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.

公开(公告)号：US20200283030A1

公开(公告)日：2020-09-10

申请号：US16628749

申请日：2018-07-04

Applicant: CORTICA LTD.

Inventor： Igal RAICHELGAUZ ,  Karina ODINAEV ,  Yehoshua Y ZEEVI

IPC: B60W60/00 ,  G06K9/00 ,  B60W50/08

Abstract: A method for determining driving policies for a vehicle includes: receiving, in real-time during a trip of a vehicle, at least a set of input multimedia content elements captured by at least one sensor deployed in proximity to the vehicle, determining a plurality of possible future scenarios based at least on the set of input multimedia content elements, determining a probability score for each of the plurality of possible future scenarios, determining at least one driving policy according to at least the probability score for at least one of the plurality of possible future scenarios, and controlling the vehicle according to the at least one driving policy.

公开(公告)号：US20200226152A1

公开(公告)日：2020-07-16

申请号：US16576818

申请日：2019-09-20

Applicant: Cortica Ltd.

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

IPC: G06F16/28 ,  G06F16/41 ,  G06F16/432 ,  G06F16/683 ,  G06F16/783 ,  G06K9/00 ,  G10L15/26 ,  G06F16/40 ,  G06F16/43 ,  G06F16/438 ,  G06F3/048 ,  G06T19/00 ,  G06N5/02 ,  H04H20/10 ,  H04H20/26 ,  H04H60/37 ,  H04H60/46 ,  H04H60/56 ,  H04H60/66 ,  H04L29/08 ,  H04N7/173 ,  H04N21/258 ,  H04N21/2668 ,  H04N21/466 ,  H04N21/81 ,  G06F16/904 ,  G06F16/35 ,  G06F16/51 ,  G06F16/22 ,  G06F16/174 ,  G06F16/48

Abstract: There is provided a method for searching a plurality of information sources using a multimedia element, the method may include receiving at least one multimedia element; generating, by a signature generator, for the at least one multimedia element at least one signature that is unidirectional, and yields compression; generating at least one textual search query using the at least one signature; wherein the generating of the textual search query comprises: (a) searching for at least one matching stored signature that matches one or more of the at least one signature; and (b) using a mapping between stored signatures and textual search queries, selecting at least one textual search query mapped to at least one matching stored signature; searching the plurality of information sources using the at least one textual search query; and causing a display of search results retrieved from the plurality of information sources.

公开(公告)号：US20180157667A1

公开(公告)日：2018-06-07

申请号：US15810532

申请日：2017-11-13

Applicant: Cortica, Ltd.

Inventor： Igal RAICHELGAUZ ,  Karina ODINAEV ,  Yehoshua Y ZEEVI

IPC: G06F17/30 ,  H04N21/81 ,  H04N21/466 ,  H04N21/2668 ,  H04N21/258 ,  H04N7/173 ,  H04H20/10 ,  H04H60/66 ,  H04H60/56 ,  H04H60/46 ,  H04H60/37 ,  H04H20/26 ,  H04L29/08

CPC classification number: G06F16/4393 ,  G06Q10/10 ,  G06Q50/01 ,  H04H20/103 ,  H04H20/26 ,  H04H60/37 ,  H04H60/40 ,  H04H60/46 ,  H04H60/56 ,  H04H60/66 ,  H04H60/73 ,  H04H2201/90 ,  H04L67/10 ,  H04N7/17318 ,  H04N21/25891 ,  H04N21/2668 ,  H04N21/466 ,  H04N21/8106

Abstract: A system and method for generating a theme for multimedia content elements (MMCEs), including analyzing a plurality of MMCEs, where the analyzing further includes generating at least one signature to each MMCE; identifying, based on the generated signatures, a plurality of concepts for each MMCE, wherein each concept is a collection of signatures and metadata describing the concept; determining, based on the identified concepts, at least one context of each MMCE; and generating, based on the determined contexts, a theme, wherein the theme is a cluster of contextually related MMCEs.

公开(公告)号：US20180137126A1

公开(公告)日：2018-05-17

申请号：US15813453

申请日：2017-11-15

Applicant: Cortica, Ltd.

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

IPC: G06F17/30 ,  H04N21/81 ,  H04N21/466 ,  H04N21/2668 ,  H04N21/258 ,  H04N7/173 ,  H04H20/10 ,  H04H60/66 ,  H04H60/56 ,  H04H60/46 ,  H04H60/37 ,  H04H20/26 ,  H04L29/08

CPC classification number: G06F16/4393 ,  G06F16/48 ,  H04H20/103 ,  H04H20/26 ,  H04H60/37 ,  H04H60/46 ,  H04H60/56 ,  H04H60/66 ,  H04L67/10 ,  H04N7/17318 ,  H04N21/234345 ,  H04N21/25891 ,  H04N21/26258 ,  H04N21/2668 ,  H04N21/466 ,  H04N21/4821 ,  H04N21/6125 ,  H04N21/8106

Abstract: A system and method for identifying influential entities depicted in multimedia content. The method includes determining, for each of a plurality of social linking graphs, a number of related entities, wherein each related entity has a social linking score above a first predetermined threshold, wherein each social linking score is generated based on at least one context of at least one multimedia content element (MMCE), and wherein each context is determined based on signatures generated for the at least one MMCE; and identifying, based on the determined number of related entities, at least one influential entity, wherein each influential entity is associated with one of the social linking graphs for which the determined number of related entities is above a second predetermined threshold.

公开(公告)号：US20170371893A1

公开(公告)日：2017-12-28

申请号：US15698317

申请日：2017-09-07

Applicant: Cortica, Ltd.

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

IPC: G06F17/30

CPC classification number: G06F16/1748 ,  G06F16/215 ,  G06F16/2228 ,  G06F16/285 ,  G06F16/41 ,  G06F16/43 ,  G06F16/48 ,  Y10S707/99943 ,  Y10S707/99948

Abstract: A system and method for enriching a concept database with homogenous concepts. The method includes determining, based on signatures of a first multimedia content element (MMCE) and signatures of a plurality of existing concepts in the concept database, at least one first concept; generating a reduced representation of the first MMCE, wherein the reduced representation excludes the signatures of the first MMCE that match the at least one first concept; comparing the reduced representation to signatures representing a plurality of second MMCEs to select a first plurality of top matching second MMCEs; generating, based on the reduced representation and the first plurality of top matching second MMCEs, at least one second concept; determining, for each second concept, whether the second concept is a homogenous concept, wherein each homogenous concept uniquely represents the same content; and adding each homogenous concept to the concept database.