Intelligent Water Administration

Overview

As water metering data has traditionally been managed manually, difficulties have arisen in billing and handling civil petitions. To address this, an intelligent water administration service was planned to integrate water bill inquiry, payment, and usage monitoring. This service implements an optimal algorithm by merging the core Azure Vision AI model with specialized local datasets to modernize administrative processes.

Project description

Yangpyeong County introduced a mobile-based "Self-Metering Function," allowing residents to verify their own water consumption and pay bills directly. Furthermore, prediction models and anomaly detection functions were developed to enable public officials to easily monitor water usage status. These tools allow for the early identification of potential leaks or meter malfunctions by analyzing usage patterns against predicted data.

Key technological features

• Transmission of Self-Metering Data via AI-powered Optical Character Recognition (OCR): Enabling the transmission of self-metering data by recognizing digits on water meters through AI OCR technology
• Implementation of Water Usage Prediction and Anomaly Detection: Applying a localized model trained on water meter data based on the Azure Vision model to predict usage and detect abnormal patterns

Expected outcomes

By improving the water metering and billing management processes, the system is expected to reduce administrative costs and significantly enhance convenience for both water users and public officials. The transition to an automated, AI-driven system ensures higher data accuracy and faster response times for water-related administrative service.

Launch year: 2024

Attribution

Case study courtesy of the National Information Society Agency, Republic of Korea, Apolitical's Content Partner. Sourced from Use Cases of Public AI Service, Vol.2, https://eng.nia.or.kr/site/nia_eng/ex/bbs/View.do?cbIdx=31975&bcIdx=29182&parentSeq=29218