Boost Report Testing Efficiency with an AI Large Model

When a new version of a reporting system is released, regression testing must verify that unchanged metrics are not inadvertently affected. Manually exporting multiple reports and comparing cell values is time‑consuming and error‑prone.

Using an AI large model for assistance

The author prompts Tencent Hunyuan with a request to outline the steps for comparing two reports and marking differences in red. The model returns a clear workflow, which the author then refines by asking it to generate Python code that can compare two Excel files (ExcelA.xlsx and ExcelB.xlsx).

Generating and validating the comparison script

The generated script is copied into Visual Studio Code, executed, and its console output confirms that the differences between the two spreadsheets are correctly identified. The author modifies one of the files to introduce multiple differing cells and observes that the script still reports all differences accurately.

Optimizing the solution

Further prompts ask the model to improve the code so that file names are supplied by the user via keyboard input, and to format differing cells with bold‑italic styling. Additional refinements enable the script to compare more than two files by accepting a list of file paths.

Conclusion

The demonstration shows that the Hunyuan large model can understand context, generate functional code, and iteratively improve it based on user feedback, thereby significantly reducing the effort required for large‑scale report comparison and improving test acceptance quality.