数据集概览
| 数据集名称 | 征收补偿项目数据集 |
| 数据总量 | 8,400 个项目案例(覆盖房屋征收 + 土地征用全流程) |
| 项目类型 | 国有土地上房屋征收 / 集体土地征收 / 城中村改造 / 棚户区改造 / 旧城改造 |
| 时间跨度 | 2012 - 2026 年 |
| 覆盖维度 | 项目概况、补偿方案、签约进度、资金管理、司法程序、信访维稳 |
| 数据来源 | 政府征收办公系统、自然资源部门、住建部门公开数据、裁判文书网 |
| 格式输出 | JSON / CSV / Excel / 知识图谱 |
数据维度详细说明
| 字段名称 | 数据类型 | 取值范围/说明 |
|---|---|---|
| project_id | String(32) | 项目___UNIQUE_TECH___专属ID___UNIQUE_TECH___ |
| project_name | Text | 项目名称(脱敏处理) |
| project_type | Enum | HOUSE_EXPROPRIATION | LAND_ACQUISITION | URBAN_RENEWAL | SHANTYTOWN |
| region | String | 省-市-区县 |
| total_area_sqm | Float | 征收总面积(平方米) |
| household_count | Integer | 涉及户数 |
| total_budget | Float | 项目总预算(万元) |
| compensation_mode | Enum | MONETARY | PROPERTY_SWAP | VOUCHER | HYBRID |
| signing_rate | Float | 签约率 0.0 - 1.0 |
| project_duration_days | Integer | 项目周期(天) |
| litigation_count | Integer | 涉及司法案件数量 |
| milestones | Array | [{phase, date, status, remark}] |
脱敏 JSON 数据样例
[
{
"project_id": "LAC-2024-GD-SZ-0012",
"project_name": "深圳市[区域]城市更新单元征收项目",
"project_type": "URBAN_RENEWAL",
"region": "广东省-深圳市-南山区",
"total_area_sqm": 48500.0,
"household_count": 312,
"total_budget": 82500.0,
"compensation_mode": "VOUCHER",
"signing_rate": 0.93,
"project_duration_days": 540,
"litigation_count": 3,
"milestones": [
{"phase": "立项公告", "date": "2024-01-15", "status": "COMPLETED"},
{"phase": "评估公示", "date": "2024-03-20", "status": "COMPLETED"},
{"phase": "签约期", "date": "2024-05-01", "status": "COMPLETED"},
{"phase": "搬迁交付", "date": "2025-01-15", "status": "IN_PROGRESS"}
]
},
{
"project_id": "LAC-2023-ZJ-HZ-0045",
"project_name": "杭州市[区域]集体土地征收项目",
"project_type": "LAND_ACQUISITION",
"region": "浙江省-杭州市-余杭区",
"total_area_sqm": 123000.0,
"household_count": 186,
"total_budget": 45200.0,
"compensation_mode": "PROPERTY_SWAP",
"signing_rate": 0.97,
"project_duration_days": 420,
"litigation_count": 0,
"milestones": [
{"phase": "预公告", "date": "2023-06-01", "status": "COMPLETED"},
{"phase": "补偿方案公告", "date": "2023-08-15", "status": "COMPLETED"},
{"phase": "签约", "date": "2023-10-01", "status": "COMPLETED"}
]
},
{
"project_id": "LAC-2024-HN-CS-0078",
"project_name": "长沙市[区域]城中村改造项目",
"project_type": "URBAN_RENEWAL",
"region": "湖南省-长沙市-岳麓区",
"total_area_sqm": 28700.0,
"household_count": 205,
"total_budget": 36800.0,
"compensation_mode": "HYBRID",
"signing_rate": 0.89,
"project_duration_days": 365,
"litigation_count": 5,
"milestones": [
{"phase": "前期调查", "date": "2024-02-10", "status": "COMPLETED"},
{"phase": "方案公示", "date": "2024-04-20", "status": "COMPLETED"},
{"phase": "集中签约", "date": "2024-06-01", "status": "IN_PROGRESS"}
]
},
{
"project_id": "LAC-2022-JS-NJ-0091",
"project_name": "南京市[区域]棚户区改造项目",
"project_type": "SHANTYTOWN",
"region": "江苏省-南京市-鼓楼区",
"total_area_sqm": 15200.0,
"household_count": 478,
"total_budget": 62300.0,
"compensation_mode": "MONETARY",
"signing_rate": 0.95,
"project_duration_days": 480,
"litigation_count": 2,
"milestones": [
{"phase": "意愿征询", "date": "2022-09-01", "status": "COMPLETED"},
{"phase": "征收决定", "date": "2023-01-10", "status": "COMPLETED"},
{"phase": "补偿完成", "date": "2023-09-30", "status": "COMPLETED"}
]
},
{
"project_id": "LAC-2025-SC-CD-0015",
"project_name": "成都市[区域]国有土地上房屋征收项目",
"project_type": "HOUSE_EXPROPRIATION",
"region": "四川省-成都市-武侯区",
"total_area_sqm": 35200.0,
"household_count": 156,
"total_budget": 51300.0,
"compensation_mode": "HYBRID",
"signing_rate": 0.91,
"project_duration_days": 390,
"litigation_count": 1,
"milestones": [
{"phase": "调查登记", "date": "2025-01-05", "status": "COMPLETED"},
{"phase": "方案论证", "date": "2025-03-15", "status": "COMPLETED"},
{"phase": "签约启动", "date": "2025-05-01", "status": "IN_PROGRESS"}
]
}
]
AI 训练适用场景
征收补偿金额预估
适用模型:XGBoost / LightGBM / CatBoost。基于历史项目多维度特征训练补偿金额回归预测模型,辅助预算编制。
签约率预测与风险预警
适用模型:Gradient Boosting + SHAP。预测项目签约率走势,识别影响签约的关键因素,提前预警风险项目。
征收项目智能排期
适用模型:CPM/PERT + 强化学习(DQN)。基于历史项目关键路径数据训练领先排期策略模型。
行政诉讼结果预测
适用模型:Legal-BERT + 多分类器。基于征收补偿司法案例训练案件胜诉/败诉预测模型,辅助应诉策略制定。
认证专家网络
5000+
认证科研专家
覆盖数学、物理、化学、生物、地学、计算机六大学科
四重
质量审核体系
学术资质审核、专业能力评估、数据标注培训、质量持续监控
AI+
人机协同标注
AI预标注+专家复核,效率提升300%,准确率99.5%+