Voice interaction method and related apparatus

A voice interaction method, comprising:

• establishing, by an electronic device, a first data connection to a terminal device;
• receiving, by the electronic device by using the first data connection, shared information sent by the terminal device, and outputting a first voice signal, wherein the first voice signal is used to prompt to the electronic device to correspondingly store the shared information and a first registered user identifier, the first registered user identifier is used to identify a voiceprint feature of a first registered voice signal in the electronic device, and the first registered user identifier is associated with the terminal device;
• receiving, by the electronic device, a second voice signal, wherein in a plurality of registered voice signals, a voiceprint feature of the second voice signal is most similar to the voiceprint feature of the first registered voice signal;
• and
• outputting, by the electronic device, a third voice signal, wherein a content of the third voice signal is used to respond to a content of the second voice signal, and the content of the third voice signal is obtained based on the shared information.

A voice interaction method, comprising:

• receiving, by an electronic device, a first voice signal, wherein the first voice signal is used to indicate to the electronic device to obtain personal information by collecting an image;
• collecting, by the electronic device, a first image of a photographed object;
• outputting, by the electronic device, a second voice signal, wherein the second voice signal is used to prompt the electronic device to correspondingly store first personal information and a first registered user identifier, the first personal information is obtained by identifying the first image, the first registered user identifier is used to identify a voiceprint feature of a first registered voice signal in the electronic device, and in a plurality of registered voice signals, a voiceprint feature of the first voice signal is most similar to the voiceprint feature of the first registered voice signal;
• receiving, by the electronic device, a third voice signal, wherein in the plurality of registered voice signals, a voiceprint feature of the third voice signal is most similar to the voiceprint feature of the first registered voice signal;
• and
• outputting, by the electronic device, a fourth voice signal, wherein a content of the fourth voice signal is used to respond to a content of the third voice signal, and the content of the fourth voice signal is obtained based on the first person information.