Country
Full text data for US,EP,CN
Type
Legal Validity
Legal Status
Filing Date
Publication Date
Inventor
Assignee
Click to expand
IPC(Section)
IPC(Class)
IPC(Subclass)
IPC(Group)
IPC(Subgroup)
LOC
Agent
Agency
Claims Number
Figures Number
Citation Number of Times
Assignee Number
No. Publication Number Title Publication/Patent Number Publication/Patent Number Publication Date Publication Date
Application Number Application Number Filing Date Filing Date
Inventor Inventor Assignee Assignee IPC IPC
1
US2021027174A1
RANDOMIZATION OF CASE-BASED KNOWLEDGE TO RULE-BASED KNOWLEDGE
Publication/Patent Number: US2021027174A1 Publication Date: 2021-01-28 Application Number: 16/523,026 Filing Date: 2019-07-26 Inventor: Rubin, Stuart H.   Assignee: The United States of America as represented by the Secretary of the Navy   IPC: G06N5/02 Abstract: Case-based information is randomized to rule-based information by accessing a case base to obtain a plurality of sets of variables representing case-based input/output constraints associated with corresponding cases. A matching is initiated, of a candidate case with one or more contexts of items included in a knowledge repository storing a plurality of cases and a plurality of rules that are organized in segments according to a plurality of domains and are comingled. At least one of the cases of the plurality of cases is generalized.
2
CN112434812A
一种基于对偶四元数的知识图谱链接预测方法及系统
Substantial Examination
Publication/Patent Number: CN112434812A Publication Date: 2021-03-02 Application Number: 202011346008.5 Filing Date: 2020-11-26 Inventor: 高黎明   卓汉逵   Assignee: 中山大学   IPC: G06N5/02 Abstract: 本发明公开了一种基于对偶四元数的知识图谱链接预测方法及系统,该方法包括:加载数据并对数据进行解析,得到知识图谱的三元组数据;根据知识图谱的三元组数据对预设的对偶四元数知识图谱模型进行训练和参数调整,得到训练完成的对偶四元数的知识图谱模型;根据训练完成的对偶四元数的知识图谱模型对待测三元组进行预测,得到预测结果。该系统包括:数据加载模块、模型训练模块和链接预测模块。通过使用本发明,能够有效有效利用对偶四元数的特性解决知识图谱中头实体和尾实体之间有多个关系的问题。本发明作为一种基于对偶四元数的知识图谱链接预测方法及系统,可广泛应用于知识图谱领域。
3
CN107784363B
数据处理方法、装置及系统
Grant
Publication/Patent Number: CN107784363B Publication Date: 2021-02-09 Application Number: 201610797641.3 Filing Date: 2016-08-31 Inventor: 刘冬   Assignee: 华为技术有限公司   IPC: G06N5/02 Abstract: 本发明公开了一种数据处理方法、装置及系统,属于计算机技术领域,该方法包括:获取待处理数据,待处理数据的一组数据参数为目标参数组;将目标参数组代入预设算法模型,确定目标参数组对应的目标算法,目标算法为:根据预设评估算法对目标参数组对应的至少一种算法进行评估,确定的最优评估值对应的算法;根据目标参数组对应的目标算法确定待处理数据的属性。本发明解决了数据处理的效果较差的问题,提高了数据处理的效果,本发明用于数据处理。
4
US2021065015A1
COMPUTERIZED PLATFORM FOR FACILITATING GROUP BASED DECISION MAKING
Publication/Patent Number: US2021065015A1 Publication Date: 2021-03-04 Application Number: 17/011,176 Filing Date: 2020-09-03 Inventor: Scott, Jordan Taylor   Assignee: IDK TONIGHT, LLC   IPC: G06N5/02 Abstract: A system and method that facilitates group based decisions. A system includes an interest discovery process including: outputting content items to clients for display; receiving responses from the clients, wherein each response is indicative of an interest in a displayed content item; and identifying matches among group members based on the responses; and a decision builder process that includes: receiving a decision outline from an initiator, wherein the decision outline specifies a decision point; outputting designated content items to the initiator capable of fulfilling the decision point, wherein the designated content items are based on matches made by the interest discovery process; receiving a subset of the designated content items from the initiator and outputting the subset to another group member; and receiving from the other group member a choice from the subset and determining whether a consensus is obtained by the group for the decision.
