公开(公告)号：US12028478B2

公开(公告)日：2024-07-02

申请号：US17650868

申请日：2022-02-14

Applicant: CAPITAL ONE SERVICES, LLC

Inventor： Dwij Trivedi ,  Jennifer Lopez

IPC: G10L15/22 ,  G06F3/0481 ,  G10L25/51 ,  G10L25/72 ,  H04M3/22 ,  H04M3/42 ,  H04M3/436

CPC classification number: H04M3/2281 ,  G06F3/0481 ,  G10L15/22 ,  G10L25/51 ,  G10L25/72 ,  H04M3/2218 ,  H04M3/42102 ,  H04M3/42221 ,  H04M3/4365 ,  H04M2201/405

Abstract: Disclosed are methods and systems for voice phishing monitoring. For instance, a method includes receiving voice data of an incoming call to a communication device from an application associated with a user account and executing on the device, identifying an entity and interaction allegedly associated with the incoming call from the voice data, determining first fraud indicator data based on a number of the incoming call and second fraud indicator data based on a correspondence of user account interaction data to the entity and/or interaction, and providing the voice data to a trained machine learning system to receive third fraud indicator data based on content and/or a voice characteristic identified from the voice data. The method may further include determining a status for the incoming call of fraudulent or confirmed based on the first, second, and third fraud indicator data, and generating a notification indicating the status for display.

公开(公告)号：US20230410801A1

公开(公告)日：2023-12-21

申请号：US18208367

申请日：2023-06-12

Applicant: LIVEPERSON, INC.

Inventor： Amit Mishra

IPC: G10L15/22 ,  H04M3/58 ,  H04M3/51 ,  H04M3/42 ,  G10L15/18 ,  G10L15/06 ,  G10L15/30

CPC classification number: G10L15/22 ,  H04M3/58 ,  H04M3/5166 ,  H04M3/5175 ,  H04M3/42221 ,  G06F9/451 ,  G10L15/063 ,  G10L15/30 ,  H04M2201/405 ,  H04M2242/08 ,  G10L2015/0635 ,  G10L15/18

Abstract: The present disclosure relates generally to systems, methods, instructions, and other aspects describing automated transcription and associated script generation. In one aspect, a method includes facilitating a voice bot segment of a two-way communication session, where the voice bot segment is between a customer device and a non-human bot agent, and transfer of the session to a human agent device as part of a human voice segment of the two-way communication session, wherein the transfer occurs following a failure of the non-human bot agent to resolve a customer issue. Accessing survey data describing the two-way communication session, wherein the survey data is associated with successful resolution of the customer issue and automatically processing transcript data from the two-way communication with the survey data to identify language data from the transcript associated with resolution of the customer issue. The non-human bot agent is then dynamically updated using the language data.

公开(公告)号：US11825022B1

公开(公告)日：2023-11-21

申请号：US17974536

申请日：2022-10-27

Applicant: CS Sharing Inc.

Inventor： Ji Eun Lim

IPC: H04M3/00 ,  H04M3/51 ,  G06Q30/016

CPC classification number: H04M3/5175 ,  G06Q30/016 ,  H04M3/5133 ,  H04M3/5183 ,  H04M2201/405 ,  H04M2203/1025 ,  H04M2203/403

Abstract: Disclosed is an AI avatar coaching system based on a free speech emotion analysis for acting for CS managers. The AI avatar coaching system includes: an AI avatar coach server generating an AI avatar coach video for practical counseling training, and providing the generated AI avatar coach video; an educated/inexperienced counselor terminal receiving and outputting the AI avatar coach video provided from the AI avatar coach server; a purchase customer terminal performing a voice call for a counseling inquiry of a purchase customer; a counselor terminal performing the voice call for a counselor to perform counseling processing for the counseling inquiry of the purchase customer; and an omni channel customer/company consulting service server setting a voice call session for the voice call between the purchase customer terminal and the counselor terminal, and transmitting a report for the counseling inquiry and the counseling processing, in order to act for counseling services for multiple selling company customers. By the AI avatar coaching system based on a free speech emotion analysis for acting for CS managers, there is an effect that a counseling video of an experienced counselor is configured to be simulated into an avatar video and provided to educated/inexperienced counselors to learn a counseling/response method and effectively train the counselors through a specific practical cases.

