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. 发明授权

US10572818B2 Horizontal decision tree learning from very high rate data streams with horizontal parallel conflict resolution 有权
公开(公告)号：US10572818B2
公开(公告)日：2020-02-25
申请号：US14727993
申请日：2015-06-02
申请人： International Business Machines Corporation
发明人： Wei Shan Dong , Peng Gao , Guo Qiang Hu , Chang Sheng Li , Xu Liang Li , Chun Yang Ma , Zhi Wang , Xin Zhang
IPC分类号： G06N20/00 , G06N5/04
摘要： A mechanism is provided in a data processing system for distributed tree learning. A source processing instance distributes data record instances to a plurality of model update processing items. The plurality of model update processing items determine candidate leaf splitting actions in a decision tree in parallel based on the data record instances. The plurality of model update processing items send the candidate leaf splitting actions to a plurality of conflict resolve processing items. The plurality of conflict resolve processing items identifies conflict leaf splitting actions. The plurality of conflict resolve processing items applies tree structure changes to the decision tree in the plurality of model update processing items.

2. 发明申请

US20160358095A1 Horizontal Decision Tree Learning from Very High Rate Data Streams 审中-公开
公开(公告)号：US20160358095A1
公开(公告)日：2016-12-08
申请号：US14727993
申请日：2015-06-02
申请人： International Business Machines Corporation
发明人： Wei Shan Dong , Peng Gao , Guo Qiang Hu , Chang Sheng Li , Xu Liang Li , Chun Yang Ma , Zhi Wang , Xin Zhang
IPC分类号： G06N99/00 , G06N5/04
CPC分类号： G06N20/00 , G06F8/35 , G06N5/045
摘要： A mechanism is provided in a data processing system for distributed tree learning. A source processing instance distributes data record instances to a plurality of model update processing items. The plurality of model update processing items determine candidate leaf splitting actions in a decision tree in parallel based on the data record instances. The plurality of model update processing items send the candidate leaf splitting actions to a plurality of conflict resolve processing items. The plurality of conflict resolve processing items identifies conflict leaf splitting actions. The plurality of conflict resolve processing items applies tree structure changes to the decision tree in the plurality of model update processing items.

3. 发明公开

US20240135102A1 WIREFRAME GENERATION 审中-公开
公开(公告)号：US20240135102A1
公开(公告)日：2024-04-25
申请号：US18048064
申请日：2022-10-19
申请人： INTERNATIONAL BUSINESS MACHINES CORPORATION
发明人： Zhaoqi Wu , Yi Fang Chen , Zhi Wang , Yi Qun Zhang , Yan Du , Li Na Yuan
IPC分类号： G06F40/295 , G06F40/216 , G06N3/04 , G06N3/08
CPC分类号： G06F40/295 , G06F40/216 , G06N3/0445 , G06N3/0454 , G06N3/08
摘要： A method of this disclosure may include performing a named entity recognition on text information related to requirements for a wireframe by a first artificial intelligence (AI) model, so as to extract entities and relations of the entities from the text information. The method may further comprise inputting the extracted entities and relations to a second AI model to generate the wireframe, wherein the second AI model is trained so that a difference between resultant relations of the entities of the generated wireframe and the extracted relations of the entities from the first AI model is decreased.

4. 发明公开

US20230186190A1 TICKET EMBEDDING BASED ON MULTI-DIMENSIONAL IT DATA 审中-公开
公开(公告)号：US20230186190A1
公开(公告)日：2023-06-15
申请号：US17548768
申请日：2021-12-13
申请人： International Business Machines Corporation
发明人： Zhi Wang , Zhao Qi Wu , Li Na Yuan , Qian Ke Fang , Li Long Chen
IPC分类号： G06Q10/06 , G06N3/08 , G06N3/04
CPC分类号： G06Q10/06311 , G06N3/08 , G06N3/04
摘要： An approach is provided that trains an artificial intelligence (AI) system, such as a neural network, to process IT ticket data. The approach receives IT tickets from various ticket sources. Ticket vectors corresponding to each of the IT tickets are computed. An analysis is performed using the ticket vectors and a node vector that corresponds to a network topology. The analysis is performed using a corpus of IT ticket data. An IT ticket model used by the AI system is trained based on the analysis. Responses are provided to requestors of the AI system using the trained IT ticket model.

