The invention provides an AI chat
breakpoint resuming method and device based on a double-storage architecture, and relates to the technical field of AI dialogues, and the method comprises the steps: after a user inputs a text at a
client, an AI
large model generates content blocks in sequence, and a
server transmits the content blocks to the
client; the
server writes the content blocks into a cache storage layer, and writes all the content blocks as complete content into a persistent storage layer after the AI
large model finishes answering; after the
client is disconnected from the
server, the server stops transmitting the content block to the client, and the client generates a stop position index of the content block; after the client and the server are reconnected, under the condition that complete content exists in the persistent storage layer, the complete content of the persistent storage layer is divided into a plurality of content blocks, and the content blocks are sequentially transmitted to the client according to the sequence; and under the condition that complete content does not exist in the persistent storage layer, sequentially transmitting the content blocks after the stop position index of the cache storage layer to the client according to a sequence.