CN106663221B - 由知识图谱偏置的数据分类 - Google Patents

由知识图谱偏置的数据分类 Download PDF

Info

Publication number
CN106663221B
CN106663221B CN201580044015.0A CN201580044015A CN106663221B CN 106663221 B CN106663221 B CN 106663221B CN 201580044015 A CN201580044015 A CN 201580044015A CN 106663221 B CN106663221 B CN 106663221B
Authority
CN
China
Prior art keywords
objects
knowledge graph
confidence value
confidence
processor
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
CN201580044015.0A
Other languages
English (en)
Chinese (zh)
Other versions
CN106663221A (zh
Inventor
S·马宗达
R·B·托瓦
S·S·塔拉迪
D·J·朱利安
V·S·R·安纳普莱蒂
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Qualcomm Inc
Original Assignee
Qualcomm Inc
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Qualcomm Inc filed Critical Qualcomm Inc
Publication of CN106663221A publication Critical patent/CN106663221A/zh
Application granted granted Critical
Publication of CN106663221B publication Critical patent/CN106663221B/zh
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/042—Knowledge-based neural networks; Logical representations of neural networks
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/0464—Convolutional networks [CNN, ConvNet]
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/047—Probabilistic or stochastic networks
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • G06N3/082—Learning methods modifying the architecture, e.g. adding, deleting or silencing nodes or connections
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • G06N3/09—Supervised learning
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N7/00—Computing arrangements based on specific mathematical models
    • G06N7/01—Probabilistic graphical models, e.g. probabilistic networks
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/049—Temporal neural networks, e.g. delay elements, oscillating neurons or pulsed inputs

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Computing Systems (AREA)
  • Software Systems (AREA)
  • Artificial Intelligence (AREA)
  • Mathematical Physics (AREA)
  • Data Mining & Analysis (AREA)
  • Evolutionary Computation (AREA)
  • General Engineering & Computer Science (AREA)
  • Biophysics (AREA)
  • Molecular Biology (AREA)
  • General Health & Medical Sciences (AREA)
  • Computational Linguistics (AREA)
  • Biomedical Technology (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Health & Medical Sciences (AREA)
  • Probability & Statistics with Applications (AREA)
  • Algebra (AREA)
  • Computational Mathematics (AREA)
  • Mathematical Analysis (AREA)
  • Mathematical Optimization (AREA)
  • Pure & Applied Mathematics (AREA)
  • Image Analysis (AREA)
CN201580044015.0A 2014-08-19 2015-07-28 由知识图谱偏置的数据分类 Active CN106663221B (zh)

Applications Claiming Priority (5)

Application Number Priority Date Filing Date Title
US201462039329P 2014-08-19 2014-08-19
US62/039,329 2014-08-19
US14/528,890 2014-10-30
US14/528,890 US10474949B2 (en) 2014-08-19 2014-10-30 Knowledge-graph biased classification for data
PCT/US2015/042488 WO2016028446A1 (en) 2014-08-19 2015-07-28 Knowledge-graph biased classification for data

Publications (2)

Publication Number Publication Date
CN106663221A CN106663221A (zh) 2017-05-10
CN106663221B true CN106663221B (zh) 2019-11-29

Family

ID=55348579

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201580044015.0A Active CN106663221B (zh) 2014-08-19 2015-07-28 由知识图谱偏置的数据分类

Country Status (9)

Country Link
US (1) US10474949B2 (enExample)
EP (2) EP3937087A1 (enExample)
JP (1) JP2017531240A (enExample)
KR (1) KR20170044102A (enExample)
CN (1) CN106663221B (enExample)
BR (1) BR112017003023A2 (enExample)
SG (1) SG11201610934SA (enExample)
TW (1) TW201626293A (enExample)
WO (1) WO2016028446A1 (enExample)

