| 摘要 |
A set of clusters (50) is selected from a concept space. The concept space includes clusters (50) with concepts (53) visualizing document content (49) based on extracted concepts (47). A theme in each of a plurality of the clusters (50) is identified. Each theme includes at least one such concept (53) ranked within the cluster (50). Unique candidate spines (55) is logically formed. Each candidate spine (55) includes clusters (50) commonly sharing at least one such concept (54). The clusters (50) are assigned to one such candidate spine (55) having a substantially best fit. Each such sufficiently unique best fit candidate spine (56) is identified and placed in a visual display space (43). Each non-identified best fit candidate spine (56) is placed in the visual display space (43) relative to an anchor cluster (60) on one such identified best fit candidate spine (56). |
