公开(公告)号：US12033258B1

公开(公告)日：2024-07-09

申请号：US16894680

申请日：2020-06-05

Applicant: Meta Platforms Technologies, LLC

Inventor： Maheen Sohail ,  Hyunbin Park ,  Ruoni Wang ,  Vincent Charles Cheung

IPC: G06T13/20 ,  G06F3/01 ,  G06Q50/00 ,  G10L15/183 ,  G10L15/26 ,  G10L21/10 ,  H04M11/10

CPC classification number: G06T13/205 ,  G06F3/011 ,  G06F3/017 ,  G06Q50/01 ,  G10L15/183 ,  G10L15/26 ,  G10L21/10 ,  H04M11/10

Abstract: A conversation augmentation system can automatically augment a conversation with content items based on natural language from the conversation. The conversation augmentation system can select content items to add to the conversation based on determined user “intents” generated using machine learning models. The conversation augmentation system can generate intents for natural language from various sources, such as video chats, audio conversations, textual conversations, virtual reality environments, etc. The conversation augmentation system can identify constraints for mapping the intents to content items or context signals for selecting appropriate content items. In various implementations, the conversation augmentation system can add selected content items to a storyline the conversation describes or can augment a platform in which an unstructured conversation is occurring.

公开(公告)号：US12003671B2

公开(公告)日：2024-06-04

申请号：US17191668

申请日：2021-03-03

Applicant: Zoom Video Communications, Inc.

Inventor： Melinda Min Xiao-Devins ,  Haifeng Geng ,  Mengxiao Qian ,  Fengcai Sun ,  Hui Wen

IPC: H04M11/10 ,  H04M1/663 ,  H04M3/436 ,  H04M3/533

CPC classification number: H04M3/53366 ,  H04M1/663 ,  H04M3/436 ,  H04M3/5335

Abstract: Voicemail spam detection is performed based on content of voicemail messages. The content of an incoming voicemail message is compared to a spam template that includes a representation of a spam voicemail. Spam templates may be generated based on spam indications provided by users for voicemail messages they have received. User indications for sufficiently similar voicemail messages may be aggregated by maintaining a vote count for a spam template that reflects how many times a user has indicated a matching voicemail message is spam. A spam template may also include an occurrence count that reflects how many times voicemail messages matching a spam template have been detected in a telephony system. An incoming voicemail message may be compared to spam templates and, responsive to a match of content and/or a corresponding vote count or occurrence count meeting a condition, the voicemail message may be identified as spam.

公开(公告)号：US20240073320A1

公开(公告)日：2024-02-29

申请号：US18388042

申请日：2023-11-08

Applicant: Express Scripts Strategic Development, Inc.

Inventor： Christopher M. Myers ,  Danielle L. Smith

IPC: H04M3/523 ,  G06N3/049 ,  G10L15/26 ,  H04M3/493 ,  H04M3/51 ,  H04M11/10

CPC classification number: H04M3/5233 ,  G06N3/049 ,  G10L15/26 ,  H04M3/4933 ,  H04M3/4936 ,  H04M3/5175 ,  H04M3/5191 ,  H04M3/5237 ,  H04M11/10

Abstract: Method starts with a processor receiving configuration settings including an identified task, a relationship data, and a criticality value. Processor initializes a communication session with an agent client device. The communication session is between a virtual caller associated with the system and the agent client device. Processor then processes an audio signal of the communication session to generate an agent utterance and generates a transcribed agent utterance based on the agent utterance using a speech-to-text processor. Processor generates a virtual caller utterance using a task-specific virtual caller neural network associated with the identified task. The virtual caller utterance can be generated based on the transcribed agent utterance. Processor then causes the virtual caller utterance to be played back in the communication session to the agent client device. Other embodiments are disclosed herein.

公开(公告)号：US20220407963A1

公开(公告)日：2022-12-22

申请号：US17895652

申请日：2022-08-25

Applicant: Express Scripts Strategic Development, Inc.

Inventor： Christopher M. Myers ,  Danielle L. Smith

IPC: H04M3/523 ,  H04M3/493 ,  H04M3/51 ,  G06N3/04 ,  H04M11/10 ,  G10L15/26

Abstract: Method starts with a processor receiving configuration settings including an identified task, a relationship data, and a criticality value. Processor initializes a communication session with an agent client device. The communication session is between a virtual caller associated with the system and the agent client device. Processor then processes an audio signal of the communication session to generate an agent utterance and generates a transcribed agent utterance based on the agent utterance using a speech-to-text processor. Processor generates a virtual caller utterance using a task-specific virtual caller neural network associated with the identified task. The virtual caller utterance can be generated based on the transcribed agent utterance. Processor then causes the virtual caller utterance to be played back in the communication session to the agent client device. Other embodiments are disclosed herein.

