Using the knife cutting method and Bayes parameter estimation method, under the weighted squared loss function, this paper obtains the exact form of Bayes estimation of the Rayleigh distribution with the prior distribution is Jefferys uninformative prior distribution and Gamma distribution. On this basis, the knife-cut Bayesian estimation of parameters is further studied. Finally, the MCMC (Markov Chain Monte Carlo) algorithm is used in the R software to conduct numerical simulations of the Bayesian estimation and jackknife Bayesian estimation of the parameters of the Rayleigh distribution. The simulation results show that when the sample size is large, the simulation effect of the jackknife Bayesian estimation is better under the same prior distribution.