公开(公告)号：US11263277B1

公开(公告)日：2022-03-01

申请号：US16177639

申请日：2018-11-01

申请人： Igor Podgorny ,  Faraz Sharafi ,  Matthew Cannon ,  Pratik Desai

发明人： Igor Podgorny ,  Faraz Sharafi ,  Matthew Cannon ,  Pratik Desai

IPC分类号： G06F7/00 ,  G06F17/30 ,  G06F16/9535 ,  G06N20/00 ,  G06F16/242 ,  G06F16/901

摘要： A method for executing a computerized query includes receiving a new query from a user device. The query includes natural language text. Based on a type of user, and using an alternative term generator, a selected data model is selected from among pre-determined data models. The selected data model is particular to the type of user. Each of the pre-determined data models includes a corresponding semantic graph data model that establishes semantic relationships between words. Query words in the natural language text are compared to the selected data model using the alternative term generator to find at least one alternative term. The alternative term has a semantic relationship to a query word in query words. The semantic relationship exceeds a first threshold value. The alternative term is substituted for a query word to form a revised query. The revised query is executed on a search engine using the alternative terms.

公开(公告)号：US11017167B1

公开(公告)日：2021-05-25

申请号：US16024550

申请日：2018-06-29

申请人： Igor Podgorny ,  Faraz Sharafi ,  Matthew Cannon ,  Pavlo Malynin ,  Jeff Geisler ,  Yason Khaburzaniya ,  Greg Coulombe

发明人： Igor Podgorny ,  Faraz Sharafi ,  Matthew Cannon ,  Pavlo Malynin ,  Jeff Geisler ,  Yason Khaburzaniya ,  Greg Coulombe

IPC分类号： G06F40/232 ,  G06N3/08 ,  G06K9/62 ,  G06N20/00 ,  G06F16/951

摘要： The invention relates to a method. The method includes receiving a flawed input comprising a domain specific misspelling. The method further includes encoding, by an encoder machine learning model executing on a computer processor, the flawed input on a per character basis to create a context vector. The method further includes decoding, by a decoder machine learning model executing on the computer processor, the context vector on the per character basis to create a rephrased input lacking the domain specific misspelling. The method further includes presenting the rephrased input.

公开(公告)号：US10810378B2

公开(公告)日：2020-10-20

申请号：US16170585

申请日：2018-10-25

申请人： Igor Podgorny ,  Faraz Sharafi ,  Matthew Cannon ,  Vitor Carvalho

发明人： Igor Podgorny ,  Faraz Sharafi ,  Matthew Cannon ,  Vitor Carvalho

IPC分类号： G06F40/30 ,  G06N3/08 ,  H04L29/08 ,  G06F16/2457

摘要： A method for decoding a natural language user query involves obtaining the user query submitted by a user, segmenting the user query into words, generating a character embedding for each of the words, and generating a word embedding for each of the words. The method further involves obtaining a clickstream from tracked clicks of the user, generating a clickstream embedding from the clickstream, and for each of the words, generating a unified feature representation based on the character embedding and the word embedding for each of the words, and the clickstream embedding. The method also involves decoding the unified feature representations to obtain a decoded user query, and processing the user query using the decoded user query.

公开(公告)号：US20200134019A1

公开(公告)日：2020-04-30

申请号：US16170585

申请日：2018-10-25

申请人： Igor Podgorny ,  Faraz Sharafi ,  Matthew Cannon ,  Vitor Carvalho

发明人： Igor Podgorny ,  Faraz Sharafi ,  Matthew Cannon ,  Vitor Carvalho

IPC分类号： G06F17/27 ,  H04L29/08 ,  G06N3/08 ,  G06F17/30

摘要： A method for decoding a natural language user query involves obtaining the user query submitted by a user, segmenting the user query into words, generating a character embedding for each of the words, and generating a word embedding for each of the words. The method further involves obtaining a clickstream from tracked clicks of the user, generating a clickstream embedding from the clickstream, and for each of the words, generating a unified feature representation based on the character embedding and the word embedding for each of the words, and the clickstream embedding. The method also involves decoding the unified feature representations to obtain a decoded user query, and processing the user query using the decoded user query.

