-
公开(公告)号：US10803107B2
公开(公告)日：2020-10-13
申请号：US15054327
申请日：2016-02-26
申请人： Primal Fusion Inc.
摘要： Computer-implemented systems and methods for synthesis of concept definitions and concept relationships from a domain of data, utilizing different semantic processing protocols such as formal concept analysis and faceted classification synthesis from existing domain concepts that have a confidence gradient built into them. A cognitive or an input agent provides an input of an active concept which is matched against existing domain concepts. The resultant pool of relevant domain concepts is then used to derive virtual concept definitions using a semantic processing protocol. The derivation is then overlaid with a concept of relative proximity of an attribute from another within an attribute set. An additional layer of coherence is given by the relative proximity measure. The end result is a pool of related virtual concept definitions in a tree structure.
-
12.发明授权Methods and apparatus for providing information of interest to one or more users 有权用于向一个或多个用户提供感兴趣的信息的方法和装置公开(公告)号：US09378203B2
公开(公告)日：2016-06-28
申请号：US13340792
申请日：2011-12-30
CPC分类号： G06N5/02 , G06F17/2785 , G06F17/30528 , G06F17/30663 , G06F17/30684 , G06F17/30734 , G06N5/022 , G06Q30/0241 , G06Q30/0269
摘要： Methods and system for providing information selected from a large set of digital content to a user. Techniques include receiving user context information associated with the user and identifying or generating a first concept in a semantic network, the first concept representing at least a portion of the user context information. The method further comprises obtaining at least one concept, including a second concept, semantically relevant to the first concept at least in part, by synthesizing the second concept based on the first concept and at least one other concept in the semantic network; and providing information to the user, wherein the information is selected by using the first concept and the at least one obtained concept semantically relevant to the first concept, wherein the first concept in a semantic network is represented by a data structure storing any data associated with a node in the semantic network.
摘要翻译： 用于向用户提供从大量数字内容中选择的信息的方法和系统。 技术包括接收与用户相关联的用户上下文信息，并在语义网络中识别或生成第一概念，第一概念表示用户上下文信息的至少一部分。 所述方法还包括至少部分地通过基于所述第一概念和所述语义网络中的至少一个其他概念来合成所述第二概念来获得包括第二概念的至少一个概念，所述第二概念与所述第一概念语义相关; 以及向用户提供信息，其中通过使用与第一概念语义相关的第一概念和至少一个获得的概念来选择信息，其中语义网络中的第一概念由存储与 语义网络中的一个节点。
-
公开(公告)号：US20160171562A1
公开(公告)日：2016-06-16
申请号：US15040842
申请日：2016-02-10
申请人： Primal Fusion Inc.
发明人： Peter Joseph Sweeney
CPC分类号： G06Q30/0276 , G06F17/3089 , G06F17/30914 , G06Q30/02 , H04L51/10 , H04L51/34
摘要： The present invention provides a computer network implementable integration of promoted information with non-promoted content before a consumer interaction with the network, such that when the consumer interacts with the network, a consumer information interacts with this integrated content and delivers a message to the consumer such that the consumer visualizes this message as part of consumer experience without distracting from the network interaction task at hand. The integration is facilitated by semantic analysis and synthesis to naturally position the promoted content as close to the consumer interaction tasks as possible at that instant. This approach displaces the current practise of matching message to media placement while further enabling a promoter to evaluate and respond to feedback data depicting the efficacy of the sponsor message. The network in question is any computer network such as the Internet or intranet.
摘要翻译： 本发明提供一种计算机网络，在消费者与网络进行交互之前，将促进信息与非提升内容可实现集成，使得当消费者与网络交互时，消费者信息与该综合内容交互并向消费者传递消息 使得消费者将该消息视为消费者体验的一部分，而不会分散在手的网络交互任务。 通过语义分析和综合来促进整合，以便自然地将宣传内容定位为尽可能接近消费者互动任务。 这种方法取代了将消息与媒体放置匹配的当前实践，同时进一步使启动者能够评估和响应描述赞助商消息的功效的反馈数据。 所涉及的网络是任何计算机网络，例如因特网或内联网。
-
公开(公告)号：US20160086085A1
公开(公告)日：2016-03-24
申请号：US14961819
申请日：2015-12-07
申请人： Primal Fusion Inc.
IPC分类号： G06N5/02
CPC分类号： G06N5/02 , G06F17/30684 , G06N7/005
摘要： Techniques for customizing knowledge representation systems including identifying, based on a plurality of concepts in a knowledge representation (KR), a group of one or more concepts relevant to user context information, and providing the identified group of one more concepts to a user. The KR may include a combination of modules. The modules may include a kernel and a customized module customized for the user. The kernel may accessible via a second KR.