公开(公告)号：US20220292218A1

公开(公告)日：2022-09-15

申请号：US17687983

申请日：2022-03-07

Applicant: State Farm Mutual Automobile Insurance Company

Inventor： Kimberly Zarecki ,  Kevin Lucht ,  Srinivasarao Kosaraju ,  Nagasudha Ravinuthala ,  Satya Ravinuthala ,  Donna Gerig

IPC: G06F21/62 ,  G06F40/166 ,  G06K9/62 ,  H04M11/10

Abstract: Various techniques described herein relate to analyzing and redacting information from customer interaction records such as call transcripts, to support transmission of the interaction records from a secured environment to various external analytics systems. Transcript texts may be received and processed by a redaction system, during which the transcript texts may be analyzed to generate conversations and convert numerical texts into numbers. One or more regular expressions defining search and replace patterns may be selected and used to redact confidential or sensitive information from the transcripts. In various implementations, the regular expressions used to redact transcripts may be determined or generated based on transcript categorization, the security characteristics of the transmission networks and/or external systems to which the redacted transcripts are to be transmitted, and/or other attributes of the transcript or the associated systems.

公开(公告)号：US11445068B1

公开(公告)日：2022-09-13

申请号：US16798082

申请日：2020-02-21

Applicant: Express Scripts Strategic Development, Inc.

Inventor： Christopher M. Myers ,  Danielle L. Smith

IPC: H04M3/523 ,  H04M3/493 ,  H04M3/51 ,  G06N3/04 ,  H04M11/10 ,  G10L15/26

Abstract: Method starts with a processor receiving configuration settings including an identified task, a relationship data, and a criticality value. Processor initializes a communication session with an agent client device. The communication session is between a virtual caller associated with the system and the agent client device. Processor then processes an audio signal of the communication session to generate an agent utterance and generates a transcribed agent utterance based on the agent utterance using a speech-to-text processor. Processor generates a virtual caller utterance using a task-specific virtual caller neural network associated with the identified task. The virtual caller utterance can be generated based on the transcribed agent utterance. Processor then causes the virtual caller utterance to be played back in the communication session to the agent client device. Other embodiments are disclosed herein.

公开(公告)号：US20220005052A1

公开(公告)日：2022-01-06

申请号：US17481094

申请日：2021-09-21

Applicant: NICE Ltd.

Inventor： Steven Richard ARNOLD ,  Katie Truong ,  Robert William Morris

IPC: G06Q30/00 ,  G06N20/10 ,  H04M3/493 ,  H04M3/523 ,  H04M11/10 ,  G10L15/16 ,  H04M3/51

Abstract: A computer based system and method for identifying complaint interactions, including: detecting appearances of linguistic structures related to complaints in an interaction; calculating at least one sentiment metric of the interaction; and classifying the interaction as being or not being a complaint interaction based on the detected linguistic structures and the at least one sentiment metric, for example using a trained supervised learning model.

公开(公告)号：US11196872B2

公开(公告)日：2021-12-07

申请号：US17108174

申请日：2020-12-01

Applicant: Bullhead Innovations Ltd.

Inventor： Peter S. Warrick

IPC: H04M11/00 ,  G10L13/04 ,  G06F3/16 ,  G10L15/26 ,  H04L12/66 ,  G05B19/042 ,  G06Q50/12 ,  H04M11/10

Abstract: A data gate apparatus for integrating functionalities of an interface format into a plurality of services. The data gate comprises a storage device, a communication interface and a processor coupled to the storage device and the communication interface. The processor detects a device supporting a first interface format that is different than the interface formats stored in the storage device. The processor learns the first interface format by receiving data function in the first interface format and associating a field in the data function with a variable representing information of a particular type. The processor verifies that the first interface format has been successfully learnt by generating a message in the first interface format and sending the message to the device. The processor receives a response to the message and parses the response to thereby confirm that the first interface format is functional and integrable into the plurality of services.

公开(公告)号：US11076052B2

公开(公告)日：2021-07-27

申请号：US15548265

申请日：2016-02-03

Applicant: DOLBY LABORATORIES LICENSING CORPORATION

Inventor： Richard J. Cartwright ,  Xuejing Sun

IPC: H04M11/10 ,  H04L29/06 ,  H04M3/56 ,  G10L21/043 ,  G10L15/02 ,  G10L15/22 ,  G10L21/04

Abstract: Various disclosed implementations involve processing and/or playback of a recording of a conference involving a plurality of conference participants. Some implementations disclosed herein involve receiving audio data corresponding to a recording of at least one conference involving a plurality of conference participants. In some examples, only a portion of the received audio data will be selected as playback audio data. The selection process may involve a topic selection process, a talkspurt filtering process and/or an acoustic feature selection process. Some examples involve receiving an indication of a target playback time duration. Selecting the portion of audio data may involve making a time duration of the playback audio data within a threshold time difference of the target playback time duration.

公开(公告)号：US20210133765A1

公开(公告)日：2021-05-06

申请号：US16668391

申请日：2019-10-30

Applicant: Talkdesk, Inc.

Inventor： Jafar Adibi ,  Tiago Paiva ,  Bruno Antunes

IPC: G06Q30/00 ,  H04M3/493 ,  H04M3/51 ,  H04M3/523 ,  G06Q50/00 ,  H04M11/10 ,  G10L15/26 ,  G10L15/18

Abstract: A Virtual agent that is a fully automated computer software solution that can engage with real people, customers, clients and even other agents. Virtual agents have personality with animation and engage with the customer via text or voice or a combination of both as an actual person. Virtual agents are able to answer customer questions and provide information to address their issues. Virtual agents transfer calls to live agents if they cannot address customer issues.