-
公开(公告)号：US20210406932A1
公开(公告)日：2021-12-30
申请号：US17056071
申请日：2020-01-20
Applicant: Rakuten Group, Inc.
Inventor： Dinesh DAULTANI , Bruno Andre CHARRON
Abstract: An information processing apparatus includes a first fitness calculation unit for calculating a fitness using a predetermined function for each of a plurality of models belonging to a population; a virtual model generating unit for selecting, as parent models, a plurality of models having higher value of the fitness among the plurality of models, and generating a virtual model that outputs an output result obtained by performing calculation of output results of the selected plurality of parent models; a second fitness calculation unit for calculating the fitness of the virtual model using the predetermined function; a model replacing unit for replacing the models constituting the population by adding the virtual model to the population and by deleting a model having a lower value of the fitness from the population; and a model extracting unit for extracting a model having a higher value of the fitness from the population.
-
Patent Agency Ranking
2.发明公开公开(公告)号：US20240135693A1
公开(公告)日：2024-04-25
申请号：US18009831
申请日：2021-12-07
Applicant: Rakuten Group, Inc.
Inventor： Dinesh DAULTANI , Mitsuru NAKAZAWA
IPC: G06V10/82 , G06V10/77 , G06V10/771
CPC classification number: G06V10/82 , G06V10/771 , G06V10/7715
Abstract: An information processing apparatus includes: a generating unit configured to generate, from a data group including training data elements given different correct labels, multiple training data sets in such a manner that the number of included training data elements changes successively, by successively selecting one or more training data elements from the data group; and a training unit configured to repeatedly train a learning model for machine learning by applying the training data sets to the learning model.
-
公开(公告)号：US20240135685A1
公开(公告)日：2024-04-25
申请号：US18013169
申请日：2021-12-27
Applicant: RAKUTEN GROUP, INC.
Inventor： Dinesh DAULTANI , Mitsuru NAKAZAWA
CPC classification number: G06V10/774 , G06T5/20 , G06T5/60 , G06T5/92 , G06T7/11 , G06T7/194 , G06T7/80 , G06T11/60 , G06T2207/20081
Abstract: [Problem] Provided is a novel information processing technology relating to a predetermined object in an image.
[Solving Means] An information processing apparatus includes: an image acquisition unit that acquires an image used as teacher data for machine learning, the image being with one or a plurality of annotations for showing a position in the image at which a predetermined object is shown; an adjustment image generation unit that generates an adjustment image in which parameters of the image are adjusted; and a machine learning unit that generates a learning model for detecting the predetermined object in an image by performing machine learning using teacher data including the adjustment image.-
公开(公告)号：US20220311790A1
公开(公告)日：2022-09-29
申请号：US17418873
申请日：2020-09-29
Applicant: RAKUTEN GROUP, INC.
Inventor： Dinesh DAULTANI , Bruno Andre CHARRON
IPC: H04L9/40
Abstract: An input data generation unit is configured to generate, based on log data indicating a log of a behavior of a user with respect to a given computer resource for each period, input data for the period, which is associated with the log data. A user probability data generation unit is configured to generate user probability data based on output obtained from a trained machine learning model when the input data is input to the trained machine learning model. An anomaly determination unit is configured to determine whether an anomaly has occurred in the behavior of the user during a latest period based on the user probability data generated based on the input data for the latest period and the user probability data generated based on the input data for a period before the latest period.
-
5.发明公开公开(公告)号：US20240233353A1
公开(公告)日：2024-07-11
申请号：US18009267
申请日：2021-12-07
Applicant: Rakuten Group, Inc.
Inventor： Dinesh DAULTANI , Mitsuru NAKAZAWA
CPC classification number: G06V10/82 , G06V10/7715
Abstract: An information processing apparatus includes an acquiring unit configured to acquire an object image that includes an object, and a predicting unit configured to predict a class of the object by applying the object image acquired by the acquiring unit to a learning model. The learning model includes a main network (201) that extracts feature amounts regarding hierarchical classes of the object based on the object image, and a sub network (202) that outputs hierarchical classes of the object based on the feature amounts. The main network (201) includes extractors that extract the feature amounts. The sub network (202) includes classifiers that output classes of the object based on the feature amounts, and in the sub network, a higher-level classifier has a connection to one or more lower-level classifiers.
-
公开(公告)号：US20240104880A1
公开(公告)日：2024-03-28
申请号：US18003385
申请日：2021-12-27
Applicant: RAKUTEN GROUP, INC.
Inventor： Dinesh DAULTANI , Mitsuru NAKAZAWA
CPC classification number: G06V10/25 , G06T7/13 , G06T7/60 , G06V20/70 , G06V2201/07
Abstract: [Problem] Provided is a novel information processing technology relating to a predetermined object in an image.
[Solving Means] An information processing apparatus includes: an image acquisition unit that acquires an image used as teacher data for machine learning, the image being with one or a plurality of annotations for showing a position in the image at which a predetermined object is shown; a region specification unit that specifies a region in which the one or the plurality of annotations satisfy a predetermined criterion in the image; an edge detection unit that preferentially detects edges in the specified region or a range set on a basis of the region; and an annotation correction unit that corrects the annotations so as to be along the detected edges.
-
-
-
-
-
Search Results
6
records
(took 0.012 seconds)
