10 KiB
10 KiB
OCR 解析功能更新文档
功能描述
修改了 /marriage/ocr/parse 接口的返回结果结构，新增 probability（识别概率）和 location（定位信息）字段，参考百度结婚证识别API的返回格式。
新增DTO类
1. OcrProbability.java
表示OCR识别结果的概率信息
{
"average": 20.68798065, // 平均概率
"min": 0.9106679559 // 最小概率
}
2. OcrLocation.java
表示OCR识别结果在图片中的位置信息
{
"width": 109, // 宽度
"height": 47, // 高度
"top": 933, // 顶部距离
"left": 253 // 左侧距离
}
3. OcrFieldData.java
表示单个字段的完整识别数据
{
"word": "王连杰", // 识别的文本内容
"probability": {...}, // 识别概率
"location": {...} // 识别结果的位置
}
API 返回格式
请求
POST /marriage/ocr/parse
Content-Type: application/json
{
"mobile": "18888888888",
"smsCode": "123456",
"uploadId": "xxxxx"
}
响应
{
"code": 200,
"msg": "success",
"data": {
"raw": "{原始百度API返回的JSON响应}",
"words": ["王连杰", "320321199504011218", ...],
"parsed": {
"husbandName": "王连杰",
"wifeName": "张丹",
"husbandId": "320321199504011218",
"wifeId": "320321199406197047",
"husbandBirthDate": "1995-04-01",
"wifeBirthDate": "1994-06-19",
"husbandNationality": "中国",
"wifeNationality": "中国",
"husbandGender": "男",
"wifeGender": "女",
"marriageNo": "320321201700004108",
"certificateHolder": "王连杰",
"registerDate": "2017-04-01"
},
"parsed_detailed": {
"husbandName": {
"word": "王连杰",
"probability": {
"average": 20.68798065,
"min": 0.9106679559
},
"location": {
"width": 109,
"height": 47,
"top": 933,
"left": 253
}
},
"wifeName": {
"word": "张丹",
"probability": {
"average": 19.14912224,
"min": 0.8554975986
},
"location": {
"width": 83,
"height": 43,
"top": 1204,
"left": 239
}
},
"husbandId": {
"word": "320321199504011218",
"probability": {
"average": 13.2870388,
"min": 0.5172381401
},
"location": {
"width": 341,
"height": 68,
"top": 1081,
"left": 343
}
},
"wifeId": {
"word": "320321199406197047",
"probability": {
"average": 15.98988342,
"min": 0.6194867492
},
"location": {
"width": 336,
"height": 56,
"top": 1351,
"left": 326
}
},
"husbandBirthDate": {
"word": "1995-04-01",
"probability": {
"average": 20.66628647,
"min": 0.7240950465
},
"location": {
"width": 250,
"height": 55,
"top": 1044,
"left": 857
}
},
"wifeBirthDate": {
"word": "1994-06-19",
"probability": {
"average": 25.62935066,
"min": 0.9226108789
},
"location": {
"width": 255,
"height": 56,
"top": 1322,
"left": 829
}
},
"husbandNationality": {
"word": "中国",
"probability": {
"average": 17.19703484,
"min": 0.7144192457
},
"location": {
"width": 79,
"height": 43,
"top": 1011,
"left": 249
}
},
"wifeNationality": {
"word": "中国",
"probability": {
"average": 23.41218376,
"min": 0.9498358369
},
"location": {
"width": 79,
"height": 46,
"top": 1264,
"left": 242
}
},
"husbandGender": {
"word": "男",
"probability": {
"average": 24.97878838,
"min": 0.9302400351
},
"location": {
"width": 39,
"height": 40,
"top": 973,
"left": 792
}
},
"wifeGender": {
"word": "女",
"probability": {
"average": 21.57674408,
"min": 0.8877936602
},
"location": {
"width": 42,
"height": 42,
"top": 1243,
"left": 765
}
},
"marriageNo": {
"word": "320321201700004108",
"probability": {
"average": 16.35309982,
"min": 0.6457977891
},
"location": {
"width": 363,
"height": 44,
"top": 650,
"left": 272
}
},
"certificateHolder": {
"word": "王连杰",
"probability": {
"average": 16.20750237,
"min": 0.6932016015
},
"location": {
"width": 119,
"height": 44,
"top": 362,
"left": 271
}
},
"registerDate": {
"word": "2017-04-01",
"probability": {
"average": 19.06731987,
"min": 0.7248777151
},
"location": {
"width": 354,
"height": 42,
"top": 511,
"left": 272
}
}
}
}
}
主要变更
1. 返回字段说明
| 字段 | 类型 | 说明 |
|---|---|---|
| raw | String | 百度API原始返回的JSON响应 |
| words | Array | 识别的所有文本内容（旧格式，用于兼容） |
| parsed | Object<String, String> | 简化后的解析结果（仅包含文本，用于向后兼容） |
| parsed_detailed | Object<String, OcrFieldData> | 新增 详细的解析结果（包含probability和location） |
2. 向后兼容性
parsed字段保持不变，仍然返回简化后的Map<String, String>格式- 新增
parsed_detailed字段，返回完整的字段数据，包括：word：识别的文本probability：识别的概率信息（average和min）location：识别结果在图片中的位置信息
3. 识别字段列表
支持的结婚证识别字段包括：
husbandName- 男方姓名husbandId- 男方身份证号husbandBirthDate- 男方出生日期husbandNationality- 男方国籍husbandGender- 男方性别wifeName- 女方姓名wifeId- 女方身份证号wifeBirthDate- 女方出生日期wifeNationality- 女方国籍wifeGender- 女方性别marriageNo- 结婚证字号certificateHolder- 持证人registerDate- 登记日期remark- 备注
使用示例
获取识别概率信息
// 获取女方姓名的识别概率
double wifeNameAverage = response.data.parsed_detailed.wifeName.probability.average;
double wifeNameMin = response.data.parsed_detailed.wifeName.probability.min;
获取识别位置信息
// 获取男方姓名的位置信息
int width = response.data.parsed_detailed.husbandName.location.width;
int height = response.data.parsed_detailed.husbandName.location.height;
int top = response.data.parsed_detailed.husbandName.location.top;
int left = response.data.parsed_detailed.husbandName.location.left;
获取简化文本（向后兼容）
// 仍然可以使用parsed字段获取简化的结果
String husbandName = response.data.parsed.husbandName;
技术实现
新增方法
-
parseMarriageFieldsFromRawDetailed(String ocrResp)
- 从百度API原始响应中提取详细的字段数据
- 返回
Map<String, OcrFieldData>格式
-
extractFieldData(JsonNode arr)
- 从JSON数组中提取单个字段的完整数据
- 包含word、probability、location三个部分
- 返回
OcrFieldData对象
-
convertToSimpleParsed(Map<String, OcrFieldData> parsedDetailed)
- 将详细的字段数据转换为简化的字符串映射
- 用于维持向后兼容性
- 返回
Map<String, String>格式
注意事项
- 如果百度API返回的字段不包含probability或location信息，这些字段将为null
- 地址信息中的width、height、top、left均为图片中的像素坐标
- 概率值为0-100之间的浮点数，越高表示识别准确度越高
- 处理日期字段会自动进行格式转换（从"YYYY年MM月DD日"转换为"YYYY-MM-DD"）
- 结婚证字号会自动提取数字部分（移除非数字字符）