Systems and methods for generating prompts for machine learning models based on user-selected source document information
AssigneeInstabase, Inc.
InventorsVishnu Chopra, Zhenya Gu
Life of this patent
Estimating the term…
Abstract
Systems and methods for generating prompts for a machine learning model based on user-selected source document information are disclosed. Exemplary implementations may: present a user interface, wherein the user interface depicts content from source documents and obtains user input to select items of user-selected information from the content; generate a prompt based on the selected items; present the generated prompt to the user; and/or perform other steps.
Claims20
A system configured for generating prompts for a machine learning model based on user-selected source document information, wherein the user-selected source document information is selected from one or more source documents, the system comprising:
- one or more hardware processors configured by machine-readable instructions to:
- effectuate a presentation of a first user interface, the first user interface being configured to:
- (i) depict content from the one or more source documents,
- (ii) navigate among the content, and
- (iii) obtain entry of user input from a user to select one or more items of user-selected information from the content as depicted;
- responsive to selection of the one or more items of user-selected information from the content as depicted, provide an input to the machine learning model that indicates the one or more items of user-selected information and instructs the machine learning model to generate a prompt effective to cause retrieval of the one or more items of user-selected information from a corpus including the one or more source documents by the machine learning model;
- receive the prompt from the machine learning model;
- and
- present the generated prompt to the user.
A method of generating prompts for a machine learning model based on user-selected source document information, wherein the user-selected source document information is selected from one or more source documents, the method comprising:
- effectuating a presentation of a first user interface to a user, wherein the first user interface (i) depicts content from the one or more source documents, (ii) allows the user to navigate among the content, and (iii) obtains entry of user input from the user to select one or more items of user-selected information from the content as depicted;
- responsive to selection of the one or more items of user-selected information from the content depicted, providing an input to the machine learning model that indicates the one or more items of user-selected information and instructs the machine learning model to generate a prompt effective to cause retrieval of the one or more items of user-selected information from a corpus including the one or more source documents by the machine learning model;
- receiving the prompt from the machine learning model;
- and
- presenting the generated prompt to the user.
Dependencies are inferred from the claim text.