2 results about "Concept space" patented technology

The application provides an overlapping clustering method and system based on hypergraph covering and a medium, relates to the technical field of complex networks, and the method comprises the following steps: acquiring a sample set, constructing at least two types of relation view hypergraphs, the hypergraphs comprising a semantic neighborhood hypergraph and a factor-induced hypergraph; representing the samples to a concept space shared by the semantic neighborhood hypergraph and the factor-induced hypergraph, obtaining a concept covering representation of the samples; determining an adaptive overlapping budget interval of each sample according to the local density of each sample and the cross-relation divergence in different views; constructing a joint optimization objective function, alternatingly and iteratively optimizing the joint optimization objective function; determining a final concept set to which each sample belongs according to the concept covering representation and the adaptive overlapping budget interval of each sample after optimization, and outputting an overlapping clustering result. The application solves the problems of sample overlapping attribution description, high-order relation fusion utilization and high-dimensional sparse data processing efficiency.

This invention discloses a semantic concept-driven visual token pruning method, relating to the field of artificial intelligence technology. The method includes: obtaining the hidden state of the visual token output by the decoder of the i-th layer of a visual language model; using a sparse autoencoder in a trained visual token pruning model to encode and project the hidden state of the visual token onto an interpretable semantic concept space of dimension i, obtaining a sparse feature vector; and pruning the i-th layer visual token using a concept-based visual token selection mechanism based on the sparse feature vector corresponding to the visual token, obtaining the pruned result. The pruning process of this invention can fully preserve semantic information.