5
CN112990466A
一种冗余规则检测方法、装置以及服务器
Substantial Examination
Publication/Patent Number: CN112990466A Publication Date: 2021-06-18 Application Number: 202110352130.1 Filing Date: 2021-03-31 Inventor: 聂镭   黄海   聂颖   Assignee: 龙马智芯(珠海横琴)科技有限公司   IPC: G06N5/02 Abstract: 本申请适用于人工智能领域,尤其涉及一种冗余检测方法、装置以及服务器,该方法包括:获取规则列表,其中,规则列表包括至少一个规则文件;解析规则列表中的规则文件;根据预设的冗余规则文件计算每个规则文件的冗余程度。可见,本申请实施例中,通过对规则列表中的规则文件进行重复性检测和逻辑性检测生成预设的冗余规则文件,再根据冗余规则文件计算出规则列表中每个规则文件的冗余程度,不需要人工检测,到达自动检测冗余规则的效果。
6
EP3874420A1
LEARNING PROPERTY GRAPH REPRESENTATIONS EDGE-BY-EDGE
Publication/Patent Number: EP3874420A1 Publication Date: 2021-09-08 Application Number: 19801447.4 Filing Date: 2019-10-18 Inventor: Patra, Rhicheek   Hong, Sungpack   Kim, Jinha   Hilloulin, Damien   Bartolini, Davide   Chafi, Hassan   Assignee: Oracle International Corporation   IPC: G06N5/02
7
CN113168576A
逐边学习属性图表示
Public
Publication/Patent Number: CN113168576A Publication Date: 2021-07-23 Application Number: 201980080282.1 Filing Date: 2019-10-18 Inventor: R·帕特拉   S·洪   J·金   D·希洛林   D·巴托里尼   H·查菲   Assignee: 甲骨文国际公司   IPC: G06N5/02 Abstract: 描述了用于逐边学习属性图表示的技术。输入图包括多个顶点和多个边缘。多个顶点中的每个顶点与相应顶点的顶点属性相关联。生成顶点到属性的映射,该映射将每个顶点映射到多个顶点属性签名中的顶点属性签名。生成多个边缘单词。每个边缘单词对应于一个或多个边缘,每个边缘起始于具有多个顶点属性签名中的特定顶点属性签名的第一顶点,并且终止于具有多个顶点属性签名中的特定顶点属性签名的第二顶点。生成多个句子,每个句子包括沿着输入图中的多个路径中的路径连接的边缘单词。文档向量化模型用于生成表示输入图的机器学习向量。
8
EP3816875A1
INFORMATION PROCESSING DEVICE, INFORMATION PROCESSING METHOD AND PROGRAM
Publication/Patent Number: EP3816875A1 Publication Date: 2021-05-05 Application Number: 19826803.9 Filing Date: 2019-06-18 Inventor: Isozaki, Takashi   Assignee: Sony Corporation   IPC: G06N5/02 Abstract: Provided is a mechanism capable of easily grasping or analyzing the relation between three or more variables. An information processing apparatus (100) includes a control unit (130) that accepts the designation of a variable of interest among multiple variables including three or more variables with respect to data including values of the multiple variables, and outputs first information indicating the strength of the relation between the variable of interest and the combinations of explanatory variables including two or more explanatory variables among the multiple variables.
9
CN112308230A
一种资产管理全生命周期知识库的构建及应用方法
Substantial Examination
Publication/Patent Number: CN112308230A Publication Date: 2021-02-02 Application Number: 202011199856.8 Filing Date: 2020-10-30 Inventor: 尹春林   刘柱揆   杨政   赵现平   张林山   李萍   覃向宇   潘侃   朱华   苏蒙   Assignee: 云南电网有限责任公司电力科学研究院   IPC: G06N5/02 Abstract: 本发明涉及一种资产管理全生命周期知识库的构建及应用方法,包括以下步骤:获取资产管理相关数据;梳理资产管理相关数据设计企业资产全生命管理的业务模型;梳理资产管理相关数据设计资产数据元模型;根据企业资产全生命管理的业务模型和资产数据元模型进行知识抽取,并生成资产管理全生命周期涉及的所有知识,构建知识库;并基于故障预测算法,对设备的健康状况进行预测与评估。与现有技术相比,本方法创新性地采用知识图谱技术对资产全生命周期管理涉及的数据进行整合,并构建了设备故障预测模型,具有知识利用率高、模型预测精准的优点。
10
CN112381228A
一种基于业务的知识体系构建和应用方法
Substantial Examination
Publication/Patent Number: CN112381228A Publication Date: 2021-02-19 Application Number: 202011213073.0 Filing Date: 2020-11-03 Inventor: 左丽华   李义章   闫鹏   叶新苗   杨宇   李凯   刘芳   杨小龙   谭伦   Assignee: 中国直升机设计研究所   IPC: G06N5/02 Abstract: 本发明属于知识工程技术领域,涉及一种基于业务的知识体系构建和应用方法。本发明通过任务进行知识的组织,每个任务包含AOS十三要素等知识点。使得设计员在设计过程中,就可以将知识记录下来,并且通过任务的审签流程进行知识的确认,然后进行归档入库。当下次设计员进行同样、类似的任务设计时,这些知识就可以推送给设计员参考,并进行补充。任务关联的知识不断补充迭代,就形成了完善的基于业务的知识。
11
US10936955B1
Computationally and network bandwidth-efficient technique to determine network-accessible content changes based on computed models
