Business document standards usually cover a hierarchical structure of thousands of elements that may be relevant in any business context (any industry, any geopolitical region, etc.). In order to use a business document standard in a specific context, user groups define so-called implementation guidelines based on a subset consisting usually of 3-5% of the overall elements. When one defines a new implementation guideline for a specific context, one has always to start from scratch, which is time-consuming and also leads to heterogeneous interpretations of the standard. It is our goal to speed up the development process and to create more homogeneous implementation guidelines by learning from existing models. In the previous phases of our research we have developed the Enhanced Unified Context (E-UCM) model to represent business context. If we could assign instances of this model to already existing business document implementation guidelines, we may guess the subset of a new implementation guideline for a required BC. Accordingly, this paper describes our approach to calculate the content model (subset) of a message implementation guideline which is relevant in a required BC presented by the E-UCM context model.