Multi-domain chatbot

Abstract

A multi-domain chatbot is used to service a message of a user. An automated agent of the multi-domain chatbot may act as an intermediary between the user and a plurality of domain-specific modules of the multi-domain chatbot. The automated agent may receive the message from the user, determine an intent of the message, and based on the intent, determine a group of the domain-specific modules that should be investigated. The automated agent may then investigate the group of domain-specific modules by sending the user message to and receiving responses from the domain-specific modules within the group. Based on the received responses, the automated agent may determine whether to provide, to the user, one of the domain-specific responses or a null response, in the event that none of the domain-specific responses is aligned with the intent of the message.

What is claimed is: 
     
         1 . A method, comprising:
 transmitting, by an automated agent, a message from a user to a group of domain-specific modules;   receiving, by the automated agent, responses from the group of domain-specific modules;   determining, by the automated agent, whether any of the responses is aligned with an intent of the user message; and   if one or more of the responses are aligned with the intent of the user message, transmitting one of the one or more aligned responses to a client device of the user; otherwise, if none of the responses is aligned with the intent of the user message, transmitting, to the client device, a null response that does not satisfy the intent of the user message,   wherein the null response is chosen from a plurality of null responses based on at least one of the intent of the user message and the responses from the group of domain-specific modules.   
     
     
         2 . The method of  claim 1 , wherein a first one of the domain-specific modules from the group of domain-specific modules is configured to communicate with the user regarding topics that fall within a first domain. 
     
     
         3 . The method of  claim 1 , wherein the group of domain-specific modules includes an information technology (IT) module, a human resource (HR) module, and a finance module. 
     
     
         4 . The method of  claim 1 , wherein the automated agent and the group of domain-specific modules are part of a multi-domain chatbot. 
     
     
         5 . The method of  claim 1 , wherein the determination of whether any of the responses is aligned with the intent of the user message is based on prior interactions between the automated agent and the user. 
     
     
         6 . The method of  claim 1 , wherein the determination of whether any of the responses is aligned with the intent of the user message is based on prior interactions between the automated agent and users other than the user. 
     
     
         7 . The method of  claim 1 , wherein the null response is chosen from the plurality of null responses based on the intent of the user message and the responses from the group of domain-specific modules. 
     
     
         8 . A computing system comprising a processor and memory storing instructions that, when executed by the processor, cause the processor to:
 transmit a message from a user to a group of domain-specific modules;   receive responses from the group of domain-specific modules;   determine whether any of the responses is aligned with an intent of the user message; and   if one or more of the responses are aligned with the intent of the user message, transmit one of the one or more aligned responses to a client device of the user; otherwise, if none of the responses is aligned with the intent of the user message, transmit, to the client device, a null response that does not satisfy the intent of the user message,   wherein the null response is chosen from a plurality of null responses based on at least one of the intent of the user message and the responses from the group of domain-specific modules.   
     
     
         9 . The computing system of  claim 8 , wherein a first one of the domain-specific modules from the group of domain-specific modules is configured to communicate with the user regarding topics that fall within a first domain. 
     
     
         10 . The computing system of  claim 8 , wherein the group of domain-specific modules includes an information technology (IT) module, a human resource (HR) module, and a finance module. 
     
     
         11 . The computing system of  claim 8 , wherein the determination of whether any of the responses is aligned with the intent of the user message is based on prior interactions between an automated agent and the user. 
     
     
         12 . The computing system of  claim 8 , wherein the determination of whether any of the responses is aligned with the intent of the user message is based on prior interactions between an automated agent and users other than the user. 
     
     
         13 . The computing system of  claim 8 , wherein the null response is chosen from the plurality of null responses based on the intent of the user message and the responses from the group of domain-specific modules. 
     
     
         14 . A non-transitory machine-readable storage medium comprising instructions that, when executed by a processor, cause the processor to:
 transmit a message from a user to a group of domain-specific modules;   receive responses from the group of domain-specific modules;   determine whether any of the responses is aligned with an intent of the user message; and   if one or more of the responses are aligned with the intent of the user message, transmit one of the one or more aligned responses to a client device of the user; otherwise, if none of the responses is aligned with the intent of the user message, transmit, to the client device, a null response that does not satisfy the intent of the user message,   wherein the null response is chosen from a plurality of null responses based on at least one of the intent of the user message and the responses from the group of domain-specific modules.   
     
     
         15 . The non-transitory machine-readable storage medium of  claim 14 , wherein a first one of the domain-specific modules from the group of domain-specific modules is configured to communicate with the user regarding topics that fall within a first domain. 
     
     
         16 . The non-transitory machine-readable storage medium of  claim 14 , wherein the group of domain-specific modules includes an information technology (IT) module, a human resource (HR) module, and a finance module. 
     
     
         17 . The non-transitory machine-readable storage medium of  claim 14 , wherein the group of domain-specific modules is part of a multi-domain chatbot. 
     
     
         18 . The non-transitory machine-readable storage medium of  claim 14 , wherein the determination of whether any of the responses is aligned with the intent of the user message is based on prior interactions between an automated agent and the user. 
     
     
         19 . The non-transitory machine-readable storage medium of  claim 14 , wherein the determination of whether any of the responses is aligned with the intent of the user message is based on prior interactions between an automated agent and users other than the user. 
     
     
         20 . The non-transitory machine-readable storage medium of  claim 14 , wherein the null response is chosen from the plurality of null responses based on the intent of the user message and the responses from the group of domain-specific modules.