Network computer system to generate voice response communications

Patent metadata

Field	Value
Publication number	US-2022199088-A1
Application number	US-202117563742-A
Country	US
Kind code	A1
Filing date	Dec 28, 2021
Priority date	Sep 4, 2018
Publication date	Jun 23, 2022
Grant date	—

Abstract

A network computer system for managing a network service (e.g., a transport service) can include a voice-assistant subsystem for generating dialogues and performing actions for service providers of the network service. The network computer system can receive, from a user device, a request for the network service. In response, the network computer system can identify a service provider and transmit an invitation to the provider device of the service provider. In response to the identification of the service provider for the request, the voice-assistant subsystem can trigger an audio voice prompt to be presented on the provider device and a listening period during which the provider device monitors for an audio input from the service provider. Based on the audio input captured by the provider device, the network computer system can determine an intent corresponding to whether the service provider accepts or declines the invitation.

First claim

What is claimed is:

1 . A network computer system comprising:
one or more processors; and one or more memory resources storing instructions that, when executed by the one or more processors, cause the network computer system to:
receive, from a requesting user device, a set of request data corresponding to a request for a location-based service;
identify a service provider from a plurality of service providers for the location-based service to potentially fulfill the request;
in response to identifying the service provider, transmit invitation data to a provider device associated with the service provider to trigger the provider device to (i) present a first voice prompt corresponding to the request, and (ii) initiate a listening period to capture an audio input from the service provider;
receive, from the provider device, a set of response data based on the audio input;
determine, based on the set of response data, whether the service provider accepts or declines the request; and
in response to determining that the service provider accepts the request, assign the service provider to fulfill the request.

2 . The network computer system of claim 1 , wherein the instructions, when executed by the one or more processors of the network computer system, cause the network computer system to cause the network computer system to present a navigation user interface.

3 . The network computer system of claim 1 , wherein the instructions, when executed by the one or more processors of the network computer system, cause the network computer system to cause the provider device to present a second voice prompt regarding the request.

4 . The network computer system of claim 3 , wherein the second voice prompt communicates a pickup location of the request.

5 . The network computer system of claim 3 , wherein the second voice prompt communicates a message from the requesting user device.

6 . The network computer system of claim 1 , wherein the instructions, when executed by the one or more processors of the network computer system, cause the network computer system obtain information about the service provider's current session with the location-based service, wherein the first voice prompt includes a personalized prompt for the service provider.

7 . The network computer system of claim 6 , wherein the personalized prompt for the service provider is regarding a milestone.

8 . The network computer system of claim 1 , wherein the instructions, when executed by the one or more processors of the network computer system, cause the network computer system to determine, based on the set of response data, a confidence score.

9 . The network computer system of claim 8 , wherein determining whether the service provider accepts or declines the request is based on the confidence score.

10 . The network computer system of claim 8 , wherein the instructions, when executed by the one or more processors of the network computer system, cause the network computer system to, in response to the confidence score being below a threshold value, cause the provider device to present a second voice prompt corresponding to the request.

11 . The network computer system of claim 8 , wherein the instructions, when executed by the one or more processors of the network computer system, cause the network computer system to, in response to the confidence score being above a low threshold value but below a high threshold value, cause the provider device to present a second voice prompt to confirm that the service provider accepts the request.

12 . A computer-implemented method comprising:
receiving, from a requesting user device, a set of request data corresponding to a request for a location-based service; identifying a service provider from a plurality of service providers for the location-based service to potentially fulfill the request; in response to identifying the service provider, transmitting invitation data to a provider device associated with the service provider to trigger the provider device to (i) present a first voice prompt corresponding to the request, and (ii) initiate a listening period to capture an audio input from the service provider; receiving, from the provider device, a set of response data based on the audio input; determining, based on the set of response data, whether the service provider accepts or declines the request; and in response to determining that the service provider accepts the request, assigning the service provider to fulfill the request.

13 . The computer-implemented method of claim 12 , further comprising causing the network computer system to cause the network computer system to present a navigation user interface.

14 . The computer-implemented method of claim 12 , further comprising causing the network computer system to cause the provider device to present a second voice prompt regarding the request.

15 . The computer-implemented method of claim 14 , wherein the second voice prompt communicates a pickup location of the request.

16 . The computer-implemented method of claim 14 , wherein the second voice prompt communicates a message from the requesting user device.

17 . The computer-implemented method of claim 12 , further comprising causing the network computer system obtain information about the service provider's current session with the location-based service, wherein the first voice prompt includes a personalized prompt for the service provider.

18 . The computer-implemented method of claim 12 , further comprising causing the network computer system to determine, based on the set of response data, a confidence score.

19 . The computer-implemented method of claim 18 , wherein determining whether the service provider accepts or declines the request is based on the confidence score.

20 . A non-transitory computer-readable medium storing instructions that, when executed by one or more processors of a network computer system, cause the network computer system to:
receive, from a requesting user device, a set of request data corresponding to a request for a location-based service; identify a service provider from a plurality of service providers for the location-based service to potentially fulfill the request; in response to identifying the service provider, transmit invitation data to a provider device associated with the service provider to trigger the provider device to (i) present a first voice prompt corresponding to the request, and (ii) initiate a listening period to capture an audio input from the service provider; receive, from the provider device, a set of response data based on the audio input; determine, based on the set of response data, whether the service provider accepts or declines the request; and in response to determining that the service provider accepts the request, assign the service provider to fulfill the request.

Assignees

• Uber Technologies Inc

Inventors

• Goldstein Lawrence Benjamin
• Vora Arjun
• Tur Gokhan
• Mundhe Manisha
• Yang Xiaochao

Classifications

• G10L15/26 Primary

  Speech to text systems (G10L15/08 takes precedence) · CPC title

• G10L15/22

  Procedures used during a speech recognition process, e.g. man-machine dialogue · CPC title

• G10L2015/223

  Execution procedure of a spoken command · CPC title

• G06F3/167

  Audio in a user interface, e.g. using voice commands for navigating, audio feedback · CPC title

• G06Q10/02 Primary

  Reservations, e.g. for tickets, services or events · CPC title