公开(公告)号：US20170192973A1

公开(公告)日：2017-07-06

申请号：US15463414

申请日：2017-03-20

Applicant: Cortica, Ltd.

Inventor： Igal Raichelgauz ,  Karina Odinaev ,  Yehoshua Y. Zeevi

IPC: G06F17/30

CPC classification number: G06F16/48 ,  G06F16/9535 ,  G06F16/954 ,  G06F16/957 ,  G06Q30/0251 ,  G06Q30/0282 ,  H04H60/37 ,  H04H60/56 ,  H04H60/73 ,  H04H2201/90 ,  H04N7/17318 ,  H04N21/25891 ,  H04N21/2668 ,  H04N21/466 ,  H04N21/8106

Abstract: A system and method for recommending trending content based on context. The method includes receiving a query, wherein the query indicates a user intent; searching in at least one data source for a plurality of multimedia content elements related to the user intent; generating at least one signature for each of the plurality of multimedia content elements, wherein each signature represents a concept, wherein each concept is a collection of signatures and metadata describing the concept; correlating the concepts of the generated signatures to determine at least one context of each multimedia content element, wherein each context represents a sentiment; and generating, based on the determined contexts, a recommendation of at least one multimedia content element from among the plurality of multimedia content elements.

公开(公告)号：US20170185690A1

公开(公告)日：2017-06-29

申请号：US15456902

申请日：2017-03-13

Applicant: Cortica, Ltd.

Inventor： Igal Raichelgauz ,  Karina Odinaev ,  Yehoshua Y. Zeevi

IPC: G06F17/30

CPC classification number: H04L67/327 ,  G06F16/435 ,  H04L67/306 ,  Y10S707/99943 ,  Y10S707/99948

Abstract: A system and method for generating recommendations based on personalized multimedia content element clusters. The method includes obtaining a personalized multimedia content element cluster associated with a user, wherein the personalized multimedia content element cluster includes a plurality of multimedia content elements related to a common concept, wherein the common concept represents a user interest of the user; analyzing the obtained personalized multimedia content element cluster to determine at least one query; searching, using the determined at least one query, for at least one relevant multimedia content element that is relevant to the user interest of the user; and providing, to the user, at least one recommended multimedia content element of the at least one relevant multimedia content element found during the search.

公开(公告)号：US09575969B2

公开(公告)日：2017-02-21

申请号：US14509558

申请日：2014-10-08

Applicant: Cortica, Ltd.

Inventor： Igal Raichelgauz ,  Karina Odinaev ,  Yehoshua Y. Zeevi

IPC: G06F7/00 ,  G06F17/30

CPC classification number: G06F17/3002 ,  G06F17/301 ,  G06F17/30109 ,  Y10S707/99943 ,  Y10S707/99948

Abstract: Methods and systems for generating concept structures from signature reduced clusters (SRCs) are provided. The method includes retrieving at least one SRC including a cluster of signatures respective of a plurality of multimedia data elements (MMDEs); generating at least one metadata for each signature of the cluster of signatures; identifying a number of repetitions of a metadata of the at least one generated metadata; and determining whether the number of repetitions of the metadata exceeds a predefined repetition threshold; upon determining that the number of repetitions of the metadata exceeds the predefined repetition threshold, identifying the metadata as representative of the SRC; comparing the representative metadata to metadata that is representative of at least one previously generated SRC to determine a metadata match; and upon determining the metadata match, identifying the retrieved SRC and the matching previously generated SRC as a concept structure.

Abstract translation: 提供了从签名减少集群（SRC）生成概念结构的方法和系统。 该方法包括：检索至少一个包括多个多媒体数据元素（MMDE）相应的签名集群的SRC; 为所述签名群的每个签名生成至少一个元数据; 识别所述至少一个生成的元数据的元数据的重复次数; 以及确定所述元数据的重复次数是否超过预定的重复阈值; 在确定所述元数据的重复次数超过所述预定义的重复阈值时，将所述元数据标识为所述SRC的代表; 将代表性元数据与代表至少一个先前生成的SRC的元数据进行比较以确定元数据匹配; 并且在确定元数据匹配时，将所检索的SRC和匹配先前生成的SRC识别为概念结构。

公开(公告)号：US20170046343A1

公开(公告)日：2017-02-16

申请号：US15296551

申请日：2016-10-18

Applicant: Cortica, Ltd.

