The percentile and K-mean clustering were applied to analyze the longitude and longitude information of Fujian ocean buoy, and solve the problem of position estimation of missing measurement and missing observation in the long sequence of ocean buoy data。On this basis, combined with the third-party data such as CLDAS and ERA 5, the inverse distance weight method and spherical Kerry gold interpolation algorithms are used to calculate the timing and longitude and latitude positions, and the corresponding temperature, pressure, humidity, wind direction and wind speed are estimated. On the evaluation results of different third-party information and different interpolation algorithms, the stability of data sequence and timing length on the filling of elements are better than spherical interpolation. Subsequently, based on the conclusions, a new data set was reconstituted by integrating the original observation data from seven Fujian marine buoys. A comparative evaluation and validation of the two data sets showed that the Pearson correlation coefficients for various meteorological elements were generally above 0.9. The new data set not only significantly improved its completeness but also preserved the consistency and robustness of the original observation data. Local abnormal element values were also effectively controlled. During the validation process of typhoon cases from 2014 to 2021, the wind speed elements were evaluated by comparing them with the real-time typhoon tracks. The correlation coefficients of the wind speed elements in the new data set is increased by 0.03, and the mean square error decreased to 0.5. The experiment shows that the original observation data of ocean buoys have good operational applicability after being continued.