The invention relates to the technical field of identity recognition methods, and discloses a multi-modal biological feature fusion identity recognition method. The multi-modal biological feature fusion identity recognition method comprises the following steps: S1, recognizing a user; s2, user registration; s3, user verification; s4, carrying out secondary verification; s5, alarm feedback; according to the invention, a dual-biological feature verification mode is adopted, any two of iris verification, fingerprint verification and voiceprint verification are selected, after identity information is input, any two verification modes of iris verification, fingerprint verification and voiceprint verification are verified, so that the risk of being stolen by people can be reduced, and when verification fails, secondary verification can be carried out, and a third verification mode is used for verification, so that the verification efficiency is improved. A user and an administrator at the receiving end judge the identity information of a user recognized at the input end, if the user is an untrusted user, positioning is started remotely, the control right of the input end is captured remotely, then the identity information is sorted, and an alarm is given.