Low data encryption efficiency and inadequate security are two issues with the current blockchain cross- chain transaction protection schemes. To address these issues, a blockchain cross-chain transaction protection scheme based on Fully Homomorphic Encryption (FHE) is proposed. In the proposed scheme, the functional relationship is established by Box-Muller, Discrete Gaussian Distribution Function (DGDF) and Uniform Random Distribution Function (URDF) are used to improve the security and efficiency of key generation. Subsequently, the data preprocessing function is introduced to perform cleaning, deduplication, and normalization operations on the transaction data of multi-key signature, and it is classified into interactive data and asset data, so as to perform different homomorphic operations in the FHE encryption stage. Ultimately, in the FHE encryption stage, homomorphic multiplication and homomorphic addition are used targeted for the interactive data and asset data, thereby reducing the computational complexity and enhancing the FHE encryption efficiency. The significance of the proposed scheme is proved by experimental results: Firstly, the multi-key generation function and its specific sampling method and transformation ensure the security and efficiency of key generation. Data preprocessing can also accelerate the FHE encryption process by eliminating invalid data and redundancy, so the FHE encryption efficiency is significantly improved. Secondly, the FHE encryption method based on discrete logarithm problem enhances the security of transaction data and can effectively resist multiple attacks. In addition, the preprocessed data also has good performance in capacity storage. The proposed scheme has significant impacts on key indicators such as encryption efficiency and security, it provides a new reference for blockchain cross-chain transaction protection technology and has an important impact on the security improvement of various cross-chain transaction data.