Families Citing this family (69)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US9953425B2 (en) 2014-07-30 2018-04-24 Adobe Systems Incorporated Learning image categorization using related attributes
US9536293B2 (en) * 2014-07-30 2017-01-03 Adobe Systems Incorporated Image assessment using deep convolutional neural networks
US20160203137A1 (en) * 2014-12-17 2016-07-14 InSnap, Inc. Imputing knowledge graph attributes to digital multimedia based on image and video metadata
US10078651B2 (en) * 2015-04-27 2018-09-18 Rovi Guides, Inc. Systems and methods for updating a knowledge graph through user input
US10726337B1 (en) * 2015-04-30 2020-07-28 Hrl Laboratories, Llc Method and apparatus for emulation of neuromorphic hardware including neurons and synapses connecting the neurons
US12361303B2 (en) 2016-05-13 2025-07-15 Numenta, Inc. Displacement processor for inferencing and learning based on sensorimotor input data
CN109478241B (zh) * 2016-05-13 2022-04-12 努门塔公司 执行推理的计算机实现的方法、存储介质及计算设备
US11100414B2 (en) 2016-05-13 2021-08-24 Numenta, Inc. Inferencing and learning based on sensorimotor input data
CN109564636B (zh) * 2016-05-31 2023-05-02 微软技术许可有限责任公司 使用一个神经网络来训练另一个神经网络
US11188823B2 (en) 2016-05-31 2021-11-30 Microsoft Technology Licensing, Llc Training a neural network using another neural network
US10380480B2 (en) 2016-05-31 2019-08-13 Microsoft Technology Licensing, Llc Changeover from one neural network to another neural network
US11194860B2 (en) * 2016-07-11 2021-12-07 Baidu Usa Llc Question generation systems and methods for automating diagnosis
US10949737B2 (en) 2016-07-13 2021-03-16 Samsung Electronics Co., Ltd. Method for neural network and apparatus performing same method
US10607142B2 (en) 2016-08-31 2020-03-31 International Business Machines Corporation Responding to user input based on confidence scores assigned to relationship entries in a knowledge graph
US10606849B2 (en) 2016-08-31 2020-03-31 International Business Machines Corporation Techniques for assigning confidence scores to relationship entries in a knowledge graph
US9767408B1 (en) 2016-09-16 2017-09-19 International Business Machines Corporation Multi-memristive synapse with clock-arbitrated weight update
US9785885B1 (en) 2016-09-16 2017-10-10 International Business Machines Corporation Arbitration schema based on a global clock
US11995539B2 (en) 2017-06-09 2024-05-28 Samsung Electronics Co., Ltd. Electronic apparatus and method for re-learning trained model
JP6886869B2 (ja) * 2017-06-09 2021-06-16 川崎重工業株式会社 動作予測システム及び動作予測方法
US10628699B2 (en) * 2017-06-13 2020-04-21 Samsung Electronics Co., Ltd. Event-based image feature extraction
US11334692B2 (en) 2017-06-29 2022-05-17 International Business Machines Corporation Extracting a knowledge graph from program source code
CN107526769A (zh) * 2017-07-10 2017-12-29 北京百度网讯科技有限公司 基于人工智能的照片处理方法及装置、设备及可读介质
US10540390B1 (en) 2017-08-07 2020-01-21 Amazon Technologies, Inc. Image-based item identification
US20190080245A1 (en) * 2017-09-08 2019-03-14 Niantic, Inc. Methods and Systems for Generation of a Knowledge Graph of an Object
US10725982B2 (en) 2017-11-20 2020-07-28 International Business Machines Corporation Knowledge graph node expiration
CN108171255A (zh) * 2017-11-22 2018-06-15 广东数相智能科技有限公司 基于图像识别的图片联想强度评分方法及装置
WO2019176420A1 (ja) * 2018-03-13 2019-09-19 ソニー株式会社 情報処理装置、移動装置、および方法、並びにプログラム
US11205114B2 (en) * 2018-03-19 2021-12-21 Intel Corporation Multi-layer neural networks using symmetric tensors
CN108536861B (zh) * 2018-04-19 2022-03-18 中国科学院重庆绿色智能技术研究院 一种医疗指南的交互式培训方法及其系统
US10776337B2 (en) 2018-07-06 2020-09-15 International Business Machines Corporation Multi-dimensional knowledge index and application thereof
CN109063021B (zh) * 2018-07-12 2021-10-15 浙江大学 一种能够编码关系语义多样性结构的知识图谱分布式表示方法
