The Effect of Educational Resource Allocation on Teaching and Teaching Ability in Colleges and Universities Based on BP Neural Networks

Along with the deepening of the economic system reform, the reform in the field of education urgently needs to be deepened, and the value and potential of resource allocation need to be further explored. This paper trains the weights and thresholds of the network and optimizes the BP neural network by using the PSO algorithm instead of the gradient descent method. An educational resource allocation model based on the optimized BP neural network is constructed. The first layer of the model is the input layer, and the input variables are indicators for educational resource allocation. The middle layer is the hidden layer. By adjusting the weights of neurons, the actual samples can be adjusted to closely match the target samples for educational resource allocation. The last layer is the output layer, which outputs the result data. The configuration results can be obtained by adjusting the network output accordingly. Through the example analysis, after the allocation of educational resources, the difference in the allocation of educational resources within the university district becomes lower, and the comprehensive resource efficiency of colleges and universities within the university district is improved. Teaching experiments explore the changes in student achievement. The significance level of the independent sample test of the students’ post-test scores before and after educational resource allocation is 0.000<0.05. This means that colleges and universities are much better at teaching and learning after educational resource allocation optimization compared to before optimization.