US2017236515A1PendingUtilityA1

Model for Enabling Service Providers to Address Voice-Activated Commands

47
Assignee: GOOGLE INCPriority: Jul 25, 2013Filed: Apr 30, 2017Published: Aug 17, 2017
Est. expiryJul 25, 2033(~7 yrs left)· nominal 20-yr term from priority
G10L 15/22G10L 2015/223G06F 3/0482G06F 3/167G10L 15/02G06Q 30/0269G06Q 30/0275G06F 3/013G06F 3/0484G02B 2027/0178G02B 2027/0138G02B 2027/014G02B 27/0172G06F 3/04842G10L 15/26
47
PatentIndex Score
0
Cited by
0
References
0
Claims

Abstract

Methods and systems are described herein related to enabling service providers to address voice-activated commands. An example method may involve: receiving a first utterance on a computing device, where the first utterance includes a first command; selecting a service action corresponding to the first command; determining a selected service provider for the selected service action, where the selected service provider is selected from a plurality of service providers; and sending a service fulfillment request to the selected service provider to execute the selected service action.

Claims

exact text as granted — not AI-modified
We claim: 
     
         1 . A method comprising:
 determining, by a computing device, for each respective service action of a plurality of service actions requiring fulfillment by third-party service providers, a respective third-party service provider that will receive future requests to execute the respective service action, wherein the respective third-party service provider is determined based on a plurality of bids received from a plurality of third-party service providers for a right to execute the respective service action;   at a first time, caching on the computing device, for each respective service action, the respective third-party service provider that will receive the future requests to execute the respective service action;   at a second time later than the first time, receiving, by the computing device, an indication of a selected service action from the plurality of service actions;   selecting, by the computing device, from the cached third-party service providers, a service provider corresponding to the selected service action, wherein the selected service provider is the respective cached third-party service provider determined to receive the future requests to execute the selected service action; and   sending a service fulfillment request to the selected service provider to execute the selected service action.   
     
     
         2 . The method of  claim 1 , further comprising:
 providing instructions for display of a voice-navigable user interface (VNUI) on a display interface, the VNUI comprising one or more visible menus that include a predetermined set of commands, wherein each command of the predetermined set of commands is mapped to a corresponding service action of the plurality of service actions.   
     
     
         3 . The method of  claim 2 , wherein the computing device is a server device communicatively connected to a client device, wherein the display interface is a display interface of the client device, wherein providing the instructions comprises transmitting the instructions from the server device to the client device, and wherein reception of the instructions causes the client device to display the VNUI on the display interface of the client device. 
     
     
         4 . The method of  claim 2 , wherein the display interface is a display interface of the computing device, wherein providing the instructions comprises transmitting the instructions from the computing device to the display interface, and wherein reception of the instructions causes the display interface of the computing device to display the VNUI. 
     
     
         5 . The method of  claim 2 , further comprising:
 receiving a request to add a new voice command to the one or more visible menus of the VNUI;   determining a smallest phonetic distance between the new voice command and each command of the predetermined set of commands of the VNUI; and   when the smallest phonetic distance is greater than a threshold, adding the new voice command to the predetermined set of commands of the VNUI and mapping the new voice command to a corresponding new service action.   
     
     
         6 . The method of  claim 1 , wherein the plurality of bids is a first plurality of bids, wherein the plurality of third-party service providers is a first plurality of third-party service providers, and wherein the method further comprises:
 receiving a request to add a new service action to the plurality of service actions; and   determining a new third-party service provider that will receive future requests to execute the new service action, wherein the new third-party service provider is determined based on a second plurality of bids received from a second plurality of third-party service providers for a right to execute the new service action.   
     
     
         7 . The method of  claim 1 , wherein receiving the indication of the selected service action comprises:
 detecting, using a microphone communicatively connected to the computing device, a first utterance; and   determining that the first utterance corresponds to the selected service action of the plurality of service actions.   
     
     
         8 . The method of  claim 1 , wherein the computing device is a wearable computing device. 
     
     
         9 . The method of  claim 1 , wherein determining the respective third-party service provider that will receive future requests to execute the respective service action comprises:
 receiving the plurality of bids from the plurality of third-party service providers; and   selecting a highest-bidding third-party service provider that provided a highest bid of the plurality of bids received from the plurality of third-party service providers.   
     