公开(公告)号：US08443403B2

公开(公告)日：2013-05-14

申请号：US12554126

申请日：2009-09-04

申请人： David G. Bell ,  Matthew Cannon ,  Chad Enney ,  Tom Gonder

发明人： David G. Bell ,  Matthew Cannon ,  Chad Enney ,  Tom Gonder

IPC分类号： H04N7/16 ,  H04M3/533

CPC分类号： H04N21/478 ,  H04M1/2473 ,  H04M3/5315 ,  H04M3/533 ,  H04M3/53333 ,  H04M7/1215 ,  H04M2201/60 ,  H04N21/234336 ,  H04N21/254 ,  H04N21/8106

摘要： Methods and apparatus for retrieving and providing voice mail messages from a server are described. In accordance with the invention voice mail messages may be retrieved via requests made via a set top box. Voice mail messages are retrieved in response to the request from a voice mail server which is also accessible via the telephone network. Retrieved voice mail is transcoded and included in a video on demand (VOD) file. Text, call ID information and/or other information as, e.g., an automatically generated transcript of the voice mail message, may be included in the VOD file. The VOD file is supplied to a VOD server which provides the file including the message to the set top box for display. A user can view the messages and switch from viewing one message to the next by using video play back commands.

摘要翻译： 描述了从服务器检索和提供语音邮件消息的方法和装置。 根据本发明，可以经由机顶盒发出的请求来检索语音邮件消息。 响应于也可以经由电话网络访问的语音邮件服务器的请求来检索语音邮件消息。 检索的语音邮件被转码并包括在视频点播（VOD）文件中。 文本，呼叫ID信息和/或诸如语音邮件消息的自动生成的记录的其他信息可以被包括在VOD文件中。 VOD文件提供给VOD服务器，该服务器将包含消息的文件提供给机顶盒进行显示。 用户可以通过使用视频播放命令查看消息并从查看一个消息切换到下一个消息。

公开(公告)号：US20080246605A1

公开(公告)日：2008-10-09

申请号：US12060855

申请日：2008-04-01

申请人： Howard Pfeffer ,  Matthew Cannon

发明人： Howard Pfeffer ,  Matthew Cannon

IPC分类号： G08B21/00 ,  G06F17/30 ,  H04M3/00

CPC分类号： H04M3/38 ,  G06Q10/06 ,  G06Q10/107 ,  H04M3/436 ,  H04M7/0033

摘要： Methods and apparatus for supporting real time parental screening of a variety of different types of communications which may be directed to or sent from children are described. The methods and apparatus may be used with voice, text messaging and/or E-mail communications individually or as part of a unified parental control system. Parents can set restrictions preventing text messages, E-mails and/or voice calls being sent to or received from particular individuals, sources or destinations. In addition, parents can configure the system to support real time parental screening of individual communications, e.g., messages or calls, with the parent being provided a real time notification of an incoming or outgoing communication and the parent being provided an opportunity to control in real time the disposition of the individual communication. Disposition options may include blocking an outgoing or incoming call, video communication such as point to point video, text message, or E-mail, or sending the communication to a storage device, e.g., voice mail system.

摘要翻译： 描述了用于支持可以针对或从儿童发送的各种不同类型的通信的实时家长筛选的方法和装置。 方法和装置可以单独使用语音，文本消息和/或电子邮件通信，或者作为统一的家长控制系统的一部分使用。 父母可以设置限制短信，电子邮件和/或语音呼叫被发送到或从特定个人，来源或目的地接收的限制。 此外，父母可以配置系统以支持对个人通信的实时家长筛选，例如消息或呼叫，父母被提供给来信或传出通信的实时通知，并且父母被提供实时控制的机会 时间处理个人沟通。 处置选项可以包括阻止传出或传入呼叫，诸如点对点视频，文本消息或电子邮件的视频通信，或者将通信发送到诸如语音邮件系统的存储设备。

公开(公告)号：US07151822B2

公开(公告)日：2006-12-19

申请号：US10867869

申请日：2004-06-15

申请人： Steven R. Donovan ,  Matthew Cannon ,  John Hearty

发明人： Steven R. Donovan ,  Matthew Cannon ,  John Hearty

IPC分类号： H04M1/64 ,  H04M11/00 ,  H04L12/66

CPC分类号： H04L65/1069 ,  H04L12/66 ,  H04L29/06027 ,  H04L65/1006 ,  H04L65/1009 ,  H04L65/4007 ,  H04M3/5166 ,  H04M3/5191 ,  H04M2207/203

摘要： An approach for processing voice calls over a packet switched network as to efficiently utilize the functionalities of a Voice Response Unit (VRU). According to one embodiment, a call originator, acting as a User Agent Client in accordance with the Session Initiation Protocol (SIP), issues messages to establish a first call-leg with the VRU. The VRU performs digit collection to obtain information to authenticate the call originator and to authorize the voice call. Based upon the issued messages from the call originator, the VRU establishes a second call-leg with the call terminator. The VRU is released from the voice call after binding the call-legs to connect the call originator to the call terminator.

