Method and system for context-specific generative model answers from context-specific queries

A system comprising:

• a computer processor;
• a data repository in communication with the computer processor, the data repository storing:
• a context-specific query received from a user device of a user, wherein the context-specific query is specific to the user,
• a computer-readable data structure for storing data, wherein the computer-readable data structure is specific to the context-specific query,
• a feature related to the context-specific query,
• a user value for the feature,
• user-specific data that includes the user value,
• a modified computer-readable data structure modified with the feature and the user value for the feature, and
• an output comprising a context-specific answer to the context-specific query;
• a server controller in communication with the computer processor and programmed to:
• receive the context-specific query,
• applying a classification model to the context-specific query to generate a numerical prediction whether a general answer answers the context-specific query,
• create, responsive to the numerical prediction satisfying a threshold value, the computer-readable data structure, wherein the numerical prediction satisfying the threshold value indicates that the general answer fails to answer the context-specific query,
• determine the feature related to the context-specific query,
• retrieve the user value for the feature, wherein the user value is retrieved from the user-specific data,
• modify the computer-readable data structure to generate the modified computer-readable data structure, and
• return the output;
• and
• a generative model in communication with the computer processor and programmed to:
• generate the output.

A non-transitory computer readable storage medium storing program code which, when executed by a computer processor, performs a computer-implemented method comprising:

• receiving a context-specific query from a user device of a user, wherein the context-specific query is specific to the user;
• applying a classification model to the context-specific query to generate a numerical prediction whether a general answer answers the context-specific query;
• creating, responsive to the numerical prediction satisfying a threshold value, a computer-readable data structure for storing data, wherein the computer-readable data structure is specific to the context-specific query, wherein the numerical prediction satisfying the threshold value indicates that the general answer fails to answer the context-specific query;
• determining a feature related to the context-specific query;
• retrieving a user value for the feature, wherein the user value is retrieved from a data repository storing user-specific data that includes the user value;
• modifying the computer-readable data structure to generate a modified computer-readable data structure by adding the feature and the user value for the feature to the computer-readable data structure;
• applying a generative model to the modified computer-readable data structure to generate an output comprising a context-specific answer to the context-specific query;
• and
• returning the output.