Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2603.18649 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915874423701504 |
|---|---|
| author | Yu, Ruizhi Zhong, Keyang Liu, Peng Wu, Qi Zhang, Haoran Zhang, Yanhao Chen, Chen Lu, Haonan |
| author_facet | Yu, Ruizhi Zhong, Keyang Liu, Peng Wu, Qi Zhang, Haoran Zhang, Yanhao Chen, Chen Lu, Haonan |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_18649 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Click-to-Ask: An AI Live Streaming Assistant with Offline Copywriting and Online Interactive QA Yu, Ruizhi Zhong, Keyang Liu, Peng Wu, Qi Zhang, Haoran Zhang, Yanhao Chen, Chen Lu, Haonan Computer Vision and Pattern Recognition 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. |
| title | Click-to-Ask: An AI Live Streaming Assistant with Offline Copywriting and Online Interactive QA |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2603.18649 |