Abstract: An information handling method in which information items are mapped to respective nodes in an array of nodes by mutual similarity of the information items, such that similar information items map to nodes at similar positions in the array of nodes; a mapping relationship being defined between feature data relating to an information item and nodes in the array of nodes comprises the steps of: (a) for each of a group of information items: detecting feature data representing each of a set of properties of that information item; (b) for the ensemble of feature data corresponding to the group of information items: detecting more significant and less significant properties within the ensemble; discarding feature data relating to less significant properties, the remaining non-discarded feature data being associated so as to generate a reduced feature vector for each information item; (c) defining a mapping between the reduced feature vectors and nodes in the array of nodes.

Abstract: An information handling method in which information items are mapped to respective nodes in an array of nodes by mutual similarity of the information items, such that similar information items map to nodes at similar positions in the array of nodes; there being a mapping relationship between frequencies of occurrence, within an information item, of each of a concordance of information features and nodes in the array of nodes, comprises the steps, in respect of an information item to be processed, of: detecting a closest node in the array of nodes, the closest node being that node for which the mapping relationship provides a closest match with the information item to be processed; selecting a group of nodes near, in the array, to the closest node; and modifying the mapping relationship so that the closest node and the group of nodes are brought generally closer to the information item to be processed; in which, for the purposes of selecting the group of nodes, the array wraps around so that a peripheral edge