CN109189937B (zh) * 2018-08-22 2021-02-09 创新先进技术有限公司 一种特征关系推荐方法及装置、一种计算设备及存储介质
US10803182B2 (en) 2018-12-03 2020-10-13 Bank Of America Corporation Threat intelligence forest for distributed software libraries
US11354351B2 (en) * 2019-01-31 2022-06-07 Chooch Intelligence Technologies Co. Contextually generated perceptions
US11403328B2 (en) 2019-03-08 2022-08-02 International Business Machines Corporation Linking and processing different knowledge graphs
KR102079970B1 (ko) * 2019-04-30 2020-04-07 (주)에스투더블유랩 지식 그래프를 이용하여 사이버 시큐리티를 제공하는 방법, 장치 및 컴퓨터 프로그램
US11308365B2 (en) * 2019-06-13 2022-04-19 Expedia, Inc. Image classification system
CN110362689A (zh) * 2019-06-21 2019-10-22 深圳壹账通智能科技有限公司 一种风险评估方法、装置、存储介质和服务器
CN110363583B (zh) * 2019-07-02 2023-08-04 北京淇瑀信息科技有限公司 一种基于位置信息创建用户消费行为标签的方法、装置和电子设备
US11379733B2 (en) 2019-07-10 2022-07-05 International Business Machines Corporation Detecting and predicting object events from images
DE102019119087A1 (de) * 2019-07-15 2021-01-21 Dr. Ing. H.C. F. Porsche Aktiengesellschaft Komponentenbasierte verarbeitung von eingangsgrössen
CN110765317B (zh) * 2019-09-18 2024-03-01 上海合合信息科技股份有限公司 一种企业受益人运算系统及方法
EP3816856A1 (en) * 2019-10-31 2021-05-05 Siemens Aktiengesellschaft Method and system for anomaly detection using multimodal knowledge graph
KR102797377B1 (ko) * 2019-11-26 2025-04-21 한국전력공사 지식 그래프 생성 방법 및 이를 이용한 신재생발전 항목 추천 시스템 및 방법
CN111177400B (zh) * 2019-12-05 2023-07-25 国网能源研究院有限公司 基于知识图谱的设备、业务及数据的关联显示方法和装置
US11176137B2 (en) 2020-02-19 2021-11-16 Bank Of America Corporation Query processing platform for performing dynamic cluster compaction and expansion
CA3146741A1 (en) * 2020-02-24 2021-09-02 Freddy Lecue Method for semantic object detection with knowledge graph
CN111367961B (zh) * 2020-02-27 2023-03-28 西安交通大学 基于图卷积神经网络的时序数据事件预测方法、系统及其应用
CN111522967B (zh) * 2020-04-27 2023-09-15 北京百度网讯科技有限公司 知识图谱构建方法、装置、设备以及存储介质
CN111753330B (zh) * 2020-06-18 2023-08-29 百度在线网络技术（北京）有限公司 数据泄露主体的确定方法、装置、设备和可读存储介质
CN111743574B (zh) * 2020-07-12 2023-04-07 西北工业大学 乳腺癌超声影像高置信实体关系的知识图谱构建方法
CN116318989A (zh) * 2020-10-16 2023-06-23 维萨国际服务协会 用于用户网络活动异常检测的系统、方法和计算机程序产品
CN112417456B (zh) * 2020-11-16 2022-02-08 中国电子科技集团公司第三十研究所 一种基于大数据的结构化敏感数据还原检测的方法
CN112417457B (zh) * 2020-11-16 2022-02-08 中国电子科技集团公司第三十研究所 一种基于大数据的敏感数据还原检测的方法与系统
US11544508B2 (en) * 2020-11-23 2023-01-03 Nielsen Consumer Llc Methods, systems, articles of manufacture, and apparatus to recalibrate confidences for image classification
US11907269B2 (en) * 2020-12-01 2024-02-20 International Business Machines Corporation Detecting non-obvious relationships between entities from visual data sources
US12217190B2 (en) 2021-02-03 2025-02-04 Bank Of America Corporation Decision making using integrated machine learning models and knowledge graphs
CN113516156A (zh) * 2021-04-13 2021-10-19 浙江工业大学 一种基于多源信息融合的细粒度图像分类方法
CN113408611B (zh) * 2021-06-18 2022-05-10 电子科技大学 一种基于延迟机制的多层图像分类方法
US12086145B2 (en) 2021-07-13 2024-09-10 International Business Machines Corporation Mapping machine learning models to answer queries
CN114691896B (zh) * 2022-05-31 2022-09-13 浙江大学 一种知识图谱数据清洗方法及装置
CN115168603B (zh) * 2022-06-27 2023-04-07 天翼爱音乐文化科技有限公司 一种彩铃业务流程自动反馈应答方法、装置及存储介质
CN115543402B (zh) * 2022-11-21 2023-03-24 北京大学 一种基于代码提交的软件知识图谱增量更新方法
CN115860152B (zh) * 2023-02-20 2023-06-27 南京星耀智能科技有限公司 一种面向人物军事知识发现的跨模态联合学习方法
CN117332282B (zh) * 2023-11-29 2024-03-08 之江实验室 一种基于知识图谱的事件匹配的方法及装置
CN117708342B (zh) * 2023-11-29 2025-11-14 西安电子科技大学 面向机械产品三维数模设计数据的知识图谱构建方法
US20250206350A1 (en) * 2023-12-22 2025-06-26 Torc Robotics, Inc. Methods and systems for multiple object classification tracking in autonomous vehicles
CN118964682B (zh) * 2024-10-17 2024-12-20 太极计算机股份有限公司 基于元级化低代码平台的软件知识图谱智能构建方法
CN120507593B (zh) * 2025-04-07 2025-11-18 国家电网有限公司华东分部 基于知识图谱的智能电网故障推演方法、装置及电子设备

