The rapid advancement of technology and innovation has triggered a notable surge in the global filing of patent applications. Evaluating the potency of a patent, namely its probability of withstanding legal challenges or being successfully enforced, holds paramount importance for both patent applicants and stakeholders within the intellectual property landscape. This paper introduces an innovative Patent Strength Predictor System (PSPS) that harnesses machine learning methodologies such as random forest, logistic regression, SVM, and fuzzy logic implemented via Python to gauge the resilience of patents. PSPS integrates a range of features, encompassing patent forward and backward citations, independent and dependent claims, counts of assignees and inventors, patent age, technical terminology extracted from the abstract and description, and the number of figures, enabling an assessment of patent strength. Through exhaustive experimentation and validation using a diverse collection of patents, this work illustrates the effectiveness of PSPS in accurately forecasting patent strength across various technological domains.