It looks like a solution, but you would have to take into account different variations of “adults” and “children”… Like “miniors”, “kids”, “son”, “sons”, “daughter”, “daughters”, “grown-ups”, etc… and have different examples in your NLU file for each one.
Filter might be quicker than a regex though:
children = tracker.get_slot('children_count')
children_value = int(''.join(filter(str.isdigit, children)))
I have a similar problem with extracting through context, that is still unsolved: