Application of Improved SOM Neural Network in Intelligent Auditing of Hospital Financial Vouchers

The traditional audit method relies on manual verification, which has a large workload and low efficiency, and is difficult to meet the work needs. In order to improve the efficiency of hospital financial audit, we studied the improvement of SOM neural network, optimized the initial weight matrix and learning rate function of SOM neural network, improved the operation performance and efficiency of neural network, combined with word co occurrence to build a financial intelligent audit model for accounting vouchers, and used the potential correspondence between voucher abstract text vocabulary and accounting subjects to provide audit suspects clues for auditors. The experimental results show that compared with the traditional SOM neural network algorithm, the precision rate of the improved sneural network model based on word co occurrence is increased by 3%, and the recall rate is increased by 2%, which can effectively improve the efficiency and quality of hospital financial audit.