Techniques to facilitate online commerce by leveraging user activity

A computer-implemented method, comprising:

• processing, by a computing system, a natural language search query from a chatbot interface, the search query comprising a set of words;
• generating, by the computing system, a result to the search query for presentation on the chatbot interface, the result comprising a list of items based on the set of words, wherein generating the search result comprises:
• correlating one or more of the words in the set of words by a trained machine learning model to determine a relevance score associated with an item based on a word-frequency pair value associated with the item;
• adding of the item to the list of items based on the relevance score exceeding a threshold value;
• determining an order for the list of items based on historical user selections associated with prior search queries;
• and
• identifying of one or more terms to suggest for a dynamic natural language search query;
• processing, by the computing system, an item selected from the list of items via the chatbot interface;
• updating, by the computing system, the trained machine learning model based on the set of words received in the search query and the item selected from the list of items;
• and
• updating a set of search filters based on the trained machine learning model updated based on the set of words and the item.

A non-transitory computer-readable storage medium, comprising a plurality of instructions, that when executed, enable processing circuitry to:

• receive a natural language search query via a chatbot interface, the search query comprising a set of words;
• generate a result to the search query via a machine learning model, generation of the result to comprise:
• correlation of one or more of the words in the set of words by the machine learning model to determine a relevance score associated with an item based on a word-frequency pair value associated with the item;
• addition of the item to a list of items based on the relevance score exceeding a threshold value;
• determination of an order for the list of items based on historical user selections associated with prior search queries;
• and
• identification of one or more terms to suggest for a dynamic natural language search query;
• cause, on the chatbot interface, presentation of the result to the search query, the result comprising the list of items generated based on the set of words and the machine learning model applied to the set of words;
• receive a selection of an item from the list of items via the chatbot interface;
• and
• update the machine learning model based on the set of words received in the search query and the selection of the item from the list of items.