Citations (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101187985A (zh) * 2006-11-17 2008-05-28 沈阳东软软件股份有限公司 确定对象分类器分类边界的方法及装置

Family Cites Families (14)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US7181062B2 (en) * 2002-08-30 2007-02-20 Lockheed Martin Corporation Modular classification architecture for a pattern recognition application
EP1413973A1 (en) * 2002-10-22 2004-04-28 Thomson Licensing S.A. Method and apparatus for automatically calculating confidence values of data classification
US7848566B2 (en) 2004-10-22 2010-12-07 Carnegie Mellon University Object recognizer and detector for two-dimensional images using bayesian network based classifier
US8732025B2 (en) 2005-05-09 2014-05-20 Google Inc. System and method for enabling image recognition and searching of remote content on display
JP4640155B2 (ja) 2005-12-15 2011-03-02 ソニー株式会社 画像処理装置および方法、並びにプログラム
JP4755632B2 (ja) 2007-08-15 2011-08-24 ヤフー株式会社 アイテム認識装置及びアイテム認識方法
TWI354904B (en) 2008-01-25 2011-12-21 Yun Ken Method of classifying documents automatically, com
JP5800494B2 (ja) 2010-11-19 2015-10-28 キヤノン株式会社 特定領域選択装置、特定領域選択方法及びプログラム
WO2012124000A1 (ja) 2011-03-17 2012-09-20 日本電気株式会社 画像認識システム、画像認識方法および画像認識用プログラムが格納された非一時的なコンピュータ可読媒体
US9916538B2 (en) 2012-09-15 2018-03-13 Z Advanced Computing, Inc. Method and system for feature detection
CN103207879B (zh) 2012-01-17 2016-03-30 阿里巴巴集团控股有限公司 图像索引的生成方法及设备
CN103699663B (zh) * 2013-12-27 2017-02-08 中国科学院自动化研究所 一种基于大规模知识库的热点事件挖掘方法
CN103699687B (zh) * 2014-01-03 2017-02-01 复旦大学 一种基于枚举的网络实体爬取方法
US20150310862A1 (en) * 2014-04-24 2015-10-29 Microsoft Corporation Deep learning for semantic parsing including semantic utterance classification

Patent Citations (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101187985A (zh) * 2006-11-17 2008-05-28 沈阳东软软件股份有限公司 确定对象分类器分类边界的方法及装置

Also Published As

Publication number Publication date
KR20170044102A (ko) 2017-04-24
US20160055409A1 (en) 2016-02-25
EP3183695A1 (en) 2017-06-28
CN106663221A (zh) 2017-05-10
BR112017003023A2 (pt) 2017-12-12
WO2016028446A1 (en) 2016-02-25
EP3937087A1 (en) 2022-01-12
US10474949B2 (en) 2019-11-12
TW201626293A (zh) 2016-07-16
JP2017531240A (ja) 2017-10-19
SG11201610934SA (en) 2017-03-30

Similar Documents

Publication Publication Date Title
CN106663221B (zh) 由知识图谱偏置的数据分类
CN106104577B (zh) 照片管理
US10339447B2 (en) Configuring sparse neuronal networks
CN106575377B (zh) 共同特征上的分类器更新
CN105229675B (zh) 尖峰网络的高效硬件实现
CN107077637B (zh) 神经网络中的差分编码
US20150278680A1 (en) Training, recognition, and generation in a spiking deep belief network (dbn)
CN105580031B (zh) 在多维范围上对包括可分离子系统的系统的评估
US20150269485A1 (en) Cold neuron spike timing back-propagation
CN106687995A (zh) 分布式模型学习
US20150242745A1 (en) Event-based inference and learning for stochastic spiking bayesian networks
US20150278641A1 (en) Invariant object representation of images using spiking neural networks
CN106663222A (zh) 神经网络中的分解卷积操作
US20150317557A1 (en) Temporal spike encoding for temporal learning
US20150212861A1 (en) Value synchronization across neural processors
US10552734B2 (en) Dynamic spatial target selection
CN109992773A (zh) 基于多任务学习的词向量训练方法、系统、设备及介质
US20150278685A1 (en) Probabilistic representation of large sequences using spiking neural network
CN106104585A (zh) 经由阈下调制的模拟信号重构和识别
US20150213356A1 (en) Method for converting values into spikes
CN105659260B (zh) 动态地指派和检查突触延迟
HK1232650B (zh) 由知識圖譜偏置的數據分類
HK1232650A1 (en) Knowledge-graph biased classification for data
CN120705747A (zh) 一种异常时序检测方法以及相关设备

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
REG Reference to a national code

Ref country code: HK

Ref legal event code: DE

Ref document number: 1232650

Country of ref document: HK

GR01 Patent grant
GR01 Patent grant