金融工程：AI识图关注电力、电网、公用事业

• The report explores the use of convolutional neural networks (CNNs) to model price-volume data and predict future prices, mapping learned features to industry theme indices such as the National Green Power Index, CSI Green Power Index, and CSI Electric Power Equipment Theme Index[80][82] - The CNN-based approach involves constructing standardized charts of price-volume data for individual stocks over specific time windows, which are then used as input for the CNN model to identify patterns and trends[80] - The latest thematic allocation based on the CNN model includes sectors like electricity, power grids, and public utilities, with specific indices such as the CSI All-Electric Power Utility Index and CSI All-Public Utility Index being highlighted[80][82]