| 摘要 |
A voice information processing method and a terminal. The method comprises: obtaining a voice signal (S101); recognizing the voice signal and obtaining corresponding text information (S102); and performing error correction on the text information on the basis of a session history database preset in the terminal, and obtaining error-corrected text information (S103), the session history database storing session history records of a user. The error-corrected text information best matches the session history records of the user, i.e., best fits the context, so the error-corrected text information is closest to the voice content actually input by the user. In this way, the technical problem in the prior art of low accuracy of voice recognition of a terminal is effectively solved, the accuracy of voice recognition of the terminal is improved, and user experience is enhanced. |
