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

US10108709B1 Systems and methods for queryable graph representations of videos 有权
公开(公告)号：US10108709B1
公开(公告)日：2018-10-23
申请号：US15829055
申请日：2017-12-01
申请人： Digital Reasoning Systems, Inc.
发明人： John Frey , James Whitaker , Matthew Russell
IPC分类号： G06K9/00 , G06F17/30 , G10L17/00 , G10L15/00 , G10L15/20 , G10L15/26 , G06K9/46 , G10L25/30 , G06K9/62
摘要： In one aspect, the present disclosure relates to a method which, in one embodiment, includes: receiving video data for a first video and deconstructing the video data of the first video into a plurality of context windows; performing, on each context window of the plurality of context windows that includes an image frame, a video analytic function on the image frame to identify one or more characteristics of the context window that are associated with image-related content of the first video; performing, on each context window of the plurality of context windows that includes an audio frame, a video analytic function on the audio frame to identify one or more characteristics of the context window that are associated with audio-related content of the first video; generating, for each of the plurality of context windows, a respective local atomic unit comprising attributes derived from the identified one or more characteristics of the respective context window, to form a plurality of local atomic units; and generating a local graph representation of the first video, comprising a plurality of nodes corresponding to the plurality of local atomic units.

2. 发明授权

US10339440B2 Systems and methods for neural language modeling 有权
公开(公告)号：US10339440B2
公开(公告)日：2019-07-02
申请号：US15047532
申请日：2016-02-18
申请人： Digital Reasoning Systems, Inc.
发明人： Andrew Trask , David Gilmore , Matthew Russell
IPC分类号： G06N3/02 , G06N3/04 , G06N3/08 , G06F17/27
摘要： In some aspects, the present disclosure relates to neural language modeling. In one embodiment, a computer-implemented neural network includes a plurality of neural nodes, where each of the neural nodes has a plurality of input weights corresponding to a vector of real numbers. The neural network also includes an input neural node corresponding to a linguistic unit selected from an ordered list of a plurality of linguistic units, and an embedding layer with a plurality of embedding node partitions. Each embedding node partition includes one or more neural nodes. Each of the embedding node partitions corresponds to a position in the ordered list relative to a focus term, is configured to receive an input from an input node, and is configured to generate an output. The neural network also includes a classifier layer with a plurality of neural nodes, each configured to receive the embedding outputs from the embedding layer, and configured to generate an output corresponding to a probability that a particular linguistic unit is the focus term.

3. 发明授权

US10049162B2 Knowledge discovery agent system 有权
公开(公告)号：US10049162B2
公开(公告)日：2018-08-14
申请号：US14935183
申请日：2015-11-06
申请人： DIGITAL REASONING SYSTEMS, INC.
发明人： Timothy W. Estes
IPC分类号： G06F15/18 , G06F17/30 , H04N21/466 , H04N21/25 , H04N21/482 , G06N3/08 , G06N5/02 , G06N99/00
摘要： A system and method for processing information in unstructured or structured form, comprising a computer running in a distributed network with one or more data agents. Associations of natural language artifacts may be learned from natural language artifacts in unstructured data sources, and semantic and syntactic relationships may be learned in structured data sources, using grouping based on a criteria of shared features that are dynamically determined without the use of a priori classifications, by employing conditional probability constraints.

4. 发明授权

US09311301B1 Systems and methods for large scale global entity resolution 有权
标题翻译：大规模全球实体解决方案的系统和方法
公开(公告)号：US09311301B1
公开(公告)日：2016-04-12
申请号：US14750936
申请日：2015-06-25
申请人： Digital Reasoning Systems, Inc.
发明人： Vishnuvardhan Balluru , Kenneth Graham , Naomi Hilliard
IPC分类号： G06F17/28 , G06N99/00 , G06N7/00 , G06F17/27
CPC分类号： G06F17/278 , G06F17/271 , G06F17/2785 , G06N5/022 , G06N7/005 , G06N99/005
摘要： Systems and methods for coreference resolution are disclosed. In one embodiment, a method includes locating, for each of a selected plurality of chains of coreferent mentions, a particular context-based name from the respective chain, wherein the coreferent mentions correspond to entities and the context-based name is a longest name in the respective chain, a last name in the respective chain, or a most frequently occurring name in the respective chain. The method also includes determining an entity category for each respective one of the plurality of chains and determining one or more entity attributes from structured data and unstructured data. The method further includes, based on the located particular context-based name, the entity category, and the one or more attributes, assigning high-probability coreferent chains to high-confidence buckets, such as to produce a Zipfian-like distribution having a head region and a tail region.
摘要翻译：披露了解决方案的系统和方法。在一个实施例中，一种方法包括针对不同提及的所选择的多个链中的每一个针对来自相应链的特定基于上下文的名称定位，其中所述不同提及对应于实体，并且基于上下文的名称是最长名称相应链，相应链中的姓氏，或相应链中最常出现的名称。所述方法还包括为所述多个链中的每一个链确定实体类别，并从结构化数据和非结构化数据确定一个或多个实体属性。该方法还包括基于定位的特定的基于上下文的名称，实体类别和一个或多个属性，将高概率的不同链分配给高置信度桶，以产生具有头的Zipfian样分布区域和尾部区域。

