Abstract: When a pathway is generated based on property information representing a property of a molecule acting on a disease or symptom, interactome information representing a connection relationship between molecules, and similarity information representing a similarity between molecules, the pathway is generated using a minimum flow algorithm to satisfy at least two conditions that (1) a path is generated by connecting only molecules whose flow values are greater than a minimum threshold and less than a maximum threshold, and (2) a path is generated by connecting only molecules whose flow values are equal to or less than a threshold related to a similarity. In this way, when a specific molecule is knocked out in a pathway once generated and the pathway is regenerated, changes occur not only in a path in which the knocked-out molecule is present but also in other paths, and an appropriate pathway reflecting the knocked-out state can be generated.

Abstract: The partial common path detection unit 12 configured to detect a common part exclusively in a portion between a start point and an end point of a path among a plurality of disease pathways representing, as a route map, an intermolecular interaction of related molecules with respect to a disease for each of a plurality of diseases related to state changes, and the common difference information provision unit 13 configured to provide information on a detected partial common path or a molecule included in the partial common path and a non-partial common path other than the partial common path or a molecule included in the non-partial common path in a state where whether the partial common path is related or the non-partial common path is related is distinguishable are provided, and a change in pathway due to the state change of the disease can be understood by providing information so that which part is common and which part is not common between a start point and an end point of a path can be understood in a re

Abstract: A depressive symptom determination unit 13 configured to determine a depressive symptom of a subject by inputting a feature vector generated based on a feature quantity of a conversation conducted by a determination target subject to a machine-trained determination model is provided, and determination is performed by a determination model generated by machine learning using, as training data, conversation data of a subject satisfying a predetermined extraction condition and exclusion condition with regard to the depressive symptom. By labeling training data with a positive example/negative example based on a HAMD score while an extraction condition is set based on a diagnosis result of a doctor, a depressive symptom can be determined according to a state of a subject when a conversation is conducted even for a subject temporarily in a state different from a diagnosis result for a depressive symptom by a doctor.

Abstract: A depressive symptom determination unit 13 configured to determine a depressive symptom of a subject by inputting a feature vector generated based on a feature quantity of a conversation conducted by a determination target subject to a machine-trained determination model is provided, and determination is performed by a determination model generated by machine learning using, as training data, conversation data of a subject satisfying a predetermined extraction condition and exclusion condition with regard to the depressive symptom.

Abstract: An information processing system includes, a supply-chain-network obtaining unit configured to obtain a supply chain network in which a plurality of nodes each corresponding to one of a plurality of companies are connected together through links, a subnetwork extracting unit configured to extract a subnetwork including at least one of an upstream subnetwork and a downstream subnetwork, the upstream subnetwork including an upstream company that supplies the product to a company corresponding to a processing target node among the plurality of companies, the downstream subnetwork including a downstream company that is supplied with the product from the company corresponding to the processing target node, a vector obtaining unit configured to determine a complex vector representing the processing target node, and a similarity calculating unit configured to calculate a similarity between two of the plurality of nodes in accordance with the two complex vectors corresponding to the two nodes.

Abstract: An information processing method includes: obtaining a first evaluation result representing performance of a first machine learning model having learned using first learning data, the first evaluation result being calculated using first validation data; obtaining a second evaluation result representing performance of a second machine learning model having learned using second learning data, the second evaluation result being calculated using second validation data; and calculating, based on the first evaluation result and the second evaluation result, a comprehensive evaluation result representing performance of a single machine learning model including the first machine learning model and the second machine learning model, the performance of the single machine learning model being predicted when the single machine learning model is applied to unevaluated, unknown data relevant to a prescribed event.

Abstract: An information processing device includes: an acquisition unit configured to acquire document data; an analysis processing unit configured to perform morphological analysis of the document data; a feature determining unit configured to determine a feature corresponding to the document data based on a result of the morphological analysis and a hash function; an export unit configured to output export data that is data based on the feature to a second information processing device; an import unit configured to acquire a result of processing performed by the second information processing device based on the export data; and a processing unit configured to perform processing based on the result of the processing acquired by the import unit.

Abstract: An information processing device includes: an acquisition unit configured to acquire document data; an analysis processing unit configured to perform morphological analysis of the document data; a feature determining unit configured to determine a feature corresponding to the document data based on a result of the morphological analysis and a hash function; an export unit configured to output export data that is data based on the feature to a second information processing device; an import unit configured to acquire a result of processing performed by the second information processing device based on the export data; and a processing unit configured to perform processing based on the result of the processing acquired by the import unit.

Abstract: An information processing device including: an obtaining unit configured to obtain document data; an analysis processing unit configured to perform morphological analysis of the document data; a feature determining unit configured to determine a feature in accordance with a result of the morphological analysis; and a learning processing unit configured to perform machine learning to determine a weight of a morpheme in a model in accordance with the feature, the morpheme being obtained by the morphological analysis, and the model being either a linear model or a generalized linear model, wherein the learning processing unit performs processing of deleting, from input data of the model, the feature corresponding to the morpheme having the weight a value of which is determined to be smaller than, or equal to, a given threshold value.

