Methods and systems for seamless outbound cold calls using virtual agents

Abstract

A Virtual Agent is a fully automated computer software solution that can engage with real people, customers, clients and even other agents. Virtual Agents have personality with animation and engage with the customer via text or voice or a combination of both as an actual person. Virtual Agents are able to answer customer questions and provide information to address their issues. Virtual Agents transfer calls to human agents if they cannot address customer issues.

What is claimed: 
     
         1 . A method for a cloud-based call center software platform, the method comprising:
 receiving, by a first virtual agent, a first speech from a customer;   converting the first speech to a first text for analysis by a knowledge graph engine to retrieve responsive information to the first text from multiple sources;   converting the responsive information to second speech; and   transferring the customer from the first virtual agent to a second virtual agent, wherein the second virtual agent uses the second speech.   
     
     
         2 . The method of  claim 1 , further comprising personalizing the second speech in accordance with a human agent to which the call will be seamlessly transferred. 
     
     
         3 . The method of  claim 1 , further comprising adapting the second speech of the virtual agent engine to a speech pattern of a human agent. 
     
     
         4 . The method of  claim 1 , further comprising adapting a diction used in the second speech of the virtual agent engine to a diction of a human agent. 
     
     
         5 . The method of  claim 1 , further comprising adapting an accent of the second speech to an accent of a human agent. 
     
     
         6 . The method of  claim 1 , further comprising authorizing the virtual agent engine to autonomously resolve a customer issue without involving a human agent. 
     
     
         7 . The method of  claim 1 , further comprising:
 using a machine learning module that builds a model from groups of words and phrases;   applying the model to the first speech input to determine a customer intent; and   taking a subsequent action based upon the determined customer intent.   
     
     
         8 . A cloud-based call center software platform system, said system comprising at least one processor and a memory for storing instructions that, when executed by the at least one processor, cause the cloud-based software platform system to perform operations comprising:
 receiving, by a first virtual agent, a first speech from a customer;   converting the first speech to a first text for analysis by a knowledge graph engine to retrieve responsive information to the first text from multiple sources;   converting the responsive information to second speech; and   transferring the customer from the first virtual agent to a second virtual agent, wherein the second virtual agent uses the second speech.   
     
     
         9 . The system of  claim 8 , further comprising personalizing the second speech in accordance with a human agent to which the call will be seamlessly transferred. 
     
     
         10 . The system of  claim 8 , further comprising adapting the second speech of the virtual agent engine to a speech pattern of a human agent. 
     
     
         11 . The system of  claim 8 , further comprising adapting a diction used in the second speech of the virtual agent engine to a diction of a human agent. 
     
     
         12 . The system of  claim 8 , further comprising adapting an accent of the second speech to an accent of a human agent. 
     
     
         13 . The system of  claim 8 , further comprising authorizing the virtual agent engine to autonomously resolve a customer issue without involving a human agent. 
     
     
         14 . The system of  claim 8 , further comprising:
 using a machine learning module that builds a model from groups of words and phrases;   applying the model to the first speech input to determine a customer intent; and   taking a subsequent action based upon the determined customer intent.   
     
     
         15 . A non-transitory computer readable medium for a cloud-based call center, the computer readable medium comprising instructions stored thereon whereby execution of the instructions by a processor cause the processor to:
 receive, by a first virtual agent, a first speech from a customer;   convert the first speech to a first text for analysis by a knowledge graph engine to retrieve responsive information to the first text from multiple sources;   convert the responsive information to second speech; and   transfer the customer from the first virtual agent to a second virtual agent, wherein the second virtual agent uses the second speech.   
     
     
         16 . The computer-readable medium of  claim 15  further comprising instructions stored thereon whereby execution of the instructions by a processor further cause the processor to personalize the second speech in accordance with a human agent to which the call will be seamlessly transferred. 
     
     
         17 . The computer-readable medium of  claim 15  further comprising instructions stored thereon whereby execution of the instructions by a processor further cause the processor to adapt the second speech of the virtual agent engine to a speech pattern of a human agent, to a diction of a human agent, or to an accent of a human agent. 
     
     
         18 . The computer-readable medium of  claim 15  further comprising instructions stored thereon whereby execution of the instructions by a processor further cause the processor to authorize the virtual agent engine to autonomously resolve a customer issue without involving a human agent. 
     
     
         19 . The computer-readable medium of  claim 15  further comprising instructions stored thereon whereby execution of the instructions by a processor further cause the processor to:
 use a machine learning module that builds a model from groups of words and phrases; 
 apply the model to the first speech input to determine a customer intent; and 
 take a subsequent action based upon the determined customer intent. 
 
     
     
         20 . The computer-readable medium of  claim 19  further comprising instructions stored thereon whereby the subsequent action includes transferring the customer to a human agent.