Initial: integrated 2025 LawGraph (graphrag_pipeline) + 2026 kg_project

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
2026-06-17 10:13:39 +08:00
commit 6c1a69af0d
83 changed files with 14295 additions and 0 deletions
@@ -0,0 +1,86 @@
+project_name: "urban_planning_law_kg"
+project_description: "城市规划法律法规知识图谱构建"
+
+data:
+  source_dir: "E:\\Project\\SI\\2026_KG_PlanningLaw\\data\\城市规划法律法规\\城市更新法规数据库"
+  total_documents: 296
+  categories:
+    - {id: 0, name: "0知识图谱目录", type: "Index"}
+    - {id: 1, name: "1法律", type: "Law"}
+    - {id: 2, name: "2行政法规", type: "AdministrativeRegulation"}
+    - {id: 3, name: "3部门规章", type: "DepartmentalRule"}
+    - {id: 4, name: "4党中央国务院文件", type: "PolicyDocument"}
+    - {id: 5, name: "5国家主管部门文件", type: "PolicyDocument"}
+    - {id: 6, name: "6主要技术标准", type: "PolicyDocument"}
+  min_text_length: 50
+
+api:
+  config_file: "config/api_keys.yaml"
+  model: "deepseek-chat"
+  max_tokens: 8192
+  temperature: 0.0
+
+processing:
+  concurrent_requests: 5
+  max_retries: 3
+  retry_delay: 2
+  batch_size: 10
+
+paths:
+  config_dir: "config"
+  data_dir: "data"
+  output_dir: "output"
+  logs_dir: "logs"
+  ontology_dir: "ontology"
+  scripts_dir: "scripts"
+  src_dir: "src"
+
+ontology:
+  ontology_file: "ontology/legal_ontology.json"
+  entity_ontology_file: "config/legal_ontology.yaml"
+
+neo4j:
+  uri: "bolt://localhost:7687"
+  username: "neo4j"
+  password: "password"
+  database: "neo4j"
+
+extraction:
+  entity_types:
+    - Law
+    - AdministrativeRegulation
+    - DepartmentalRule
+    - PolicyDocument
+    - Chapter
+    - Section
+    - Article
+    - GovernmentBody
+    - LegalSubject
+    - SpatialConcept
+    - AdministrativeProcedure
+    - Obligation
+    - Penalty
+    - TimePoint
+    - Region
+  relation_types:
+    - cites
+    - implements
+    - amends
+    - replaces
+    - supplements
+    - issued_by
+    - implemented_by
+    - regulates
+    - defines_spatial
+    - requires_procedure
+    - sets_obligation
+    - prescribes_penalty
+    - applies_to
+    - governs_region
+  confidence_threshold:
+    entity: 0.8
+    relation: 0.7
+
+logging:
+  level: "INFO"
+  format: "%(asctime)s - %(name)s - %(levelname)s - %(message)s"