Kabushiki Kaisha Toshiba

Yasuto Ishitani

Masaru Suzuki

Kosei Fume

Ken Ueno

An email processing apparatus determines, from at least one or more of a main body of an email and a subject of an email stored in an email storage unit, a content category of the email; specifies, based on the content category, a search target category of a search target email that relates to the email of the content category; acquires search target information for searching for a search target email of the search target category; and creates a search condition for searching for the search target email containing the search target information in the email storage unit.

Apparatus, method and computer program product for processing email, and apparatus for searching email

An information processing apparatus includes an input unit configured to input an annotation of at least one of an underline, a box, a character, a character string, a symbol and a symbol string to a displayed document, an annotation recognition unit configured to recognize a type of the annotation and a coverage of the annotation in the document, an intention estimation unit configured to estimate intention of a user based on the type of the annotation and information in the coverage, an action storage unit configured to store a plurality of actions, an action selection unit configured to select an action to be performed for the document from the action storage based on the intention estimated by the intention estimation unit, and an execution unit configured to execute the action selected by the action selection unit.

Information processing method and apparatus

An information searching apparatus stores, in a character-string accumulating unit, first character strings in correspondence with second character strings while classifying each of the second character strings according to an attribute thereof. The information searching apparatus further stores, in a storage unit, the attributes in correspondence with specified information each of which is specified based on at least one of the corresponding first character string and the containing document. The information searching apparatus obtains specified information based on at least one of a first character string and a document that contains the first character string and extracts, from the storage unit, the attributes. The information searching apparatus then extracts, from the character-string accumulating unit, one of the second character strings.

Apparatus and method for searching information based on character strings in documents

A search support apparatus estimates, based on a document and a specific phrase (keyword) in the document, a theme of the document, a site type of a website that provides the document, and a content type of the document, and selects a search condition corresponding to the theme, the site type, and the content type, to be presented to the user.

Search support apparatus, computer program product, and search support system

An information retrieval apparatus includes a display unit which displays a first display menu showing a plurality of estimated meaning items and a second display menu showing a plurality of retrieval target items corresponding to the meaning items selected on the first display menu. A log storage unit stores a selection log on the first and second display menus. An estimation unit estimates a retrieval target item selection tendency from the selection log. A ranking unit ranks the plurality of retrieval target items on the basis of the selection tendency. The display unit displays a plurality of retrieval target items on the second display menu upon arranging them in accordance with ranking.

Information retrieval apparatus and method

A character line is identified with a keyword included in the relevant logical element of a keyword dictionary, and the identification result is output to a &ldquo;keyword identification part&rdquo; to store the result. All the character lines processed through a &ldquo;division process part&rdquo; are output to a &ldquo;tagging modification part&rdquo; to replace tags so that there is no logically inconsistent in adjacent character lines, when tags given to adjacent character lines are in logically inconsistent as a combination of tags. A character line to which an appropriate tag may not be given in the &ldquo;tagging modification part&rdquo; is output to an &ldquo;indecisive tag estimation part&rdquo; where an appropriate tag is estimated and is given with reference to a tag adjacent the character lines. The process in the &ldquo;indecisive tag estimation part&rdquo; is applied to all the character lines, and repeated till there is no replacement of tags. Thereby, desired information with desired tags given may be extracted from printed documents and automatically input to a computer system.

Apparatus and method for reading a document image

A document skew detection apparatus for facilitating the recognition of the contents of a printed document includes an image processing section for generating a binary coded image of the document containing a plurality of black picture elements distributed among white picture elements to depict pure text lines and non-text portions of the document. The binary coded image is then modified so that certain ones of the black picture elements satisfying a predetermined condition are integrated together to generate a coarse document image being decreased in resolution. The apparatus also includes an image extraction section for extracting from the document image a local image region containing pure text lines occupying an almost entire area thereof, and skew detection section for detecting a direction of orientation of the text lines of the local region, and for determining an angular difference between a detected direction and a reference direction as a skew angle of the printed document.

Growing community of inventors

Kanagawa, Japan

Yasuto Ishitani