Hi

I have a word processing project

And different texts are going to get different tags (for example, categories, etc.)

And I want to find the percentage of similarity between the two texts, and if they are very similar (percentage of variable estimates), then the whole process of the method is not done and I understand duplication

Now this part can have nothing to do with Learning, and the search can be done with different algorithms.

It can also be different

I have little knowledge of word processing

And I used to have a few small projects with Python that, for example, out of the last 100 texts, check that they are not duplicates and get the duplication vector.

I wanted to see what is the optimal way ??