Abstract: An information processing device includes: a model obtaining unit configured to obtain a learned model generated by machine learning that includes: determining a weight of a morpheme in a model, in accordance with a feature determined using a result of morphological analysis; and deleting, from input data of the model, the feature corresponding to the morpheme having the weight determined to be smaller than, or equal to, a threshold value; an obtaining unit configured to obtain document data ; a feature determining unit configured to determine the feature to be input to the learned model, in accordance with the result of the morphological analysis; an inference processing unit configured to input the feature to the learned model, to calculate a score indicating a degree of relevance between the document data and an event; and a display control unit configured to perform display control using the score.

Abstract: Vector computation units 1 and 2 for forming first and second vector spaces by computing a plurality of feature vectors from each of a first data set and a second data set, and a vector mapping unit 3 for mapping a feature vector not synonymous with a feature vector in the second vector space from the first vector space to the second vector space are included. Further, by mapping a feature vector not synonymous with a plurality of feature vectors included in the second vector space from the first vector space to the second vector space without changing the plurality of feature vectors, data analysis can be performed on, as targets, a feature vector originally included in the second vector space and a feature vector added from the first vector space.

Abstract: Included are a 2D processing unit 11 that generates 2D latitude and longitude information by dimensionally compressing a feature vector generated from target information, and a map generation unit 12 that generates a 2D map in which a plurality of pieces of target information is plotted on a 2D plane based on a plurality of pieces of latitude and longitude information generated for a plurality of pieces of target information.

Abstract: A word extraction unit 11 that analyzes m texts to extract n words, a vector computation unit 12 that converts each of the m texts into a q-dimension vector and each of the n words into a q-dimension vector, thereby computing m text vectors including q axis components and n word vectors including q axis components, and an index value computation unit 13 that takes each of inner products of the m text vectors and the n word vectors, thereby computing a similarity index value reflecting a relationship between the m texts and the n words are included, and it is possible to obtain a similarity index value representing which word contributes to which text and to what extent as an inner product value by calculating an inner product of a text vector computed from a text and a word vector computed from a word included in the text.

Abstract: An information processing device is configured to identify language of character strings in a text. The information processing device includes a processor and a memory storing a program. The processor is configured to or the program, when executed by the processor, causes the processor to: identify a first character, which is used commonly in a plurality of languages, in an input text; infer to which one of the plurality of languages the first character belongs based on a second character used only in one of the plurality of languages in the input text; and infer that the first character belongs to a language that is the one of the plurality of languages to which the second character belongs, based on whether a string of characters immediately preceding or following the first character in the input text contains the second character.

Abstract: A correlation display system, correlation display method, and correlation display program capable of outputting the relationship between a plurality of persons in a manner visibly recognizable by a user are provided. A correlation display system 1 includes: a communication data acquisition unit 10 that acquires communication data transmitted and received between a plurality of terminals and thereby associated with each of a plurality of persons; an analysis unit 12 that analyzes content of the communication data acquired by the communication data acquisition unit 10; an evaluation unit 16 that evaluates the relationship between the content of the communication data and a predetermined event by using an analysis result of the analysis unit 12; and a display unit 18 that displays the relationship between a plurality of persons related to the event on the basis of an evaluation result of the evaluation unit 16.

Abstract: Provided is a data analysis system that generates effective information affecting a user's tendency to buy a product and service. The data analysis system analyzes data to generate information on a tendency of a user, and includes: a memory that stores at least temporarily a plurality of evaluation data to be analyzed; and a controller that evaluates each of the plurality of evaluation data based on training data, wherein the controller extracts first information from the plurality of evaluation data based on results of the evaluation of the plurality of evaluation data, extracts second information from the training data based on a characteristic pattern included in the first information, and generates the information on the tendency of the user from the first information and the second information.

Abstract: An information processing method includes: obtaining a first evaluation result representing performance of a first machine learning model having learned using first learning data, the first evaluation result being calculated using first validation data; obtaining a second evaluation result representing performance of a second machine learning model having learned using second learning data, the second evaluation result being calculated using second validation data; and calculating, based on the first evaluation result and the second evaluation result, a comprehensive evaluation result representing performance of a single machine learning model including the first machine learning model and the second machine learning model, the performance of the single machine learning model being predicted when the single machine learning model is applied to unevaluated, unknown data relevant to a prescribed event.

Abstract: An object is to efficiently generate a list of data elements that complement a given key element. A computer includes a memory and a controller, wherein the memory stores data, and the controller performs: selection processing of selecting data elements in vicinity of a predetermined data element as cooccurrence data elements; calculation processing of calculating a degree of importance of each cooccurrence data element; and presentation processing of presenting the cooccurrence data elements.

Abstract: [Problem to be Solved] Provided is a computer system that can accurately evaluate data to be analyzed without adding training data. [Solution] The computer system forms, from a matrix based on a co-occurrence frequency of first data elements forming at least one piece of data out of a plurality of data and second data elements appearing in vicinity of the first data elements, vectors for a plurality of data elements as the first data elements, calculates similarities for the first data elements on the basis of the vectors, and sets evaluation values for the first data elements on the basis of evaluation values corrected in accordance with the similarities.

Abstract: A document processing device includes: a document classification section configured to sequentially apply a plurality of classification processes in a prescribed sequence to a plurality of documents to classify the plurality of documents into a plurality of groups; and a classification determination section configured to every time one of the plurality of classification processes is applied, determine whether or not each group contains two or more documents. The document classification section, after applying a preceding one of the plurality of classification processes, applies a succeeding one of the plurality of classification processes to the two or more documents in each group determined as containing the two or more documents. The prescribed sequence is an ascending order of an amount of calculation involved in the plurality of classification processes.