专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

1. 发明申请

US20130243263A1 INFORMATION PROCESSOR, METHOD, AND PROGRAM FOR DOCUMENT PROOFREADING 有权
标题翻译：信息处理程序，方法和文件编制程序
公开(公告)号：US20130243263A1
公开(公告)日：2013-09-19
申请号：US13784897
申请日：2013-03-05
申请人： INTERNATIONAL BUSINESS MACHINES CORPORATION
发明人： Tatsuya Ishihara , Hironobu Takagi
IPC分类号： G06K9/00
CPC分类号： G06K9/00442 , G06K9/033
摘要： A method, apparatus and program for proofreading a document. The information processor includes a first storage unit for storing output information which includes information text and positional information obtained by performing Optical Character Recognition (OCR) on a source manuscript image. A second storage unit for storing a document file that is proofread by a user, wherein the document file is generated by reading the OCR-processed text according to the order of reading the output information A line movement detection unit for detected movement of a line which includes text in the document file based on the proofreading performed by the user on the document file. A merge unit for reflecting result of the proofreading of the document file in the output information.
摘要翻译：用于校对文件的方法，装置和程序。信息处理器包括：第一存储单元，用于存储输出信息，该输出信息包括通过在源原稿图像上执行光学字符识别（OCR）而获得的信息文本和位置信息。第二存储单元，用于存储由用户校对的文件文件，其中，通过根据读取输出信息的顺序读取OCR处理的文本来生成文档文件。A行移动检测单元，用于检测到的行的移动，基于用户对文档文件执行的校对，在文档文件中包含文本。合并单元，用于反映输出信息中文件文件的校对结果。

2. 发明授权

US10104159B2 Task processing method, program, and system 有权
公开(公告)号：US10104159B2
公开(公告)日：2018-10-16
申请号：US14028722
申请日：2013-09-17
申请人： International Business Machines Corporation
发明人： Tatsuya Ishihara , Hironobu Takagi
IPC分类号： H04L29/08 , H04L12/58 , G06Q10/10 , H04L12/26 , G06Q10/06
摘要： A contribution value necessary for achieving a target accuracy from a correct answer probability of each participant is calculated, a contribution value of the participant is added for an answer in accordance with the calculation, and it is set at a condition for determining completion of a task, that is, determining that a correct answer is obtained and no additional participant is necessary. The contribution value is calculated as the inverse of the number of participants at which the target accuracy is reached with a predetermined correct answer probability. The contribution value of the participant is added to the contribution value for the task in which that participant participates. At the time when the sum of the contribution values for a task exceeds one or when one option is certain to be a correct answer, the result having the largest sum of the contribution values is output.

3. 发明授权

US11042756B1 Semi-supervised grouping and classifying groups from images 有权
公开(公告)号：US11042756B1
公开(公告)日：2021-06-22
申请号：US16786628
申请日：2020-02-10
申请人： INTERNATIONAL BUSINESS MACHINES CORPORATION
发明人： Jayakorn Vongkulbhisal , Tatsuya Ishihara
IPC分类号： G06T13/40 , G06K9/00 , G06N3/08 , G06T7/62 , G06T11/20 , G06F17/16
摘要： A semi-supervised computer-implemented method for group and group activity detection is provided. The method includes detecting, by a hardware processor, entity areas in an image. The method further includes extracting relative position features from pairs of the entity areas. The method also includes extracting pixel features from the pairs of the entity areas. The method additionally includes combining the relative position features and the pixel features to generate edge features. The method further includes identifying, using a display device, groups formed from the entity areas by processing the edge features using an Edge-Labeling Graph Neural Network. The method also includes identifying, using the display device, for each of the groups of the entity areas, a group activity performed by the persons therein based on a result of a voting scheme.

