The Kisan Call Centre is a crucial platform that bridges the farming communities and the government in addressing the various agricultural queries across India. However, the predominant redundant queries concerning geographical location strain human advisors by making them perform the routine, mundane tasks. By harnessing advanced analytics, this study uncovers geospatial patterns in farmer queries with the intention of driving IPA (Intelligent Process Automation) in agricultural advisories. By using the dataset sourced from the Open Government Data portal, which had 1,59,325 Kisan Call Centre records from various districts of Tamil Nadu, Geo-clustering via K-Means clustering was performed by geotagging districts with latitude-longitude coordinates, which was then validated through the Elbow Method and Silhouette Score, resulting in four optimal regional clusters. Frequent patterns were extracted using the FP-Growth algorithm within each cluster, uncovering hidden, seasonal, and location-specific high-frequency queries. Key insights include increased Animal Husbandry and Weather queries during summer, a concentration of Black Gram-related questions in Viluppuram during winter, and consistent horticulture queries in Kanchipuram. These findings enable two impactful recommendations in reducing advisor workload by implementing IVRS automation for high-frequency questions and integrating a district-aware AI recommender bot for query suggestions tailored to regional needs. This research promotes a scalable, data-driven, enhanced agri-advisory system that supports digital governance and improves service delivery efficiency across the nation.