5. 发明申请

US20170061327A1 SCALABLE STREAMING DECISION TREE LEARNING 审中-公开
标题翻译：可定量流动决策树的学习
公开(公告)号：US20170061327A1
公开(公告)日：2017-03-02
申请号：US14953457
申请日：2015-11-30
申请人： International Business Machines Corporation
发明人： Wei Shan Dong , Peng Gao , Guo Qiang Hu , Chang Sheng LI , Xu Liang Li , Chun Yang Ma , Zhi Wang , Xin Zhang
IPC分类号： G06N99/00 , G06N5/02
CPC分类号： G06N5/02 , G06N5/025
摘要： In one embodiment, a computer-implemented method includes receiving training data including a plurality of records, each record having a plurality of attributes. The training data is horizontally parallelized across two or more processing elements. This horizontal parallelizing includes dividing the training data into two or more subsets of records; assigning each subset of records to a corresponding processing element of the two or more processing elements; transmitting each subset of records to its assigned processing element; and sorting, at the two or more processing elements, the two or more subsets of records to two or more candidate leaves of a decision tree. The output from horizontally parallelizing is converted into input for vertically parallelizing the training data. The training data is vertically parallelized across the two or more processing elements. The decision tree is grown based at least in part on the horizontally parallelizing, the converting, and the vertically parallelizing.
摘要翻译：在一个实施例中，计算机实现的方法包括接收包括多个记录的训练数据，每个记录具有多个属性。训练数据在两个或多个处理元件之间水平并行化。这种水平并行化包括将训练数据分成两个或更多个记录子集; 将每个记录子集分配给所述两个或多个处理元件的相应处理元件; 将每个记录子集传送到其分配的处理元件; 并且在所述两个或更多个处理元素处将所述两个或多个记录子集分类到决策树的两个或更多个候选叶。水平并行化的输出被转换为用于垂直并行化训练数据的输入。训练数据跨越两个或多个处理元件垂直并行化。决策树至少部分地基于水平并行化，转换和垂直并行化生长。

6. 发明申请

US20170061318A1 SCALABLE STREAMING DECISION TREE LEARNING 审中-公开
公开(公告)号：US20170061318A1
公开(公告)日：2017-03-02
申请号：US14833397
申请日：2015-08-24
申请人： International Business Machines Corporation
发明人： Wei Shan Dong , Peng Gao , Guo Qiang Hu , Cheng Sheng LI , Xu Liang Li , Chun Yang Ma , Zhi Wang , Xin Zhang
IPC分类号： G06N99/00
摘要： In one embodiment, a computer-implemented method includes receiving training data including a plurality of records, each record having a plurality of attributes. The training data is horizontally parallelized across two or more processing elements. This horizontal parallelizing includes dividing the training data into two or more subsets of records; assigning each subset of records to a corresponding processing element of the two or more processing elements; transmitting each subset of records to its assigned processing element; and sorting, at the two or more processing elements, the two or more subsets of records to two or more candidate leaves of a decision tree. The output from horizontally parallelizing is converted into input for vertically parallelizing the training data. The training data is vertically parallelized across the two or more processing elements. The decision tree is grown based at least in part on the horizontally parallelizing, the converting, and the vertically parallelizing.