公开(公告)号：US20180255180A1

公开(公告)日：2018-09-06

申请号：US15446646

申请日：2017-03-01

Applicant: Speech-Soft Solutions LLC

Inventor： Randy G. Goldberg ,  Deborah W. Brown ,  Janardhan P. Reddy

IPC: H04M3/493 ,  H04L12/58 ,  G10L15/26 ,  G10L15/22

CPC classification number: H04M3/4938 ,  G06F3/167 ,  G06F17/2765 ,  G10L15/19 ,  H04L51/02 ,  H04L51/046 ,  H04L51/066 ,  H04M2201/405 ,  H04M2203/254

Abstract: A bridging for using a non-voice-based user interface, such as a text chat interface, with a voice-enabled interactive voice response system which, during a non-voice-based communication session with a client user device, receives from the client user device, a non-voice entry entered by a client user into the communication session; identifies one or more elements in the non-voice entry constrained by one or more allowed responses by the voice-enabled interactive voice response system; maps the one or more elements to one or more of the allowed responses; and passes the mapped one or more identified elements to a voice-enabled interactive voice response system as a input via emulation of a voice recognition analysis response.

公开(公告)号：US09860381B1

公开(公告)日：2018-01-02

申请号：US14987884

申请日：2016-01-05

Applicant: West Corporation

Inventor： Silke Witt-ehsani ,  Aaron Scott Fisher

IPC: H04M1/64 ,  H04M3/523 ,  G10L15/08

CPC classification number: H04M3/5232 ,  G10L2015/088 ,  H04M3/4936 ,  H04M3/5166 ,  H04M2201/18 ,  H04M2201/405 ,  H04M2203/158 ,  H04M2203/556

Abstract: A method and apparatus of processing caller experiences is disclosed. One example method may include determining a call event type occurring during a call and assigning a weight to the call event type via a processing device. The method may also include calculating a caller experience metric value representing a caller's current call status responsive to determining the at least one call event type, the caller experience metric being a function of the current event type weight and a discounting variable that discounts a value of past events. The method may also provide comparing the caller experience metric to a predefined threshold value and determining whether to perform at least one of transferring the call to a live agent and switching from a current caller modality to a different caller modality.

公开(公告)号：US20170201625A1

公开(公告)日：2017-07-13

申请号：US15470824

申请日：2017-03-27

Applicant: Shanghai Xiaoi Robot Technology Co., Ltd.

Inventor： Bo LI ,  Di CHEN ,  Pinpin ZHU

IPC: H04M3/533 ,  H04M1/65 ,  H04M1/64

CPC classification number: H04M3/53333 ,  G10L15/22 ,  G10L25/33 ,  G10L2015/223 ,  H04M1/645 ,  H04M1/651 ,  H04M3/4938 ,  H04M3/53308 ,  H04M3/53366 ,  H04M2201/39 ,  H04M2201/40 ,  H04M2201/405 ,  H04M2201/41

Abstract: A method and a system for voice transmission control. The method comprises: receiving, by a voice answering device, a voice command and transmitting the voice command to a sound control server through a network data transmission channel; recognizing, by the sound control server, the voice command, generating corresponding second VXML control information based on a recognition result, and transmitting the second VXML control information to the voice answering device through the network data transmission channel; and performing, by the voice answering device, an operation according to the received second VXML control information. With this method, the architecture and workflow of the communication system can be simplified, and the difficulty of design thereof can be reduced.

公开(公告)号：US09641680B1

公开(公告)日：2017-05-02

申请号：US15134265

申请日：2016-04-20

Applicant: Eric Wold

Inventor： Eric Wold

IPC: H04M1/64 ,  H04M3/51 ,  H04M3/42 ,  H04W84/04 ,  A61B5/16 ,  H04W84/12

CPC classification number: H04M3/5141 ,  A61B5/167 ,  G06F17/30 ,  G06Q30/01 ,  G10L17/00 ,  H04M3/42221 ,  H04M3/5175 ,  H04M3/523 ,  H04M2201/405 ,  H04M2203/556 ,  H04W84/042 ,  H04W84/12

Abstract: Methods, systems, and devices for cross-linking events and persons using anonymized voice fingerprint identifiers (IDs) and call metadata are described. The method can include retrieving, form a centralized database, call metadata associated with a caller index ID. The method can include determining call metadata characteristics for the call metadata. The method can include matching the call metadata characteristics of the call metadata with characteristics associated with a personality type of a psychological behavioral model. The method can include generating a caller profile that comprises personality type information for the personality type. The method can include associating the caller profile with the caller index ID. The method can include storing the caller profile in an entry in the centralized database associated with the caller index ID.

