COMPREHENSIVE ASSESSMENT OF INFOGRAPHIC IMAGES USING AESTHETICS ADHERENCE TO DATA AND TEXT (AADaT) SCORES

A system comprising:

• a memory storing instructions;
• one or more communication interfaces;
• and
• one or more hardware processors coupled to the memory via the one or more communication interfaces, wherein the one or more hardware processors are configured by the instructions to:
• receive an input data comprising a textual information, and one or more tables pertaining to each of a plurality of information resources;
• generate one or more anchor plots from the one or more tables, via a Large Language Model (LLM), using a predefined plot prompt, for each of the plurality of information resources;
• generate a plurality of infographic images associated with the plurality of information resources, using the textual information and the one or more anchor plots, wherein each of the plurality of infographic images is associated with a plurality of attributes comprising a text alignment attribute, a data adherence attribute, an aesthetics attribute, and an infographic image quality attribute;
• compute a plurality of attribute scores of the plurality of attributes for each of the plurality of infographic images, using the textual information, and the one or more anchor plots;
• calculate a plurality of Aesthetics Adherence to Data and Text (AADaT) scores for the plurality of infographic images, using the plurality of attribute scores of the plurality of infographic images;
• generate a plurality of LLM scores along with a plurality of feedback instructions for the plurality of attributes, using the associated AADaT score for each the plurality of infographic images;
• and
• train an infographic evaluation model with the plurality of infographic images, the plurality of feedback instructions, the plurality of AADaT scores, and the plurality of LLM scores, to generate a trained infographic evaluation model.

One or more non-transitory machine-readable information storage mediums comprising one or more instructions which when executed by one or more hardware processors cause:

• receiving an input data comprising a textual information, and one or more tables pertaining to each of a plurality of information resources;
• generating one or more anchor plots from the one or more tables, via a Large Language Model (LLM), using a predefined plot prompt, for each of the plurality of information resources;
• generating a plurality of infographic images associated with the plurality of information resources, using the textual information and the one or more anchor plots, wherein each of the plurality of infographic images is associated with a plurality of attributes comprising a text alignment attribute, a data adherence attribute, an aesthetics attribute, and an infographic image quality attribute;
• computing a plurality of attribute scores of the plurality of attributes for each of the plurality of infographic images, using the textual information, and the one or more anchor plots;
• calculating a plurality of Aesthetics Adherence to Data and Text (AADaT) scores for the plurality of infographic images, using the plurality of attribute scores of the plurality of infographic images;
• generating a plurality of LLM scores along with a plurality of feedback instructions for the plurality of attributes, using the associated AADaT score for each the plurality of infographic images;
• and
• training an infographic evaluation model with the plurality of infographic images, the plurality of feedback instructions, the plurality of AADaT scores, and the plurality of LLM scores, to generate a trained infographic evaluation model.