4. 发明授权

US10982966B2 Generation of route network data for movement 有权
公开(公告)号：US10982966B2
公开(公告)日：2021-04-20
申请号：US16777004
申请日：2020-01-30
申请人： INTERNATIONAL BUSINESS MACHINES CORPORATION
发明人： Tatsuya Ishihara , Masayuki Murata , Daisuke Sato
IPC分类号： G01C21/00 , G01C21/34 , G01C21/20 , G06T17/00
摘要： A method for generating route network data for movement includes calculating a movable area in a place for a target type of movement using a space model of the place and an object model for the target type. The method also includes building network structure for route network data of the place using the movable area for the target type, in which the network structure includes a plurality of nodes and a plurality of links representing routes within the place. The method further includes updating the network structure by shifting a node to orient a link connected to the node toward any one of predetermined directions under a condition relating to an initial position of the node.

5. 发明授权

US10332273B2 Building 3D map 有权
公开(公告)号：US10332273B2
公开(公告)日：2019-06-25
申请号：US15379377
申请日：2016-12-14
申请人： INTERNATIONAL BUSINESS MACHINES CORPORATION
发明人： Tatsuya Ishihara , Jayakorn Vongkulbhisal
IPC分类号： G06T7/73 , G06T7/579
摘要： A computer-implemented method for building a 3D map, includes: obtaining plural videos and plural video-related data units, each of the plural video-related data units indicating a feature of radio wave signals received at a place where a corresponding video has been taken; reconstructing plural 3D models, respectively, based on the plural videos; selecting a pair of 3D models from the plural 3D models based on similarity between a corresponding pair of video-related data units; and merging the pair of 3D models to obtain the 3D map.

6. 发明申请

US20170169583A1 BUILDING 3D MAP 审中-公开
公开(公告)号：US20170169583A1
公开(公告)日：2017-06-15
申请号：US15379377
申请日：2016-12-14
申请人： INTERNATIONAL BUSINESS MACHINES CORPORATION
发明人： Tatsuya Ishihara , Jayakorn Vongkulbhisal
IPC分类号： G06T7/73
CPC分类号： G06T7/73 , G06T7/579 , G06T2207/10016 , G06T2207/10021
摘要： A computer-implemented method for building a 3D map, includes: obtaining plural videos and plural video-related data units, each of the plural video-related data units indicating a feature of radio wave signals received at a place where a corresponding video has been taken; reconstructing plural 3D models, respectively, based on the plural videos; selecting a pair of 3D models from the plural 3D models based on similarity between a corresponding pair of video-related data units; and merging the pair of 3D models to obtain the 3D map.

7. 发明申请

US20230124348A1 RECOGNIZING SOCIAL GROUPS AND IDENTIFYING ORDER IN QUEUES FROM RGB IMAGES 有权
公开(公告)号：US20230124348A1
公开(公告)日：2023-04-20
申请号：US17492208
申请日：2021-10-01
申请人： INTERNATIONAL BUSINESS MACHINES CORPORATION
发明人： Jayakorn Vongkulbhisal , Tatsuya Ishihara
IPC分类号： G06N3/08 , G06K9/62 , G06K9/46 , G06K9/00
摘要： A method for training a neural network to cluster multiple people in an image into groups and estimate an activity of each of the groups is provided. The method extracts a feature of each of the multiple people in the image. The method inputs the feature to the neural network to estimate an affinity matrix A and the activity of each of the groups. The method calculates a first loss between the estimated affinity matrix and a ground truth affinity matrix for the image, and a second loss between the estimated activity of each of the groups and a ground truth activity of each of the groups for the image. The first loss is calculated using Maximum Spanning Trees. The method trains the neural network based on the first and second losses.

