User perception evaluation method and system based on PCA (Principal Component Analysis) and integrated auto-encoder

The invention discloses a user perception evaluation method and system based on PCA (Principal Component Analysis) and an integrated auto-encoder, belongs to the technical field of artificial intelligence and user perception evaluation, and aims to solve the technical problems that the robustness is insufficient, user perception evaluation tasks under different environments and different service types are difficult to adapt, and the user perception evaluation efficiency is high. According to the technical scheme, the method specifically comprises the following steps: obtaining a voice-related KQI index and a video-related KQI index of a high-speed rail user through a sensor; data cleaning: when a vacancy value exists under the VOLTE response call drop rate index of one piece of data, the value is set to be zero; when any other index in one piece of data has a vacancy value, the piece of user data is deleted and does not participate in modeling; the cleaned data is preprocessed; obtaining initial perception by