公开(公告)号：US20140082211A1

公开(公告)日：2014-03-20

申请号：US14087800

申请日：2013-11-22

Applicant: CORTICA LTD.

Inventor： Igal RAICHELGAUZ ,  Karina ODINAEV ,  Yehoshua Y. ZEEVI

IPC: H04L29/06

CPC classification number: G06F17/30109 ,  G06F17/3002

Abstract: A method and system for method for generating concept structures are disclosed. The method comprises receiving a request to create a new concept structure, wherein the request includes at least a multimedia data element (MMDE) related to the new concept structure; querying a deep-content-classification (DCC) system using the MMDE to find at least one sub-concept, wherein a sub-concept is a concept structure that partially matches the received MMDE; checking if the at least one sub-concept satisfies at least one predefined logic rule; generating one or more sub-concepts from the at least MMDE; and generating the new concept structure using one or more sub-concepts out of the at least one sub-concepts that satisfies the predefined logic rule.

Abstract translation: 公开了一种用于产生概念结构的方法和系统。 该方法包括接收创建新概念结构的请求，其中所述请求至少包括与新概念结构相关的多媒体数据元素（MMDE）; 使用所述MMDE查询深度内容分类（DCC）系统以找到至少一个子概念，其中子概念是部分地匹配所接收的MMDE的概念结构; 检查所述至少一个子概念是否满足至少一个预定逻辑规则; 从所述至少MMDE生成一个或多个子概念; 以及使用满足预定逻辑规则的至少一个子概念中的一个或多个子概念生成新概念结构。

公开(公告)号：US20130138653A1

公开(公告)日：2013-05-30

申请号：US13731921

申请日：2012-12-31

Applicant: Cortica, Ltd.

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

IPC: G06F17/30

CPC classification number: G06F17/30598 ,  G06F17/3028 ,  G06F17/30705 ,  G06F17/30994 ,  G06N5/025

Abstract: A method for reducing an amount of storage required for maintaining a large-scale collection of multimedia data elements by unsupervised clustering of multimedia data elements. The method comprises processing the multimedia data elements in the large-scale collection to generate a first cluster of multimedia data elements; storing the first cluster in a storage unit; repeating the generation of a new cluster from the first cluster and un-clustered multimedia elements in the large-scale collection until a single cluster is reached; and storing the new cluster generated at each iteration in the storage unit, wherein a N-th cluster generated at the N-th iteration is stored in the storage unit, wherein the amount of storage required to store the N-th cluster is less than an amount of storage of the large-scale collection, thereby the unsupervised clustering enables reducing the storage amount required to store the multimedia data elements in the large-scale collection.

Abstract translation: 一种用于通过多媒体数据元素的无监督聚类来减少维护多媒体数据元素的大规模收集所需的存储量的方法。 该方法包括处理大规模集合中的多媒体数据元素以产生多媒体数据元素的第一簇; 将所述第一集群存储在存储单元中; 重复从第一个集群生成新集群，并在大规模集合中重新生成非集群多媒体元素，直到达到单个集群; 以及将在每次迭代生成的新集群存储在所述存储单元中，其中在所述第N次迭代中生成的第N个集群被存储在所述存储单元中，其中存储所述第N个集群所需的存储量小于 大规模收集的存储量，从而无监督的聚类使得能够减少在大规模集合中存储多媒体数据元素所需的存储量。

公开(公告)号：US11758004B2

公开(公告)日：2023-09-12

申请号：US16726933

申请日：2019-12-26

Applicant: Cortica Ltd.

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

IPC: G06F16/00 ,  H04L67/306 ,  H04H60/46 ,  H04N21/2668 ,  H04N7/173 ,  H04N21/258 ,  H04N21/81 ,  G06F16/9535 ,  H04N21/466

CPC classification number: H04L67/306 ,  G06F16/9535 ,  H04H60/46 ,  H04N7/17318 ,  H04N21/25891 ,  H04N21/2668 ,  H04N21/466 ,  H04N21/8106 ,  H04H2201/90

Abstract: A system and method for providing recommendations based on current user interests. The method includes identifying at least one current variable, wherein each current variable is associated with a user device or a user; determining, based on the identified at least one current variable, at least one current user interest of a user profile, the user profile including at least one contextual insight, wherein each contextual insight is based on at least one signature for at least one multimedia content element associated with the user; searching for at least one multimedia content element that matches the at least one current user interest; and causing a display of the at least one matching content item as a recommendation.

公开(公告)号：US20230230341A1

公开(公告)日：2023-07-20

申请号：US18155725

申请日：2023-01-17

Applicant: Cortica Ltd.

Inventor： Karina Odinaev

IPC: G06V10/26 ,  G06V10/44 ,  G06V10/20 ,  G06V10/774

CPC classification number: G06V10/26 ,  G06V10/44 ,  G06V10/255 ,  G06V10/774 ,  G06V2201/10

Abstract: A method for concept based segmentation, the method may include (a) detecting an object within a region of an image; wherein the object is associated with characteristic pixels metadata that indicative of multiple examples of pixels properties of pixels that are included in at least one appearance of the object within at least one image; and (b) finding, within the region, one or more object boundaries, based on the characteristic pixels metadata.

