公开(公告)号：US20170053653A1

公开(公告)日：2017-02-23

申请号：US15254326

申请日：2016-09-01

Applicant: Verint Systems Ltd.

Inventor： Oana Sidi ,  Ron Wein

IPC: G10L17/06 ,  G10L17/02 ,  H04M3/51 ,  G10L15/02 ,  G10L17/16 ,  G10L17/04 ,  G10L15/26 ,  G10L25/78

CPC classification number: G10L17/06 ,  G10L15/02 ,  G10L15/26 ,  G10L17/02 ,  G10L17/04 ,  G10L17/16 ,  G10L25/78 ,  G10L2015/025 ,  H04M3/5175 ,  H04M2201/41 ,  H04M2203/303

Abstract: In a method of diarization of audio data, audio data is segmented into a plurality of utterances. Each utterance is represented as an utterance model representative of a plurality of feature vectors. The utterance models are clustered. A plurality of speaker models are constructed from the clustered utterance models. A hidden Markov model is constructed of the plurality of speaker models. A sequence of identified speaker models is decoded.

Abstract translation: 在音频数据的分类方法中，将音频数据分割为多个话语。 每个话语被表示为代表多个特征向量的话语模型。 话语模型是聚类的。 从群集话语模型构建多个说话者模型。 由多个扬声器模型构成隐马尔可夫模型。 已识别的扬声器模型的序列被解码。

公开(公告)号：US09552522B2

公开(公告)日：2017-01-24

申请号：US14593144

申请日：2015-01-09

Applicant: Verint Systems Ltd.

Inventor： Boaz Dudovich

IPC: G06K9/00 ,  H04N5/225

CPC classification number: G06K9/00295 ,  G06F3/0481 ,  G06F17/30259 ,  G06F17/3028 ,  G06K9/00362 ,  G06K9/00711 ,  G06K9/00778

Abstract: Video is often used to count and identify people entering and exiting an area, such as a store. This information may be used to determine the number and amount of time people are in the area, and other statistics and characteristics. These variables may be skewed by the associates employed or working in the area, instead of patrons or others. The present disclosure is directed to method for eliminating associates from video by facial analysis and the application of analytics.

Abstract translation: 视频通常用于计数和识别进入和退出某个区域（如商店）的人员。 该信息可用于确定人们在该地区的人数和人数以及其他统计和特征。 这些变量可能由在该地区雇用或在该地区工作的员工而不是顾客或其他人员倾斜。 本公开涉及通过面部分析和分析的应用来消除来自视频的关联的方法。

公开(公告)号：US20170013203A1

公开(公告)日：2017-01-12

申请号：US15163782

申请日：2016-05-25

Applicant: Verint Systems Ltd.

Inventor： Gideon Hazzani

IPC: H04N5/268 ,  H04N5/232 ,  H04W4/02 ,  H04N7/18

CPC classification number: H04N5/268 ,  G08B13/19608 ,  G08B13/19645 ,  G08B13/19658 ,  G08B13/2462 ,  H04L67/18 ,  H04N5/23296 ,  H04N7/181 ,  H04N21/21805 ,  H04W4/02

Abstract: Systems and methods for receiving video images from a plurality of video cameras having respective fields of view that cover a geographical region. At a first time, first video images of an object may be output, where the images are captured by a first video camera selected from the plurality of video cameras. Location indications may be received, which specify a geographical location of the object in the geographical region and which are determined independently of the video images. At a second time subsequent to the first time, a second video camera from the plurality may be selected based on the location indications. The output may be switched to the second video images of the object, which are captured by the selected second video camera.

Abstract translation: 用于从具有覆盖地理区域的各个视野的多个摄像机接收视频图像的系统和方法。 在第一时间，可以输出对象的第一视频图像，其中由从多个摄像机中选择的第一摄像机拍摄图像。 可以接收位置指示，其指定地理区域中对象的地理位置，并且独立于视频图像来确定。 在第一次之后的第二时间，可以基于位置指示来选择来自多个的第二摄像机。 可以将输出切换到由所选择的第二摄像机捕获的对象的第二视频图像。

公开(公告)号：US09536308B2

公开(公告)日：2017-01-03

申请号：US14100895

申请日：2013-12-09

Applicant: Verint Systems Ltd.

Inventor： Yaron Ostrovsky-Berman ,  Ran Gur ,  Nir Naor ,  Ran Wronsky ,  Michael Milman

IPC: G06K9/00 ,  G06T7/00 ,  G06Q10/10

CPC classification number: G06K9/00718 ,  G06F17/211 ,  G06F17/248 ,  G06K9/00771 ,  G06K2009/00738 ,  G06Q10/10 ,  G06T7/70

Abstract: Systems and methods of detecting irregular events include the extraction of values for measure in each of a plurality of notifications. The extracted values are stored in a measures database and a distribution is calculated for the values of each of the measures. The extracted values are compared to the calculated distributions to determine if an irregular event has occurred. An irregularity alert is produced if an irregular event has occurred.