Inventor： Igal Raichelgauz ,  Karina Odinaev ,  Yehoshua Y. Zeevi

IPC: G06F17/30

CPC classification number: G06F16/48 ,  G06F16/1748 ,  G06F16/41 ,  Y10S707/99943 ,  Y10S707/99948

Abstract: A system and method for removing contextually identical multimedia content elements. The method includes analyzing a plurality of multimedia content elements to identify at least two multimedia content elements of the plurality of multimedia content elements that are contextually identical; selecting, from among the at least two contextually identical multimedia content elements, at least one optimal multimedia content element; and removing, from a storage, all multimedia content elements of the group of contextually identical multimedia content elements other than the at least one optimal multimedia content element.

Abstract translation: 一种用于删除上下文相同的多媒体内容元素的系统和方法。 该方法包括分析多个多媒体内容元素以识别在上下文相同的多个多媒体内容元素中的至少两个多媒体内容元素; 从所述至少两个上下文相同的多媒体内容元素中选择至少一个最佳多媒体内容元素; 以及从所述至少一个最佳多媒体内容元素除去所述上下文相同的多媒体内容元素组中的所有多媒体内容元素的存储。

公开(公告)号：US09558449B2

公开(公告)日：2017-01-31

申请号：US14530913

申请日：2014-11-03

Applicant: Cortica, Ltd.

Inventor： Igal Raichelgauz ,  Karina Odinaev ,  Yehoshua Y. Zeevi

IPC: G06N5/00 ,  G06F1/00 ,  G06N5/04 ,  G06N7/00 ,  G06F17/30 ,  G06Q30/02 ,  H04H60/37 ,  H04H60/56 ,  H04N7/173 ,  H04N21/258 ,  H04N21/2668 ,  H04N21/466 ,  H04N21/81 ,  H04H60/46

CPC classification number: G06F17/2235 ,  G06F1/163 ,  G06F3/04883 ,  G06F17/2247 ,  G06F17/2765 ,  G06F17/30017 ,  G06F17/30899 ,  G06N5/04 ,  G06N7/005 ,  G06Q30/0251 ,  G06Q30/0263 ,  H04H60/37 ,  H04H60/46 ,  H04H60/56 ,  H04H2201/90 ,  H04N7/17318 ,  H04N21/25891 ,  H04N21/2668 ,  H04N21/466 ,  H04N21/8106

Abstract: A system and method for detecting a target area of user interest within a multimedia content element are provided. The method includes receiving the multimedia content element from a user computing device; partitioning the multimedia content element into a number of partitions, each partition having at least one object therein; generating at least one signature for each partition of the multimedia content element, wherein each of the at least one signatures for each partition represents a concept; determining a context of the multimedia content element based on the concepts; and identifying at least one partition of the multimedia content as a target area of user interest based on the context of the multimedia content element.

Abstract translation: 提供了一种用于检测多媒体内容元素内的用户感兴趣的目标区域的系统和方法。 该方法包括从用户计算设备接收多媒体内容元素; 将多媒体内容元素划分成多个分区，每个分区具有至少一个对象; 为所述多媒体内容元素的每个分区生成至少一个签名，其中每个分区的所述至少一个签名中的每一个表示概念; 基于概念确定多媒体内容元素的上下文; 以及基于所述多媒体内容元素的上下文，将所述多媒体内容的至少一个分区识别为用户感兴趣的目标区域。

公开(公告)号：US20160378755A1

公开(公告)日：2016-12-29

申请号：US15259907

申请日：2016-09-08

Applicant: Cortica, Ltd.

