Among the many possible observations, we point out only the role of blinking: there is usually as an accompaniment agreement, either its beginning or its end (although with fewer incidents, the same goes for disagreements). The beginning of the agreement is also strongly related to “e,down”, that is, the spokesperson stops looking down – look up effectively, it will most likely touch the eyes of the agent. If the speaker often begins to look down (“b,down”), as he begins to accept, this may suggest a moment of reflection and, ultimately, it is the turn to continue the conversation. Table 11 confirms what we have seen in the simplest two-event diagrams: head-shaking is both before and after the expression of disagreements. In addition, conthesatatives and backchannel are among the most common events involved in more complex patterns, including integration. The set of 111 formal dialogues and 111 informal dialogues (each of the same 60 male spokespeople and 51 women) was included in the discovery of models. Comments from an action, for example. B “rotation of the head to the right based on video observation” were divided into two events: one for the beginning, the other for the end of the given head turn, such as “v_head,b, right” and “v_head,e,right”. Out of a total of 3,929,630 with ratings (1,964,815 for the start and the same amount, 1.964,815 for the end of an action) a large number of them were actually found in either model: 1,699,825 described the beginning (86.5% of all “Begin” events designated by ratings) and 1,469,751 designated the end of a particular event (74.8% of all event end events). Events contributed to the complexity of the resulting patterns so that more than one instance of the same type of event could be part of a particular (more complex) model as shown in the f003 file: We can see that the frequency of the elements in the notes does not necessarily correspond to their frequency in the actual models: attention, the most common element is classified only as the third most common element that appears in a diagram , it is determined by a frequency. These frequency data give us an insight into the nature of recorded conversations: there were many moments of attention, as a natural component of a dialogue, but the fact that there were more moments of disagreement (by default) than the agreement also suggests that the interaction was fairly free. The small number of rejection objects, axis increases of doubts and surprise hands suggest that the interaction does not contain much direct confrontation. Another set of observations to determine the degree of agreement showed that there were 2331 cases of the uninteresting element – another reflection of the interlocutor on a moment of interaction.