Customer Service Automation · Document Processing
Samsung needed to bring reliable generative-AI capabilities into its China smartphone lineup, covering typing, office work, voice assistance and call handling while reducing hallucinations and unstable output formatting.
Reported impact
Samsung expanded Galaxy AI across text, office, voice and call scenarios, improved assistant comprehension and gave users a more practical, current and personalized mobile AI experience.
Samsung Electronics China worked with Baidu AI Cloud to embed large-model services inside Galaxy AI experiences on mobile devices. Baidu's Qianfan model-development stack and ERNIE-based reasoning were used to support several user-facing workflows: the Samsung keyboard now rewrites and expands text in different tones, office functions transform recordings, webpages and documents into structured summaries, and Bixby gains stronger natural-language understanding for fast, current answers. The call assistant adds preconfigured call-management behavior so the phone can answer common delivery or courier calls with context-appropriate language. In practice, the architecture routes user prompts from typing, meetings, browsing and voice interactions into model inference and retrieval logic, then returns formatted results through Galaxy AI interfaces, helping Samsung deploy more consistent, multi-scenario AI assistance without rebuilding each feature separately.
User prompts from the keyboard, meeting recordings, webpages, documents, voice commands and phone calls are sent into Galaxy AI workflows, where Qianfan-backed models interpret intent, generate rewrites or summaries, and return results to Bixby, the keyboard and call-assistant interfaces.
Bixby is upgraded through natural-language interaction to provide highly timely information and execute owner commands (original: 升级Bixby语音助手。通过自然语言的交互，为用户提供高时效性的可用信息，执行机主指令).
Samsung and Baidu AI Cloud worked together in China to comprehensively build AI scenarios while dealing with hallucinations and unstable output formats (original: 在中国市场，百度智能云与中国三星深入合作，面对大模型幻觉、格式输出不稳定等多重挑战，不断打磨、优化效果，全面打造AI场景).
The assistant's understanding improved by 50% (original: 语音助手理解力提升50%).
The office scenario can intelligently typeset meeting minutes and summarize recordings, webpages and documents (original: 不仅可以将会议纪要进行智能排版，对录音、网页、文档等内容还可以提取摘要与总结).
The upgraded Samsung input method offers grammar correction, tone conversion and scene-based expansion (original: 升级三星输入法，为用户提供语法修正与校对、包括随意风格在内的多种语气转换、根据场景进行扩写等功能).
Review how this reference was scored and trace each normalized claim back to its documented source.
Scoring methodology
Customer Reference Value measures usefulness as a customer reference. Evidence Confidence measures the quality and traceability of available evidence, not independent verification.
Traceability
Field coverage shows which facts each source supports. Dates are shown only when documented by the source.
Related
Baidu AI Cloud Sample Jun 20, 2025 OPPO OPPO needed to bring trustworthy real-time information, personalization, multimodal understanding and developer tooling into its AI-phone strategy while still protecting user data and keeping assistant experiences… Baidu Search-Sourced Retrieval · ERNIE Large Model · Qianfan AppBuilder Baidu AI Cloud Sample Jun 16, 2025 Shifeng Culture Development Co., Ltd. Shifeng Culture wanted to turn traditional children's toys into interactive AI products, but needed help with large-model integration, low-latency interaction, security and scalable product delivery. Cloud Security Services · Intelligent Interaction Platform · Qianfan AppBuilder Baidu AI Cloud Sample May 14, 2025 vivo vivo wanted its BlueLM-powered phone assistant to answer general questions while also retrieving current and authoritative information without forcing users to open browsers or other apps. BlueLM Assistant · Qianfan Application Platform · Qianfan ModelBuilder 