7. 发明授权

US10565517B2 Horizontal decision tree learning from very high rate data streams with horizontal parallel conflict resolution 有权
公开(公告)号：US10565517B2
公开(公告)日：2020-02-18
申请号：US14744708
申请日：2015-06-19
申请人： International Business Machines Corporation
发明人： Wei Shan Dong , Peng Gao , Guo Qiang Hu , Chang Sheng Li , Xu Liang Li , Chun Yang Ma , Zhi Wang , Xin Zhang
IPC分类号： G06N20/00 , G06N5/04
摘要： A mechanism is provided in a data processing system for distributed tree learning. A source processing instance distributes data record instances to a plurality of model update processing items. The plurality of model update processing items determine candidate leaf splitting actions in a decision tree in parallel based on the data record instances. The plurality of model update processing items send the candidate leaf splitting actions to a plurality of conflict resolve processing items. The plurality of conflict resolve processing items identifies conflict leaf splitting actions. The plurality of conflict resolve processing items applies tree structure changes to the decision tree in the plurality of model update processing items.

8. 发明公开

US20240232533A9 WIREFRAME GENERATION 审中-公开
公开(公告)号：US20240232533A9
公开(公告)日：2024-07-11
申请号：US18048064
申请日：2022-10-20
申请人： INTERNATIONAL BUSINESS MACHINES CORPORATION
发明人： Zhaoqi Wu , Yi Fang Chen , Zhi Wang , Yi Qun Zhang , Yan Du , Li Na Yuan
IPC分类号： G06F40/295 , G06F40/216 , G06N3/04 , G06N3/08
CPC分类号： G06F40/295 , G06F40/216 , G06N3/0445 , G06N3/0454 , G06N3/08
摘要： A method of this disclosure may include performing a named entity recognition on text information related to requirements for a wireframe by a first artificial intelligence (AI) model, so as to extract entities and relations of the entities from the text information. The method may further comprise inputting the extracted entities and relations to a second AI model to generate the wireframe, wherein the second AI model is trained so that a difference between resultant relations of the entities of the generated wireframe and the extracted relations of the entities from the first AI model is decreased.

9. 发明授权

US10671924B2 Scalable streaming decision tree learning 审中-公开
公开(公告)号：US10671924B2
公开(公告)日：2020-06-02
申请号：US14833397
申请日：2015-08-24
申请人： International Business Machines Corporation
发明人： Wei Shan Dong , Peng Gao , Guo Qiang Hu , Chang Sheng Li , Xu Liang Li , Chun Yang Ma , Zhi Wang , Xin Zhang
IPC分类号： G06N5/02
摘要： In one embodiment, a computer-implemented method includes receiving training data including a plurality of records, each record having a plurality of attributes. The training data is horizontally parallelized across two or more processing elements. This horizontal parallelizing includes dividing the training data into two or more subsets of records; assigning each subset of records to a corresponding processing element of the two or more processing elements; transmitting each subset of records to its assigned processing element; and sorting, at the two or more processing elements, the two or more subsets of records to two or more candidate leaves of a decision tree. The output from horizontally parallelizing is converted into input for vertically parallelizing the training data. The training data is vertically parallelized across the two or more processing elements. The decision tree is grown based at least in part on the horizontally parallelizing, the converting, and the vertically parallelizing.

10. 发明授权

US10664756B2 Scalable streaming decision tree learning 有权
公开(公告)号：US10664756B2
公开(公告)日：2020-05-26
申请号：US14953457
申请日：2015-11-30
申请人： International Business Machines Corporation
发明人： Wei Shan Dong , Peng Gao , Guo Qiang Hu , Chang Sheng Li , Xu Liang Li , Chun Yang Ma , Zhi Wang , Xin Zhang
IPC分类号： G06N5/02
摘要： In one embodiment, a computer-implemented method includes receiving training data including a plurality of records, each record having a plurality of attributes. The training data is horizontally parallelized across two or more processing elements. This horizontal parallelizing includes dividing the training data into two or more subsets of records; assigning each subset of records to a corresponding processing element of the two or more processing elements; transmitting each subset of records to its assigned processing element; and sorting, at the two or more processing elements, the two or more subsets of records to two or more candidate leaves of a decision tree. The output from horizontally parallelizing is converted into input for vertically parallelizing the training data. The training data is vertically parallelized across the two or more processing elements. The decision tree is grown based at least in part on the horizontally parallelizing, the converting, and the vertically parallelizing.

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