| CPC G06F 16/9535 (2019.01) [G06F 16/9532 (2019.01); G06F 16/9536 (2019.01); G06F 16/9577 (2019.01)] | 20 Claims |

|
1. A computer-implemented method comprising:
receiving a search query from a device of a user, wherein the search query is associated with executing a function on an online platform;
performing a search, via the online platform, based on the search query to generate search results;
determining, by a machine learning (ML) model, an intent of the user associated with the search query based on input for the ML model comprising the search query, user profile information associated with the user, and activity information of the user;
generating a prompt based on the search query, the intent of the user, and one or more relationships between the user and one or more entities, wherein generating the prompt further comprises:
selecting a prompt template from a plurality of prompt templates based on the intent of the user, wherein different intents are associated with different prompt templates, the prompt template including a field for the intent of the user that is different from fields in other prompt templates from the plurality of prompt templates, the prompt template comprising fields for the intent, the search query, and the one or more relationships; and
filling in the fields in the selected prompt template with the intent, the search query, and the one or more relationships;
feeding as input the prompt and a subset of the search results to a generative artificial intelligence (GAI) model;
receiving a summary from the GAI model in response to the prompt, wherein the summary is based on the intent of the user; and
causing presentation of the summary and one or more of the search results returned by the search on a user interface (UI) of the device of the user.
|