Inventor： Igal Raichelgauz ,  Karina Odinaev ,  Yehoshua Y. Zeevi

IPC: G06F17/30 ,  H04L29/08

CPC classification number: H04L67/22 ,  G06F17/30029 ,  G06K9/00744 ,  H04L67/306

Abstract: A system and method for creating user profiles based on multimedia content. The method may include identifying a plurality of multimedia content elements associated with a user; generating at least one signature for each of the plurality of multimedia content elements; analyzing the at least one signature to identify at least one concept matching the multimedia content elements; generating, based on the at least one matching concept, at least one contextual insight, wherein each contextual insight indicates a preference of the user; and generating, based on the at least one contextual insight, a user profile for the user.

Abstract translation: 一种基于多媒体内容创建用户简档的系统和方法。 该方法可以包括识别与用户相关联的多个多媒体内容元素; 为所述多个多媒体内容元素中的每一个生成至少一个签名; 分析所述至少一个签名以识别与所述多媒体内容元素匹配的至少一个概念; 基于所述至少一个匹配概念生成至少一个情境洞察，其中每个上下文的洞察指示所述用户的偏好; 以及基于所述至少一个上下文观察，生成所述用户的用户简档。

公开(公告)号：US09489431B2

公开(公告)日：2016-11-08

申请号：US14096802

申请日：2013-12-04

Applicant: CORTICA, LTD.

Inventor： Igal Raichelgauz ,  Karina Odinaev ,  Yehoshua Y. Zeevi

IPC: G06G5/00 ,  G06F1/00 ,  G06F17/30 ,  H04H60/37 ,  H04N7/173 ,  H04N21/258 ,  H04N21/2668 ,  H04N21/466 ,  H04N21/81 ,  H04H60/47 ,  H04H60/46 ,  H04H60/58 ,  H04H60/59 ,  H04H60/65 ,  H04H60/73

CPC classification number: G06F17/30554 ,  G06F17/30023 ,  H04H60/37 ,  H04H60/46 ,  H04H60/47 ,  H04H60/58 ,  H04H60/59 ,  H04H60/65 ,  H04H60/73 ,  H04H2201/90 ,  H04N7/17318 ,  H04N21/25891 ,  H04N21/2668 ,  H04N21/466 ,  H04N21/8106

Abstract: A method for conducting search-by-content is provided. The method includes responsive to an input multimedia content item provided to a user device, checking if the input multimedia content item matches at least one concept of a plurality of concepts cached in the user device; retrieving characteristics set for a user of the user device; performing a search, using the at least one matching concept, for multimedia content items similar to the input multimedia content item; determining which of the search results are of interest to the user based on the characteristics set for the user; and saving results that are of interest to the user in the user device, wherein the saved results include multimedia content items.

Abstract translation: 提供了一种用于进行内容搜索的方法。 该方法包括响应于提供给用户设备的输入多媒体内容项，检查输入多媒体内容项是否与缓存在用户设备中的多个概念的至少一个概念相匹配; 检索为用户设备的用户设置的特征; 使用所述至少一个匹配概念对与所述输入多媒体内容项相似的多媒体内容进行搜索; 基于为用户设置的特征来确定用户感兴趣的哪个搜索结果; 并且保存用户在用户设备中感兴趣的结果，其中所保存的结果包括多媒体内容项。

公开(公告)号：US20160321256A1

公开(公告)日：2016-11-03

申请号：US15206792

申请日：2016-07-11

Applicant: Cortica, Ltd.

Inventor： Igal Raichelgauz ,  Karina Odinaev ,  Yehoshua Y. Zeevi

IPC: G06F17/30 ,  G06K9/00

CPC classification number: G06K9/00281 ,  G06F16/41 ,  G06K2209/27

Abstract: A system and method for generating a facial representation. The method includes identifying, via at least one data source, at least one multimedia content element; generating at least one signature for at least a portion of each identified multimedia content element, wherein each generated signature represents at least one facial concept; analyzing the generated signatures to determine a cluster of signatures of facial concepts; and generating, based on the cluster of facial concept signatures, a facial representation.

