Abstract: As a document analysis system to calculate a similarity degree between texts with high accuracy, an information processing device includes: a common character string calculation unit to extract character strings that are common between two texts and to determine whether or not the two texts are to be set as calculation objects based on a number of the extracted character strings that are common; and a similarity degree calculation unit to calculate, when the two texts are the determined calculation objects, a similarity degree therebetween by using an approximation of a Kolmogorov complexity, and when the two texts are not the calculation objects, handling the similarity degree between the two texts as being dissimilar.

Abstract: To determine a contradiction between requirements and specifications in a specification document for system/software development without labor for preparation in advance, provided is a requirements contradiction detection system, including: a relevancy detection part for detecting, for two requirements expressed in texts, a relevancy between the two requirements based on a similarity between one requirement acquired by converting one of the texts based on a predetermined contradiction rule and another requirement that is not converted; and a contradiction detection part for detecting whether or not the two requirements contradict each other based on a detection result of the relevancy detection part, the similarity calculated by the relevancy detection part, and a similarity between the two original requirements before conversion.

Abstract: To determine a contradiction between requirements and specifications in a specification document for system/software development without labor for preparation in advance, provided is a requirements contradiction detection system, including: a relevancy detection part for detecting, for two requirements expressed in texts, a relevancy between the two requirements based on a similarity between one requirement acquired by converting one of the texts based on a predetermined contradiction rule and another requirement that is not converted; and a contradiction detection part for detecting whether or not the two requirements contradict each other based on a detection result of the relevancy detection part, the similarity calculated by the relevancy detection part, and a similarity between the two original requirements before conversion.

Abstract: A requirement acquisition system for grasping requirements from related documents such as documents the client holds, investigation results of an interview or questionnaire, meeting minutes, specification and the like, in system or software development, by reduced efforts and hours is provided. In particular, from a document being a group of character strings, one or more partial string which is a common part of the plurality of character strings is extracted as an important phrase. When the important phrase does not exist, the processing is finished. When the important phrase exists, a representative character string of the document is extracted as a candidate character string, deleting the candidate character string is deleted from the document, and the important phrase is deleted from the candidate character string. When the number of the important phrase being deleted is one or more, the candidate character string is set as an important character string.

Abstract: A technique extracts an object that is characteristic although the number of appearances is less demanded. A clustering apparatus includes: a similarity degree calculating section calculating a similarity degree of a combination of optional two of objects to store the calculated similarity degree in a similarity degree table, excluding a combination of one of the optional two and itself; a merging object selecting section selecting as merging objects, two objects related to the similarity degree which satisfies a predetermined reference; a new object generating section generating a new object from the merging objects; a merging object removing section removing from the similarity degree table, a similarity degree between each of the two objects selected as the merging objects and each of the objects; and a new object adding section calculating a similarity degree between the new object and each of the plurality of objects other than the new object.

Abstract: A mismatch detection system includes: a statement unit extracting portion that extracts a set of statement units by dividing a given document, which is written in a natural language, into pieces; a statement constructing portion that constructs each statement as a combination of a context and specifics by sorting each of the statement units into the context, which indicate additional information of statements, and the specifics, which indicate information of the statements; and a data generating portion that generates a data set obtained by merging a set of predetermined check specifics and a set of the statements generated by the statement constructing portion.

Abstract: As a document analysis system to calculate a similarity degree between texts with high accuracy, an information processing device includes: a common character string calculation unit to extract character strings that are common between two texts and to determine whether or not the two texts are to be set as calculation objects based on a number of the extracted character strings that are common; and a similarity degree calculation unit to calculate, when the two texts are the determined calculation objects, a similarity degree therebetween by using an approximation of a Kolmogorov complexity, and when the two texts are not the calculation objects, handling the similarity degree between the two texts as being dissimilar.

Abstract: A requirement acquisition system for grasping requirements from related documents such as documents the client holds, investigation results of an interview or questionnaire, meeting minutes, specification and the like, in system or software development, by reduced efforts and hours is provided. In particular, from a document being a group of character strings, one or more partial string which is a common part of the plurality of character strings is extracted as an important phrase. When the important phrase does not exist, the processing is finished. When the important phrase exists, a representative character string of the document is extracted as a candidate character string, deleting the candidate character string is deleted from the document, and the important phrase is deleted from the candidate character string. When the number of the important phrase being deleted is one or more, the candidate character string is set as an important character string.

Abstract: A mismatch detection system includes: a statement unit extracting portion that extracts a set of statement units by dividing a given document, which is written in a natural language, into pieces; a statement constructing portion that constructs each statement as a combination of a context and specifics by sorting each of the statement units into the context, which indicate additional information of statements, and the specifics, which indicate information of the statements; and a data generating portion that generates a data set obtained by merging a set of predetermined check specifics and a set of the statements generated by the statement constructing portion.

