Hitachi, Ltd.

Makoto Iwayama

Yoshiki Niwa

Shingo Nishioka

Osamu Imaichi

Akihiko Takano

Atsuko Yamaguchi

Yu Asano

Kazuhiro Ono

Tomohiro Yasuda

Toru Hisamitsu

Bin Tong

Yoshiyuki Kobayashi

Kazutomo Ushijima

Tetsuo Nishikawa

Ravigopal Vennelakanti

Masakazu Fujio

Hisashi Ikeda

Naohiro Furukawa

Hiroaki Ozaki

Anshuman Sahu

Yusuke Sato

An information processing apparatus has an inference unit with a first function of inputting first text data including a set of a first question text and a first answer text, and second text data including a set of a second question text and a second answer text; and a second function of, in a case in which a first synonym relationship in which a word a in the first text data is capable of being substituted with a word b is established and a second synonym relationship in which the word a in the second text data is capable of being substituted with a word c is established. A similarity between the word b and the word c is calculated from a first similarity between the first answer text and the second answer text and a second similarity between the first question text and the second question text.

Information processing method and information processing apparatus

A text preparation apparatus is configured to in the decoding processing: perform first-layer recurrent neural network processing for phrase types to be used in the text and second-layer recurrent neural network processing for words appropriate for each of the phrase types; determine a phrase appropriate for each of the phrase types based on outputs of the second-layer recurrent neural network processing; generate a first vector set from a state vector of a previous step in the first-layer recurrent neural network processing and the feature vector sets, each vector of the first vector set being generated based on similarity degrees between individual vectors in one of the feature vector sets and the state vector; generate a second vector based on similarity degrees between individual vectors in the first vector set and the state vector; and input the second vector to a given step in the first-layer recurrent neural network processing.

Text preparation apparatus

An information processing device includes an input device, an output device, a processing device, a storage device, and a generating unit. The generating unit includes a first function of inputting text data; a second function of inputting a synonym dictionary including synonyms; a third function of extracting a first piece of text data from the multiple pieces of text data; a fourth function of extracting from the synonym dictionary synonyms in which a certain word in the first piece of text data is included; a fifth function of extracting from the text data second multiple pieces of text data including a synonym belonging to the extracted synonyms; and a sixth function of generating a score to evaluate a relationship between the first piece of text data and the extracted synonyms from a relationship between the first piece of text data and the second multiple pieces of text data.

Score generation for relationships between extracted text and synonyms

Provided is a technique for easily using a dialogue service that reduces an effect of a change in a task of the dialogue service and provides a plurality of tasks. In the dialogue method, a computer including a processor and a memory executes a dialogue. The dialogue method includes: a text input step in which the computer receives text; a task execution step in which the computer causes the text to be separately executed by a plurality of types of tasks; an execution result obtaining step in which the computer separately obtains execution results from the plurality of types of tasks; a task selection step in which the computer selects one of the obtained execution results; and a response output step in which the computer outputs the selected execution result as an answer to the text.

Dialogue method, dialogue system, and program

The problem solved by this invention is to convert text information in a geology report to numerical values which reflects geological characteristics of a well's subsurface. Prior art referred above cannot be applicable to this problem. Since text information in the geology report is in the natural language form. This information is not widely used in this industry, due to the fact that the text information can be hardly extracted and summarized into numerical values and integrated into current physical geology models or statistical models. This invention makes the text information in geology report, which is often in a natural language form, easier to be integrated into current geology physical models or statistical models. Also, the numerical values extracted from the geology report can be integrated with other kinds of data, such as seismic data and well-logging data, to obtain more accurate and comprehensive analysis results.

Information analysis system

The invention includes a first process of inserting one row below each row of a column heading of an original table, inserting one column to the right of each column of a row heading, and entering a corresponding ID into each cell of the inserted row or column; a second process of inserting one row between the column heading and data portion, inserting one column between the row heading and data portion, and entering an ID of the dimension when inserted cells indicate a value of a dimension, entering no data when inserted cells indicate a measure, and entering an ID of a measure into a cell at the intersection of the inserted row and column when column headings and row headings indicate dimension's values; and a third process of identifying a dimension, value thereof, or measure corresponding to each cell of the data portion of the created template table.

Table format multi-dimensional data translation method and device

Provided is a system for enumerating local alignments, comprising a local alignment enumeration module for enumerating local alignments, in a case where the cell of a second matrix corresponding to a cell at a transition source indicates that the cell belongs to a local alignment, and in a case where the maximum score calculated is larger than the predetermined value, registers, in the cell of the second matrix corresponding to the cell to be calculated, an identifier of a local alignment registered in the cell of the second matrix corresponding to the cell at the transition source, and further, in a case where the maximum score calculated is larger than a maximum score of the cells belonging to the same local alignment, stores the cell to be calculated as an end point of the local alignment.

