luckypant10307-coder/sih26018_landrecorddigitization

How luckypant10307-coder/sih26018_landrecorddigitization works

This is a land-record digitization and validation application. An operator submits a document; the server extracts text, structures land-record fields, validates them and routes the result for approval, review, or blocking. Records and audit history are stored, and human corrections feed the learning loop. The README documents additional cadastral-map, geospatial and building-analysis capabilities. Some links are supported only by documented workflow or the source index; unsampled implementations are not assumed to have been inspected.

Main entry points: server.py HTTP API and ingestion · validator.py Rules and trust scoring · app.js Web application · ocr_engine.py OCR and text extraction

Components 20

User interface

Web application frontend/app.js

Document processing

HTTP API and ingestion backend/server.py
OCR and text extraction backend/ocr_engine.py
Land-field extraction backend/field_extractor.py
Document classification backend/doc_type.py
Optional field suggestions backend/llm_extractor.py
Indic script bridge backend/bhashini.py

Validation and learning

Rules and trust scoring backend/validator.py
Registry fact-check backend/fact_checker.py
Entity cross-check backend/ner_extractor.py
API authentication backend/auth.py
Records and audit store backend/db.py
Correction learning backend/learning.py
Anomaly detection backend/anomaly_detector.py

Cadastral and geospatial

Parcel map processing backend/cadastral.py
CityJSON processing backend/cityjson.py
Building height analysis backend/building_height.py
Open buildings data backend/open_buildings.py
Vertical analysis backend/vertical.py

Other components

Land-record operator

Connections 19

Land-record operator → Web application: submits documents README.md
Web application → HTTP API and ingestion: calls API README.md
HTTP API and ingestion → API authentication: verifies callers backend/server.py
HTTP API and ingestion → OCR and text extraction: extracts text README.md
HTTP API and ingestion → Land-field extraction: extracts fields README.md
HTTP API and ingestion → Document classification: classifies document backend/server.py
HTTP API and ingestion → Optional field suggestions: requests suggestions backend/server.py
HTTP API and ingestion → Rules and trust scoring: validates fields README.md
Rules and trust scoring → Registry fact-check: checks registry backend/validator.py
Rules and trust scoring → Entity cross-check: cross-checks entities backend/validator.py
HTTP API and ingestion → Records and audit store: stores outcomes README.md
HTTP API and ingestion → Correction learning: applies corrections README.md
HTTP API and ingestion → Anomaly detection: uses detection backend/server.py
HTTP API and ingestion → Indic script bridge: uses script bridge backend/server.py
HTTP API and ingestion → Parcel map processing: serves map workflows backend/server.py
HTTP API and ingestion → CityJSON processing: serves map workflows backend/server.py
HTTP API and ingestion → Building height analysis: serves building analysis run.py
HTTP API and ingestion → Open buildings data: uses building data run.py
HTTP API and ingestion → Vertical analysis: serves vertical analysis run.py

Drawn by GitDiagram on November 14, 2026 from the repository's file tree, README and source files. Read as Markdown ·