Similar video lookup method and apparatus, device and storage medium

A computer device, comprising a memory, a processor and a computer program which is stored on the memory and runnable on the processor, wherein the processor, upon executing the program, implements a similar video lookup method, wherein the method comprises:

• during video playing, receiving a similar video lookup request from a user;
• obtaining a feature vector of a first video segment which is currently being played, wherein each video is divided into a series of video segments according to a predetermined time length;
• determining a second video segment most similar to the first video segment according to a similarity between feature vectors of respective video segments stored in a database and the feature vector of the first video segment;
• and
• displaying the second video segment to the user,
• wherein the obtaining a feature vector of a first video segment which is currently being played comprises:
• if the feature vector of the first video segment is stored in the database, directly obtaining the feature vector of the first video segment from the database;
• and
• if the feature vector of the first video segment is not stored in the database, generating the feature vector of the first video segment.

A non-transitory computer-readable storage medium on which a computer program is stored, wherein the program, when executed by a processor, implements a similar video lookup method, wherein the method comprises:

• during video playing, receiving a similar video lookup request from a user;
• obtaining a feature vector of a first video segment which is currently being played, wherein each video is divided into a series of video segments according to a predetermined time length;
• determining a second video segment most similar to the first video segment according to a similarity between feature vectors of respective video segments stored in a database and the feature vector of the first video segment;
• and
• displaying the second video segment to the user,
• wherein the obtaining a feature vector of a first video segment which is currently being played comprises:
• if the feature vector of the first video segment is stored in the database, directly obtaining the feature vector of the first video segment from the database;
• and
• if the feature vector of the first video segment is not stored in the database, generating the feature vector of the first video segment.