System, method and program for enumerating local alignments from pair of documents

To provide a technique for accurately and efficiently generating Boolean search formulas that serve as a basis of similarity search. A Boolean search formula generation apparatus according to the present invention establishes Boolean search formulas expressed in a standard sum of products form connecting products of search terms by a sum and evaluates the Boolean search formulas based on a recall and a precision. The Boolean search formula generation apparatus repeats connecting the products of the search terms with maximum evaluation values by a sum to establish a Boolean search formula.

System and program for generating boolean search formulas

To achieve high speed document search, an inverted index is compressed at high compressibility by an encoding method decodable in a high process speed. In compressing an identification number of a document to obtain a byte sequence by the variable byte method, w bits are used to represent the number of occurrences of the indexing term in the document, and x bits are used to represent additional information of the posting, where x and w are integers given as parameters. When the number of occurrences cannot be represented within w bits, a certain value indicating a numeric value that cannot be represented by w bits is stored is written to the said w bits, and anther byte sequence that represents the value by the variable byte method follows. Additionally provided is a means for reading a compressed posting from any position of a list of postings called inverted lists, allowing a binary search on an inverted list.

Device and method for constructing inverted indexes

In document search for searching a document by use of a query formula composed of a Boolean formula of keywords, a plurality of query formulas arriving at about the same time from a plurality of users are efficiently processed. A system or a program for searching documents includes: a query formula controller for sorting a plurality of query formulas into a plurality of query formula sets based on predicted search speeds of the respective query formulas; and a search unit for searches for the plurality of sorted query formula sets sequentially from the set having the fastest predicted search speed, and for, in each search processing, merging the query formulas in the corresponding query formula set into a formula and thereby searching from the merged formula.

System or program for searching documents

A document search apparatus capable of an index-type search and a scan-type search performs a search in a combination of the two search types while compensating for the disadvantages of the two search types with each other. A search query for index-type search and a search query for scan-type search are constructed based on a search query consisting of a logical formula of keywords. Then, a character 2-gram for performing an index search is set to shorten the whole search time, and the index-type search is performed. Finally, a scan-type search is performed on this search result of the index-type search.

Document search method and document search apparatus that use a combination of index-type search and scan-type search

A device for recording positions within an electronic document and capable of recreating those recorded positions afterwards even if the electronic document has been changed to some extent. An index data creation unit in an information terminal creates index information for a page to display from the electronic document, and records it along with time information in an index database. When a time is specified, the index data search unit searches the index database for index information recorded near that time, and identifies the page position of that electronic document from the searched index information. A data display unit displays the beginning of the electronic document at the identified position. The information terminal is capable of managing information by linking electronic data from handwritten information written on paper with a digital pen, with the display page the electronic document by utilizing a stroke set database and a pen data processor.

Device, a program and a system for managing electronic documents

This invention aims to provide an efficient means of performing a document search wherein relevance between plural document databases is examined. A summary making module and a search module are provided to document databases, and these are connected to a network as a server. A client obtains a relevant set of documents in a specified document database via this summary from a set of documents in the specified document database. The summary obtained is sent to another server, and a search is performed according to the summary in a document database in the server to which the summary is transferred.

Method of searching documents and a service for searching documents

Ordering is properly performed for document databases registered in an associative search server. In an associative search server capable of performing an associative search by correlating a plurality of document databases, the history of the associative search is stored as an associative search recording table by associative search recording table storing means. By using this associative search recording table, a showing order of document databases presented by document database selecting means is properly set by showing order changing means. Alternatively, by registration fee calculating means, calculation is properly carried out as to registration fees of the document database registered in the associative search server.

Document retrieval system and search server

A system for displaying the results of a search provided by one of two different search systems enabling continuous searching. One search system includes a search takeover data production command used to output search takeover data articles from the search. The other search system includes a search takeover data reading command used to read search takeover data. A document identifier correspondence table associates the identifiers specified in the search takeover data. When a user clicks a search system transfer instruction button in one search system, the search takeover data producing command is executed to produce search takeover data which is passed to the other search system. The latter search system regards the list of identifiers of articles which was passed by the search takeover data reading command as the search results, and thus operates continuously.

Growing community of inventors

Tokorozawa, Japan

Makoto Iwayama