ESTIMATION DEVICE, ESTIMATION METHOD, AND PROGRAM

    公开(公告)号:EP4443346A1

    公开(公告)日:2024-10-09

    申请号:EP22901384.2

    申请日:2022-11-30

    发明人: SUZUKI Kenji

    IPC分类号: G06N20/00 A61B6/03 G06T7/00

    CPC分类号: A61B6/03 G06T7/00 G06N20/00

    摘要: The present invention makes it possible to analyze the reason for estimation when estimation is implemented by a model constructed through machine learning. A data acquisition unit (11) acquires input data (IN). An estimation processing unit (12) estimates information relating to an estimation object represented by a signal included in the input data (IN) by inputting the input data (IN) into a trained model (100). An image display unit (13) displays the information relating to the estimation object and the reason for estimation. The trained model (100) includes a plurality of modularized networks constructed in such a manner that characteristics of the estimation object represented by a signal included in first training image data are divided by type and training is implemented in advance, and a fusion network constructed in such a manner that a plurality of output signals obtained by input of second training data into the plurality of modularized networks are input and supervised training is implemented, whereby estimating information relating to the estimation object represented by a signal included in an input image, according to a signal to be input.

    METHOD AND DEVICES FOR AUTOMATICALLY TRIGGERING AN AUDIT PROCESS

    公开(公告)号:EP4439408A1

    公开(公告)日:2024-10-02

    申请号:EP23166112.5

    申请日:2023-03-31

    申请人: Helsing GmbH

    IPC分类号: G06N20/00

    CPC分类号: G06N20/00

    摘要: There is provided a computer implemented method, a platform and a system configured to perform the method, a computer-readable medium and a computer program comprising instructions to carry out the method, the method comprising: monitoring a provenance data structure of one or more algorithms and/or of an artefact generated by one or more algorithms, the provenance data structure comprising provenance data on which the one or more algorithms and/or the artefact are based and, preferably, the one or more algorithms and/or the artefact; determining a change of the monitored provenance data structure; and automatically triggering an audit process for the one or more algorithms and/or the artefact based on the determined change of the monitored provenance data structure.