Voice gateway for federated voice services

Abstract

Devices, computer-readable media, and methods for submitting a modified voice input to a service based upon a user intent determined from a voice input in accordance with a voice interface of the service are disclosed. A processing system including at least one processor may obtain a voice input of a user, determine an intent from the voice input, identify a first service, from among a plurality of services, in accordance with the intent, and formulate a first modified voice input from the voice input in accordance with a voice interface of the first service, where each of the services is associated with one of a plurality of different voice interfaces. The processing system may further submit the first modified voice input to the first service, obtain a first voice response from the first service, and present a voice output to the user in accordance with the first voice response.

What is claimed is: 
     
         1 . A method comprising:
 obtaining, by a processing system including at least one processor, a voice input of a user;   determining, by the processing system, an intent from the voice input;   identifying, by the processing system, a first service, from among a plurality of services, in accordance with the intent via an intent-to-service mapping;   formulating, by the processing system, a first modified voice input from the voice input in accordance with a voice interface of the first service, wherein each of the plurality of services is associated with one of a plurality of different voice interfaces;   submitting, by the processing system, the first modified voice input to the first service;   obtaining, by the processing system, a first voice response from the first service; and   presenting, by the processing system, a voice output to the user in accordance with the first voice response.   
     
     
         2 . The method of  claim 1 , wherein the identifying further comprises:
 identifying at least a second service, from among the plurality of services, in accordance with the intent.   
     
     
         3 . The method of  claim 2 , wherein the formulating further comprises:
 formulating a second modified voice input from the voice input in accordance with a voice interface of the second service.   
     
     
         4 . The method of  claim 3 , wherein the submitting further comprises:
 submitting the second modified voice input to the second service.   
     
     
         5 . The method of  claim 4 , wherein the obtaining further comprises:
 obtaining a second voice response from the second service.   
     
     
         6 . The method of  claim 5 , further comprising:
 creating the voice output from the first voice response and the second voice response.   
     
     
         7 . The method of  claim 1 , wherein the plurality of different voice interfaces comprises a plurality of different voice application programming interfaces. 
     
     
         8 . The method of  claim 1 , wherein the voice input is obtained from a mobile computing device of the user. 
     
     
         9 . The method of  claim 1 , wherein the processing system comprises a telecommunication network edge computing infrastructure. 
     
     
         10 . The method of  claim 1 , wherein the formulating the first modified voice input further comprises:
 modifying the voice input in accordance with user context information.   
     
     
         11 . The method of  claim 10 , wherein the user context information comprises location information of the user. 
     
     
         12 . The method of  claim 10 , wherein the user context information comprises at least one of:
 an interest of the user;   calendar information of the user; or   biometric information of the user.   
     
     
         13 . The method of  claim 1 , wherein the identifying is further in accordance with a user preference for the first service. 
     
     
         14 . The method of  claim 13 , wherein the user preference for the first service is learned by the processing system in accordance with a plurality of interactions of the user with the processing system. 
     
     
         15 . The method of  claim 1 , wherein the determining the intent from the voice input comprises:
 converting the voice input to text; and   applying a natural language understanding pipeline to the text, wherein an output of the natural language understanding pipeline comprises the intent.   
     
     
         16 . The method of  claim 1 , wherein the formulating the first modified voice input from the voice input comprise adding a wake-up phrase in accordance with the voice interface of the first service. 
     
     
         17 . The method of  claim 16 , wherein the first service comprises a voice assistant service. 
     
     
         18 . The method of  claim 1 , wherein the first service comprises:
 an online merchant service;   an online information service;   an online enterprise service;   a telecommunications service; or   a voice assistant service.   
     
     
         19 . A non-transitory computer-readable medium storing instructions which, when executed by a processing system including at least one processor, cause the processing system to perform operations, the operations comprising:
 obtaining a voice input of a user;   determining an intent from the voice input;   identifying a first service, from among a plurality of services, in accordance with the intent via an intent-to-service mapping;   formulating a first modified voice input from the voice input in accordance with a voice interface of the first service, wherein each of the plurality of services is associated with one of a plurality of different voice interfaces;   submitting the first modified voice input to the first service;   obtaining a first voice response from the first service; and   presenting a voice output to the user in accordance with the first voice response.   
     
     
         20 . A device comprising:
 a processing system including at least one processor; and   a non-transitory computer-readable medium storing instructions which, when executed by the processing system, cause the processing system to perform operations, the operations comprising:
 obtaining a voice input of a user; 
 determining an intent from the voice input; 
 identifying a first service, from among a plurality of services, in accordance with the intent via an intent-to-service mapping; 
 formulating a first modified voice input from the voice input in accordance with a voice interface of the first service, wherein each of the plurality of services is associated with one of a plurality of different voice interfaces; 
 submitting the first modified voice input to the first service; 
 obtaining a first voice response from the first service; and 
 presenting a voice output to the user in accordance with the first voice response.