Abstract translation: 一种用于生成面部表情的系统和方法。 该方法包括通过至少一个数据源识别至少一个多媒体内容元素; 为每个所标识的多媒体内容元素的至少一部分生成至少一个签名，其中每个生成的签名代表至少一个面部概念; 分析生成的签名以确定面部概念的签名簇; 并且基于面部概念签名的集群生成面部表情。

公开(公告)号：US09466068B2

公开(公告)日：2016-10-11

申请号：US14621653

申请日：2015-02-13

Applicant: Cortica, Ltd.

Inventor： Igal Raichelgauz ,  Karina Odinaev ,  Yehoshua Y. Zeevi

IPC: G06K9/00 ,  G06Q30/02 ,  G06F17/30

CPC classification number: G06Q30/0269 ,  G06F17/3002 ,  G06Q30/0241

Abstract: A method for determining a pupillary response to a multimedia data element viewed through a user computing device. The method comprises receiving a first image of a viewer's pupil captured prior to display of the MMDE over the user computing device; receiving a second image of a viewer's pupil captured after the display of the MMDE over the user computing device; determining, using the first image and the second image, if the viewer's pupil has been dilated; querying a deep-content-classification system to find a match between at least one concept structure and the at least second image of the user's pupil; upon identification of at least one matching concept, receiving a first set of metadata related to the at least one matching concept structure; determining the viewer's attention to the displayed MMDE respective of the first set of metadata; associating the at least one MMDE with the determined user attention.

Abstract translation: 一种用于确定通过用户计算设备观看的多媒体数据元素的瞳孔响应的方法。 该方法包括在用户计算设备之前接收在MMDE显示之前捕获的观看者瞳孔的第一图像; 在所述用户计算设备上显示所述MMDE之后，接收观看者瞳孔的第二图像; 使用第一图像和第二图像确定观看者的瞳孔是否已经被扩张; 查询深度内容分类系统以在至少一个概念结构与用户学生的至少第二图像之间找到匹配; 在识别至少一个匹配概念时，接收与所述至少一个匹配概念结构相关的第一组元数据; 确定观众对所显示的MMDE的注意力分别对应于第一组元数据; 将所述至少一个MMDE与确定的用户注意相关联。

公开(公告)号：US09449001B2

公开(公告)日：2016-09-20

申请号：US14530970

申请日：2014-11-03

Applicant: Cortica, Ltd.

Inventor： Igal Raichelgauz ,  Karina Odinaev ,  Yehoshua Y. Zeevi

IPC: G06F7/00 ,  G06F17/30

CPC classification number: G06F17/3002 ,  G06F17/30017 ,  G06F17/30023 ,  G06F17/30109 ,  G06F17/30312 ,  G06F17/30598 ,  Y10S707/913 ,  Y10S707/99943 ,  Y10S707/99948

Abstract: A method and system for generating a complex signature respective of a multimedia data element (MMDE) are provided. The method includes partitioning the MMDE into a plurality of different minimum size MMDEs; generating, for each of the different minimum MMDEs, at least one signature, wherein generation of each at least one signature is performed by a plurality of computational cores, each computational core having at least one configurable property characterizing the core, and wherein configuration of the at least one configurable property respective of each core results in statistical independence among the plurality of cores; and assembling at least a complex signature for the MMDE comprised of a plurality of the generated signatures.

Abstract translation: 提供了一种生成多媒体数据元素（MMDE）的复杂签名的方法和系统。 该方法包括将MMDE分成多个不同的最小大小的MMDE; 为每个不同的最小MMDE生成至少一个签名，其中每个至少一个签名的生成由多个计算核执行，每个计算核具有表征核的至少一个可配置属性，并且其中， 每个核心相应的至少一个可配置属性导致多个核心之间的统计独立性; 以及至少组合由多个生成的签名组成的MMDE的复杂签名。