AI-based ims enhanced multilingual real-time call system and method

By integrating an AI service module into the IMS core network element S-CSCF and adopting a standardized interface based on the SIP protocol, a multilingual real-time call system was built. This solved the problem of the separation between AI services and IMS, achieving low-latency and highly secure multilingual real-time calls and meeting the demand for high-quality calls.

CN122420286APending Publication Date: 2026-07-17NANJING AIPULU SATELLITE COMMUNICATION TECHNOLOGY CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
NANJING AIPULU SATELLITE COMMUNICATION TECHNOLOGY CO LTD
Filing Date
2026-04-28
Publication Date
2026-07-17

AI Technical Summary

Technical Problem

In existing multilingual calling solutions, AI services are separated from IMS core network elements, resulting in the inability to reuse signaling control, security authentication, and QoS guarantee mechanisms. Furthermore, there are high latency and privacy and security risks, which cannot meet the demand for high-quality, low-latency real-time calls.

Method used

The AI ​​service module is deeply integrated into the S-CSCF core network element of the 3GPP standard IMS. The AI ​​service interacts with the native signaling of the S-CSCF through a standardized interface based on the SIP protocol, and a complete AI processing link for multilingual real-time calls is built. Combined with technologies such as parallel processing and frame-based streaming processing, voice enhancement and virtual avatar simulation functions are integrated, relying on the QoS and security mechanisms of IMS.

Benefits of technology

It enables the synchronous triggering and adjustment of AI services and call sessions, reduces end-to-end multilingual translation latency to within 200ms, improves call quality and privacy security, and meets the needs of enterprise-level cross-border business.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN122420286A_ABST
    Figure CN122420286A_ABST
Patent Text Reader

Abstract

本发明公开了基于AI的IMS增强型多语言实时通话系统及方法,属于实时通话技术领域。该系统包括IMS核心网元S‑CSCF及与其共平台部署的AI服务模块,二者通过基于SIP协议的AI服务标准化接口进行信令与媒体流交互。通话建立时,S‑CSCF触发AI模块并对媒体流分叉处理,将对端下行流替换为AI模块回传的目标语言流;AI模块依次对媒体流进行语音增强、源语言识别、机器翻译及目标语言语音合成的流式处理。方法包括呼叫与AI并行触发、分帧流式AI处理、媒体流回传及资源释放步骤。本发明深度融合IMS与AI,通过并行处理、分帧流式及预测缓存技术将端到端延迟控制在200ms以内,并具备自适应策略与容错降级机制,全程在IMS内部处理保障隐私安全,且无需改造终端。
Need to check novelty before this filing date? Find Prior Art