公开(公告)号：US20220360665A1

公开(公告)日：2022-11-10

申请号：US17869151

申请日：2022-07-20

Applicant: Google LLC

Inventor： Shi Lu ,  Jun Yin ,  Ji Yang

IPC: H04M3/42 ,  H04M3/22 ,  H04W4/16

Abstract: Implementations described herein relate to methods, systems, and computer-readable media to label incoming phone calls. A method to label an incoming phone call includes detecting the incoming phone call associated with a caller identifier (ID), determining a location associated with the call, and analyzing a call header of the call to determine one or more call characteristics. The method further includes determining, based on the location and the call characteristics, if the location is spoofed and determining, based on the caller ID and the call characteristics, if an access network associated with the call is spoofed. The method further includes applying a trained machine learning model to determine whether the call is a robocall. The method further includes assigning a label to the call that indicates whether the call is a spoofed call or is the robocall and sending the label to a callee device associated with the call.

公开(公告)号：US11425240B2

公开(公告)日：2022-08-23

申请号：US17258738

申请日：2020-08-25

Applicant: Google LLC

Inventor： Shi Lu ,  Jun Yin ,  Ji Yang

IPC: H04M3/42 ,  H04W4/16 ,  H04M3/22

Abstract: Implementations described herein relate to methods, systems, and computer-readable media to label incoming phone calls. A method to label an incoming phone call includes detecting the incoming phone call associated with a caller identifier (ID), determining a location associated with the call, and analyzing a call header of the call to determine one or more call characteristics. The method further includes determining, based on the location and the call characteristics, if the location is spoofed and determining, based on the caller ID and the call characteristics, if an access network associated with the call is spoofed. The method further includes applying a trained machine learning model to determine whether the call is a robocall. The method further includes assigning a label to the call that indicates whether the call is a spoofed call or is the robocall and sending the label to a callee device associated with the call.

公开(公告)号：US20210250438A1

公开(公告)日：2021-08-12

申请号：US16973977

申请日：2018-07-16

Applicant: Google LLC

Inventor： Shi Lu ,  Sathish Karunakaran ,  Naveen Kalla

IPC: H04M1/72403 ,  G06F3/16 ,  G06F3/0482 ,  H04M3/493 ,  G06Q20/32 ,  G06N20/00

Abstract: A system is described including a mobile device that receives a user request to initiate a phone call to an entity associated with an interactive-voice-response (IVR) interface of an IVR system. The system obtains information about a hierarchy of options associated with the interactive-voice-response system and causes a graphical user interface (GUI) for navigating the hierarchy of options associated with the interactive-voice-response system to be displayed at the mobile device. The system converts user inputs associated with the GUI to inputs recognized by the IVR system and the mobile device outputs, to the entity, the converted inputs and other information required by the entity to perform an operation based on the inputs. In response, the system updates the GUI based on additional information received from the IVR system.

公开(公告)号：US20220124195A1

公开(公告)日：2022-04-21

申请号：US17258738

申请日：2020-08-25

Applicant: Google LLC

Inventor： Shi Lu ,  Jun Yin ,  Ji Yang

IPC: H04M3/42 ,  H04M3/22 ,  H04W4/16

Abstract: Implementations described herein relate to methods, systems, and computer-readable media to label incoming phone calls. A method to label an incoming phone call includes detecting the incoming phone call associated with a caller identifier (ID), determining a location associated with the call, and analyzing a call header of the call to determine one or more call characteristics. The method further includes determining, based on the location and the call characteristics, if the location is spoofed and determining, based on the caller ID and the call characteristics, if an access network associated with the call is spoofed. The method further includes applying a trained machine learning model to determine whether the call is a robocall. The method further includes assigning a label to the call that indicates whether the call is a spoofed call or is the robocall and sending the label to a callee device associated with the call.