Abstract: Included are a candidate extraction unit 61 that extracts, from a document formed by a group of character strings, a longest consecutive partial string common to one character string and the other character string as a candidate for an important word related to the one character string; a candidate integration unit 62 that selects a longest partial string of the candidate for the important word related to the one character string and extracted by the candidate extraction unit 61; and a group integration unit 63 that integrates a group of the longest partial string of each character string selected by the candidate integration unit 62, this group not forming a subset of a group of the other character string, thereby forming a group of the important word.

Abstract: A technique extracts an object that is characteristic although the number of appearances is less demanded. A clustering apparatus includes: a similarity degree calculating section calculating a similarity degree of a combination of optional two of objects to store the calculated similarity degree in a similarity degree table, excluding a combination of one of the optional two and itself; a merging object selecting section selecting as merging objects, two objects related to the similarity degree which satisfies a predetermined reference; a new object generating section generating a new object from the merging objects; a merging object removing section removing from the similarity degree table, a similarity degree between each of the two objects selected as the merging objects and each of the objects; and a new object adding section calculating a similarity degree between the new object and each of the plurality of objects other than the new object.

Abstract: Disclosed is a survival analysis system for determining an estimated time until an event occurs on the basis of a group of cases each including at least one attribute value indicating a feature value of a case and information on the measured actual time until an event occurs. The survival analysis system includes: an estimator creating section for creating an estimator for estimating whether or not an event occurs according to the attributes of the group of cases for each actual time; an estimator selecting section for judging whether or not the estimator meets a predetermined selection condition and to selecting an estimator used for calculating the estimated time; and a time calculating section for calculating the estimated time by using the estimator selected by the estimator selecting section.

Abstract: A learning system that can predict a desired result, and can have stable and improved prediction precision is presented. The learning system includes a learning section which learns the learning data using a learning algorithm to generate hypotheses, a storage section containing at least a plurality of un-labeled candidate data, a calculating section which uses the hypotheses to calculate a score for each of the plurality of candidate data, a selecting section that selects desired candidate data based on the calculated scores and a predetermined stochastic selection function, a data updating section which affixes a user-determined label to the desired candidate data and outputs the desired candidate data to the learning data, and a control unit which outputs the hypotheses to an output unit when an end condition is met, so that a desired result is predicted.

Abstract: A processing unit (2) of an active learning system calculates the degree of similarity of data for which the label value is unknown with respect to data for which the label value is known by using a first data selection section 26, and iterates at least on cycle of the active learning cycle that selects the data to be learned next based on the calculated degree of similarity, to thereby enable finding of the desired data needed for learning a rule more efficiently than a random selection. Thereafter, the processing unit (2) learns a rule based on the data for which the label value is known, and applies the learned rule to a set of unknown data for which the label value is unknown, to shift another active learning cycle that selects the data to be learned next.

Abstract: In order to carry out a learning in which newly acquired data is taken to be more important than data previously accumulated, a function is provided which sets a weight for learning data based on an acquisition order of the learning data. Furthermore, in order to carry out a learning which reflects data acquired in the last cycle and a result with respect to the data, a function is provided which feeds back a result of a learning in the last cycle to a rule and sets a weight for learning data based on a relation between a label of data and a prediction value.

Abstract: A learning data memory unit stores a set of learning data that are composed of a plurality of descriptors and a plurality of labels. When positive cases, in which the values of desired labels are desired values, are few in number or nonexistent in the learning data memory unit, a control unit rewrites the values of desired labels to values of other similar labels to generate provisional positive cases. An active learning unit uses the provisional positive cases and negative cases to learn rules, applies these learned rules to a set of candidate data that are stored in a candidate data memory unit in which desired labels are unknown to predict the resemblance of each item of candidate data to positive cases, and based on these prediction results, selects and supplies data that are to be learned next from an input/output device.

Abstract: A learning system includes an input section which inputs learning data to which labels are set and an end condition. A learning section which learns the learning data using a learning algorithm to generate hypotheses, and a plurality of candidate data to with no label are stored in a storage section. A calculating section refers to the storage section and calculates a score to each of the plurality of candidate data by using the hypotheses, and a selecting section selects desired candidate data from among the plurality of candidate data based on the calculated scores. A setting section sets a label determined by a user to the desired candidate data, and a data updating section adds the desired candidate data to the learning data and outputs to the learning section. A control unit outputs the hypotheses generated by the learning section to an output unit when the end condition is met.