Kabushiki Kaisha Toshiba

Toshiba Solutions Corporation

Toshiba Digital Solutions Corporation

Shigeaki Sakurai

Shigeru Matsumoto

Kazuyoshi Nishi

Rumi Hayakawa

Shozo Isobe

Ryohei Orihara

Akihiro Suyama

Kyoko Makino

Seiji Egawa

Minoru Nishizawa

Ken Ueno

Tomoko Murakami

Hideki Iwasaki

Hiroyuki Suzuki

Yoshimi Saito

Youichi Kitahara

Yoshinori Masaoka

Norihiko Sawa

An embodiment of a data pattern analysis optimizer includes a time sequence data memory, an estimator, a grouping unit, and a time sequence pattern extractor. The time sequence data memory stores a plurality of time sequence data made from items in time order. The estimator estimates the upper limit of the total number of types of time sequence patterns present in the time sequence data at a rate higher than a minimum support level, based on a respective rate of presence of each item, wherein each of the time sequence patterns present in the time sequence data is a predefined number of items. In case that the estimated upper limit exceeds an upper limit of the number of types of time sequence patterns as a maximum processing load to a computer, the grouping unit groups a plurality of time sequence data into sub-groups, based on a group of items having the increased number of items and gives the estimator instructions to perform estimation. The time sequence pattern extractor gives the computer instructs to extract the time sequence patterns for each of the sub-groups, in case that the estimated upper limit does not exceed the upper limit of the number of time sequence patterns.

Data pattern analysis optimizer, and method of data pattern analysis optimization processing

A sequential data analysis apparatus extracts a pattern of two or more sets of items based on an appearance frequency of each of different sets of items in first sequential data, selects a pattern of two or more sets of items based on an appearance frequency of a sub-pattern formed of a portion of the extracted pattern, creates a related pattern including the same last set of items as and the other sets of items different from the selected characteristic pattern, calculates an evaluation value of the related pattern, creates a prediction model by organizing data of the characteristic pattern and the related pattern, and applies second sequential data to the prediction model to determine a result which the second sequential data is likely to lead to.

Sequential data analysis apparatus and program

An evaluation device of an embodiment includes a storage, a data generator, a class definer, a characteristic data divider, and an evaluator. The data generator is configured to generate a set of characteristic data from both a set of first data and at least a set of second data, the at least set of second data being associated in time information with the set of first data, the set of characteristic data representing a plurality of characteristics. The characteristic data divider is configured to divide the plurality of sets of characteristic data into a plurality of groups on the basis of the plurality of classes defined by the class definer and condition of operations included in the set of first data. The evaluator is configured to evaluate a operating state using a first model defined for each of the plurality of groups divided by the characteristic data divider.

Evaluation device, evaluation method, and evaluation program

A pattern finding device of embodiments includes a pattern generator, a pattern storage, a pattern selector, a pattern deleter. The pattern generator generates a group of patterns from data including a plurality of items. The pattern storage stores the group of patterns generated by the pattern generator. The pattern selector selects at least one pattern to be deleted from the group of patterns with reference to an evaluated value indicating a change of an item distribution condition in the group of patterns when at least one pattern which is selected as a candidate is excluded from the group of patterns stored in the pattern storage. The pattern deleter deletes the at least one pattern that is selected by the pattern selector from the pattern storage.

Pattern finding device and program

An evaluation target of interest extraction apparatus of one embodiment extracts a plurality of items for each piece of text information. When the items include an item which matches an evaluation target expression or related expression, the apparatus allocates the evaluation target expression or that of the related expression to the text information as an evaluation target item. The apparatus distinguishes a class from a change in numeric information related to the evaluation target item, and allocates the class to the text information. The apparatus generates a class-attached transaction including the evaluation target item, the items, and the class. The apparatus discovers a pattern from a set of the transactions.

Evaluation target of interest extraction apparatus and program

A data analysis supporting apparatus according to an embodiment comprises a variable-type determining device, a variable-variation generating device, and a variable-contribution rate determining device. The variable-type determining device determines the type of each variable. The variable-variation generating device generates variations of each variable in accordance with the variable type determined and with a variable variation rule that defines a method of generating the variations of each variable of any type. The variable-contribution rate determining device calculates the rate at which the variations and analysis data contribute to the objective variable, and determines, from the rate, whether the variations should be used or deleted.

Data analysis supporting apparatus

A data analyzing apparatus of an embodiment generates a format variation, analytical algorithm name, and analytical parameter not stored in a first storage device, and executes analysis. The data analyzing apparatus determines whether the application accuracy is lower than the knowledge model accuracy. If the determination result is 'not lower', the data analyzing apparatus reactivates a format variation generating device and an analytical parameter generating device. If the determination result is 'lower', the data analyzing apparatus reads out a format variation and knowledge model name associated with the highest priority order in the first storage device, and executes analysis.