公开(公告)号：US11694088B2

公开(公告)日：2023-07-04

申请号：US16782087

申请日：2020-02-05

Applicant: Cortica Ltd.

Inventor： Igal Raichelgauz ,  Eli Passov

IPC: G06N3/08 ,  G06N3/088 ,  G06N3/045 ,  G06N3/048

CPC classification number: G06N3/088 ,  G06N3/045 ,  G06N3/048

Abstract: A method that may include training a student ODNN to mimic a teacher ODNN. The training may include calculating a teacher student detection loss that is based on a pre-bounding-box output of the teacher ODNN. The pre-bounding-box output of the teacher ODNN is a function of pre-bounding-box outputs of different ODNNs that belong to the teacher ODNN. The method may also include detecting one or more objects in an image, by feeding the image to the trained student ODNN; outputting by the trained student ODNN a student pre-bounding-box output; and calculating one or more bounding boxes based on the student pre-bounding-box output.

公开(公告)号：US20230177405A1

公开(公告)日：2023-06-08

申请号：US17755822

申请日：2020-11-09

Applicant: Cortica Ltd.

Inventor： Karina Odinaev

IPC: G06N20/20 ,  G06N3/08

CPC classification number: G06N20/20 ,  G06N3/08

Abstract: A method for operating an ensemble of narrow AI agents, the method may include obtaining one or more sensed information units; determining, by a perception unit and based on the one or more sensed information units, one or more relevant narrow AI agents of the ensemble, that are relevant to a processing of the one or more sensed information units; wherein the ensemble is relevant to a first plurality of scenarios; processing the one or more sensed information units, by the one or more relevant narrow AI agents, to provide one or more narrow AI agent outputs; and processing, by an intermediate result unit, the one or more narrow AI agent outputs to provide an intermediate result; and generating a response, by a response unit, based on the intermediate result; wherein each narrow AI agent is relevant to a respective fraction of the first plurality of scenarios.

公开(公告)号：US11543360B2

公开(公告)日：2023-01-03

申请号：US16942712

申请日：2020-07-29

Applicant: Cortica Ltd.

Inventor： Igal Raichelgauz ,  Karina Odinaev

IPC: G01N21/87 ,  G01N33/38 ,  G06V10/56 ,  G06K9/62 ,  G01J3/46 ,  G01N21/95 ,  G06V10/42 ,  G06V10/75 ,  B07B13/00

Abstract: A method for generating a highly distinctive signature of a certain diamond, the method may include generating, based on one or more images of the certain diamond, a certain diamond signature of the certain diamond; finding, out of a group of reference diamonds, other diamonds having other diamond signatures; wherein the finding comprises calculating similarities between the certain diamond signature and reference diamond signatures of the reference diamonds of the group; and generating a new certain diamond signature that significantly differs from signatures of the other diamonds.

公开(公告)号：US20220343620A1

公开(公告)日：2022-10-27

申请号：US17594001

申请日：2020-03-25

Applicant: Cortica, Ltd.

Inventor： Igal Raichelgauz ,  karina Odinaev

IPC: G06V10/20 ,  G06V10/422 ,  G06V10/50

Abstract: Systems, and method and computer readable media that store instructions for calculating signatures, utilizing signatures and the like, wherein for a low-power calculation of a signature, the method comprises: receiving or generating a media unit of multiple objects: processing the media unit by performing multiple iterations, determining a relevancy of the spanning elements of the iteration; completing the dimension expansion process by relevant spanning elements of the iteration and reducing a power consumption of irrelevant spanning; determining identifiers that are associated with significant portions of an output of the multiple iterations; and providing a signature that comprises the identifiers and represents the multiple objects.

公开(公告)号：US20220182535A1

公开(公告)日：2022-06-09

申请号：US17643159

申请日：2021-12-07

Applicant: Cortica Ltd.

Inventor： Karina ODINAEV

IPC: H04N5/232 ,  G06V10/74 ,  G06V20/00 ,  B64C39/02

Abstract: A method for filming an event by an autonomous drone, the method may include acquiring, by the autonomous drone, a current set of images of the event; generating signatures of the current set of images to provide current signatures; searching for one or more relevant concept structures out of a group of concept structures; wherein each relevant concept structure comprises at least one signature that matches at least one of first signatures; wherein each concept structure is associated with filming parameters; and determining, at least in part, based on the filming parameters associated with at least one of the one or more relevant concept structures, next filming parameters to be applied during an acquisition of one or more next sets of images.

公开(公告)号：US20220027742A1

公开(公告)日：2022-01-27

申请号：US17443476

申请日：2021-07-27

Applicant: Cortica Ltd.

Inventor： Karina ODINAEV

IPC: G06N3/08 ,  G06N3/04 ,  G06K9/62

Abstract: A method for an unsupervised training of a neural network, the method may include initializing a neural network that exhibits at least one invariance; performing multiple training iterations until reaching a last training iteration in which a stop condition is fulfilled; wherein each training iteration except the last training iteration comprises: processing a vast number of media units by the neural network to provide media unit signatures; finding that the stop condition is not reached, and changing multiple neural network weights; wherein the stop condition is related to signatures similarities.