Digital Human Intelligent Interaction System Based on Multimodal Pre-training Mode
As the forefront of human–computer intelligent interaction, digital humans have increasingly diverse application scenarios, but also face many challenges. In order to enhance the intelligence level and interaction capability of digital human, the study first optimizes the traditional UniLM model, th...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Taylor & Francis Group
2024-12-01
|
| Series: | Applied Artificial Intelligence |
| Online Access: | https://www.tandfonline.com/doi/10.1080/08839514.2024.2405953 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850116295955054592 |
|---|---|
| author | Xuliang Yang Yong Fang Lili Wang Rodolfo C. Raga |
| author_facet | Xuliang Yang Yong Fang Lili Wang Rodolfo C. Raga |
| author_sort | Xuliang Yang |
| collection | DOAJ |
| description | As the forefront of human–computer intelligent interaction, digital humans have increasingly diverse application scenarios, but also face many challenges. In order to enhance the intelligence level and interaction capability of digital human, the study first optimizes the traditional UniLM model, then introduces the mechanism of multi-head attention, and mitigates the exposure bias by using adversarial training and random replacement of decoder to design an improved UniLM model, and finally applies the improved model to the digital human management system. The results show that the precision rate of the improved UniLM model is improved by 7.68%, 6.4%, and 4.96%, the recall rate is improved by 11.94%, 9.69%, and 8.83%, and the F1-score is improved by 8.34%, 6.41%, and 7.68% compared with the other three models, which proves that it has a better precision rate, robustness, and generalization ability. The perplexity of the improved UniLM model is 135, 95, 76, 71, and 55 under five text lengths, which is significantly lower than the other models, proving that its text generation ability is better. The above results demonstrate the performance of the research-designed digital human system based on the Improved UniLM model, which provides a direction for the further development of digital human technology. |
| format | Article |
| id | doaj-art-24a7bbd672f64a16bce0e0780fea14fb |
| institution | OA Journals |
| issn | 0883-9514 1087-6545 |
| language | English |
| publishDate | 2024-12-01 |
| publisher | Taylor & Francis Group |
| record_format | Article |
| series | Applied Artificial Intelligence |
| spelling | doaj-art-24a7bbd672f64a16bce0e0780fea14fb2025-08-20T02:36:22ZengTaylor & Francis GroupApplied Artificial Intelligence0883-95141087-65452024-12-0138110.1080/08839514.2024.2405953Digital Human Intelligent Interaction System Based on Multimodal Pre-training ModeXuliang Yang0Yong Fang1Lili Wang2Rodolfo C. Raga3Dongguan City University, University and Urban Integration Development Research Center, Dongguan, ChinaDongguan City University, University and Urban Integration Development Research Center, Dongguan, ChinaDongguan City University, University and Urban Integration Development Research Center, Dongguan, ChinaCollege of Computing & Information Technologies, National University, Manila, PhilippinesAs the forefront of human–computer intelligent interaction, digital humans have increasingly diverse application scenarios, but also face many challenges. In order to enhance the intelligence level and interaction capability of digital human, the study first optimizes the traditional UniLM model, then introduces the mechanism of multi-head attention, and mitigates the exposure bias by using adversarial training and random replacement of decoder to design an improved UniLM model, and finally applies the improved model to the digital human management system. The results show that the precision rate of the improved UniLM model is improved by 7.68%, 6.4%, and 4.96%, the recall rate is improved by 11.94%, 9.69%, and 8.83%, and the F1-score is improved by 8.34%, 6.41%, and 7.68% compared with the other three models, which proves that it has a better precision rate, robustness, and generalization ability. The perplexity of the improved UniLM model is 135, 95, 76, 71, and 55 under five text lengths, which is significantly lower than the other models, proving that its text generation ability is better. The above results demonstrate the performance of the research-designed digital human system based on the Improved UniLM model, which provides a direction for the further development of digital human technology.https://www.tandfonline.com/doi/10.1080/08839514.2024.2405953 |
| spellingShingle | Xuliang Yang Yong Fang Lili Wang Rodolfo C. Raga Digital Human Intelligent Interaction System Based on Multimodal Pre-training Mode Applied Artificial Intelligence |
| title | Digital Human Intelligent Interaction System Based on Multimodal Pre-training Mode |
| title_full | Digital Human Intelligent Interaction System Based on Multimodal Pre-training Mode |
| title_fullStr | Digital Human Intelligent Interaction System Based on Multimodal Pre-training Mode |
| title_full_unstemmed | Digital Human Intelligent Interaction System Based on Multimodal Pre-training Mode |
| title_short | Digital Human Intelligent Interaction System Based on Multimodal Pre-training Mode |
| title_sort | digital human intelligent interaction system based on multimodal pre training mode |
| url | https://www.tandfonline.com/doi/10.1080/08839514.2024.2405953 |
| work_keys_str_mv | AT xuliangyang digitalhumanintelligentinteractionsystembasedonmultimodalpretrainingmode AT yongfang digitalhumanintelligentinteractionsystembasedonmultimodalpretrainingmode AT liliwang digitalhumanintelligentinteractionsystembasedonmultimodalpretrainingmode AT rodolfocraga digitalhumanintelligentinteractionsystembasedonmultimodalpretrainingmode |