公开(公告)号：US20060115062A1

公开(公告)日：2006-06-01

申请号：US11001444

申请日：2004-12-01

申请人： Tom Gonder ,  Scott Ramsdell ,  Howard Pfeffer ,  Matthew Cannon ,  James Balasalle ,  Albert Straub

发明人： Tom Gonder ,  Scott Ramsdell ,  Howard Pfeffer ,  Matthew Cannon ,  James Balasalle ,  Albert Straub

IPC分类号： H04M15/06 ,  H04M3/42

CPC分类号： H04M3/42042 ,  H04M15/06 ,  H04M15/56 ,  H04M15/63 ,  H04M15/8292 ,  H04M2215/202

摘要： A system and method for providing caller ID in a multi-region cable network. Caller identifying (CID) information of an incoming VoIP call is provided to a digital telephone subscriber through a video termination device (VTD) using a path that is different from the path by which the VoIP call packets are delivered to the digital telephone subscriber. The telephone number of a digital telephone subscriber is associated with the IP address and/or MAC address of the subscriber's VTD. The called number of the incoming VoIP call is used to select the VTD to which the CID information is delivered. A message is then sent through an out-of-band to the digital telephone subscriber's VTD comprising the CID information for display on video display equipment. Alternatively, the VTD is DOCSIS-compliant and a message is addressed to the VTD using the IP address of the VTD DOCSIS modem.

公开(公告)号：US06512818B1

公开(公告)日：2003-01-28

申请号：US09441438

申请日：1999-11-17

申请人： Steven R. Donovan ,  Matthew Cannon ,  John Hearty

发明人： Steven R. Donovan ,  Matthew Cannon ,  John Hearty

IPC分类号： H04M1100

CPC分类号： H04L65/1069 ,  H04L12/66 ,  H04L29/06027 ,  H04L65/1006 ,  H04L65/1009 ,  H04L65/4007 ,  H04M3/5166 ,  H04M3/5191 ,  H04M2207/203

摘要： An approach for processing voice calls over a packet switched network as to efficiently utilize the functionalities of a Voice Response Unit (VRU). According to one embodiment, a call originator, acting as a User Agent Client in accordance with the Session Initiation Protocol (SIP), issues messages to establish a first call-leg with the VRU. The VRU performs digit collection to obtain information to authenticate the call originator and to authorize the voice call. Based upon the issued messages from the call originator, the VRU establishes a second call-leg with the call terminator. The VRU is released from the voice call after binding the call-legs to connect the call originator to the call terminator.

公开(公告)号：US09398261B1

公开(公告)日：2016-07-19

申请号：US13554728

申请日：2012-07-20

申请人： Howard Pfeffer ,  Matthew Cannon

发明人： Howard Pfeffer ,  Matthew Cannon

IPC分类号： H04N7/14 ,  H04N7/15

CPC分类号： H04N7/147 ,  G06F3/017 ,  H04L12/1813 ,  H04L12/1822 ,  H04L65/00 ,  H04L65/1093 ,  H04M3/567 ,  H04N7/15 ,  H04N7/157 ,  H04N21/4788 ,  H04N21/64753

摘要： A flip signal is received from a first device, at a signaling server, during a video chat between the first device and a second device. The flip signal indicates that media packets from the second device intended for the first device are to be sent to a third device. Responsive to the signaling server receiving the flip signal, the signaling server sends a call request to the third device; and the signaling server sends a message to the second device to cause the second device to send the media packets to the third device. In another aspect, at the first device, during the video chat, a gesture is detected which indicates that media packets from the second device intended for the first device are to be sent to the third device; and, responsive to the detecting, the flip signal is sent.

摘要翻译： 在第一设备和第二设备之间的视频聊天期间，在信令服务器处，从第一设备接收翻转信号。 翻转信号指示来自第一设备的第二设备的媒体分组将被发送到第三设备。 响应于信令服务器接收翻转信号，信令服务器向第三设备发送呼叫请求; 并且信令服务器向第二设备发送消息以使得第二设备将媒体分组发送到第三设备。 在另一方面，在第一设备中，在视频聊天期间，检测到指示来自第一设备的第二设备的媒体分组将被发送到第三设备的手势; 并且响应于检测，发送翻转信号。