公开(公告)号：US11115529B2

公开(公告)日：2021-09-07

申请号：US16714586

申请日：2019-12-13

Applicant: Google LLC

Inventor： Amit Agarwal ,  Varun Soundararajan ,  Gaurav Bhaya

IPC: G06Q30/02 ,  H04M3/436 ,  H04M3/42 ,  H04M3/51 ,  H04M3/493

Abstract: Systems and methods for implementing an online content item campaign with selective call functionality can include a processor determining a rendering frequency of instances of a third-party content item for rendering with a call icon, based on a resource of the third-party content provider. The processor can provide a first instance of the content item for rendering with the call icon in accordance with the rendering frequency of instances. A call bridge device can receive a call from the client computing device upon actuation of the call icon, direct the call to a phone number of the third-party content provider, and determine a parameter of the call. The processor can adjust the rendering frequency of instances based on the parameter of the call and provide instances of the content item for display by client computing devices with the call icon in accordance with the adjusted rendering frequency of instances.

公开(公告)号：US11093692B2

公开(公告)日：2021-08-17

申请号：US15638304

申请日：2017-06-29

Applicant: GOOGLE LLC

Inventor： Boon-Lock Yeo ,  Xuemei Gu ,  Gangjiang Li ,  Gaurav Bhaya ,  Robert Stets

IPC: G06F40/134 ,  G06K9/00 ,  G06F16/432 ,  G06F16/583 ,  G06F40/279 ,  G06K9/46 ,  G06K9/62

Abstract: Systems and methods for extracting audiovisual features from images and other digital components. A data processing system can extract image data and image features from an input image. The data processing system can match the image features to the image features of a plurality of image to identify candidate images. A second image can be selected from the candidate images based on a request that the data processing system received with the input image.

公开(公告)号：US11087751B2

公开(公告)日：2021-08-10

申请号：US16063122

申请日：2017-12-08

Applicant: Google LLC

Inventor： Gaurav Bhaya ,  Tarun Jain ,  Anshul Kothari

IPC: G10L15/18 ,  G06F3/16 ,  H04L29/06 ,  G10L15/22 ,  H04L12/801 ,  G10L15/08

Abstract: A system of reducing transmissions of packetized data in a voice activated data packet based computer network environment is provided. A natural language processor component can parse an input audio signal to identify a request and a trigger keyword. Based on the input audio signal, a direct action application programming interface can generate a first action data structure, and a content selector component can select a content item. An interface management component can identify candidate interfaces and determine if prior instances of the packetized data was transmitted to the candidate interfaces. The interface management component can prevent the transmission of the packetized data if determined to be redundant, such as having previously received the data, and instead transmit it to a separate client device of a different device type.

公开(公告)号：US11011164B2

公开(公告)日：2021-05-18

申请号：US16107617

申请日：2018-08-21

Applicant: Google LLC

Inventor： Gaurav Bhaya ,  Ulas Kirazci ,  Bradley Abrams ,  Adam Coimbra ,  Ilya Firman ,  Carey Radebaugh

IPC: G10L15/22 ,  G10L15/18 ,  G10L15/30 ,  G06F40/216 ,  G06F40/30 ,  G06F16/901 ,  G06F40/35

Abstract: The present disclosure is generally directed to the generation of voice-activated data flows in interconnected network. The voice-activated data flows can include input audio signals that include a request and are detected at a client device. The client device can transmit the input audio signal to a data processing system, where the input audio signal can be parsed and passed to the data processing system of a service provider to fulfill the request in the input audio signal. The present solution is configured to conserve network resources by reducing the number of network transmissions needed to fulfill a request.

公开(公告)号：US20210125238A1

公开(公告)日：2021-04-29

申请号：US17139728

申请日：2020-12-31

Applicant: Google LLC

Inventor： Amit Agarwal ,  Surojit Chatterjee ,  Gaurav Bhaya ,  Anshul Kothari ,  Vibhor Nanavati

IPC: G06Q30/02 ,  H04L29/08

Abstract: The present disclosure is directed to systems and methods of providing content. A server can generate a request for a push content item for an account identifier linked with a computing device. The server can establish a push auction for the account identifier with multiple candidate push content items. The server can determine an auction score for each candidate push content item and select a push content item therefrom based on the auction score. The server can determine a parameter for the account identifier and control delivery of the selected push content item based on a delivery control policy. The server can compare a value of the parameter with a threshold value to authorize the push content item. The server can provide the selected and authorized push content item for presentation in a push content slot via the computing device linked to the account identifier.

公开(公告)号：US20210099511A1

公开(公告)日：2021-04-01

申请号：US17119563

申请日：2020-12-11

Applicant: Google LLC

Inventor： Gaurav Bhaya ,  Robert James Stets, JR.

