A six-dimensional linear interpolation theory was proposed to solve the difficult problem of the inverse kinematics equation of six Degree Of Freedom (DOF) manipulator with general structure. Firstly, seven adjacent non-linear correlation nodes were searched from a large number of empirical data to compose hyper-body. Secondly, these seven nodes were used to obtain a six-dimensional linear predictive function. Finally, the predictive function was used to interpolate and inversely interpolate to predict poses and joint angles. The Matlab simulation was used to generate one million group of empirical data according to the positive kinematics equation, and the target pose was inversely interpolated iteratively to predict six joint angles. The experimental results show that compared with the Radial Basis Function Network (RBFN) and the six-dimensional linear inverse interpolation method, the proposed method can approach the target pose faster and more accuratly. The proposed method is based on data, which avoids complicated theory and can meet the requirements of robot daily applications.