Voice response system with live agent assisted information selection and machine playback
First Claim
1. A method, comprising:
- upon receiving a telephone call from a caller, switching to interacting with the caller in a non-live agent mode;
processing the call in the non-live agent mode;
receiving an utterance from the caller;
performing a machine selection of voice content to play to the caller based on the utterance by performing a linguistic analysis of the utterance by the caller to determine an appropriate topic among a plurality of relevant subject topics within a text knowledge base to play to the caller;
creating a navigation topic question comprising a plurality of different subject topics related to the appropriate topic and forwarding the navigation topic question to the caller;
receiving a subject topic selection among the plurality of different subject topics and identifying the machine-selected voice content to play to the caller based on the subject topic selection;
playing the identified machine-selected voice content to the caller based on the determined appropriate topic in the text knowledge base;
while in the non-live agent mode, upon receiving a request to speak to a live agent from the caller, switching to a live agent mode wherein a live agent holds a conversation with the caller, wherein said switching to a live agent mode comprises selecting the live agent based on expertise of the live agent to answer questions by the caller; and
selectively switching to the non-live agent mode and playing the live agent-selected voice content to the caller.
13 Assignments
0 Petitions
Accused Products
Abstract
In accordance with one embodiment, a method for operating a telephonic voice content system is provided. The method, comprises in a non-live agent mode, interacting with a caller by receiving an utterance from the caller, performing a machine selection of voice content to play to the caller based on the utterance, and playing the machine-selected voice content to the caller; and upon receiving a request to speak to a live agent from the caller, switching to a live agent mode wherein a live agent holds a conversation with the caller, and selects voice content to play to the caller based on the conversation; and switching to the non-live agent mode and playing the live agent-selected voice content to the caller.
-
Citations
12 Claims
-
1. A method, comprising:
-
upon receiving a telephone call from a caller, switching to interacting with the caller in a non-live agent mode; processing the call in the non-live agent mode; receiving an utterance from the caller; performing a machine selection of voice content to play to the caller based on the utterance by performing a linguistic analysis of the utterance by the caller to determine an appropriate topic among a plurality of relevant subject topics within a text knowledge base to play to the caller; creating a navigation topic question comprising a plurality of different subject topics related to the appropriate topic and forwarding the navigation topic question to the caller; receiving a subject topic selection among the plurality of different subject topics and identifying the machine-selected voice content to play to the caller based on the subject topic selection; playing the identified machine-selected voice content to the caller based on the determined appropriate topic in the text knowledge base; while in the non-live agent mode, upon receiving a request to speak to a live agent from the caller, switching to a live agent mode wherein a live agent holds a conversation with the caller, wherein said switching to a live agent mode comprises selecting the live agent based on expertise of the live agent to answer questions by the caller; and selectively switching to the non-live agent mode and playing the live agent-selected voice content to the caller. - View Dependent Claims (2, 3)
-
-
4. A method, comprising:
-
upon receiving a telephone call from a caller, switching to interacting with the caller in a non-live agent mode; processing the call in the non-live agent mode receiving at least one utterance from the caller; performing a machine selection operation wherein the utterance is analyzed and correlated to a topic within a text knowledge base by performing a linguistic analysis of the utterance by the caller in order to a determine an appropriate topic among a plurality of relevant subject topics within the text knowledge base to play to the caller; creating a navigation topic question comprising a plurality of different subject topics related to the appropriate topic and forwarding the navigation topic question to the caller; receiving a subject topic selection among the plurality of different subject topics and identifying the machine-selected voice content to play to the caller based on the subject topic selection; playing the identified machine-selected voice content relating to the topic to the caller based on the determined appropriate topic in the text knowledge base; while in the non-live agent mode, receiving a request to speak to a live agent from the caller switching to a live-agent mode comprising analyzing utterances of the caller to determine what expertise is needed by a live agent in order to answer questions by the caller; selecting a live agent with the expertise; transferring the caller to the selected live agent who then holds a conversation with the caller and determines what information the caller requires, wherein the agent selects a topic from the text knowledge base corresponding to the information if the topic exists; and selectively switching back to the non-live agent mode and playing the selected topic to the caller. - View Dependent Claims (5, 6, 7)
-
-
8. A system, comprising:
-
a database that includes a text knowledge base organized into topics; a telephony interface to receive a telephone call; a non-live agent processor to handle the telephone call wherein a voice content selection mechanism selects a topic based on a correlation of an utterance received from the caller to a topic in the text knowledge base the correlation including a linguistic analysis of the utterance by the caller to determine an appropriate topic among a plurality of relevant subject topics within the text knowledge base to play to the caller, and create a navigation topic question comprising a plurality of different subject topics related to the appropriate topic and forward the navigation topic question to the caller, and receive a subject topic selection among the plurality of different subject topics and identify the machine-selected voice content to play to the caller based on the subject topic selection; a voice content player that plays the identified machine-selected voice content related to the topic to the caller; and a call transfer mechanism to transfer the telephone call to a live agent, selected to have expertise to answer questions by the caller based on analysis of utterances by the caller to determine said expertise, if requested by the caller for a selection of a topic from the knowledge base based on a request for information by the caller;
wherein the live agent provides the information if there is not topic in the knowledge base to match the information; and
to selectively switch the system back to the non-live agent mode for initiate playback of the live agent selected voice content by the voice content player. - View Dependent Claims (9, 10, 11, 12)
-
Specification