Abstract translation: 检测不规则事件的系统和方法包括提取在多个通知中的每一个中测量的值。 提取的值存储在度量数据库中，并且针对每个度量的值计算分布。 将提取的值与计算的分布进行比较，以确定是否发生了不规则事件。 如果发生不规则事件，则产生不规则警报。

公开(公告)号：US20160337620A1

公开(公告)日：2016-11-17

申请号：US15224019

申请日：2016-07-29

Applicant: Verint Systems Ltd.

Inventor： Itsik Horovitz ,  Shmuel Kiro ,  Or Sheffet

IPC: H04N7/18 ,  G06F3/0484 ,  G06K9/00 ,  G06F3/0481

CPC classification number: H04N7/181 ,  G06F3/04817 ,  G06F3/04842 ,  G06K9/00771

Abstract: A subject can be tracking using a plurality of physical video monitoring or image acquisition devices deployed in a delimited area. A map represents the delimited area. Icons representing the physical monitoring devices can be placed and configured on the map representing the delimited area. Some or all of the placed and configured video monitoring devices can be logically linked together to form scenes. The video feed from the physical video monitoring devices may be recorded in stable storage. A layout for display of the video feeds may be selected. Upon playing the video feed, whether live or recorded, a subject can be tracked through the delimited area by selecting one of the video monitoring devices in one of the available scenes.

Abstract translation: 主体可以使用部署在界定区域中的多个物理视频监视或图像采集装置进行跟踪。 地图表示分界区域。 可以在代表定界区域的地图上放置和配置表示物理监视设备的图标。 部分或全部放置和配置的视频监控设备可以逻辑链接在一起形成场景。 来自物理视频监视设备的视频馈送可以被记录在稳定的存储器中。 可以选择用于显示视频馈送的布局。 在播放视频馈送（无论是实况还是录制）时，可以通过在可用场景之一中选择一个视频监控设备，通过分隔区域跟踪主体。

公开(公告)号：US09401145B1

公开(公告)日：2016-07-26

申请号：US14270280

申请日：2014-05-05

Applicant: Verint Systems, Ltd.

Inventor： Omer Ziv ,  Ran Achituv ,  Ido Shapira

IPC: G10L15/00 ,  G10L15/20 ,  G10L15/19 ,  G10L15/26

CPC classification number: G10L15/20 ,  G10L15/19 ,  G10L15/197 ,  G10L15/26

Abstract: A method for converting speech to text in a speech analytics system is provided. The method includes receiving audio data containing speech made up of sounds from an audio source, processing the sounds with a phonetic module resulting in symbols corresponding to the sounds, and processing the symbols with a language module and occurrence table resulting in text. The method also includes determining a probability of correct translation for each word in the text, comparing the probability of correct translation for each word in the text to the occurrence table, and adjusting the occurrence table based on the probability of correct translation for each word in the text.

Abstract translation: 提供了一种在语音分析系统中将语音转换为文本的方法。 该方法包括接收包含来自音频源的声音的音频数据，用声音模块处理声音，产生与声音相对应的符号，以及用导致文本的语言模块和出现表处理符号。 该方法还包括确定文本中的每个单词的正确翻译的概率，将文本中的每个单词的正确翻译的概率与出现表进行比较，并且基于每个单词的正确翻译的概率来调整出现表 文本。

公开(公告)号：US20160189160A1

公开(公告)日：2016-06-30

申请号：US14980811

申请日：2015-12-28

Applicant: Verint Systems Ltd.

Inventor： Ziv Katzir

IPC: G06Q20/40

CPC classification number: G06Q20/4014 ,  G06Q20/0855

Abstract: Methods and systems for deanonymizing digital currency users and transactions. The deanonymization system monitors communication sessions that are conducted in a communication network. From among the monitored sessions, the system detects sessions in which users carry out digital currency transactions. Having detected such a session, the system attempts to deanonymize the user, i.e., to correlate the digital currency pseudonym given in the session with some other information that is indicative of the user. The system may determined the identity of the terminal on which the user conducts the session, and uses the identity of the terminal to establish a correlation between the pseudonym and the user. In some cases the terminal is known to belong to a specific user.

Abstract translation: 对数字货币用户和交易进行脱名的方法和系统。 脱离系统监视在通信网络中进行的通信会话。 在受监视的会话中，系统检测用户执行数字货币交易的会话。 在检测到这样的会话之后，系统尝试对用户进行去匿名，即将会话中给出的数字货币假名与指示用户的一些其它信息相关联。 系统可以确定用户进行会话的终端的身份，并且使用终端的身份来建立假名和用户之间的相关性。 在某些情况下，终端被称为属于特定用户。

公开(公告)号：US20160154782A1

公开(公告)日：2016-06-02

申请号：US14951546

申请日：2015-11-25

Applicant: Verint Systems Ltd.

