745482683181763, "Y": 0.06821706146001816 }, { "X": 0.2382034957408905, "Y": 0.06821706146001816 }, { "X": 0.2382034957408905, "Y": 0.09234252572059631 }, { "X": 0.11745482683181763, "Y": 0.09234252572059631 } ] }, "Relationships": [{ "Ids": [ "b105c561-c8d9-485a-a728-7a5b1a308935", "60ecb119-3173-4de2-8c5d-de182a5f86a5" ], "Type": "CHILD" }] }] }

以下示例显示了用于分析原生 PDF 文档的输出。

例 PDF 文档自定义实体识别分析的输出示例
{ "Blocks": [ { "BlockType": "LINE", "Geometry": { "BoundingBox": { "Height": 0.012575757575757575, "Left": 0.0, "Top": 0.0015063131313131314, "Width": 0.02262091503267974 }, "Polygon": [ { "X": 0.0, "Y": 0.0015063131313131314 }, { "X": 0.02262091503267974, "Y": 0.0015063131313131314 }, { "X": 0.02262091503267974, "Y": 0.014082070707070706 }, { "X": 0.0, "Y": 0.014082070707070706 } ] }, "Id": "4330efed-6334-4fc4-ba48-e050afa95c8d", "Page": 1, "Relationships": [ { "ids": [ "f343ce48-583d-4abe-b84b-a232e266450f" ], "type": "CHILD" } ], "Text": "S-3" }, { "BlockType": "WORD", "Geometry": { "BoundingBox": { "Height": 0.012575757575757575, "Left": 0.0, "Top": 0.0015063131313131314, "Width": 0.02262091503267974 }, "Polygon": [ { "X": 0.0, "Y": 0.0015063131313131314 }, { "X": 0.02262091503267974, "Y": 0.0015063131313131314 }, { "X": 0.02262091503267974, "Y": 0.014082070707070706 }, { "X": 0.0, "Y": 0.014082070707070706 } ] }, "Id": "f343ce48-583d-4abe-b84b-a232e266450f", "Page": 1, "Relationships": [], "Text": "S-3" } ], "DocumentMetadata": { "PageNumber": 1, "Pages": 1 }, "DocumentType": "NativePDF", "Entities": [ { "BlockReferences": [ { "BeginOffset": 25, "BlockId": "4330efed-6334-4fc4-ba48-e050afa95c8d", "ChildBlocks": [ { "BeginOffset": 1, "ChildBlockId": "cbba5534-ac69-4bc4-beef-306c659f70a6", "EndOffset": 6 } ], "EndOffset": 30 } ], "Score": 0.9998825926329088, "Text": "0.001", "Type": "OFFERING_PRICE" }, { "BlockReferences": [ { "BeginOffset": 41, "BlockId": "f343ce48-583d-4abe-b84b-a232e266450f", "ChildBlocks": [ { "BeginOffset": 0, "ChildBlockId": "292a2e26-21f0-401b-a2bf-03aa4c47f787", "EndOffset": 9 } ], "EndOffset": 50 } ], "Score": 0.9809727537330395, "Text": "6,097,560", "Type": "OFFERED_SHARES" } ], "File": "example.pdf", "Version": "2021-04-30" }