Queryless information retrieval during a live conversation via a bifurcated model implemented in a secured computer network

A method for facilitating queryless information retrieval during a live conversation via a bifurcated model implemented in a secured computer network, the method comprising:

• receiving, during a live conversation over a computer network, a first set of decrypted utterances spoken during the live conversation;
• providing the first set of decrypted utterances as input to a bifurcated model, trained to generate computer file identifiers corresponding to utterances as output, the bifurcated model comprising (i) a first bifurcated model portion associated with a dynamic utterance embedding space and (ii) a second bifurcated model portion associated with a static computer file embedding space;
• in response to providing the first set of decrypted utterances as input to the bifurcated model, generating, via the bifurcated model, a first intermediate output from the first bifurcated model portion indicating a first utterance embedding;
• determining, via the bifurcated model, based on the first utterance embedding, a second intermediate output from the second bifurcated model portion indicating a first computer file embedding;
• generating as output, via the bifurcated model, a first computer file identifier corresponding to the first computer file embedding based on a similarity value between the first computer file embedding and the first utterance embedding satisfying a similarity threshold;
• and
• generating for display, on a user interface of a user device, during the live conversation, a graphical representation of a computer file corresponding to the first computer file identifier.

One or more non-transitory computer-readable media comprising instructions that, when executed by one or more processors, cause operations comprising:

• receiving, during a live conversation, a first set of decrypted utterances communicated during the live conversation;
• generating, via a bifurcated model based on the first set of decrypted utterances, a first intermediate output, from a first bifurcated model portion associated with a dynamic embedding space, indicating a first utterance embedding;
• determining, via the bifurcated model, based on the first utterance embedding, a second intermediate output, from a second bifurcated model portion associated with a static embedding space, indicating a first file embedding;
• determining a first file identifier corresponding to the first file embedding based on a similarity value between the first file embedding and the first utterance embedding satisfying a similarity threshold;
• and
• generating for display, on a user interface of a user device, during the live conversation, a graphical representation of a file corresponding to the first file identifier.