8. 发明申请

US20200166355A1 GENERATION OF ROUTE NETWORK DATA FOR MOVEMENT 审中-公开
公开(公告)号：US20200166355A1
公开(公告)日：2020-05-28
申请号：US16777004
申请日：2020-01-30
申请人： INTERNATIONAL BUSINESS MACHINES CORPORATION
发明人： Tatsuya Ishihara , Masayuki Murata , Daisuke Sato
IPC分类号： G01C21/34 , G06T17/00 , G01C21/20
摘要： A method for generating route network data for movement includes calculating a movable area in a place for a target type of movement using a space model of the place and an object model for the target type. The method also includes building network structure for route network data of the place using the movable area for the target type, in which the network structure includes a plurality of nodes and a plurality of links representing routes within the place. The method further includes updating the network structure by shifting a node to orient a link connected to the node toward any one of predetermined directions under a condition relating to an initial position of the node.

9. 发明授权

US08908999B2 Information processor, method, and program for document proofreading 有权
标题翻译：信息处理器，方法和文档校对程序
公开(公告)号：US08908999B2
公开(公告)日：2014-12-09
申请号：US13784897
申请日：2013-03-05
申请人： International Business Machines Corporation
发明人： Tatsuya Ishihara , Hironobu Takagi
IPC分类号： G06K7/10 , G06K9/00 , G06K9/03
CPC分类号： G06K9/00442 , G06K9/033
摘要： A method, apparatus and program for proofreading a document. The information processor includes a first storage unit for storing output information which includes information text and positional information obtained by performing Optical Character Recognition (OCR) on a source manuscript image. A second storage unit for storing a document file that is proofread by a user, wherein the document file is generated by reading the OCR-processed text according to the order of reading the output information A line movement detection unit for detected movement of a line which includes text in the document file based on the proofreading performed by the user on the document file. A merge unit for reflecting result of the proofreading of the document file in the output information.
摘要翻译：用于校对文件的方法，装置和程序。信息处理器包括：第一存储单元，用于存储输出信息，该输出信息包括通过在源原稿图像上执行光学字符识别（OCR）而获得的信息文本和位置信息。第二存储单元，用于存储由用户校对的文件文件，其中，通过根据读取输出信息的顺序读取OCR处理的文本来生成文档文件。A行移动检测单元，用于检测到的行的移动，基于用户对文档文件执行的校对，在文档文件中包含文本。合并单元，用于反映输出信息中文件文件的校对结果。

10. 发明申请

US20140095590A1 TASK PROCESSING METHOD, PROGRAM, AND SYSTEM 审中-公开
标题翻译：任务处理方法，程序和系统
公开(公告)号：US20140095590A1
公开(公告)日：2014-04-03
申请号：US14028722
申请日：2013-09-17
申请人： International Business Machines Corporation
发明人： Tatsuya Ishihara , Hironobu Takagi
IPC分类号： H04L29/08
CPC分类号： H04L67/10 , G06Q10/06 , G06Q10/101 , G06Q10/103 , H04L43/16 , H04L51/32
摘要： A contribution value necessary for achieving a target accuracy from a correct answer probability of each participant is calculated, a contribution value of the participant is added for an answer in accordance with the calculation, and it is set at a condition for determining completion of a task, that is, determining that a correct answer is obtained and no additional participant is necessary. The contribution value is calculated as the inverse of the number of participants at which the target accuracy is reached with a predetermined correct answer probability. The contribution value of the participant is added to the contribution value for the task in which that participant participates. At the time when the sum of the contribution values for a task exceeds one or when one option is certain to be a correct answer, the result having the largest sum of the contribution values is output.
摘要翻译：计算从每个参与者的正确答案概率获得目标准确度所需的贡献值，根据计算将参与者的贡献值加到答案中，并且将其设置为确定任务完成的条件，即确定获得正确的答案，并且不需要额外的参与者。贡献值被计算为具有预定正确答案概率的达到目标精度的参与者人数的倒数。参与者的贡献值被添加到参与者参与的任务的贡献值中。在任务的贡献值的总和超过一个或当一个选项确定为正确答案的时候，输出具有最大贡献值之和的结果。

你已经成功收藏专利！

检索式保存成功!

IPRDB

热门服务

关于我们

友情链接

联系方式