Method and apparatus for performing categorised matching of videos, and selection engine

A video classification apparatus for classification matching of videos, comprising:

• a memory,
• a processor coupled to the memory, the processor being configured to:
• perform multi-dimensional identification of content of at least one video to determine abstract information of the at least one video;
• generate classification attribute information of the at least one video based on the abstract information of the at least one video, wherein the classification attribute information includes humanistic attribute information of the at least one video;
• wherein the humanistic attribute information is used to indicate a value judgement corresponding to the at least one video;
• determine the respective humanistic attribute information of the at least one video based on the abstract information of the at least one video and in connection with relevant information of at least one subject area, wherein machine learning models for determining the humanistic attribute information in the respective subject areas are established based on the abstract information and the subject characteristics of the respective subject areas;
• obtain a user's usage demands, wherein the usage demands include the user's usage scenario demands, emotional demands, or both;
• determine one or more videos corresponding to the usage demands;
• and
• determine at least one recommended video corresponding to the user based on the respective classification attribute information of the one or more videos and the user humanistic attributes of the user.

A selection engine comprising:

• a video classification apparatus comprising a memory and a processor coupled to the memory, wherein the processor is configured to:
• perform multi-dimensional identification of content of at least one video to determine abstract information of the at least one video;
• and
• generate classification attribute information of the at least one video based on the abstract information of the at least one video, wherein the classification attribute information includes humanistic attribute information of the at least one video;
• wherein the humanistic attribute information is used to indicate a value judgement corresponding to the video;
• wherein, the generation of classification attribute information further comprises:
• determining the respective humanistic attribute information of at least one video based on the abstract information of the at least one video and in connection with the relevant information of at least one subject area, and
• determining, using machine learning models, the humanistic attribute information in the respective subject areas based on the abstract information and the subject characteristics of the respective subject areas;
• wherein the processor is further configured to:
• obtain a user's usage demands, wherein the usage demands include the user's usage scenario demands, emotional demands, or both;
• determine one or more videos corresponding to the usage demands;
• and
• determine at least one recommended video corresponding to the user based on the respective classification attribute information of the one or more videos and the user humanistic attributes of the user.