Hitachi, Ltd.

Hitachi Solutions, Ltd.

Yuxin Liang

Masayoshi Mase

Masashi Egi

Junji Yamamoto

Naoaki Yokoi

Yasuhide Mori

Daisuke Tashiro

Hiroyuki Namba

Naofumi Hama

A computer system accurately selects learning data for improving a prediction accuracy of a predictor, and is connected to a database that stores a plurality of pieces of learning data and information for managing a plurality of predictors generated under different learning conditions. A target predictor is selected, an influence degree representing strength of an influence of the learning data on a prediction accuracy of the target predictor for test data is calculated for each of a plurality of pieces of test data, an influence score of the learning data is calculated for the plurality of predictors based on a plurality of influence degrees of the learning data associated with the predictors, and the learning data to be used is selected from the plurality of pieces of learning data on the basis of a plurality of the influence scores of each of the plurality of pieces of learning data.

Selection method of learning data and computer system

There is provided is a computer system that outputs a predicted value of data to be evaluated using a predictor generated using learning data. The computer system includes the predictor; an index calculation unit that calculates an interpretation index of the data to be evaluated; and an extraction unit that selects the learning data useful for a user to interpret the predicted value of the data to be evaluated, wherein index management information for managing an interpretation index of the learning data is stored, the index calculation unit calculates the interpretation index of the data to be evaluated, and the extraction unit calculates a selection index based on the interpretation index of the data to be evaluated and the interpretation index of the learning data, selects the learning data based on the selection index, and outputs display information for presenting information indicating a processing result.

Computer system and method of presenting information related to basis of predicted value output by predictor

Provided is a computer system to present information useful for achieving purposes related to an object by utilizing AI prediction. The computer system manages a prediction model for predicting an object event based on evaluation data and feature profiling database that defines a change rule of each of the plurality of feature values included in the evaluation data, generates change policy data by changing the plurality of feature values included in the evaluation data based on the feature profiling database, calculates an evaluation value indicating effectiveness of the change policy data, and generates display data for presenting the change policy data and the evaluation value as information useful for achieving purposes related to the object.

Computer system and method of evaluating changes to data in a prediction model

Provided is a technique for reducing the calculation load in navigation management of a moving body within a freely navigable space. The system has a storage unitfor storing movement locus data showing a plurality of movement loci in which a moving body is moved in a two-dimensional or three-dimensional space in which free movement is possible; a network model management unitfor integrating sections approximated by the plurality of movement loci on the basis of the movement locus data, and generating a network model showing a route within the space; a navigation schedule calculation unitfor calculating a navigation schedule when a plurality of moving bodies planning to pass within the space navigate within that space according to the network model route; and a display processing unitfor outputting the calculated navigation schedule to a display apparatus.

Moving body management system and method

A traffic control assisting system ('assisting system') stores action data on an action of a moving object, geographic data in which geographic attribute information, which is information on a reference of movement of the moving object, is imparted to individual segments that are meshes into which a map is divided, and responsiveness data on the moving object's responsiveness to an instruction. The assisting system estimates an ideal action of the moving object based on the responsiveness data; calculates a difference between the estimated action and an action in the action data; updates the responsiveness data based on a result of the calculation; estimates probability of presence of the moving object at certain coordinates at each time point based on the action data, the geographic data, and the responsiveness data and generates a geographic E map; and predicts future coordinates of the moving object based on the geographic E map.

Growing community of inventors

Tokyo, Japan

Yuxin Liang