Kddi Corporation

Gen Hattori

Yasuhiro Takishima

Fumiaki Sugaya

Chihiro Ono

Kazunori Matsumoto

Hiromi Ishizaki

Kazushi Ikeda

A scenario generation system, a scenario generation method, and a scenario generation program are provided. A scenario generation system used for video playback synchronized with musical piece playback includes a situation estimating portion for estimating a situation expressed by the musical piece, a video specifying portion for specifying at least one video suited for the estimated situation in the video constituted by scenes each having a time-series order, and a scenario generating portion for generating a scenario associating the scenes constituting the specified video with each section of the musical piece. As a result, a scenario can be generated by the scenes each having the time-series order, and the synchronized video with a natural impression can be reproduced corresponding to the musical piece playback on the basis of the scenario.

Scenario generation system, scenario generation method and scenario generation program

A method of selecting a factor for estimating characteristics of viewers who view a same content is disclosed. This method includes: storing a multi-layered hierarchal list of attribute words expressing viewer attributes, each of which is a candidate of the factor; extracting the attribute words from the same content; generating a first vector indicative of frequencies with which the attribute words occur in the same content; for a successively-selected one of the attribute words, successively generating a second vector indicative of frequencies with which the attribute words occur in ones of sets of learned-text information which contain the successively-selected attribute word; calculating a similarity score between the vectors on a per-attribute-word basis; and selecting one of the attribute words as the factor, which is associated with subordinate attribute words on a lower layer, based on a dispersion level of the similarity scores calculated for the subordinate attribute words.

Context-based automatic selection of factor for use in estimating characteristics of viewers viewing same content

A content conversion system according to the present invention divides content data in which a display layout of content components is described using tags, so as to display, on a terminal, contents formed of the content components displayed on a screen, and includes: a primary division unit that divides the content data on a basis of the display layout of the content components; and a secondary division unit that divides the content data on a basis of a distance between the content components in a data description, the secondary division unit divides primary divided content data divided by the primary division unit, and the primary division unit performs re-division of the primary divided content data according to number of divisions made by the secondary division unit.

Content conversion system and recording medium storing computer program

A search unitpresents a Web search result report to a client terminal. A theme space construction unitupdates theme information within a theme information DBby a user-acquired information feedback from the client terminal, and performs a Web search to construct a theme space. The search unitincludes an exhaustivity calculation unit that calculates exhaustivity being a ratio of a user-acquired part to a part of an entire target theme. Moreover, the search unitincludes a difference calculation unit that calculates a difference between a 'user-acquired' range when a user has acquired target Web pages and a user-acquired range before that, and a relevance calculation unit that calculates relevance of the target Web pages to the target theme.

Information filtering apparatus

An information retrieval apparatus for retrieving a web page using a retrieval keyword includes a word extract portion for extracting an objective word from the web page on a display based on the specifying a display position of the web page on the display, wherein the word extract portion further extracts a peripheral word placed around the objective word, and a retrieval portion that performs web page retrieval using the objective and peripheral words.

Growing community of inventors

Fujimino, Japan

Gen Hattori