摘要：The problem of objectively assessing activity patterns of individual players in team sports in terms of tactics skills is addressed
by employing concepts from fuzzy logics and state-transition graph models. This approach aims at providing high level
descriptions of activity patterns based on local positioning measurements. Mackenzie & Cushion (2013) conclude in their
critical review about current performance analysis (PA) research that variables are often investigated as a result of availability
rather than to develop a deeper understanding of performance. Therefore, PA studies often fail to provide useful information for
the coaching practice due to the multifaceted, complex and largely unpredictable behaviour in team sports like football. In the
author’s opinion holistic approaches are needed that include more naturalistic and qualitative methods such as case studies and
interviews. The overall goal is to develop a data-based approach based on position and tracking data provided by local
positioning measurement systems (see, e.g., Leser et al. (2011), Mackenzie & Cushion (2013), Ogris et al. (2012)) that allows
the qualification of assessments based on measurements. Tactical assessments are typically semi-structured and, above all,
expressed in qualitative, vague and imprecisely defined linguistic concepts. Moreover, often such assessment statements rely on
implicit common-sense and intuitive reasoning assumptions. Therefore, we postulate that the knowledge representation has to
satisfy the following properties: K1) the vagueness and imprecision related to temporal, spatial and spatio-temporal
relationships have to be expressed in a form that is appropriate for human experts and users; K2) the knowledge base design
should allow a hierarchical representation of the scenarios at different abstraction levels; K3) the design has to be based on a
well-defined formalism and semantics that allows a formal analysis of different spatial, temporal and spatio-temporal
relationships among the objects and conclusions based thereupon. Further, from the point of view of feasibility and practical
usefulness, we postulate that the design of the knowledge base allows D1) a modular, object-oriented programming paradigm
based approach in the sense that the overall knowledge base results from designing the knowledge bases for each player
independently and, in a second step, the interaction options between the players, D2) an efficient evaluation of hypotheses for
real-time applications, D3) to visualize at least small or moderate-sized parts of the knowledge base by intuitive graphical
representation models.
