| CPC G06F 40/40 (2020.01) [G06F 16/328 (2019.01); G06F 18/24147 (2023.01); G06F 40/284 (2020.01)] | 26 Claims |

|
1. A system for efficient caching and retrieval of responses in conversation service application communication sessions, the system comprising a server computing device having a memory that stores computer-executable instructions and a processor that executes the computer-executable instructions to:
capture an utterance generated by a user of a client computing device during a conversation service application communication session between the server computing device and the client computing device;
convert the utterance into an utterance index key;
search a first response cache comprising a plurality of response index keys to determine whether the utterance index key matches one of the response index keys;
when the utterance index key matches one of the response index keys in the first response cache:
transmit a response associated with the response index key that matches the utterance index key from the first response cache to the client computing device;
when the utterance index key does not match any of the response index keys in the first response cache:
convert the utterance into an utterance embedding;
search a second response cache comprising a plurality of response embeddings to identify one of the response embeddings that is a closest match to the utterance embedding;
capture a fuzzy response index key associated with the closest matching response embedding in the second response cache;
search the first response cache to identify a response index key that matches the fuzzy response index key; and
transmit a response associated with the response index key that matches the fuzzy response index key from the first response cache to the client computing device.
|