Real-Time Semantic Search Using Approximate Methodology for Large-Scale Storage Systems

摘要: The challenges of handling the explosive growth in data volume and complexity cause increasing needs for semantic queries. queries can be interpreted as correlation-aware retrieval, while containing approximate results. Existing cloud storage systems mainly fail to offer an adequate capability Since true value or worth heavily depends on how efficiently search carried out (near-) real-time, large fractions end up with their values being lost significantly reduced due staleness. To address this problem, we propose a near-real-time cost-effective based methodology, called FAST. idea behind FAST is explore exploit correlation within among datasets via hashing manageable flat-structured addressing reduce processing latency, incurring acceptably small loss data-search accuracy. property enables rapid identification correlated files significant narrowing scope processed. supports several types analytics, which implemented existing searchable systems. We conduct real-world use case children reported missing extremely crowded environment (e.g., highly popular scenic spot peak tourist day) are identified timely fashion by analyzing 60 million images using further improved semantic-aware namespace provide dynamic adaptive management ultra-large Extensive experimental results demonstrate efficiency efficacy performance improvements.