IPC: H04L29/08 ,  G06F16/951 ,  G06F16/9032 ,  G10L15/26 ,  G06F40/279

Abstract: Systems and methods to combine multiple voice activated audio input data packets that indicate sequence dependent operations are provided. A natural language processor component can receive first and second input audio signal from a client computing device, and can identify respective requests and corresponding trigger keywords. A direct action application programming interface (“API”) can generate respective action data structures, and can construct respective data transmissions including the respective action data structures. A thread optimization component can obtain data packets of the first data transmission, and can obtain data packets of the second data transmission. The thread optimization component can determine, based on a heuristic technique applied to the data packets of the respective data transmissions a sequence dependency parameter. The thread optimization component can merge, based on a comparison of the sequence dependency parameter with a threshold, the first and second data transmissions into a single thread.

公开(公告)号：US10956485B2

公开(公告)日：2021-03-23

申请号：US15590861

申请日：2017-05-09

Applicant: GOOGLE LLC

Inventor： Wei-Hsin Lee ,  Jacob D. Schonberg ,  Chiu Wah Kelvin So ,  Jianfeng Shen ,  Gaurav Bhaya ,  Robert Stets

IPC: G06F16/00 ,  G06F16/48 ,  G06F16/432

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for retargeting content in a search environment. A method can include receiving a request for a content item to be provided with a search results page and determining that one or more retargeted content items are eligible for presentation with the search results page. Each retargeted content item is a content item that is eligible for presentation with the search results page based on: (1) the search query matching a targeting keyword for the retargeted content item, and (2) the user identifier matching a retargeted identifier that is included in a retargeting set for the retargeted content item. A responsive content item to be presented with the search results page is selected, based at least in part on bids that are associated with the retargeted content items, and data specifying the responsive content item are provided.

公开(公告)号：US10893088B2

公开(公告)日：2021-01-12

申请号：US16818736

申请日：2020-03-13

Applicant: Google LLC

Inventor： Gaurav Bhaya ,  Robert James Stets, Jr.

IPC: H01L29/08 ,  G06F16/951 ,  G06F16/9032 ,  G06F40/279 ,  G10L15/26 ,  H04L29/08

Abstract: Systems and methods to combine multiple voice activated audio input data packets that indicate sequence dependent operations are provided. A natural language processor component can receive first and second input audio signal from a client computing device, and can identify respective requests and corresponding trigger keywords. A direct action application programming interface (“API”) can generate respective action data structures, and can construct respective data transmissions including the respective action data structures. A thread optimization component can obtain data packets of the first data transmission, and can obtain data packets of the second data transmission. The thread optimization component can determine, based on a heuristic technique applied to the data packets of the respective data transmissions a sequence dependency parameter. The thread optimization component can merge, based on a comparison of the sequence dependency parameter with a threshold, the first and second data transmissions into a single thread.

公开(公告)号：US20200327121A1

公开(公告)日：2020-10-15

申请号：US16915231

申请日：2020-06-29

Applicant: Google LLC

Inventor： Gaurav Bhaya ,  Robert Stets

IPC: G06F16/2455 ,  G10L15/18 ,  G10L15/30 ,  G10L15/22 ,  G06F16/242

Abstract: Systems and methods of voice activated thread management in a voice activated data packet based environment are provided. A natural language processor (“NLP”) component can receive and parse data packets comprising a first input audio signal to identify a first request and a first trigger keyword. A direct action application programming interface (“API”) can generate a first action data structure with a parameter defining a first action. The NLP component can receive and parse a second input audio signal to identify a second request and a second trigger keyword, and can generate a second action data structure with a parameter defining a second action. A pooling component can generate the first and second action data structures into a pooled data structure, and can transmit the pooled data structure to a service provider computing device to cause it device to perform an operation defined by the pooled data structure.

公开(公告)号：US20200322396A1

公开(公告)日：2020-10-08

申请号：US16909375

申请日：2020-06-23

Applicant: Google LLC

Inventor： Justin Lewis ,  Richard Rapp ,  Gaurav Bhaya ,  Robert Stets

IPC: H04L29/06 ,  G06F9/50 ,  G06F9/451 ,  G10L15/18 ,  H04L12/721

Abstract: A system of multi-modal transmission of packetized data in a voice activated data packet based computer network environment is provided. A natural language processor component can parse an input audio signal to identify a request and a trigger keyword. Based on the input audio signal, a direct action application programming interface can generate a first action data structure, and a content selector component can select a content item. An interface management component can identify first and second candidate interfaces, and respective resource utilization values. The interface management component can select, based on the resource utilization values, the first candidate interface to present the content item. The interface management component can provide the first action data structure to the client computing device for rendering as audio output, and can transmit the content item converted for a first modality to deliver the content item for rendering from the selected interface.