Live conversation information retrieval via context tokens and real-time natural language utterances systems and methods

A system for improving information retrieval during a live conversation via context

• tokens and real-time natural language utterances, the system comprising:
• one or more processors and non-transitory computer-readable media storing instructions, that when executed by the one or more processors, perform operations comprising:
• receive, during a live conversation between a first user and a second user over a computer network, a first set of decrypted natural language utterances spoken within a first time period during the live conversation;
• generating a token comprising token data indicating an embedding of the first set of decrypted natural language utterances with a timestamp indicating a time at which the token is generated;
• storing the token in a token vault database;
• provide the first set of decrypted natural language utterances as input to a first secured model trained to generate first outputs indicating queries and second outputs indicating subsets of natural language utterances;
• in response to providing the first set of decrypted natural language utterances as input to the first secured model, generating, via the first secured model, a first query corresponding to the first set of decrypted natural language utterances and a subset of natural language utterances of the first set of decrypted natural language utterances;
• perform (i) a semantic search using the first query on a first database and (ii) a lexical search using the subset of natural language utterances on a second database to retrieve a set of relevant computer files based on both the semantic search and the lexical search;
• receive, during the live conversation, a second set of decrypted natural language utterances spoken during the live conversation within a second time period subsequent to the first time period;
• providing the token data and the second set of decrypted natural language utterances to the first secured model to generate, via the first secured model, (i) a second query corresponding to both the token and the second set of decrypted natural language utterances and (ii) a second subset of natural language utterances of both the second set of decrypted natural language utterances and the first set of decrypted natural language utterances;
• update the set of relevant computer files by performing (i) a second semantic search using the second query on the first database and (ii) a lexical search using the second subset of natural language utterances on the second database;
• and
• generating, for display on a user interface of a user terminal, during the live conversation, a graphical representation of the set of relevant computer files.