Electric power artificial intelligence model effect feedback evaluation method and system

• Main Authors: ZHANG CHUNDONG, LI RONGSHENG, SUN HU, YONG JUNYAN, ZHANG BIN, YANG YUECHEN, WANG YUHANG, DU YANQING, SUN ZHIZHOU, CUI HAOYI, WANG LIANG, YUAN HONG
• Format: Patent
• Language: Chinese; English
• Published: 26.03.2024
• Subjects: CALCULATING; COMPUTING; COUNTING; DATA PROCESSING SYSTEMS OR METHODS, SPECIALLY ADAPTED FORADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORYOR FORECASTING PURPOSES; ELECTRIC DIGITAL DATA PROCESSING; PHYSICS; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE,COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORY OR FORECASTINGPURPOSES, NOT OTHERWISE PROVIDED FOR

The invention discloses an electric power artificial intelligence model effect feedback evaluation method and system, and the method comprises the following steps: obtaining operation behavior data and corresponding model effect feedback information when a user uses a model each time, the user operation behavior data comprising keyboard and mouse operation behaviors and page operation behaviors; according to the similarity between the operation behavior data of each time and the operation habit model of the user, evaluating the confidence coefficient of the effect feedback information of the model; wherein the operation habit model is established based on historical operation behavior data of a user; according to the method, all effect feedback information for a certain target model is obtained, weighting is carried out according to the confidence degree of each piece of feedback information, and a corrected effect feedback result is obtained and used for learning optimization of the target model, so that con