0

当我上传文档以进行表单识别时,我得到的结果似乎与文档的结构不一致。它似乎很受欢迎或错过。在我的示例中,有一个包含产品描述、数量、零件编号和价格的网格。只有描述中的第一行与数量、价格和部件号相关。描述的其余行位于响应的其他位置,与第一行无关。

这是报价布局的示例

在此处输入图像描述

我已经上传了完整的文件和一个空白表格,既简单又复杂,有多个页面。这是缺少数据的结果的一部分。

{   
    "header": [
        {
            "text": "ITEM",
            "boundingBox": [
                43.8,
                527.5,
                65.4,
                527.5,
                65.4,
                519.7,
                43.8,
                519.7
            ]
        }
    ],
    "entries": [
        [
            {
                "text": "F5 BIG-IP Service Premium (Level 1-3) - technical support",
                "boundingBox": [
                    43.7,
                    512.1,
                    278.7,
                    512.1,
                    278.7,
                    504.3,
                    43.7,
                    504.3
                ],
                "confidence": 1.0
            }
        ],
        [
            {
                "text": "F5 BIG-IP Service Premium (Level 1-3) - technical support",
                "boundingBox": [
                    43.7,
                    438.7,
                    278.7,
                    438.7,
                    278.7,
                    430.9,
                    43.7,
                    430.9
                ],
                "confidence": 1.0
            }
        ],
        [
            {
                "text": "F5 BIG-IP Service Premium (Level 1-3) - technical support",
                "boundingBox": [
                    43.7,
                    357.7,
                    278.7,
                    357.7,
                    278.7,
                    349.9,
                    43.7,
                    349.9
                ],
                "confidence": 1.0
            }
        ],
        [
            {
                "text": "F5 BIG-IP Service Premium (Level 1-3) - technical support",
                "boundingBox": [
                    43.7,
                    276.4,
                    278.7,
                    276.4,
                    278.7,
                    268.7,
                    43.7,
                    268.7
                ],
                "confidence": 1.0
            }
        ],
        [
            {
                "text": "F5 BIG-IP Service Premium (Level 1-3) - technical support",
                "boundingBox": [
                    43.7,
                    195.4,
                    278.7,
                    195.4,
                    278.7,
                    187.7,
                    43.7,
                    187.7
                ],
                "confidence": 1.0
            }
        ],
        [
            {
                "text": "F5 BIG-IP Service Premium (Level 1-3) - technical support",
                "boundingBox": [
                    43.8,
                    114.5,
                    278.8,
                    114.5,
                    278.8,
                    106.8,
                    43.8,
                    106.8
                ],
                "confidence": 1.0
            }
        ]
    ]
},
{
    "header": [
        {
            "text": "QTY",
            "boundingBox": [
                304.9,
                527.5,
                320.6,
                527.5,
                320.6,
                519.7,
                304.9,
                519.7
            ]
        }
    ],
    "entries": [
        [
            {
                "text": "1",
                "boundingBox": [
                    310.7,
                    512.8,
                    315.1,
                    512.8,
                    315.1,
                    504.3,
                    310.7,
                    504.3
                ],
                "confidence": 1.0
            }
        ],
        [
            {
                "text": "1",
                "boundingBox": [
                    310.7,
                    439.3,
                    315.1,
                    439.3,
                    315.1,
                    430.9,
                    310.7,
                    430.9
                ],
                "confidence": 1.0
            }
        ],
        [
            {
                "text": "1",
                "boundingBox": [
                    310.7,
                    358.3,
                    315.1,
                    358.3,
                    315.1,
                    349.9,
                    310.7,
                    349.9
                ],
                "confidence": 1.0
            }
        ],
        [
            {
                "text": "1",
                "boundingBox": [
                    310.7,
                    277.1,
                    315.1,
                    277.1,
                    315.1,
                    268.7,
                    310.7,
                    268.7
                ],
                "confidence": 1.0
            }
        ],
        [
            {
                "text": "1",
                "boundingBox": [
                    310.7,
                    196.1,
                    315.1,
                    196.1,
                    315.1,
                    187.7,
                    310.7,
                    187.7
                ],
                "confidence": 1.0
            }
        ],
        [
            {
                "text": "1",
                "boundingBox": [
                    310.7,
                    115.2,
                    315.1,
                    115.2,
                    315.1,
                    106.8,
                    310.7,
                    106.8
                ],
                "confidence": 1.0
            }
        ]
    ]
},
{
    "header": [
        {
            "text": "Part#",
            "boundingBox": [
                356.2,
                527.5,
                381.9,
                527.5,
                381.9,
                519.7,
                356.2,
                519.7
            ]
        }
    ],
    "entries": [
        [
            {
                "text": "3158598",
                "boundingBox": [
                    353.6,
                    512.8,
                    384.6,
                    512.8,
                    384.6,
                    504.3,
                    353.6,
                    504.3
                ],
                "confidence": 1.0
            }
        ],
        [
            {
                "text": "3158598",
                "boundingBox": [
                    353.6,
                    439.3,
                    384.6,
                    439.3,
                    384.6,
                    430.9,
                    353.6,
                    430.9
                ],
                "confidence": 1.0
            }
        ],
        [
            {
                "text": "3158598",
                "boundingBox": [
                    353.6,
                    358.3,