5. 发明授权

US08457950B1 System and method for coreference resolution 有权
标题翻译：共同解析的系统和方法
公开(公告)号：US08457950B1
公开(公告)日：2013-06-04
申请号：US13666722
申请日：2012-11-01
申请人： Digital Reasoning Systems, Inc.
发明人： James Johnson Gardner , Vishnuvardhan Balluru , Phillip Daniel Michalak , Kenneth Loran Graham , John Wagster
IPC分类号： G10L15/00
CPC分类号： G10L15/1815
摘要： According to one aspect, a method for coreference resolution is provided. In one embodiment, the method includes receiving a segment of text that includes mentions corresponding to entities. A first feature vector is generated based on one or more features associated with a first mention, and a second feature vector is generated based on based on one or more features associated with a second mention. A measure of similarity between the first feature vector and second feature vector is computed and, based on the computed measure of similarity, it is determined if the first mention and the second mention both correspond to the same entity.
摘要翻译：根据一个方面，提供了一种用于融合解析的方法。在一个实施例中，该方法包括接收包括对应于实体的提及的文本段。基于与第一提及相关联的一个或多个特征生成第一特征向量，并且基于与第二提及相关联的一个或多个特征来生成第二特征向量。计算第一特征向量和第二特征向量之间的相似性度量，并且基于所计算的相似度测量，确定第一提及和第二提及是否对应于相同实体。

6. 发明授权

US11640494B1 Systems and methods for construction, maintenance, and improvement of knowledge representations 有权
公开(公告)号：US11640494B1
公开(公告)日：2023-05-02
申请号：US17135218
申请日：2020-12-28
申请人： Digital Reasoning Systems, Inc.
发明人： Timothy Wayne Estes , James Johnson Gardner , Matthew Russell , Phillip Daniel Michalak
IPC分类号： G06F40/169 , G06Q10/107 , G06F40/30 , G06F40/40 , G06F40/211
摘要： In one aspect, the present disclosure relates to a method which, in one example embodiment, can include receiving text data that includes at least unstructured data and wherein the text data is associated with a plurality of messages communicated between a plurality of entities. The method can also include determining relationships between the entities, based on the text data associated with the plurality of messages, and generating, from a knowledge base assembled from at least the text data, a response to a user interaction representing a query for information that corresponds to at least one of the entities and indicates information on one or more of the determined relationships between the entities. The method can also include detecting a deviation in communication between the entities that indicates unauthorized disclosure of information between a first entity and a second entity.

7. 发明申请

US20220292427A1 Alert Actioning and Machine Learning Feedback 有权
公开(公告)号：US20220292427A1
公开(公告)日：2022-09-15
申请号：US17694293
申请日：2022-03-14
申请人： Digital Reasoning Systems, Inc.
发明人： Jena Acuff , Brandon Carl , Uday Kamath , Cory Hughes
IPC分类号： G06Q10/06 , G06F40/40 , G06F40/284 , G06K9/62
摘要： Some aspects of the present disclosure relate to systems, methods, and computer-readable media for configuring a conduct surveillance system. In one example implementation, a computer implemented method includes: receiving at least one alert from a conduct surveillance system, where the at least one alert represents a potential violation of a predetermined policy, where the predetermined policy includes a scenario, a target population, and a workflow; determining whether each of the at least one alert represents an actual violation of the predetermined policy; calculating a metric based on the actual violations and the potential violations where the metric includes a number of false positives associated with the at least one alert or the number of false negatives associated with the at least one alert; and changing at least one of the scenario, the target population, or the workflow based on the calculated metric.

