发明名称 Word cloud rotatable through N dimensions via user interface
摘要 A system and related method are disclosed for rendering a set of words linked to an n-dimensional vector space in a word cloud rendered from a two-dimensional projection of the vector space, where the user can click and drag a word, and the subspace and projection thereon will shift to place the word where the user has dragged it in a new projection, and the other words in the cloud will shift correspondingly, offering the user new insights. The importance of words in a document set is represented by word size, and relatedness between words demonstrated by color similarity.
申请公布号 US9164667(B2) 申请公布日期 2015.10.20
申请号 US201313840009 申请日期 2013.03.15
申请人 Luminoso Technologies, Inc. 发明人 Speer Robert;Vishnevsky Yuri
分类号 G06F17/20;G06F3/0484;G06F17/21;G06F17/30 主分类号 G06F17/20
代理机构 Law Office of Ilya Libenzon 代理人 Law Office of Ilya Libenzon
主权项 1. A method performed by at least one electronic device having a processor and a memory for exploring an n-dimensional textual data set using word cloud representations of two-dimensional projections of the data set, comprising: providing a display space with a two dimensional coordinate system; generating a textual data set whose members comprise a set of words, each of which is associated with an n-dimensional vector populated by n numerical values, said vectors defining an n-dimensional data space; storing said textual data set in said memory so as to preserve each word's relationship with its associated vector; calculating a size attribute for each word in said textual data set; creating an initial two-dimensional subspace of the n-dimensional data space and storing said subspace in said memory; calculating the projection of each said n-dimensional vector onto said subspace, and saving said projection to memory; displaying a word cloud by performing steps comprising: placing each word from the textual data set in said display space at coordinates determined by its projection on said subspace; anddisplaying said word with a font size corresponding to its size attribute; receiving a user's selection of a word displayed in the word cloud via said electronic device's manual data entry means; receiving a user's motion input via said electronic device's manual data entry means; shifting said word cloud by performing steps comprising: selecting a frame rate for animating the movement corresponding to said user's motion input;for each frame, calculating the change in position in the display space corresponding to the portion of said user's motion input that occurred during said frame;replacing said two-dimensional subspace with another two-dimensional subspace in which the projection of the selected word's associated vector causes the selected word to be displayed at the new location dictated by said change in position;projecting each vector on the new subspace and saving each said projection to said memory;placing each word at coordinates in said display space corresponding to its vector's new projection; andrepeating for each frame until detecting cessation of motion; upon cessation of motion, repeating the steps comprising displaying a word cloud using each word's associated vector's most recent projection on the most recent subspace.
地址 Cambridge MA US