Inventor： Roni Romano ,  Rahm Fehr

IPC: G06F17/27

CPC classification number: G06F17/271 ,  G06F17/2785 ,  G06N5/022 ,  G06N99/005 ,  H04M3/2218 ,  H04M3/42221 ,  H04M3/5175 ,  H04M3/5183 ,  H04M2203/2038

Abstract: The disclosed solution uses machine learning-based methods to improve the knowledge extraction process in a specific domain or business environment. By formulizing a specific company's internal knowledge and terminology, the ontology programming accounts for linguistic meaning to surface relevant and important content for analysis. Based on the self-training mechanism developed by the inventors, the ontology programming automatically trains itself to understand the business environment by processing and analyzing a defined corpus of communication data. For example, the disclosed ontology programming adapts to the language used in a specific domain, including linguistic patterns and properties, such as word order, relationships between terms, and syntactical variations. The disclosed system and method further relates to leveraging the ontology to assess a dataset and conduct a funnel analysis to identify patterns, or sequences of events, in the dataset.

公开(公告)号：US09306971B2

公开(公告)日：2016-04-05

申请号：US14295758

申请日：2014-06-04

Applicant: Verint Systems, Ltd.

Inventor： Yuval Altman ,  Assaf Yosef Keren ,  Ido Krupkin

IPC: H04L29/06

CPC classification number: H04L63/1425 ,  G06N99/005 ,  H04L63/1441 ,  H04L63/145

Abstract: Malware detection techniques that detect malware by identifying the C&C communication between the malware and the remote host, and distinguish between communication transactions that carry C&C communication and transactions of innocent traffic. The system distinguishes between malware transactions and innocent transactions using malware identification models, which it adapts using machine learning algorithms. However, the number and variety of malicious transactions that can be obtained from the protected network are often too limited for effectively training the machine learning algorithms. Therefore, the system obtains additional malicious transactions from another computer network that is known to be relatively rich in malicious activity. The system is thus able to adapt the malware identification models based on a large number of positive examples—The malicious transactions obtained from both the protected network and the infected network. As a result, the malware identification models are adapted with high speed and accuracy.

Abstract translation: 通过识别恶意软件和远程主机之间的C＆C通信来检测恶意软件的恶意软件检测技术，并区分进行C＆C通信的通信事务和无害流量的交易。 该系统使用恶意软件识别模型区分恶意软件事务和无害事务，它使用机器学习算法进行调整。 然而，可以从受保护的网络获得的恶意交易的数量和种类往往太有限，以有效地训练机器学习算法。 因此，系统从已知相对较丰富的恶意活动的另一计算机网络获得额外的恶意事务。 因此，该系统能够基于大量正面示例来适应恶意软件识别模型 - 从受保护网络和受感染网络获得的恶意交易。 因此，恶意软件识别模型以高速度和准确度进行了调整。

公开(公告)号：US09185519B2

公开(公告)日：2015-11-10

申请号：US14167062

申请日：2014-01-29

Applicant: Verint Systems Ltd.

Inventor： Eithan Goldfarb

IPC: H04M1/00 ,  H04W4/02 ,  H04M1/725 ,  H04W40/00

CPC classification number: H04W4/026 ,  H04M1/72519 ,  H04W4/02 ,  H04W4/025 ,  H04W40/00 ,  H04W84/042 ,  H04W84/12 ,  H04W88/06

Abstract: Methods and systems for tracking mobile communication terminals based on their identifiers. The disclosed techniques identify cellular terminals and Wireless Local Area Network (WLAN) terminals that are likely to be carried by the same individual, or cellular and WLAN identifiers that belong to the same multi-mode terminal. A correlation system is connected to a cellular network and to a WLAN. The system receives location coordinates of cellular identifiers used by mobile terminals in the cellular network, and location coordinates of WLAN identifiers used by mobile terminals in the WLAN. Based on the location coordinates, the system is able to construct routes that are traversed by the terminals having the various cellular and WLAN identifiers. The system attempts to find correlations in time and space between the routes.

Abstract translation: 基于其标识符跟踪移动通信终端的方法和系统。 所公开的技术标识可能由属于相同多模终端的相同个人或蜂窝和WLAN标识符承载的蜂窝终端和无线局域网（WLAN）终端。 相关系统连接到蜂窝网络和WLAN。 系统接收移动终端在蜂窝网络中使用的蜂窝标识符的位置坐标，以及移动终端在WLAN中使用的WLAN标识符的位置坐标。 基于位置坐标，系统能够构建由具有各种蜂窝和WLAN标识符的终端遍历的路由。 系统尝试在路由之间找到时间和空间的相关性。