Disclosed are a Chinese coding method and apparatus based on a bidirectional long short-term memory network model, relating to the technical field of artificial intelligence. The method comprises: converting training linguistic data into character-level data; partitioning the character-level data according to a preset symbol to obtain multiple pieces of first character-level data, and grouping the multiple pieces of first character-level data according to the lengths of the pieces of first character-level data to obtain K data sets; obtaining, according to the K data sets, K trained bidirectional long short-term memory network models; and processing target linguistic data and then inputting same into at least one trained bidirectional long short-term memory network model of the K trained bidirectional long short-term memory network models to obtain a coding result of the target linguistic data. Therefore, the problem of low accuracy of Chinese coding can be solved.
展开▼