-
公开(公告)号：US09235806B2
公开(公告)日：2016-01-12
申请号：US13844009
申请日：2013-03-15
CPC分类号： G06N5/02 , G06F17/30684 , G06N7/005
摘要： Techniques for customizing knowledge representation systems including identifying, based on a plurality of concepts in a knowledge representation (KR), a group of one or more concepts relevant to user context information, and providing the identified group of one more concepts to a user. The KR may include a combination of modules. The modules may include a kernel and a customized module customized for the user. The kernel may accessible via a second KR.
摘要翻译： 用于定制知识表示系统的技术，包括基于知识表示（KR）中的多个概念来识别与用户上下文信息相关的一个或多个概念的组，以及将识别出的一个概念组提供给用户。 KR可以包括模块的组合。 模块可以包括为用户定制的内核和定制模块。 内核可以通过第二个KR访问。
-
公开(公告)号：US09177248B2
公开(公告)日：2015-11-03
申请号：US13609223
申请日：2012-09-10
CPC分类号： G06N5/02 , G06F17/30684 , G06N5/00 , G06N7/005
摘要： Techniques for analyzing and synthesizing complex knowledge representations (KRs) may utilize an atomic knowledge representation model including an elemental data structure and knowledge processing rules that are machine-readable. The elemental data structure may include a universal kernel and customized modules, which may represent knowledge that is generally applicable to a population and knowledge that is specifically applicable to individual data consumers, respectively. A method of constructing an elemental data structure may include analyzing first information to identify a first elemental component associated with a data consumer, and adding the first elemental component to a customized module corresponding to the data consumer. The method may also include analyzing second information to identify a second elemental component associated with a population, and adding the second elemental component to the universal kernel.
摘要翻译： 用于分析和合成复杂知识表示（KR）的技术可以利用包括机器可读的元素数据结构和知识处理规则的原子知识表示模型。 元素数据结构可以包括通用内核和定制模块，其可以分别表示通常适用于群体的知识和专门适用于个人数据消费者的知识。 构成元数据结构的方法可以包括分析第一信息以识别与数据消费者相关联的第一元素组件，以及将第一元素组件添加到与数据消费者对应的定制模块中。 该方法还可以包括分析第二信息以识别与群体相关联的第二元素分量，以及将第二元素分量添加到通用内核。
-
17.发明授权Systems and methods for analyzing and synthesizing complex knowledge representations 有权用于分析和综合复杂知识表示的系统和方法公开(公告)号：US09104779B2
公开(公告)日：2015-08-11
申请号：US13165423
申请日：2011-06-21
CPC分类号： G06N5/02 , G06F17/30914
摘要： Techniques for analyzing and synthesizing complex knowledge representations (KRs) may utilize an atomic knowledge representation model including both an elemental data structure and knowledge processing rules stored as machine-readable data and/or programming instructions. One or more of the knowledge processing rules may be applied to analyze an input complex KR to deconstruct its complex concepts and/or concept relationships to elemental concepts and/or concept relationships to be included in the elemental data structure. One or more of the knowledge processing rules may be applied to synthesize an output complex KR from the stored elemental data structure in accordance with an input context. Multiple input complex KRs of various types may be analyzed and deconstructed to populate the elemental data structure, and input complex KRs may be transformed through the elemental data structure to output complex KRs of different types, providing semantic interoperability to KRs of different types and/or KR models.
摘要翻译： 用于分析和合成复杂知识表示（KR）的技术可以利用原子知识表示模型，其包括存储为机器可读数据和/或编程指令的元数据结构和知识处理规则。 可以应用知识处理规则中的一个或多个来分析输入复合体KR以将其复杂概念和/或概念关系解构为要包括在基本数据结构中的元素概念和/或概念关系。 一个或多个知识处理规则可以被应用以根据输入上下文从存储的基本数据结构合成输出复合体KR。 可以对各种类型的多输入复合体KR进行分析和解构以填充元素数据结构，并且可以通过元素数据结构来转换输入复数KR，以输出不同类型的复合KR，为不同类型和/或不同类型的KR提供语义互操作性 KR型号。
-
18.发明申请SYSTEMS AND METHODS FOR SEMANTIC CONCEPT DEFINITION AND SEMANTIC CONCEPT RELATIONSHIP SYNTHESIS UTILIZING EXISTING DOMAIN DEFINITIONS 有权用于语义概念定义和语义概念的系统和方法利用现有的域定义进行合成公开(公告)号：US20150100540A1
公开(公告)日：2015-04-09
申请号：US14571902
申请日：2014-12-16
申请人： Primal Fusion Inc.
