Knowledge base for voice large language model applications
AssigneeSalesforce, Inc.
InventorsSarath Shekkizhar, Romain Cosentino
Life of this patent
Estimating the term…
Abstract
A voice-based agent service provides one or more voice agents to respond to voice-based requests. For example, when a question is received by the voice-based agent service it can be matched to a voice-ready knowledge base. The voice-ready knowledge base has been generated offline such that it includes concise answers without language that results in artifacts when converted to voice. These answers are organized in nodes in a conversation graph. The question can be matched to a node and then subsequent nodes can be predicted by a conversation model based on the previously traversed nodes and further user input during a real-time conversation.
Claims20
A non-transitory machine-readable storage medium that provides instructions that, if executed by a processor the processor to perform operations comprising:
- receiving, by a voice-based agent service, voice data representing a question;
- identifying a node in a conversation graph of a voice-ready knowledge base corresponding to the question;
- retrieving an answer based on the node;
- providing a voice response corresponding to the answer;
- and
- predicting, by a conversation model, a next node in the conversation graph based at least on the question and the node.
A method comprising:
- receiving, by a voice-based agent service, voice data representing a question;
- identifying a node in a conversation graph of a voice-ready knowledge base corresponding to the question;
- retrieving an answer based on the node;
- providing a voice response corresponding to the answer;
- and
- predicting, by a conversation model, a next node in the conversation graph based at least on the question and the node.
An apparatus comprising:
- a processor or set of one or more processors;
- and
- a non-transitory machine-readable storage medium that provides instructions that, if executed by the processor, are configurable to cause the apparatus to perform operations comprising,
- receiving, by a voice-based agent service, voice data representing a question;
- identifying a node in a conversation graph of a voice-ready knowledge base corresponding to the question;
- retrieving an answer based on the node;
- providing a voice response corresponding to the answer;
- and
- predicting, by a conversation model, a next node in the conversation graph based at least on the question and the node.
Dependencies are inferred from the claim text.