The problem with having a plugin AI system is that It will be very generic and might not cover the area of interest that you are working on. Good news is that all pretrained models can be trained specifically for one's use case, but to achieve a good accuracy one will need a lot of data which can either be generated or gathered. Once the data is in place and selection of pre-trained model has been made, it is just matter of time before you can have a good - great system working for you. One can keep training the system every time it the system runs into a dead end to make it more robust and aligned to the task at hand. Let me know if you'd like a detailed orientation on the above approach. regards, Deepesh

1. To tackle the problem of extracting relevant topics of "key-words" from a text (posts, tags, conversation) a simple NER (Named Entity Recognition) system can be used. It can create a list of all the relevant Topics in the text. 2. Once you have the list, this list can be used in another DL algorithm - Recommendation System. Challenges with a Recommendation System is that it requires a lot of pre-training data and a huge resource to train. (This is only viable in cases where you already have a good amount of tagged data and do not have any constraints in terms of using bigger resources). 3. Another simpler, faster but less accurate way is to use a clustering model ( can be from ML or DL depending on the data ). This approach creates multiple clusters and can tag each element in the NER list with one of the clusters. Then using distance formula within the cluster one can find out the most relevant topics that are related to the element in the NER list. If you'd like more details on the approach let me know. Regards, Deepesh