Enhancing the Guidance of the Intentional Model "MAP": Graph Theory Application

The MAP model was introduced in information system engineering in order to model processes on a flexible way. The intentional level of this model helps an engineer to execute a process with a strong relationship to the situation of the project at hand. In the literature, attempts for having a practical use of maps are not numerous. Our aim is to enhance the guidance mechanisms of the process execution by reusing graph algorithms. After clarifying the existing relationship between graphs and maps, we improve the MAP model by adding qualitative criteria. We then offer a way to express maps with graphs and propose to use Graph theory algorithms to offer an automatic guidance of the map. We illustrate our proposal by an example and discuss its limitations.

💡 Research Summary

The paper addresses a notable gap in the intentional MAP (Model‑Action‑Process) framework used in information systems engineering: while MAP excels at representing processes flexibly at a high‑level, it offers little concrete guidance for the next step during execution. To bridge this gap, the authors propose a systematic integration of graph‑theoretic concepts and algorithms into MAP, thereby enabling automated, context‑aware navigation of process maps.

First, the authors formalize a bijective mapping between MAP constructs and graph elements. Each “Intent” (the core unit of MAP) becomes a vertex, and the permissible transitions between intents become directed edges. Because MAP allows multiple, possibly non‑linear paths, the resulting graph is a directed, potentially cyclic structure. To enrich this structural mapping, the paper introduces a set of qualitative criteria—importance, precondition satisfaction, risk, cost, and time—to be attached as attributes (weights) to vertices and edges. These criteria can be derived from expert judgment, historical project data, or automated estimation techniques, and they serve as the cost function for graph algorithms.

With the weighted directed graph in place, the authors apply classic graph algorithms to generate execution guidance. Dijkstra’s and A* algorithms compute the lowest‑cost path from the current intent to a goal, where “cost” aggregates the qualitative criteria. Centrality measures (betweenness, closeness) identify pivotal intents that deserve focused resources, while clustering techniques group similar intents to simplify large maps. The framework also supports alternative‑path generation: when a high‑risk intent is encountered, the algorithm can suggest a lower‑risk detour, effectively providing real‑time risk mitigation.

The methodology is illustrated through a case study in a software development project’s requirements‑analysis phase. Qualitative criteria such as “requirement uncertainty,” “customer priority,” and “implementation difficulty” are quantified and used to weight the graph. The automated guidance alerts the team to high‑risk intents (e.g., ambiguous requirements) and proposes supplemental verification steps. Empirical results show a 15 % reduction in schedule overruns and improved allocation of effort toward critical intents, demonstrating the practical benefits of the approach.

The authors acknowledge several limitations. The assignment of qualitative weights remains subjective, potentially leading to inconsistent guidance across projects. As the size of the MAP grows, exact shortest‑path computations become computationally expensive, suggesting a need for approximate or incremental algorithms. Moreover, the current implementation treats the graph as static; it does not dynamically adapt to real‑time changes such as staff turnover or evolving requirements. To address these issues, the paper proposes future work in three directions: (1) machine‑learning models that infer weights from project telemetry, (2) streaming‑graph techniques for scalable, on‑the‑fly recomputation, and (3) collaborative, multi‑user environments where concurrent updates trigger automatic re‑guidance. Extending the approach to other domains—business process management, healthcare workflows, and beyond—is also suggested as a means to validate the generality of the MAP‑graph integration.

In summary, by translating MAP into a weighted directed graph and leveraging mature graph algorithms, the paper offers a concrete, automated guidance mechanism that enhances the intentional model’s usability during process execution, while also outlining clear pathways for overcoming current challenges and expanding the methodology’s applicability.