A dual-channel session information association system and method

Abstract

The invention provides a dual-channel conversation information association system and method, wherein the system is respectively connected to a call center system, a seat system and a plurality of intelligent voice processing engines, including an acquisition module, an analysis module, a retrieval module, a Association module and a communication module. This technical solution realizes the traffic correlation between the calling user information and the traffic agent information through the two-way voice stream capture on the call center side and the agent side, and can realize dual-channel traffic information management and real-time integration in the system; The artificial intelligence speech recognition engine processes and analyzes real-time traffic, and can accurately push the transcription results to the operator seat; in addition, the MRCP protocol architecture is removed by capturing packets, which breaks through the need for privatized deployment of traditional artificial intelligence speech recognition engines Limitations, with high applicability, scalability and reusability value.

Description

technical field [0001] The invention relates to the field of intelligent call center systems, in particular to a dual-channel conversation information association system and method. Background technique [0002] The call center, also known as the customer service center, originated in the 1930s, and initially transferred the user's call to the answering service desk or the corresponding expert; since then, with the increasing demand for transferred calls and answers, interactive The prototype of the voice response system began to be established - this system can realize the answer to some common questions of customers by the machine "automatic operator" to answer and deal with. A call center in the traditional sense refers to a call response center that focuses on telephone access and provides customers with various telephone response services. It has the function of displaying the calling number and can automatically assign incoming calls to personnel with corresponding ski...

AI Technical Summary

Problems solved by technology

[0003] At present, most of the existing call centers need to realize the output of the voice stream through the interactive voice response driver, which does not yet support the acquisition and output of the voice stream during the call; and in the implementation of the intelligent application of the call center, most of them use the Capture the real-time call voice stream by mirroring and capturing packets at the port of the call center, and transfer it to artificial intelligence engines such as voice recognition for corresponding processing

[0004] For the existing application scenarios, there are still new problems—since the captured voice stream only covers the content of the calling number and the access number of the call center, and does not carry the channel-related information related to the agent, the artificial intelligence engine returns the Speech recognition results cannot be accurately and directly pushed to the corresponding operator seat; in addition, the current connection between the call center and the artificial intelligence speech recognition engine uses the MRCP interface carried by the SIP session initiation protocol, resulting in the need for a call center system and an artificial intelligence speech recognition engine Need to be deployed in the same local area network, which limits the popularization and application of this technology

Images