                    384.6,
                    358.3,
                    384.6,
                    349.9,
                    353.6,
                    349.9
                ],
                "confidence": 1.0
            }
        ],
        [
            {
                "text": "3158598",
                "boundingBox": [
                    353.6,
                    277.1,
                    384.6,
                    277.1,
                    384.6,
                    268.7,
                    353.6,
                    268.7
                ],
                "confidence": 1.0
            }
        ],
        [
            {
                "text": "3158598",
                "boundingBox": [
                    353.6,
                    196.1,
                    384.6,
                    196.1,
                    384.6,
                    187.7,
                    353.6,
                    187.7
                ],
                "confidence": 1.0
            }
        ],
        [
            {
                "text": "3158598",
                "boundingBox": [
                    353.6,
                    115.2,
                    384.6,
                    115.2,
                    384.6,
                    106.8,
                    353.6,
                    106.8
                ],
                "confidence": 1.0
            }
        ]
    ]
},
{
    "header": [
        {
            "text": "UNIT PRICE",
            "boundingBox": [
                431.0,
                527.5,
                480.5,
                527.5,
                480.5,
                519.7,
                431.0,
                519.7
            ]
        }
    ],
    "entries": [
        [
            {
                "text": "$10,003.53",
                "boundingBox": [
                    439.7,
                    512.8,
                    480.1,
                    512.8,
                    480.1,
                    504.3,
                    439.7,
                    504.3
                ],
                "confidence": 1.0
            }
        ],
        [
            {
                "text": "$30,815.03",
                "boundingBox": [
                    439.7,
                    439.3,
                    480.1,
                    439.3,
                    480.1,
                    430.9,
                    439.7,
                    430.9
                ],
                "confidence": 1.0
            }
        ],
        [
            {
                "text": "$6,401.54",
                "boundingBox": [
                    444.2,
                    358.3,
                    480.3,
                    358.3,
                    480.3,
                    349.9,
                    444.2,
                    349.9
                ],
                "confidence": 1.0
            }
        ],
        [
            {
                "text": "$10,003.53",
                "boundingBox": [
                    439.7,
                    277.1,
                    480.1,
                    277.1,
                    480.1,
                    268.7,
                    439.7,
                    268.7
                ],
                "confidence": 1.0
            }
        ],
        [
            {
                "text": "$16,006.85",
                "boundingBox": [
                    439.7,
                    196.1,
                    480.1,
                    196.1,
                    480.1,
                    187.7,
                    439.7,
                    187.7
                ],
                "confidence": 1.0
            }
        ],
        [
            {
                "text": "$2,399.33",
                "boundingBox": [
                    444.2,
                    115.2,
                    480.3,
                    115.2,
                    480.3,
                    106.8,
                    444.2,
                    106.8
                ],
                "confidence": 1.0
            }
        ]
    ]
},
{
    "header": [
        {
            "text": "EXT. PRICE",
            "boundingBox": [
                513.7,
                527.5,
                558.2,
                527.5,
                558.2,
                519.7,
                513.7,
                519.7
            ]
        }
    ],
    "entries": [
        [
            {
                "text": "$10,003.53",
                "boundingBox": [
                    517.8,
                    512.8,
                    558.3,
                    512.8,
                    558.3,
                    504.3,
                    517.8,
                    504.3
                ],
                "confidence": 1.0
            }
        ],
        [
            {
                "text": "$30,815.03",
                "boundingBox": [
                    517.8,
                    439.3,
                    558.3,
                    439.3,
                    558.3,
                    430.9,
                    517.8,
                    430.9
                ],
                "confidence": 1.0
            }
        ],
        [
            {
                "text": "$6,401.54",
                "boundingBox": [
                    522.4,
                    358.3,
                    558.4,
                    358.3,
                    558.4,
                    349.9,
                    522.4,
                    349.9
                ],
                "confidence": 1.0
            }
        ],
        [
            {
                "text": "$10,003.53",
                "boundingBox": [
                    517.8,
                    277.1,
                    558.3,
                    277.1,
                    558.3,
                    268.7,
                    517.8,
                    268.7
                ],
                "confidence": 1.0
            }
        ],
        [
            {
                "text": "$16,006.85",
                "boundingBox": [
                    517.8,
                    196.1,
                    558.3,
                    196.1,
                    558.3,
                    187.7,
                    517.8,
                    187.7
                ],
                "confidence": 1.0
            }
        ],
        [
            {
                "text": "$2,399.33",
                "boundingBox": [
                    522.4,
                    115.2,
                    558.4,
                    115.2,
                    558.4,
                    106.8,
                    522.4,
                    106.8
                ],
                "confidence": 1.0
            }
        ]
    ]
}
4

1 回答 1

0

表单识别器 V2 最近已发布公开预览版。它现在支持带有标签功能的训练,您可以在训练模型之前尝试标记一些样本表单。通过这种方式,您可以更好地控制表单中的哪些数据是您感兴趣的。 https://docs.microsoft.com/en-us/azure/cognitive-services/form-recognizer/overview

于 2020-01-27T21:40:16.827 回答