     
         10 . The method of  claim 9 , wherein caching on the computing device the respective third-party service provider that will receive the future requests to execute the respective service action comprises:
 caching on the computing device the highest-bidding third-party service provider.   
     
     
         11 . The method of  claim 1 , wherein the respective third-party service provider is determined further based on a preference metric for each of the plurality of third-party service providers that provided the plurality of received bids. 
     
     
         12 . The method of  claim 1 , further comprising:
 refreshing the respective third-party service provider after sending the service fulfillment request to the selected service provider.   
     
     
         13 . A non-transitory computer readable medium having stored thereon instructions that, when executed by a computing device, cause the computing device to perform operations comprising:
 determining for each respective service action of a plurality of service actions requiring fulfillment by third-party service providers, a respective third-party service provider that will receive future requests to execute the respective service action, wherein the respective third-party service provider is determined based on a plurality of bids received from a plurality of third-party service providers for a right to execute the respective service action;   at a first time, caching on the computing device, for each respective service action, the respective third-party service provider that will receive the future requests to execute the respective service action;   at a second time later than the first time, receiving an indication of a selected service action from the plurality of service actions;   selecting from the cached third-party service providers, a service provider corresponding to the selected service action, wherein the selected service provider is the respective cached third-party service provider determined to receive the future requests to execute the selected service action; and   sending a service fulfillment request to the selected service provider to execute the selected service action.   
     
     
         14 . The non-transitory computer readable medium of  claim 13 , wherein the operations further comprise:
 providing instructions for display of a voice-navigable user interface (VNUI) on a display interface, the VNUI comprising one or more visible menus that include a predetermined set of commands, wherein each command of the predetermined set of commands is mapped to a corresponding service action of the plurality of service actions.   
     
     
         15 . The non-transitory computer readable medium of  claim 13 , wherein receiving the indication of the selected service action comprises:
 detecting, using a microphone communicatively connected to the computing device, a first utterance; and   determining that the first utterance corresponds to the selected service action of the plurality of service actions.   
     
     
         16 . The non-transitory computer readable medium of  claim 13 , wherein determining the respective third-party service provider that will receive future requests to execute the respective service action comprises:
 receiving the plurality of bids from the plurality of third-party service providers; and   selecting a highest-bidding third-party service provider that provided a highest bid of the plurality of bids received from the plurality of third-party service providers.   
     
     
         17 . The non-transitory computer readable medium of  claim 16 , wherein caching on the computing device the respective third-party service provider that will receive the future requests to execute the respective service action comprises:
 caching on the computing device the highest-bidding third-party service provider.   
     
     
         18 . A computing system comprising:
 a processor;   a non-transitory computer readable memory; and   program instructions stored on the non-transitory computer readable memory and executable by the processor to perform operations comprising:
 determining for each respective service action of a plurality of service actions requiring fulfillment by third-party service providers, a respective third-party service provider that will receive future requests to execute the respective service action, wherein the respective third-party service provider is determined based on a plurality of bids received from a plurality of third-party service providers for a right to execute the respective service action; 
 at a first time, caching on the computing system, for each respective service action, the respective third-party service provider that will receive the future requests to execute the respective service action; 
 at a second time later than the first time, receiving an indication of a selected service action from the plurality of service actions; 
 selecting from the cached third-party service providers, a service provider corresponding to the selected service action, wherein the selected service provider is the respective cached third-party service provider determined to receive the future requests to execute the selected service action; and 
 sending a service fulfillment request to the selected service provider to execute the selected service action. 
   
     
     
         19 . The computing system of  claim 18 , wherein receiving the indication of the selected service action comprises:
 detecting, using a microphone communicatively connected to the computing system, a first utterance; and   determining that the first utterance corresponds to the selected service action of the plurality of service actions.   
     
     
         20 . The computing system of  claim 18 , wherein determining the respective third-party service provider that will receive future requests to execute the respective service action comprises:
 receiving the plurality of bids from the plurality of third-party service providers; and   selecting a highest-bidding third-party service provider that provided a highest bid of the plurality of bids received from the plurality of third-party service providers.

Cited by (0)

No later patents cite this yet.

References (0)

No backward citations on record.