This paper combines the project response theory to dynamically adjust and update the resources according to the learning effect and learning feedback in the process of Civic Education, so as to achieve the goal of matching the learners with the learning resources and realize efficient learning. The differential artificial raindrop algorithm based on perturbation mechanism is designed to realize the solution of multi-objective combinatorial optimization of learning resource allocation. Performance experiments show that the convergence curve of the resource allocation algorithm in this paper is gradually flattened, and the algorithm still has the evolutionary ability, the convergence curve is still decreasing, and the final characteristic difference value is also better than other BPSOR and GAR algorithms. In the case of the number of learning resources of 10, 20, 30, 50, 100, the time consumed is 207ms, 1602ms, 20506ms, 68430ms, 354687, all of which are the lowest, and the success rate is also the highest in the model. The optimal learning path is applied to an experimental class in a university for a 6-week teaching experiment, and the experimental class scores 87.2 points in the Civics test, which is much higher than the control class. This paper realizes the accurate capture of students’ Civics learning problems and the recommendation of targeted teaching resources, which can improve the quality and effect of Civics teaching.