Data processing method, apparatus, electronic device and storage medium

An electronic device comprising:

• at least one processor;
• a storage device configured to store at least one program;
• when the at least one program is executed by the at least one processor, the at least one processor implements acts comprising:
• collecting audio and video frame data associated with a target user, wherein the audio and video frame data includes voice information to be processed and a face image to be processed;
• processing the face image to be processed based on a target line-of-sight angle adjustment model to obtain a target face image corresponding to the face image to be processed;
• performing a following process on the voice information to be processed based on an audio content following method and determining a target sentence in a target text associated with the voice information to be processed;
• and
• displaying the target sentence and the target face image separately on clients associated with the target user, or displaying the target sentence and the target face image on a client associated with the target user together;
• wherein the target line-of-sight angle adjustment model is trained according to a plurality of training samples in a training sample set, and each of the plurality of training samples comprises a target line-of-sight angle image and a non-target line-of-sight angle image.

A non-transitory storage medium comprising computer-executable instructions for performing acts comprising:

• collecting audio and video frame data associated with a target user, wherein the audio and video frame data includes voice information to be processed and a face image to be processed;
• processing the face image to be processed based on a target line-of-sight angle adjustment model to obtain a target face image corresponding to the face image to be processed;
• performing a following process on the voice information to be processed based on an audio content following method and determining a target sentence in a target text associated with the voice information to be processed;
• and
• displaying the target sentence and the target face image separately on clients associated with the target user, or displaying the target sentence and the target face image on a client associated with the target user together;
• wherein the target line-of-sight angle adjustment model is trained according to a plurality of training samples in a training sample set, and each of the plurality of training samples comprises a target line-of-sight angle image and a non-target line-of-sight angle image.