Method and system for virtual assistant conversations
Techniques and architectures for implementing a team of virtual assistants are described herein. The team may include multiple virtual assistants that are configured with different characteristics, such as different functionality, base language models, levels of training, visual appearances, personalities, and so on. The characteristics of the virtual assistants may be configured by trainers, end-users, and/or a virtual assistant service. The virtual assistants may be presented to end-users in conversation user interfaces to perform different tasks for the users in a conversational manner. The different virtual assistants may adapt to different contexts. The virtual assistants may additionally, or alternatively, interact with each other to carry out tasks for the users, which may be illustrated in conversation user interfaces.
1. A system for providing virtual assistance in a customer-agent interaction, comprising:
at least one agent device configured to accommodate multidirectional communications over a network among the at least one agent device, a remote user device, and a network server;
the network server comprising computerized software that implements a bi-directional human-machine interface between the at least one agent device and an artificial intelligence robot configured as a virtual-assistance agent and another bi-directional human-machine interface between the virtual assistance agent and the remote user device, wherein the human-machine interfaces operate simultaneously on the network;
a communications conferencing channel on the network that is simultaneously accessible by the at least one agent device, the remote user device, and the virtual assistance agent on the network server, wherein the communications conferencing channel accommodates simultaneous multi-party interaction among a live agent, a remote user, and the virtual assistance agent; and
a multimedia gateway connected on the network, wherein the multimedia gateway comprises telecommunications protocol programming to direct transmission of multimedia data from the network server to the remote user device;
a context module implemented by the computerized software to interpret an input received at the virtual assistance agent from either the live agent or the remote user;
a task and response module to output content in a formulated response to the input as interpreted by the context module, wherein the virtual assistance agent comprises at least one pre-programmed characteristic providing functionality to process the formulated response according to a level of security access.
2. The system according to claim 1 , wherein the communications conferencing channel comprises a bi-directional audio data channel between the at least one agent device and the network server.
3. The system according to claim 2 , wherein the audio data comprises voice activated command data from the live agent to the virtual assistance agent, said voice activated command data being audible to the remote user during a transaction.
4. The system according to claim 3 , wherein the audio data comprises an audio output from the virtual assistance agent to the live agent, said audio output being audible to and accessible by the remote user via the communications conferencing channel.
5. The system according to claim 3 , wherein the voice activated command data from the live agent comprises a trigger condition that is recognizable by the virtual assistance agent as a request for information, and in response to the trigger condition, the virtual assistance agent provides, from the server, relevant audio response data to the communications conferencing channel.
6. The system according to claim 5 , wherein the virtual assistance agent accesses another channel to provide onscreen data to the live agent computer.
7. The system according to claim 6 , wherein the on-screen data instructs the live agent in regard to advice for assisting the remote user.
8. The system according to claim 1 , wherein the conferencing communication channel transmits audio data that comprises voice activated command data from the live agent to the virtual assistance agent, said voice activated command data being simultaneously audible to the remote user during a transaction, and wherein the server comprises a natural language processing service that converts the voice activated command data to machine language that comprises a trigger condition therein.
9. The system according to claim 8 , wherein the remote user accesses audio output data from the virtual assistance agent on the conference communications channel.
10. The system according to claim 1 , wherein the remote user device comprises a video output display, and wherein the communications conferencing channel comprises a multimedia data channel.
11. The system according to claim 10 , wherein the multimedia data channel transmits audio data and video data to and from the live agent, the remote user, and the virtual assistance agent in a format that is commonly accessible by both the live agent device and the remote user device simultaneously.
12. The system according to claim 11 , wherein the audio data comprises voice activated command data from the live agent to the virtual assistance agent, said voice activated command data being audible to the remote user during a transaction.
13. The system according to claim 12 , wherein the multimedia data channel further comprises multimedia output data from the virtual assistance that is accessible by both the live agent device and the remote user device.
14. The system according to claim 13 , further comprising a recording system configured to store information from the multimedia data channel.
15. A system for providing virtual assistance in a customer-agent interaction, comprising:
at least one agent device configured to accommodate multi-directional communications over a network among the at least one agent device, a remote user device, and a network server;
the network server comprising computerized software that implements a bi-directional human-machine interface between the at least one agent device and an artificial intelligence robot configured as a virtual-assistance agent and another bi-directional human machine interface between the virtual assistance agent and the remote user device, wherein the human-machine interfaces operate simultaneously on the network;
a communications conferencing channel on the network that is simultaneously accessible by the at least one agent device, the remote user device, and the virtual assistance agent on the network server;
wherein the communications conferencing channel otherwise accommodates simultaneous multi-party interaction among a live agent, a remote user, and the virtual assistance agent,
a multimedia gateway connected on the network, wherein the multimedia gateway comprises telecommunications protocol programming to receive multimedia data from the network server, the agent device, and the remote user device, and wherein the multi-media gateway is further configured to identify and direct transmission of multimedia data from the network server to the remote user device;
a context module implemented by the computerized software to interpret an input received at the virtual assistance agent from either the live agent or the remote user;
a task and response module to output content in a formulated response to the input as interpreted by the context module, wherein the virtual assistance agent comprises at least one pre-programmed characteristic providing functionality to process the formulated response according to a level of security access.