Publication/Patent Number: US10936955B1 Publication Date: 2021-03-02 Application Number: 15/406,282 Filing Date: 2017-01-13 Inventor: Muralidharan, Pramod   Chen, Ray   Kane, Donald   Kannappan, Vignesh   Li, Hancao   Singh, Ajay Kant   Kreek, Robert Andrew   Bargreen, Richard   Chen, Rui   Collado, Michael Luis   Kelly, Kevin Donald   Li, Shen   Rajyaguru, Sameer Rajendra   Stepaniants, Serguei B.   Brahmadesam, Murali   Assignee: Amazon Technologies, Inc.   IPC: G06N5/02 Abstract: Technologies are disclosed for determining network-accessible content changes based on computed models and providing a long term forecast of user interaction at a network accessible site based upon a short term experiment at the site. A forecast model for a period of time is generated based upon historical data of user interactions at the site. An experiment is run for a short term at the site based upon a potential change at the site. Based upon data obtained during the experiment, scores are generated for a control group (no change) and a treatment group (potential change) and compared. If there are statistically significant differences between the control group and the treatment group scores, the long term forecast may be used to forecast what the long term impact of the experiment would be based upon the short term experiment.
12
EP2810223B1
METHOD OF UNCERTAIN INFORMATION MANAGEMENT FROM DIFFERENT HETEROGENEOUS INFORMATION SOURCES AND OF DECISION MAKING
Publication/Patent Number: EP2810223B1 Publication Date: 2021-03-24 Application Number: 13702075.6 Filing Date: 2013-02-04 Inventor: Laudy, Claire   Pichon, Frédéric   Fossier, Simon   Museux, Nicolas   Aligne, Florence   Assignee: THALES   IPC: G06N5/02
13
US10970635B1
Data processing for making predictive determinations
Publication/Patent Number: US10970635B1 Publication Date: 2021-04-06 Application Number: 15/299,324 Filing Date: 2016-10-20 Inventor: Perlin, Jonathan   Reiner, Deborah   Jirjis, Jim Najib   Jackson, Edmund Stephen   Gregg, William Michael   Doyle, Thomas Andrew   Paslick, Paul Martin   Assignee: C/HCA, Inc.   IPC: G06N5/02 Abstract: In some examples, structured and unstructured data is evaluated using one or more predictive models to determine whether a dependent user is at risk for a certain condition. In other examples, structured and unstructured data is evaluated using one or more predictive models to determine a contact plan for contacting dependent users regarding follow-up appointments related to release of the dependent user.
14
US10990881B1
Predictive analytics using sentence data model
Publication/Patent Number: US10990881B1 Publication Date: 2021-04-27 Application Number: 14/835,151 Filing Date: 2015-08-25 Inventor: Osmak, Ivan   Krüger, Thomas   Assignee: Progress Software Corporation   IPC: G06N5/02 Abstract: Systems and methods are described herein. In one embodiment, the method includes receiving a goal associated with a predicate-object pair; receiving utilization data including a plurality of predicate-object pairs including the predicate-object pair associated with the goal; determining a prediction model comprising a plurality of nodes that form a hierarchical structure including a root node and two or more leaf nodes and organized based on one or more of an information gain and a business gain, the two or more leaf nodes including a leaf node associated with the predicate-object pair of the goal; identifying nodes in the hierarchical structure that trace a path from the root node to the node associated with the goal; and causing a recommendation for at least partial completion of the goal to be presented to a user, the recommendation based on the one or more nodes that trace the path.
15
US2021125081A1
Dynamic Knowledge Transfer
Publication/Patent Number: US2021125081A1 Publication Date: 2021-04-29 Application Number: 16/785,234 Filing Date: 2020-02-07 Inventor: Nevins, Terrrence   Young, David   De, La Torre Doug   Assignee: Nevins, Terrrence   Young, David   de la Torre, Doug   IPC: G06N5/02 Abstract: Dynamic knowledge transfer may provide a system and method for creating modules, for example, crowd-sourced or employee-curated trainings, instruction manuals, or tutorials, comprising dynamic, as opposed to fixed, streams of information. Dynamic knowledge transfer may provide significant improvements to sharing or retention of information, benefitting desk-less workers or other users who will be enabled to make revisions or submit new content to keep the information up-to-date and relevant.
