Human-computer interaction user experience evaluation and optimization method and system, and storage medium

A system for evaluating and optimizing user experience in human-computer interaction, comprising:

• a processor;
• and
• a memory having computer instructions stored therein, wherein
• the processor is configured to execute the computer instructions stored in the memory, and the system, when the computer instructions are executed by the processor, implements a method for evaluating and optimizing user experience in human-computer interaction, the method comprising:
• acquiring a multimodal biological signal of a user during a human-computer interaction process, the multimodal biological signal at least comprising eye movement data;
• preprocessing the multimodal biological signal to extract a fixation position and index parameters of a plurality of dimensions at each time point, the fixation position being extracted based on an eye movement data feature corresponding to the eye movement data;
• standardizing the index parameters of each of the plurality of dimensions, and obtaining, based on each standardized index parameter of each dimension and a predetermined weight for each index parameter, a user experience evaluation score of each dimension by means of a weighted average;
• obtaining, based on the user experience evaluation score of each dimension and a predetermined weight for the user experience evaluation score, an overall user experience evaluation result by means of the weighted average;
• visually presenting, based on the overall user experience evaluation result, user experience situation data of the user for a current fixation position on a human-computer interaction interface;
• and
• acquiring a correction parameter based on at least one of the user experience evaluation score of the user for each dimension or the visually presented user experience situation data of the user for different fixation positions on the human-computer interaction interface, and optimizing, based on the correction parameter, a weight for each index parameter of each dimension and a weight for the user experience evaluation score of each dimension for a finite number of iterations using a machine learning optimization algorithm.

A non-transient computer-readable storage medium, having a computer program stored thereon, wherein the computer program, when executed by a processor, implements a method for evaluating and optimizing user experience in human-computer interaction, the method comprising:

• acquiring a multimodal biological signal of a user during a human-computer interaction process, the multimodal biological signal at least comprising eye movement data;
• preprocessing the multimodal biological signal to extract a fixation position and index parameters of a plurality of dimensions at each time point, the fixation position being extracted based on an eye movement data feature corresponding to the eye movement data;
• standardizing the index parameters of each of the plurality of dimensions, and obtaining, based on each standardized index parameter of each dimension and a predetermined weight for each index parameter, a user experience evaluation score of each dimension by means of a weighted average;
• obtaining, based on the user experience evaluation score of each dimension and a predetermined weight for the user experience evaluation score, an overall user experience evaluation result by means of the weighted average;
• visually presenting, based on the overall user experience evaluation result, user experience situation data of the user for a current fixation position on a human-computer interaction interface;
• and
• acquiring a correction parameter based on at least one of the user experience evaluation score of the user for each dimension or the visually presented user experience situation data of the user for different fixation positions on the human-computer interaction interface, and optimizing, based on the correction parameter, a weight for each index parameter of each dimension and a weight for the user experience evaluation score of each dimension for a finite number of iterations using a machine learning optimization algorithm.