Abstract: Sequence Memory is intended for entering sequences and creating a statistical map of the weights of the joint occurrence of sequence objects and analyzing the map for solving problems: 1) predicting the appearance of the next sequence objects in the past or future; 2) determining the context and the point of changing the context of the sequence with the assignment of individual sections of the sequence unique identifiers of the context; 3) input of sequences of context identifiers in the Sequence Memory of the next level of the hierarchy in order to create a Hierarchical Sequence Memory; 4) Representation of cause-and-effect relationships as relationships of mutual occurrence of objects of different levels of the hierarchy for analysis 5) identification of cause-and-effect relationships of the corresponding level of the hierarchy for making conclusions and judgments.

Abstract: A method and an apparatus for creating and using recursive index in search engines. In particular, extracting text from an index of a search engine starting at an arbitrary position in the text, and analyzing texts for co-occurrence of words, and using said extraction and analysis for inferring implicit relationships among objects in sequences thereof. As such, utility of search engines to index and retrieve information represented by a sequence of objects different from text information objects are extended. A method and an apparatus extends the basic hit with at least two word identifications, one for the previous word and one for the next word.

Abstract: The present invention pertains to extraction of text from an index of a search engine starting at an arbitrary position in the text, and to analysis of texts for co-occurrence of words, and to the use of said extraction and analysis for inferring implicit (causal, associative, etc) relationships among objects in sequences thereof. The present invention is particularly useful in extending the utility of search engines to index and retrieve information represented by a sequence of objects different from text information objects. The present invention extends the basic hit with at least two wordID's, one for the “previous word”, whose position in the document is position?1, and one for the “next word”, whose position in the document is position+1.