16
CN107092962B
一种分布式机器学习方法和平台
Grant Assignment
Publication/Patent Number: CN107092962B Publication Date: 2021-01-26 Application Number: 201610090044.7 Filing Date: 2016-02-17 Inventor: 毛仁歆   Assignee: 创新先进技术有限公司   IPC: G06N5/02 Abstract: 本申请提供一种分布式机器学习方法和平台,其中平台包括:逻辑构架模块,用于构建数据处理任务的执行逻辑,所述数据处理任务包括多个算法模块,每个所述算法模块包括:输入部分、算法部分、输出部分,且所述输入部分和输出部分具有相同的接口格式,以供所述多个算法模块之间根据所述接口格式进行串接;所述输入部分包括本算法模块与其他算法模块之间的依赖信息;算法执行模块,用于根据所述逻辑架构模块构建的执行逻辑,分别执行所述各个算法模块,且根据所述算法模块中的算法部分,调用资源层中的算法库进行运算。本申请提高了数据处理的效率。
17
CN107077640B
经由经验归属来分析、资格化和摄取非结构化数据源的系统和处理
Grant
Publication/Patent Number: CN107077640B Publication Date: 2021-07-06 Application Number: 201580059999.X Filing Date: 2015-09-03 Inventor: 安东尼·j·斯克里菲尼亚诺   耶姆·森伯哈尼奇   罗宾·弗莱·戴维斯   沃威克·马修斯   Assignee: 邓白氏公司   IPC: G06N5/02 Abstract: 本发明提供了一种方法,其包括:(a)从数据源接收数据;(b)根据规则对数据源进行归属,从而产生属性;(c)分析数据以识别数据中的混杂特性;(d)计算属性的定性度量,从而产生加权属性;(e)计算混杂特性的定性度量,从而产生加权混杂特性,(f)分析加权属性和加权混杂特性,以产生处置;(g)根据处置过滤数据,从而产生提取的数据;以及(h)将提取的数据发送至下游处理。本发明还提供了一种执行该方法的系统以及一种包含用于控制处理器执行该方法的指令的存储装置。
18
US2021248483A1
DATA CLASSIFICATION AND CONFORMATION SYSTEM AND METHOD
Publication/Patent Number: US2021248483A1 Publication Date: 2021-08-12 Application Number: 16/789,384 Filing Date: 2020-02-12 Inventor: Tomasik, Piotr   Sculli, Nathan   Assignee: Shark & Cooper LLC   IPC: G06N5/02 Abstract: A data classification and conformation system conforms data for safe use at one or more service provider devices. The data classification and conformation system automatically detects and classifies form data to properly conform the form data for use at a service provider device. Data is typically conformed by sanitization, validation, normalization, or various subsets thereof. One or more data routing mechanisms are provided to allow a service provider to integrate a data classification and conformation system with one or more service provider devices with minimal effort.
19
CN113255914A
一种结构化表示智能体目标实现过程的方法
Substantial Examination
Publication/Patent Number: CN113255914A Publication Date: 2021-08-13 Application Number: 202110401225.8 Filing Date: 2021-04-14 Inventor: 姚远   吴迪   夏江涵   王晓璇   胡佳仪   Assignee: 浙江工业大学   IPC: G06N5/02 Abstract: 本发明涉及一种结构化表示智能体目标实现过程的方法,构建基于目标计划图的多元组G,多元组中包括目标计划图中的节点的集合及节点间不同类型的有向边集合,基于任一智能体的目标生成目标计划图,选择计划并构建实例后实现智能体目标实现过程的结构化执行;提供了更加灵活的表示智能体目标实现过程的结构,并给出了该结构的具体使用方式,基于“有向无环图”,使用图结构表示各步骤间的偏序执行依赖关系,并以此取代传统目标计划树中的严格全序关系,允许没有顺序依赖关系的步骤调换执行顺序甚至并行执行,可以更客观地表示更准确的目标实现方式,在所有节点基于目标计划库生成的前提下可重复再现。
20
EP3759656A1
SYSTEM AND METHOD FOR A THING MACHINE TO PERFORM MODELS
Publication/Patent Number: EP3759656A1 Publication Date: 2021-01-06 Application Number: 19759947.5 Filing Date: 2019-02-27 Inventor: Northrup, Charles   Burns, John King   Assignee: Northrup, Charles   Burns, John, King   IPC: G06N5/02
Total 500 pages