Semantic consistency model for determining a semantic consistency of contents of at least two screenshots

A computer program product, the computer program product comprising a computer readable storage medium having program instructions embodied therewith, the program instructions readable and/or executable by a computer to cause the computer to:

• train, by the computer, a semantic consistency model with historical data, wherein the training includes tuning hyper-parameters to improve an accuracy of the semantic consistency model;
• in response to a determination that a predetermined threshold of accuracy is met during the training, use, by the computer, the trained semantic consistency model to determine a semantic consistency of contents of two screenshots that include images,
• wherein the trained semantic consistency model bases the semantic consistency on dimensions including:
• a linguistic comparison of the contents, an image comparison of the contents and a text location comparison of the contents;
• and
• output, by the computer, the determined semantic consistency for display on a user device.

A system, comprising:

• a processor;
• and
• logic integrated with the processor, executable by the processor, or integrated with and executable by the processor, the logic being configured to:
• train a semantic consistency model with historical data, wherein the training includes tuning hyper-parameters to improve an accuracy of the semantic consistency model;
• in response to a determination that a predetermined threshold of accuracy is met during the training, use the trained semantic consistency model to determine a semantic consistency of contents of two screenshots that include images,
• wherein the trained semantic consistency model bases the semantic consistency on dimensions including:
• a linguistic comparison of the contents, an image comparison of the contents and a text location comparison of the contents;
• and
• output the determined semantic consistency for display on a user device.