In order to meet the intelligent demand of modern financial data analysis, this paper proposes a financial accounting information data analysis system based on the Internet of things. Based on the central reinforcement learning architecture, the model uses multiple execution modules to enhance the computing and generalization ability of the single-agent reinforcement learning algorithm. In the selection of reinforcement learning algorithm, the instantaneous time difference algorithm is introduced. The algorithm can synchronize the experience of the previous iteration state in the learning process and does not depend on the final prediction value, which greatly saves the storage cost. In the establishment of the financial data analysis index system, the paper comprehensively considers the enterprise’s operation, development, debt repayment, and other capabilities, ensuring the integrity and rationality of the index system. In order to evaluate the performance of the algorithm, this paper takes the real financial data as the sample and uses BP neural network to conduct a comparative experiment. The experimental results show that the recognition accuracy of the model is better than that of the BP neural network in each experimental scenario, and the recognition accuracy of Experiment 3 is improved by 4.6%. Conclusion. The performance of the distributed reinforcement learning algorithm is better than that of the common back-propagation neural network in the real data set scenario.

In order to better construct the financial management standard distribution architecture, this paper proposes a financial management target architecture based on the ISM model. By discussing the stability, periodicity, and hierarchy of enterprise financial management objectives, this paper describes the system structure of enterprise financial management objectives by using the ISM model method of system engineering and establishes a five-level hierarchical structure model of financial management objective system. In this paper, the ISM algorithm is improved, two algorithms are proposed and their root mean square error is compared and analyzed. The experimental results show that the root mean square error of the EWISM algorithm and ETISM algorithm is significantly smaller than that of the traditional ism algorithm when the signal-to-noise ratio is 5–20db. Conclusion. By analyzing the architecture of financial management objectives based on the ISM model and improving the ISM algorithm, it can provide a better reference for enterprises to determine financial management objectives.

In order to realize the optimal allocation of human resources and avoid the waste or relative shortage of human resources, human resources and marketing based on the genetic algorithm are combined together and a combined evaluation management model is established in this study. By constructing a weight vector to represent the evaluation performance of different evaluation models for talent evaluation, the combination problem of multiple evaluation models is transformed into an optimization problem of weights. Based on the evaluation accuracy, the fitness function is designed, the weight vector is optimized by the genetic algorithm, and the individual selection strategy is designed to avoid falling into local optimization. The validity of the model and algorithm is verified by a numerical example, and the calculation results show that the proposed method can gradually improve the average working ability of employed employees by reasonably controlling the number of employment at different periods and the number of dismissals, and the average working ability of employees can be improved by 41%, thus realizing the optimization of human resources for the project.