8. 发明申请

US20160140236A1 KNOWLEDGE DISCOVERY AGENT SYSTEM 审中-公开
公开(公告)号：US20160140236A1
公开(公告)日：2016-05-19
申请号：US14935183
申请日：2015-11-06
申请人： DIGITAL REASONING SYSTEMS, INC.
发明人： Timothy W. Estes
IPC分类号： G06F17/30
CPC分类号： G06F17/30864 , G06F17/30395 , G06F17/30554 , G06F17/30997 , G06N3/08 , G06N5/022 , G06N99/005 , H04N21/251 , H04N21/466 , H04N21/4662 , H04N21/4668 , H04N21/4826
摘要： A system and method for processing information in unstructured or structured form, comprising a computer running in a distributed network with one or more data agents. Associations of natural language artifacts may be learned from natural language artifacts in unstructured data sources, and semantic and syntactic relationships may be learned in structured data sources, using grouping based on a criteria of shared features that are dynamically determined without the use of a priori classifications, by employing conditional probability constraints.

9. 发明授权

US09858340B1 Systems and methods for queryable graph representations of videos 有权
公开(公告)号：US09858340B1
公开(公告)日：2018-01-02
申请号：US15484406
申请日：2017-04-11
申请人： Digital Reasoning Systems, Inc.
发明人： John Frey , James Whitaker , Matthew Russell
IPC分类号： G06K9/34 , G06F17/30 , G06K9/00 , G06K9/62 , G10L25/30 , G06K9/46 , G10L15/26 , G10L15/20 , G10L15/00 , G10L17/00
CPC分类号： G06F17/30787 , G06F17/3079 , G06K9/00765 , G06K9/4628 , G06K9/6296 , G10L15/005 , G10L15/20 , G10L15/265 , G10L17/005 , G10L25/30
摘要： In one aspect, the present disclosure relates to a method which, in one embodiment, includes: receiving video data for a first video; deconstructing the video data of the first video into a plurality of context windows; performing, on each context window that includes an image frame, a video analytic function on the image frame to identify one or more characteristics of the context window; performing, on each context window that includes an audio frame, a video analytic function on the audio frame to identify one or more characteristics of the context window; generating, for each context windows, a respective local atomic unit comprising attributes derived from the identified one or more characteristics of the respective context window, to form a plurality of local atomic units; and generating a local graph representation of the first video, comprising a plurality of nodes corresponding to the plurality of local atomic units.

10. 发明申请

US20160247061A1 Systems and Methods for Neural Language Modeling 审中-公开
标题翻译：神经语言建模系统与方法
公开(公告)号：US20160247061A1
公开(公告)日：2016-08-25
申请号：US15047532
申请日：2016-02-18
申请人： Digital Reasoning Systems, Inc.
发明人： Andrew Trask , David Gilmore , Matthew Russell
IPC分类号： G06N3/04 , G06N3/08
CPC分类号： G06N3/04 , G06F17/2715 , G06F17/2785 , G06N3/02 , G06N3/0454 , G06N3/08
摘要： In some aspects, the present disclosure relates to neural language modeling. In one embodiment, a computer-implemented neural network includes a plurality of neural nodes, where each of the neural nodes has a plurality of input weights corresponding to a vector of real numbers. The neural network also includes an input neural node corresponding to a linguistic unit selected from an ordered list of a plurality of linguistic units, and an embedding layer with a plurality of embedding node partitions. Each embedding node partition includes one or more neural nodes. Each of the embedding node partitions corresponds to a position in the ordered list relative to a focus term, is configured to receive an input from an input node, and is configured to generate an output. The neural network also includes a classifier layer with a plurality of neural nodes, each configured to receive the embedding outputs from the embedding layer, and configured to generate an output corresponding to a probability that a particular linguistic unit is the focus term.
摘要翻译：在一些方面，本公开涉及神经语言建模。在一个实施例中，计算机实现的神经网络包括多个神经节点，其中每个神经节点具有对应于实数向量的多个输入权重。神经网络还包括对应于从多个语言单元的有序列表中选择的语言单元的输入神经元节点和具有多个嵌入节点分区的嵌入层。每个嵌入节点分区包括一个或多个神经节点。每个嵌入节点分区对应于有序列表中相对于聚焦项的位置，被配置为从输入节点接收输入，并且被配置为生成输出。神经网络还包括具有多个神经节点的分类器层，每个神经节点被配置为从嵌入层接收嵌入输出，并且被配置为生成对应于特定语言单元是焦点项的概率的输出。

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