Imagine that you were a representative replying to customer online and you are asking more or less the same questions over and over to your customer. Would you like to get automatic suggestions instead of typing the same thing again and again? An autocomplete can be helpful, faster, and convenient and also correct any grammatical / spelling error at the same time. In the jupyter notebook in this project, we select a history of sentences written by the representatives and the customer, format and correct them using a few regex rules and count them so we can estimate their frequency and likeliness to be useful again. After the calculation of a similarity matrix based on the sklearn tfidf tool (frequency and normalization of words), we use this matrix to calculate the similarity between the new few words written by the representative and the history of messages written in the past. The Autocomplete will recognize the closest sentences and rank 3 final proposals:
ahad1105/Automatic-Text-Suggestion-System-
Folders and files
| Name | Name | Last commit date | ||
|---|---|---|---|---|