Dynamic Knowledge Intelligence for Human AI Collaborative Operational Decision Making Across Distributed Enterprise Data Environments

Abstract

Distributed enterprise environments frequently contain fragmented operational data distributed across ERP platforms, CRM systems, workflow logs, IoT streams, and unstructured document repositories, which reduces the speed and consistency of managerial response. This study proposes a dynamic knowledge intelligence framework that integrates heterogeneous enterprise data, transforms them into a temporal contextual knowledge layer, and connects that layer to an operational decision engine for action prioritization. The framework was evaluated across five analytical dimensions, namely integration quality, knowledge graph enrichment, recommendation performance, response efficiency, and cross-domain business impact. The harmonization stage improved integration consistency from 0.61 to 0.89 for ERP data, from 0.58 to 0.85 for CRM data, from 0.64 to 0.91 for workflow logs, from 0.47 to 0.78 for documents, and from 0.55 to 0.84 for IoT streams, with error reduction ranging from 26% to 34%. In the contextual intelligence layer, knowledge graph nodes increased from 120 at T1 to 352 at T5, while relations expanded from 210 to 812, indicating that contextual linkage grew faster than object accumulation. The decision engine produced strong recommendation performance across five enterprise scenarios, with accuracy values of 0.88 for backlog control, 0.91 for inventory risk, 0.86 for escalation routing, 0.83 for policy conflict, and 0.89 for resource allocation, while expert alignment ranged from 0.81 to 0.90. Efficiency analysis showed average decision latency of 0.82 seconds at 50 concurrent requests, 1.04 seconds at 100 requests, 1.36 seconds at 200 requests, 1.95 seconds at 400 requests, and 2.88 seconds at 800 requests, confirming stable operational responsiveness under low to heavy workloads and controlled degradation only under stress-level concurrency. Business impact analysis further showed differentiated strategic gains, including 28% higher response speed in service management, 31% stronger risk mitigation in supply chain settings, 33% better decision traceability in governance contexts, 20% stronger coordination quality in resource alignment, and 24% better decision consistency in enterprise-wide operations. These findings demonstrate that the proposed framework effectively converts fragmented enterprise data into contextual, updateable, and decision-ready intelligence, thereby improving operational agility, recommendation credibility, and cross-domain decision value in distributed enterprise environments.