公开(公告)号：US20170084272A1

公开(公告)日：2017-03-23

申请号：US15339619

申请日：2016-10-31

Applicant: Marchex, Inc.

Inventor： Jason Flaks ,  Ziad Ismail ,  Chris Kolbegger

IPC: G10L15/193 ,  G10L15/14 ,  H04M3/51 ,  G10L15/16

CPC classification number: G10L15/193 ,  G10L15/142 ,  G10L15/16 ,  G10L15/1822 ,  G10L2015/088 ,  H04M3/5175 ,  H04M2201/18 ,  H04M2201/40 ,  H04M2201/405 ,  H04M2203/6009 ,  H04M2242/12

Abstract: A facility and method for analyzing and classifying calls without transcription via keyword spotting is disclosed. The facility uses a group of calls having known outcomes to generate one or more domain- or entity-specific grammars containing keywords and related information that are indicative of particular outcome. The facility monitors telephone calls by determining the domain or entity associated with the call, loading the appropriate grammar or grammars associated with the determined domain or entity, and tracking keywords contained in the loaded grammar or grammars that are spoken during the monitored call, along with additional information. The facility performs a statistical analysis on the tracked keywords and additional information to determine a classification for the monitored telephone call.

公开(公告)号：US09571617B2

公开(公告)日：2017-02-14

申请号：US15168757

申请日：2016-05-31

Applicant: International Business Machines Corporation

Inventor： Roberto Battaglini ,  Brian P. Singer

IPC: H04M3/00 ,  H04M1/19 ,  H04M1/247 ,  G10L15/22 ,  G10L17/04 ,  G10L17/06 ,  G10L25/84 ,  H04M1/60

CPC classification number: H04M1/19 ,  G10L15/22 ,  G10L17/04 ,  G10L17/06 ,  G10L25/84 ,  G10L2015/223 ,  H04M1/247 ,  H04M1/6008 ,  H04M1/6033 ,  H04M2201/405 ,  H04M2203/258 ,  H04M2250/74

Abstract: A method for controlling a mute function in a telephone device, and the telephone device and a computer program product that implements the method. The method includes: while the mute function is active, voice recognition software in the telephone device processes sound detected by a microphone in the telephone device to recognize and identify one or more specific words as having been spoken by a specific person and not by another person, and in response, the telephone device activates an alarm in the telephone device to communicate that the mute function is active.

Abstract translation: 一种用于控制电话设备中的静音功能的方法，以及实现该方法的电话设备和计算机程序产品。 该方法包括：当静音功能激活时，电话设备中的语音识别软件处理由电话设备中的麦克风检测到的声音，以识别并识别一个或多个特定词语已被特定的人而不是另一个人所说 并且作为响应，电话设备激活电话设备中的报警，以通知静音功能是活动的。

公开(公告)号：US20160307583A1

公开(公告)日：2016-10-20

申请号：US15193517

申请日：2016-06-27

Applicant: Parus Holdings, Inc.

Inventor： Alexander Kurganov

IPC: G10L25/54 ,  H04M3/493 ,  G06F17/30 ,  H04L29/08 ,  G06F3/16 ,  G10L15/08

CPC classification number: H04M3/4938 ,  G06F3/167 ,  G06F17/30769 ,  G06F17/30861 ,  G10L13/08 ,  G10L15/02 ,  G10L15/06 ,  G10L15/08 ,  G10L15/22 ,  G10L15/26 ,  G10L17/24 ,  G10L25/54 ,  G10L2015/223 ,  H04L29/0809 ,  H04L67/02 ,  H04M2201/39 ,  H04M2201/40 ,  H04M2201/405 ,  H04M2207/40

Abstract: The present invention relates to a system for retrieving information from a network such as the Internet. A user creates a user-defined record in a database that identifies an information source, such as a web site, containing information of interest to the user. This record identifies the location of the information source and also contains a recognition grammar based upon a speech command assigned by the user. Upon receiving the speech command from the user that is described within the recognition grammar, a network interface system accesses the information source and retrieves the information requested by the user.

Abstract translation: 本发明涉及一种用于从诸如因特网的网络检索信息的系统。 用户在数据库中创建用户定义的记录，该记录标识包含用户感兴趣的信息的信息源（例如网站）。 该记录识别信息源的位置，并且还包含基于用户分配的语音命令的识别语法。 在接收到在识别语法中描述的用户的语音命令之前，网络接口系统访问信息源并检索用户请求的信息。