Keyword search over encrypted data is essential for getting to outsourced sensitive data in cloud computing. In some conditions, the keywords that the client searches on are only semantically identified with the data instead of by means of a correct or fuzzy match. Subsequently, semantic-based keyword search over scrambled cloud data becomes of paramount importance. Nonetheless, existing schemes usually depend on a global dictionary, affects the accuracy of search results but also causes inefficiency in data updating. Moreover, although compound keyword search is common practice, the existing approach process them as single words, which split the original semantics and achieve low accuracy. To address these limitations, we initially propose a compound concept of semantic similarity (CCSS) computation technique to gauge the semantic similarity between compound concepts.
Next, by coordinating CCSS with Locality-Sensitive Hashing function and the safe k-Nearest Neighbor scheme, a semantic-based compound keyword search (SCKS) scheme is proposed. SCKS accomplishes semantic-based search, as well as multi-keyword, search and ranked keyword search. Furthermore, SCKS likewise disposes of the predefined global library and can efficiently support data update. The experimental results about on real-world dataset demonstrate that SCKS presents low overhead on calculation and the search accuracy output performances the existing schemes.