Nowadays, Software development process has incorporated many techniques, scientific approaches and advanced tools to develop the highest quality featured software. The size of the software systems also become large and make the system more complex. So that, it is necessary to ensure the quality of software system before its delivery. Software reliability is one of the important measurement to predict the quality of software which will be used to reduce the time, cost and other resources required for the testing process. Here we have proposed one novel framework to predict the software reliability based on software architecture and path testing by incorporating indegree and out-degree concept used in graph theory. This proposed framework will reduce the number of test path in the system which will be used to reduce the testing time and resources. The applicability of our proposed framework is validated by using two real time case studies and these results are compared with the prevailing standard reliability models to assess the prediction accuracy of our proposed framework. The result shows that our proposed framework is simple to apply in the real time system and prediction accuracy is also acceptable compared to the other models.