Baidu AI Cloud Commercial and Professional Services China Translated from Chinese

Achievo (Beijing Teamsun Technology Co., Ltd.)

Customer Service Automation

Achievo wanted to upgrade its traditional intelligent-customer-service stack, which struggled with intent errors, weak context handling and repetitive answers, even though the company already had deep industry knowledge and many delivery projects.

Reported impact

Business outcome

Achievo upgraded its support products from scripted automation to context-aware generative AI, improved service quality and created a second internal-use analytics assistant on the same model foundation.

  • Customer Experience
  • Productivity Improvement
  • Risk Reduction

Solution

Achievo rebuilt its enterprise AI-service portfolio on Baidu AI Cloud to move from rule-heavy support tooling to generative customer-service products. The new stack combines Baidu's ERNIE large-model capabilities, a multi-turn dialogue engine and an intelligent speech engine, all delivered through the Qianfan platforms. Prompt-engineering and training toolchains are used to cluster and segment target customer groups, accelerate demand discovery and power agent-assist functions such as product-material guidance, workflow help and recommended talk tracks. Large-model summarization and entity-understanding features analyze whole conversation histories instead of isolated turns, which improves compliance insight, risk detection and response quality. Achievo also launched an intelligent data assistant that lets business users generate reports through natural-language interaction, turning the same foundation into an internal analytics product. In effect, Baidu's models became a shared service layer for both customer-facing and management-facing AI applications.

Data flow

Customer conversations and target-group data feed the Qianfan training and prompt-engineering stack, which powers agent-assist responses and compliance analysis; business users then query the same model foundation through the Intelligent Data Assistant to generate reports and decisions.

Solution architecture

5 components · 3 layers
  1. Compute
    • Qianfan ModelBuilder Supports prompt engineering, model tuning and scenario-specific optimization for Achievo's AI products.
  2. Serving
    • Multi-Turn Dialogue Engine Handles context-aware conversations across longer customer-service interactions.
    • Intelligent Speech Engine Adds speech interaction to the upgraded service experience.
    • Intelligent Data Assistant Lets managers create reports and business analyses through natural-language interaction.
  3. Orchestration
    • Qianfan AppBuilder Packages customer-service and analytics application workflows on top of Baidu's large models.

Architecture clues

  • Conversation-wide summarization supports compliance and risk analysis
  • Prompt engineering and training toolchains are used to segment customer groups
  • The same model base serves both service-assist and business-reporting scenarios

Evidence from the source

Achievo rebuilt its technology foundation with ERNIE, a multi-turn dialogue engine and an intelligent speech engine to create a new generation of generative AI plus customer-service products (original: 华胜天成基于百度文心大模型能力、多轮对话引擎、智能语音引擎等核心技术,对原技术底座进行了重构).
Baidu AI Cloud and Achievo jointly released an intelligent data assistant that lets operators generate reports through natural-language interaction (original: 百度智能云与华胜天成联合发布智能数据助手,通过自然语言交互,让企业经营者语言表达即生成报表).
Qianfan prompt-engineering and training tools help cluster target customer groups and give agent-assist products multiple assistant capabilities (original: 借助百度智能云千帆大模型平台,利用提示词工程及训练工具链,对目标客群聚类分类、切片分层).
The large model's summary and entity capabilities provide global contextual understanding, compliance insight and risk identification (original: 利用百度文心大模型实体摘要及总结能力,实现全局上下文语义理解和分析……识别违规现象和潜在风险).
Transparency Evidence & methodology 75/100 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 value75/100
  • 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 scale10/10
    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

    Achievo (Beijing Teamsun Technology Co., Ltd.) customer story

    First-party
    https://cloud.baidu.com/customer/case/huasheng.html
    Source type
    Vendor-published customer story
    Published
    Jun 19, 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 19, 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.