fix(data-process): 收准结构化预处理能力文案
This commit is contained in:
@@ -99,8 +99,8 @@ const chunkMethodLabelMap: Record<string, string> = {
|
||||
|
||||
const preprocessOptionLabelMap: Record<string, string> = {
|
||||
clean_invalid: '清理无效数据',
|
||||
detect_structure: '识别表格结构',
|
||||
deduplicate: '重复数据去重',
|
||||
detect_structure: '嵌套结构展平',
|
||||
deduplicate: '重复记录去重',
|
||||
normalize_format: '数据格式标准化',
|
||||
filter_anomaly: '异常数据过滤',
|
||||
desensitize: '敏感信息脱敏',
|
||||
|
||||
@@ -27,8 +27,16 @@ const PREPROCESS_OPTIONS: Array<{
|
||||
description: string
|
||||
}> = [
|
||||
{ value: 'clean_invalid', label: '清理无效数据', description: '清理全空列,并剔除关键字段残缺的数据行' },
|
||||
{ value: 'detect_structure', label: '识别表格结构', description: '识别多级表头与合并单元格,并将嵌套字段展平' },
|
||||
{ value: 'deduplicate', label: '重复数据去重', description: '基于整行精确匹配和关键字段组合删除重复记录' },
|
||||
{
|
||||
value: 'detect_structure',
|
||||
label: '嵌套结构展平',
|
||||
description: '展平嵌套对象和可解析的 JSON 字段;Excel 表头与合并单元格在上传时自动解析',
|
||||
},
|
||||
{
|
||||
value: 'deduplicate',
|
||||
label: '重复记录去重',
|
||||
description: '按整行内容或 id、uuid、key、code、*_id 等身份字段去重,暂不支持自定义组合字段',
|
||||
},
|
||||
{ value: 'normalize_format', label: '数据格式标准化', description: '按所选规则统一编码、空白、字段名及 JSON 序列化格式' },
|
||||
{ value: 'filter_anomaly', label: '异常数据过滤', description: '使用 IQR 识别数值离群值,并过滤乱码等异常记录' },
|
||||
{ value: 'desensitize', label: '敏感信息脱敏', description: '识别并脱敏姓名、手机号、邮箱和身份证号' },
|
||||
|
||||
Reference in New Issue
Block a user