-
公开(公告)号:US20240070545A1
公开(公告)日:2024-02-29
申请号:US18458135
申请日:2023-08-29
Applicant: FUJIFILM Corporation
Inventor: Taiki FURUKAWA , Shotaro MISAWA , Hirokazu YARIMIZU , Ryuji KANO , Tomoki TANIGUCHI , Tomoko OHKUMA , Kohei ONODA
IPC: G06N20/00
CPC classification number: G06N20/00
Abstract: An information processing apparatus includes at least one processor, in which the processor is configured to: for a machine learning model that uses a document data group including a plurality of document data as input and outputs output data, derive an evaluation value in the machine learning model for each document data included in the document data group.
-
2.
公开(公告)号:US20240330592A1
公开(公告)日:2024-10-03
申请号:US18596629
申请日:2024-03-06
Applicant: FUJIFILM CORPORATION
Inventor: Shotaro MISAWA , Ryuji KANO , Hirokazu YARIMIZU , Tomoki TANIGUCHI , Kohei ONODA
IPC: G06F40/30 , G06F40/205
CPC classification number: G06F40/30 , G06F40/205
Abstract: An information processing apparatus generates a first character string set by dividing first document data into different lengths, derives an evaluation value of each character string constituting the first character string set by using the first character string set and second document data created from the first document data in accordance with a purpose, and selects, based on the derived evaluation value, a plurality of character strings from the first character string set as correct answer data of a generative model that receives input of document data and outputs a second character string set including a plurality of character strings included in the input document data.
-
3.
公开(公告)号:US20240070544A1
公开(公告)日:2024-02-29
申请号:US18458130
申请日:2023-08-29
Applicant: FUJIFILM Corporation
Inventor: Shotaro MISAWA , Hirokazu YARIMIZU , Ryuji KANO , Tomoki TANIGUCHI , Tomoko OHKUMA , Kohei ONODA
Abstract: A model generation apparatus includes a processor that is configured to: acquire information data for learning, acquire document data for learning, extract a first portion and a second portion having a lower rate of match with the information data than the first portion from the document data based on a rate of match between the information data and each portion of the document data, generate a first machine learning model by using first learning data in which first data for learning included in the information data is used as input data and the first portion is used as correct answer data, and generate a second machine learning model by using second learning data in which second data for learning included in the information data is used as input data and the second portion is used as correct answer data.
-
公开(公告)号:US20250021746A1
公开(公告)日:2025-01-16
申请号:US18748064
申请日:2024-06-19
Applicant: FUJIFILM Corporation
Inventor: Shotaro MISAWA , Nobuya KITAMURA , Yukie SUGIYAMA , Hiroki SATO , Hirokazu YARIMIZU , Kohei ONODA
IPC: G06F40/166 , G06F40/279
Abstract: A document creation support apparatus displays a subject document creation screen for creating a subject document and a reference document display screen for displaying a reference document to be used for creating the subject document, and in a case where a plurality of the reference documents are displayed on the reference document display screen, displays an overlapping part included in the reference document in a non-highlighted manner with respect to a non-overlapping part.
-
5.
公开(公告)号:US20230335226A1
公开(公告)日:2023-10-19
申请号:US18340038
申请日:2023-06-23
Applicant: FUJIFILM CORPORATION
Inventor: Hirokazu YARIMIZU , Yasushi HIKIDA
Abstract: An information processing apparatus includes at least one processor. The processor receives input of partial structure data indicating a partial structure of a chemical substance and a condition regarding an index value indicating performance of the chemical substance; extracts, for each of a plurality of known chemical substances, a known chemical substance including an input partial structure which is a partial structure indicated by the partial structure data and satisfying the condition from a database in which structure data indicating a structure of the chemical substance is recorded; extracts a partial structure other than the input partial structure, which is included in a structure of the extracted known chemical substance as a co-occurrence partial structure; and displays the extracted co-occurrence partial structure.
-
6.
公开(公告)号:US20250021740A1
公开(公告)日:2025-01-16
申请号:US18749507
申请日:2024-06-20
Applicant: FUJIFILM Corporation
Inventor: Shotaro MISAWA , Taiki FURUKAWA , Shintaro OYAMA , Nobuya KITAMURA , Hirokazu YARIMIZU , Kohei ONODA
IPC: G06F40/103 , G16H15/00
Abstract: A document presentation apparatus acquires date information based on text information included in a document, extracts a plurality of the documents based on a set condition, and presents the document of which an evaluation value based on the date information acquired for each of the plurality of extracted documents is relatively high with priority over the document of which the evaluation value is relatively low.
-
公开(公告)号:US20240193484A1
公开(公告)日:2024-06-13
申请号:US18582692
申请日:2024-02-21
Applicant: FUJIFILM CORPORATION
Inventor: Shotaro MISAWA , Ryuji KANO , Tomoko OHKUMA , Tomoki TANIGUCHI , Hirokazu YARIMIZU , Kohei ONODA
IPC: G06N20/00
CPC classification number: G06N20/00
Abstract: There is provided a device for generating a data merging rule for a machine learning model, the device including: a processor, and a memory connected to or built in the processor, in which the processor is configured to execute specifying processing of specifying a combination of feature vectors that are included in a data set including a correct answer label and are allowed to be merged, and rule generation processing of generating a merging rule of the feature vectors based on a combination of the feature vectors that are allowed to be merged.
-
8.
公开(公告)号:US20240071619A1
公开(公告)日:2024-02-29
申请号:US18457331
申请日:2023-08-28
Applicant: FUJIFILM Corporation
Inventor: Taiki FURUKAWA , Shotaro MISAWA , Ryuji KANO , Hirokazu YARIMIZU , Tomoki TANIGUCHI , Tomoko OHKUMA , Kohei ONODA
Abstract: An information processing apparatus including: plural models including at least a first model that uses first data as input to carry out a first prediction task and a second model that uses second data as input to carry out a second prediction task different from the first prediction task, and at least one processor, in which the processor is configured to: acquire information data representing information related to a specific target; select a selection model to be used for prediction from among the plural models based on the information data; and derive a degree of importance to the specific target for each item included in the information data by using the selection model.
-
9.
公开(公告)号:US20230326560A1
公开(公告)日:2023-10-12
申请号:US18334389
申请日:2023-06-14
Applicant: FUJIFILM CORPORATION
Inventor: Hirokazu YARIMIZU , Yasushi HIKIDA
Abstract: An information processing apparatus performs a first search for searching structure data indicating a structure of a chemical substance, which is a processing target, for a partial structure included in partial structure data in which the partial structure of the chemical substance and an index value indicating performance or a structure of the partial structure are associated with each other, performs a second search for searching past data for a chemical substance including the partial structure extracted by the first search, derives a reliability degree of the index value of the partial structure based on a total number of the chemical substances extracted by the second search and an index value corresponding to the chemical substance, and performs control of displaying the partial structure extracted by the first search and the reliability degree of the partial structure on a display device.
-
公开(公告)号:US20250103630A1
公开(公告)日:2025-03-27
申请号:US18892555
申请日:2024-09-23
Applicant: FUJIFILM Corporation
Inventor: Shotaro MISAWA , Shintaro OYAMA , Taiki FURUKAWA , Hirokazu YARIMIZU , Kohei ONODA , Nobuya KITAMURA
Abstract: A document creation support apparatus acquires document information associated with an input target person, derives the number of pieces of examination information included in the document information for each examination item, and derives a degree of importance of the examination item for the target person based on the derived number of pieces of the examination information.
-
-
-
-
-
-
-
-
-