Fujitsu Corporation

Nobuko Takase

Kazuo Mineno

Naohiro Itou

Tomoko Tanaka

Kazuyuki Sakai

Hisashi Sawada

Toshihide Miyagi

Hiroshi Nakanishi

Hisashi Tsujide

Daiki Hanawa

Takeya Mutoh

Yutaka Arakawa

Toshiyuki Utsumi

Keisuke Hirota

Yoshio Oki

Michio Masuno

Hiroyoshi Okada

Jumma Kudo

Yuko Matsushita

Navid Afzal Shooshtary

A machine learning method includes: obtaining first teacher data, which includes first encrypted words and corresponding search word information including one or more second encrypted words to be used for search, the first encrypted words being generated such that the first encrypted word includes a code sequence different from other encrypted words even though both of the first encrypted words and the other encrypted words have been generated from a same word; obtaining a group of words from among the first encrypted words by using a trapdoor scheme; generating second teacher data by using one encrypted word included in the obtained group to replace a rest of the obtained group of words; and performing, on the basis of the second teacher data, machine learning of a parameter to determine, in response to receiving of one or more encrypted words, one or more encrypted words to be used for search.

Machine learning method and machine learning device

When retrieving specific text from a search target document, an information processing apparatus receives text, generates a semantic structure indicating a meaning of a word that is included in the received text, by subjecting the received text to semantic analysis, identifies a word that is associated with the generated semantic structure, by referring to a synonym dictionary that stores a word and semantic structure indicating a meaning of the word in an associated manner, determines whether the identified word is included in the search target document, and outputs information according to a determination result.

Computer-readable recording medium, retrieval device, and retrieval method

A determination method executed by a computer including a memory and a processor coupled to the memory, includes receiving a plurality of sentences and designation of terms included in the plurality of sentences, generating, for each term for which the designation is received, information indicating a relation between the term and each of other terms included in one of the plurality of sentences containing the term, extracting, for each term for which the designation is received, information indicating a specific relation from the generated information indicating the relation, generating characteristic information that uses the extracted information as a feature, and determining similarity between a plurality of the terms based on the generated characteristic information for each term.

Determination method and determination apparatus

A non-transitory computer-readable recording medium stores an operation process creation program that causes a computer to execute a process, the process including extracting a candidate operation manipulation component to be combined with an operation process following an operation manipulation component that has been determined to be arranged, when creating the operation process by arranging a plurality of the operation manipulation components on a screen, the candidate being extracted based on previously set relevance information indicating relevance between operation manipulation components and usage frequency information indicating usage frequencies of operation manipulation components in past instances of creating the operation processes; and displaying the extracted candidate operation manipulation component on the screen, by combining the extracted candidate operation manipulation component with the operation manipulation component that has been determined to be arranged.

Operation process creation program, operation process creation method, and information processing device

Growing community of inventors

Mizuho, Japan

Nobuko Takase