Data analyzing apparatus and program

Provided is a knowledge extracting apparatus for extracting knowledge information related to a knowledge-extraction target from an electronic document distributed continually in a state where the electronic document is not associated with the knowledge-information extraction target. A knowledge extracting apparatus according to one embodiment is a knowledge extracting apparatus including: an information receiving section for receiving an electronic document; a knowledge extracting section for extracting a concept from the electronic document based on a target word to extract knowledge information and a clue word to extract knowledge information and forming knowledge information in which the concept thus extracted and the target word are associated with each other; a storage section for storing the knowledge information thus extracted; and an information analysis section for, after the knowledge information is stored, analyzing the electronic document based on the knowledge information in the storage section.

Forming knowledge information based on a predetermined threshold of a concept and a predetermined threshold of a target word extracted from a document

A pattern extracting apparatus includes a first storing section storing plural target information pieces, a candidate pattern producing section producing candidate patterns each including two or more items different from each other based on each of the items included in the plural target information pieces, a candidate evaluation value calculating section calculating an extraction evaluation value of the candidate pattern based on a frequency of appearance at which the produced candidate pattern appears in the plural target information pieces, a pattern extracting section determining and extracting any of the candidate patterns having the calculated extraction evaluation value satisfying a predetermined threshold value, and a second storing section storing an association degree between the items. The candidate evaluation value calculating section calculates the extraction evaluation value based on a weight based on an identified association degree between the items included in the candidate pattern and the frequency of appearance.

Pattern extracting apparatus and method

A thread ranking system includes: a thread collector for collecting a thread from a bulletin board website, a thread information storage for storing the collected thread, an event extractor for extracting the event from respective threads by using the event knowledge stored in the event knowledge storage, a related expression extractor for extracting a related expression characterizing the thread from expressions contained in the thread every thread, an input/output controller for presenting information that calls upon the user to input an evaluation of a predetermined thread to the user and inputting an evaluation of the user, a related expression importance calculator for calculating importance based on the input evaluation of the user every related expression, and a thread ranking unitfor deciding ranks of respective threads based on the extracted event and the calculated importance every related expression.

Thread ranking system and thread ranking method

According to one embodiment, the Web pages that match a user's designated collection condition are collected from a plurality of Web sites. The collected Web pages are divided into a plurality of clusters, based on URL information of the Web pages. A date expression is extracted from Web pages included in each of the clusters. A typical date expression form is determined for each of the clusters, based on the extracted date expression. The Web pages included in each of the clusters are divided into a plurality of items, based on the date expression form. The items are sorted for each of the clusters in order of time, based on date expressions corresponding to the items. Time-series data is generated for each of the clusters by sorting the items.

Method and apparatus for generating time-series data from web pages

A text data storage unit stores a plurality of text data having attribute data and time data. A dictionary storage unit stores a plurality of events each associated with text data. An analysis condition indication unit indicates an analysis target as attribute data and an analysis condition as an event sequence. A time series data generation unit assigns an event to each of the plurality of text data by referring to the dictionary storage unit, extracts a group of text data each having the same attribute data as the analysis target from the plurality of text data, and generates time series data each representing the event assigned to the text data of the group in order of the time data of the text data. A time series data analysis unit analyzes the time series data each having the same event sequence as the analysis condition.

Time series data analysis apparatus and method

A time series pattern generation unit extracts a key concept corresponding to a text of each data element of a plurality of time series data by referring to an extraction rule memory, and generates a plurality of time series patterns. A colony generation unit unifies a plurality of data elements having the same key concept and substantially the same time duration, and generates colonies of unified elements. In response to a selection of a first colony, a colony extraction unit specifies a second colony having a key concept contrary to the first colony, and extracts colonies earlier than the first colony and the second colony. A time reason extraction unit extracts a time reason as a divergence condition of the first colony from the second colony from the extracted colonies.

Time series pattern extraction apparatus and method

A method for displaying multidimensional data on a screen of a display device, includes assigning a first dimension element, having been selected by a user from among the multidimensional data, to an axis; giving weights to a plurality of member regions using a function of number of data belonging to respective members of the first dimension element; defining the weighted member regions as a plurality of regions on the axis, which are partitioned for the respective members of the first dimension element; arranging the weighted member regions within the screen to form a table; and displaying, in each cell region corresponding to the weighted member region, data belonging to each cell region and belonging to a second dimension element having been selected by the user from among the multidimensional data. The second dimension element is different from the first dimension element.

Multidimensional data display program

Constraining sequential data expressing sequential data which a sequential pattern to be extracted must include is specified in advance. Sequential pattern candidates with sequence lengthare initially determined from among a plurality of input sequential data. Next, a set of sequential pattern candidates is generated by determining a plurality of new sequential pattern candidates by elongating the sequence length of the sequential pattern candidates. In this sequential pattern candidate set, after sequential pattern candidates which can generate only a sequential pattern which does not include constraining sequential data are eliminated, sequential data which include constraining data, and frequently appear are extracted as a new sequential pattern.

Growing community of inventors

Tokyo, Japan

Shigeaki Sakurai