Use Case Intelligence RSS Search use cases Search
Baidu AI Cloud Consumer Goods Global Translated from Chinese

HONOR

Enterprise Knowledge Search

HONOR needed to strengthen the intelligence of its YOYO assistant and device experiences so users could complete richer interaction, productivity, and content-creation tasks without forcing the handset maker to build every model capability alone.

Read the original story Explore all use cases

Reported impact

Business outcome

HONOR expanded the intelligence of its assistant, improved intent recognition and conversation quality, automated meeting-note and task-generation work, and opened a path for richer vertical-agent experiences on devices.

  • Customer Experience
  • Productivity Improvement
  • Scalability

Solution

HONOR and Baidu AI Cloud built an end-cloud collaborative assistant architecture around YOYO using Qianfan ModelBuilder, Qianfan AppBuilder, and ERNIE models. HONOR's MagicOS already included device-side AI, but the project added cloud large-model capabilities for PC and mobile assistant workflows such as intelligent creation, meeting-note generation, document question answering, free-form chat, role play, and emotional companionship. The design blends device intelligence with cloud inference so user intent can be recognized more accurately and service responses can be routed across contexts. Long-context ERNIE 3.5-128K models support meeting summarization, task extraction, and templated note generation, while content-generation capabilities enable rewriting, expansion, continuation, and correction across many genres.

Data flow

User requests from HONOR PC and mobile devices enter YOYO, where device-side AI hands complex tasks to Baidu's cloud models. The platform interprets intent, grounds answers with search or document context when needed, and returns outputs such as meeting summaries, generated content, or multi-document answers back into the assistant UI.

Solution architecture

3 components · 2 layers
  1. Compute
    • Qianfan ModelBuilder Provides the cloud large-model capabilities used to power HONOR's assistant and productivity functions.
    • ERNIE 3.5-128K Handles long-context meeting understanding, summarization, and task extraction for the assistant experience.
  2. Orchestration
    • Qianfan AppBuilder Organizes assistant-side application flows for creation, summarization, and document interaction.

Architecture clues

  • Long-context ERNIE models are used for meeting-note generation and structured to-do extraction
  • The assistant is being extended into vertical ecosystems such as education, office work, search, maternal care, health, and commerce
  • The design is explicitly described as an end-cloud collaborative solution

Evidence from the source

ERNIE 3.5-128K is used for long meeting conversations, intelligent summarization, one-click meeting-note generation, and automatic to-do extraction (original: 文心3.5-128k长上下文模型，高效处理长对话、会议内容智能总结、AI一键生成会议纪要…待办自动生成).
HONOR and Baidu AI Cloud used ERNIE large models through end-cloud collaboration to upgrade YOYO for interaction, office productivity, and content creation scenarios (original: 荣耀与百度智能云通过端云协同的文心大模型赋能YOYO助手，实现智能交互、办公提效、内容创作等场景升级).
The assistant is also being expanded into vertical ecosystems across education, office, search, maternal care, health, and commerce (original: 智能体生态…在教育、办公、搜索、母婴、健康、商业等垂类展开生态合作).
The solution lets YOYO on both PC and mobile support intelligent creation, meeting notes, multi-document Q&A, free chat, role play, and emotional companionship (original: 基于文心大模型支持YOYO助手PC端和手机端实现智能创作、会议纪要、多文档问答、通用闲聊、角色扮演、情感陪伴等多个智能化能力).
Transparency Evidence & methodology 70/100 reference value · 87% confidence · 1 source

Review how this reference was scored and trace each normalized claim back to its documented source.

01

Scoring methodology

How scores are calculated

Customer Reference Value measures usefulness as a customer reference. Evidence Confidence measures the quality and traceability of available evidence, not independent verification.

Customer reference value70/100
  • Problem clarity20/20
    Measures whether the customer's operational problem is specific enough to compare.
  • Implementation depth25/25
    Rewards named components, data flow, integrations, and architecture detail.
  • Outcome specificity20/20
    Measures whether the reported benefit is concrete rather than a generic claim.
  • Quantified impact0/25
    0 metrics describe measurable impact.
  • Deployment scale5/10
    Rewards evidence of a live or scaled deployment and meaningful integration scope.
Evidence confidence87%
  • Source authority20/25
    The main evidence is an official vendor-published customer story.
  • Claim traceability21/25
    10 of 12 key fields link to a named source.
  • Direct evidence20/20
    4 direct source quotes retained.
  • Date provenance10/10
    The publication date comes from the source page or publisher.
  • Source transparency8/10
    1 source reference document publisher, URL, authority, retrieval, and supported fields.
  • Implementation specificity8/10
    Rewards source-backed components, data flow, quantified impact, and a specific outcome.
02

Traceability

Sources & provenance

Field coverage shows which facts each source supports. Dates are shown only when documented by the source.

  1. Baidu AI Cloud

    HONOR customer story

    First-party
    https://cloud.baidu.com/customer/case/honor.html
    Source type
    Vendor-published customer story
    Published
    Jun 20, 2025
    Supports
    • Customer
    • Business problem
    • Solution
    • Products
    • Solution components
    • Data flow
    • Integrations
    • technical area
    • use case category
    • Business outcome
    • outcome category
    • Metrics
    • Architecture
    • evidence quotes
    • Publication date

Date evidence

  • Published on source page Jun 20, 2025 · Baidu AI Cloud · First-party
    Open date source
Not separately sourced Industry, Region, Company size. Treat these normalized attributes as lower-confidence until a dedicated source is added.

Related

Similar use cases

See all like this
NVIDIA Feb 2, 2026 Amway Consumer Goods China Amway wanted to scale internal and marketer-facing generative AI while keeping data secure, inference efficient, and operations manageable, but it needed a controlled infrastructure for document analysis, presentation… 35 days to 15 days Enterprise Knowledge SearchSales Automation NVIDIA AI Enterprise · NVIDIA Base Command Manager Essentials · NVIDIA DeepSeek R1 NIM Google Cloud Archived · Jan 31, 2026 Gordon Food Service Consumer Goods United States To fully realize its vision of AI for the workplace and make AI more helpful for its employees, Gordon Food Service needed AI to understand business context, which means AI needs controlled access to business… Enabled universal knowledge discovery from core business application data sources and supercharged productivity… Enterprise Knowledge Search Gemini models · Google Workspace · Google Workspace with Gemini Baidu AI Cloud Dec 29, 2025 Beijing Yilian Tongda Technology Co., Ltd. Software / SaaS China Yilian Tongda needed a safer and more efficient way to help power-industry staff work with scattered standards, maintenance records, inspection documents and risk-control knowledge that were difficult to search and keep… Enterprise Knowledge SearchRisk Management Agent Technology · Qianfan AppBuilder · Qianfan ModelBuilder