Human–AI Collaborative Decision Intelligence for Enterprise Knowledge Navigation and Strategic Action Recommendation Through Conversational Interaction
Main Article Content
Abstract
Enterprise decision-making increasingly depends on the ability to navigate fragmented organizational knowledge and convert it into actionable strategic guidance. This study proposes a conversational decision intelligence framework that integrates user intent interpretation, enterprise-aware knowledge retrieval, contextual reasoning, and criteria-based strategic action recommendation. The framework transforms heterogeneous enterprise documents, including policies, reports, meeting notes, project logs, and risk records, into indexed knowledge units through preprocessing, semantic segmentation, metadata enrichment, and embedding generation. The corpus transformation results show that 1,040 raw documents were converted into 2,890 knowledge chunks, with metadata completion ranging from 94.4% to 95.9% across source types. Retrieval evaluation across five decision scenarios produced strong performance, with precision scores between 0.82 and 0.93, recall scores between 0.86 and 0.92, and F1-scores between 0.84 and 0.90. Policy compliance achieved the highest precision at 0.93, while operational diagnosis achieved the highest recall at 0.92. The recommendation mechanism ranked strategic actions using impact, feasibility, urgency, risk control, and organizational fit, where risk escalation achieved the highest priority due to strong impact and urgency values. Conversational coherence remained stable across multi-turn same-domain dialogues, increasing from 0.86 to 0.92, while domain-shift dialogue showed lower coherence between 0.74 and 0.81. Compared with conventional search-based support, the proposed framework improved retrieval precision by 18.9%, recommendation relevance by 24.3%, conversational coherence by 19.4%, strategic usability by 23.5%, and transparency by 38.5%. These findings indicate that conversational decision intelligence can reduce knowledge navigation friction, improve evidence traceability, and support more accountable strategic action recommendation in enterprise environments.
Article Details

This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
Authors who publish with International Journal for Applied Information Management agree to the following terms: Authors retain copyright and grant the International Journal for Applied Information Management right of first publication with the work simultaneously licensed under a Creative Commons Attribution License (CC BY-SA 4.0) that allows others to share (copy and redistribute the material in any medium or format) and adapt (remix, transform, and build upon the material) the work for any purpose, even commercially with an acknowledgement of the work's authorship and initial publication in International Journal for Applied Information Management. Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in International Journal for Applied Information Management. Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).