Organizations generate structured and unstructured evidence across workforce activities, projects, assessments, reports, and managerial communication, yet these data are often fragmented across different organizational systems. This study presents IntellicaHR, an Organizational Decision Support System assisted by Large Language Models. The system transforms everyday organizational activities into structured indicators and semantic evidence that can support analysis across organizational and management levels. The McKinsey 7S Framework organizes the collected evidence across key organizational dimensions, whereas Deming’s System of Profound Knowledge guides executive-level interpretation. We evaluated the proposed system through three literature-grounded synthetic organizational scenarios, along with supplementary analyses of its semantic-classification and executive-interpretation components. The scenarios produced distinct organizational profiles and role-specific decision-support outputs. An exploratory evaluation of the semantic-classification component showed substantial repeatability, robustness to prompt reformulation, and 95.0% agreement with human-derived sentiment labels, but it was not organization-specific validation. In a blinded human evaluation, 16 participants assessed three alternative executive interpretations: a descriptive Business Intelligence baseline, a generic Large Language Model interpretation, and the proposed Deming-grounded interpretation. The Deming-grounded interpretation received the highest overall ratings and significantly outperformed the Business Intelligence baseline, but not the generic Large Language Model condition. These findings support functional and interpretive coherence without establishing real-world diagnostic validity or organizational effectiveness.

Predefined educational content provides curricular control and consistent quality but remains non-personalized when all learners receive the same sequence and amount of practice. This study proposes Fuzzy Adaptive Revision with Bayesian Knowledge Tracing (FAR-BKT), a framework based on the assumption that educational items assessing the same or closely related knowledge can share learner evidence while retaining separate question-level mastery estimates and revision decisions. FAR-BKT extends fixed-parameter BKT through three adaptive mechanisms: a dynamic learning-transition probability $p\left(T\right)$, a context-sensitive slip probability $p\left(S\right)$, and an adaptive fuzzy mastery threshold $\theta$. The transition probability is adjusted based on group-level response accuracy, $p\left(S\right)$ from option confusability and learner error history, and the threshold determines whether individual questions remain active for further revision. Six matched policies were evaluated using 1000 heterogeneous synthetic learners, 24 questions, and eight knowledge groups. Dynamic $p\left(T\right)$ produced the greatest standalone improvement. FAR-BKT achieved the highest mastery coverage (0.462), lowest final estimation MAE (0.167), and highest removal precision (0.453), but required 11.1% more attempts than fixed BKT. The findings demonstrate an interpretable effectiveness–effort trade-off and provide computational, rather than classroom, evidence.

Organizations increasingly require integrated mechanisms to continuously interpret human, structural, and cultural signals often overlooked by conventional business intelligence and human resource systems. This study presents IntellicaHR, a web-based socio-technical Organizational Intelligence System integrating role-based workflows, normalized performance indicators, Large Language Model–supported semantic analysis and interpretation, gamification, and established management theory. The platform operationalizes the McKinsey 7S Framework for continuous organizational alignment monitoring and uses Deming’s System of Profound Knowledge to structure executive-level explanations and recommendations. Because real workplace data on emotional climate, leadership behavior, skill alignment, and conflict are ethically and practically difficult to obtain, the system is demonstrated using three literature-grounded synthetic organizational scenarios: a Healthy Organization, a Skill-Misaligned Organization, and a Toxic Management Environment. Scenario characteristics are formalized through fuzzy linguistic states and overlapping membership functions to generate synthetic users, reports, assessments, project interactions, and managerial communications over a 45-day simulation. These artifacts are processed through IntellicaHR’s native analytics and interpretation pipeline. The resulting metric profiles matched the intended scenario definitions and were clearly distinguishable. The Healthy Organization exhibited high participation, strong skill adequacy, positive emotional tone, and low conflict; the Skill-Misaligned Organization showed capability and execution deficiencies; and the Toxic Management Environment exhibited elevated conflict, negative emotional patterns, and weaker managerial responsiveness. These findings demonstrate the functional coherence and scenario-sensitive behavior of IntellicaHR as a proof-of-concept artifact but do not establish real-world diagnostic accuracy, predictive validity, or organizational effectiveness, which require future longitudinal evaluation with real users and organizational data.