Research on internal control of accounting information system based on BP neural network

Abstract

In this paper, qualitative and quantitative evaluation criteria can be used to evaluate the internal control system. Qualitative evaluation is influenced by the subjective judgment of evaluators and often lacks objectivity, while quantitative evaluation is welcomed by audit institutions because of its scientific, accurate and comparable characteristics. This paper constructs the internal control evaluation index, takes the characteristic information describing the internal control status of accounting information as the input vector of the neural network, and takes the value representing the corresponding comprehensive evaluation result as the output of the neural network, and trains the network with enough samples to make different input vectors get different output values, This paper makes a quantitative evaluation on the control status of accounting information system.