一个输入框搞定所有文本功能，智能识别意图并自动执行。
TextOnly: A Unified Function Portal for Text-Related Functions on Smartphones
- 用单一输入框接收文本，结合大模型与BERT理解用户意图。
- 真实测试中准确率达71.35%，且随使用持续提升速度与精度。
- 适合追求高效操作的手机用户，尤其优于语音助手的文本场景。
文本框是当前智能手机应用中实现多种功能的入口。然而，在调用特定功能时，用户需经过多步操作才能定位到相应输入框。我们提出TextOnly，一个统一的功能门户，仅通过一个文本框即可访问跨应用的文本相关功能。例如输入餐厅名称可触发Google Maps搜索，输入问候语可启动WhatsApp对话。尽管输入简洁，TextOnly充分利用原始文本中的丰富信息，有效解析用户意图。该系统融合大语言模型（LLM）与BERT模型：LLM提供通用知识，BERT则持续学习用户偏好，实现更快预测。真实用户研究显示，TextOnly在顶1准确率上达71.35%，且能持续提升准确率与推理速度。参与者普遍认为其可用性良好，并更倾向使用TextOnly而非手动操作。相比语音助手，TextOnly支持更广泛文本功能，且输入更简洁。
原文摘要 · Abstract (English)
Text boxes serve as portals to diverse functionalities in today's smartphone applications. However, when it comes to specific functionalities, users always need to navigate through multiple steps to access particular text boxes for input. We propose TextOnly, a unified function portal that enables users to access text-related functions from various applications by simply inputting text into a sole text box. For instance, entering a restaurant name could trigger a Google Maps search, while a greeting could initiate a conversation in WhatsApp. Despite their brevity, TextOnly maximizes the utilization of these raw text inputs, which contain rich information, to interpret user intentions effectively. TextOnly integrates large language models(LLM) and a BERT model. The LLM consistently provides general knowledge, while the BERT model can continuously learn user-specific preferences and enable quicker predictions. Real-world user studies demonstrated TextOnly's effectiveness with a top-1 accuracy of 71.35%, and its ability to continuously improve both its accuracy and inference speed. Participants perceived TextOnly as having satisfactory usability and expressed a preference for TextOnly over manual executions. Compared with voice assistants, TextOnly supports a greater range of text-related functions and allows for more concise inputs.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。