US Patent 11880389 Unified context-aware content archive system

The disclosed systems and methods relate to searching archived communications. A computing device can receive information associated with documents captured for multiple communication modalities. The computing device can normalize the information associated with each of the documents into a single information structure to generate normalized information. The computing device can generate a transcript of an interaction between participants for the communication modalities based on the normalized information. The computing device can store the transcript of the interaction between the participants in the data archive. The computing device can search the data archive to surface the transcript of the interaction across the communication modalities based on a context corresponding to the single information structure.