IPC分类号： G06N5/02
CPC分类号： G06F17/30731 , G06N5/022
摘要： Computer-implemented systems and methods for synthesis of concept definitions and concept relationships from a domain of data, utilizing different semantic processing protocols such as formal concept analysis and faceted classification synthesis from existing domain concepts that have a confidence gradient built into them. A cognitive or an input agent provides an input of an active concept which is matched against existing domain concepts. The resultant pool of relevant domain concepts is then used to derive virtual concept definitions using a semantic processing protocol. The derivation is then overlaid with a concept of relative proximity of an attribute from another within an attribute set. An additional layer of coherence is given by the relative proximity measure. The end result is a pool of related virtual concept definitions in a tree structure.
摘要翻译： 用于从数据领域合成概念定义和概念关系的计算机实现的系统和方法，利用不同的语义处理协议，如形式化概念分析，以及内置置信度梯度的现有领域概念的分面分类综合。 认知或输入代理提供与现有领域概念相匹配的活动概念的输入。 然后使用相关领域概念的合成池来使用语义处理协议来导出虚拟概念定义。 然后用属性集中的另一个属性的相对接近度的概念覆盖推导。 通过相对邻近度量给出附加的一致性层。 最终结果是树结构中相关的虚拟概念定义池。
-
19.发明授权公开(公告)号：US08943016B2
公开(公告)日：2015-01-27
申请号：US13919934
申请日：2013-06-17
申请人： Primal Fusion Inc.
CPC分类号： G06F17/30731 , G06N5/022
摘要： Computer-implemented systems and methods for synthesis of concept definitions and concept relationships from a domain of data, utilizing different semantic processing protocols such as formal concept analysis and faceted classification synthesis from existing domain concepts that have a confidence gradient built into them. A cognitive of an input agent provides an input of an active concept which is matched against existing domain concepts. The resultant pool of relevant domain concepts is then used to derive virtual concept definitions using a semantic processing protocol. The derivation is then overlaid with a concept of relative proximity of an attribute from another within an attribute set. An additional layer of coherence is given by the relative proximity measure. The end result is a pool of related virtual concept definitions in a tree structure.
摘要翻译： 用于从数据领域合成概念定义和概念关系的计算机实现的系统和方法，利用不同的语义处理协议，如形式化概念分析，以及内置置信度梯度的现有领域概念的分面分类综合。 认知或输入代理提供与现有领域概念相匹配的活动概念的输入。 然后使用相关领域概念的合成池来使用语义处理协议来导出虚拟概念定义。 然后用属性集中的另一个属性的相对接近度的概念覆盖推导。 通过相对邻近度量给出附加的一致性层。 最终结果是树结构中相关的虚拟概念定义池。
-
20.发明授权Method, system, and computer program for user-driven dynamic generation of semantic networks and media synthesis 有权方法，系统和计算机程序，用于用户动态生成语义网络和媒体综合公开(公告)号：US08676722B2
公开(公告)日：2014-03-18
申请号：US12671846
申请日：2009-05-01
IPC分类号： G06F15/18
CPC分类号： G06N5/02 , G06F17/2785 , G06F17/30528 , G06F17/30663 , G06F17/30684 , G06F17/30734 , G06N5/022 , G06Q30/0241 , G06Q30/0269
摘要： This invention relates generally to classification systems. More particularly this invention relates to a system, method, and computer program to dynamically generate a domain of information synthesized by a classification system or semantic network. The invention discloses a method, system, and computer program providing a means by which an information store comprised of knowledge representations, such as a web site comprised of a plurality of web pages or a database comprised of a plurality of data instances, may be optimally organized and accessed based on relational links between ideas defined by one or more thoughts identified by an agent and one or more ideas embodied by the data instances. Such means is hereinafter referred to as a “thought network”.
摘要翻译： 本发明一般涉及分类系统。 更具体地说，本发明涉及动态生成由分类系统或语义网络合成的信息领域的系统，方法和计算机程序。 本发明公开了一种方法，系统和计算机程序，其提供了一种包括知识表示的信息存储（诸如包括多个网页的网站或由多个数据实例组成的数据库）的装置可以是最佳的 基于由代理识别的一个或多个想法定义的想法与由数据实例体现的一个或多个想法之间的关系链接来组织和访问。 以下将这种手段称为“思想网络”。
-
-
-
-
-
-
-
-
-
搜索结果
85 条记录 (耗时 0.048 秒)
