Click-to-Ask: An AI Live Streaming Assistant with Offline Copywriting and Online Interactive QA

2026-03-19

AI Summary

This work proposes an AI-powered live-streaming assistant designed to address the inefficiencies in content preparation and real-time audience engagement prevalent in live commerce. The system features a novel dual-module architecture: in the offline phase, it generates structured product data and compliant promotional scripts from multimodal product information; in the online phase, it employs an event-level streaming memory mechanism that enables instant, context-aware responses to viewer queries upon主播 click. Evaluated on a self-constructed TikTok live-streaming frame dataset, the system achieves a question recognition accuracy of 0.913 and an answer quality score of 0.876, demonstrating significant improvements in both pre-stream preparation efficiency and real-time viewer interaction effectiveness.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Natural Language Processing: Question Answering
• Data Mining & Knowledge Management: Conversational Systems for Recommendation & Retrieval

Application Category

• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems
• Search and Retrieval-Augmented AI: Assisted, interactive, and conversational search
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

Live streaming commerce has become a prominent form of broadcasting in the modern era. To facilitate more efficient and convenient product promotions for streamers, we present Click-to-Ask, an AI-driven assistant for live streaming commerce with complementary offline and online components. The offline module processes diverse multimodal product information, transforming complex inputs into structured product data and generating compliant promotional copywriting. During live broadcasts, the online module enables real-time responses to viewer inquiries by allowing streamers to click on questions and leveraging both the structured product information generated by the offline module and an event-level historical memory maintained in a streaming architecture. This system significantly reduces the time needed for promotional preparation, enhances content engagement, and enables prompt interaction with audience inquiries, ultimately improving the effectiveness of live streaming commerce. On our collected dataset of TikTok live stream frames, the proposed method achieves a Question Recognition Accuracy of 0.913 and a Response Quality score of 0.876, demonstrating considerable potential for practical application. The video demonstration can be viewed here: https://www.youtube.com/shorts/mWIXK-SWhiE.

Problem

• live streaming commerce
• real-time QA
• promotional efficiency
• audience interaction
• product promotion

Innovation

• AI live streaming assistant
• offline copywriting generation
• online interactive QA
• multimodal product understanding
• streaming architecture