Tencent Cloud Financial Services China Translated from Chinese

WeBank (微众银行)

Risk Management

WeBank needed to launch and scale an internet-only banking model quickly while keeping infrastructure cost under control and making remote customer identity verification trustworthy enough for core account-opening and card-binding workflows.

Account-management cost fell by 80%.
Average public-network latency fell from 100ms to 20ms.
DDoS protection provided 20Gbps of scrubbing capacity.
Remote identity verification achieved more than 95% accuracy.

Reported impact

Business outcome

WeBank launched an all-cloud banking model with lower operating cost, faster network response, and production facial-verification workflows that let customers complete key identity checks remotely instead of relying on offline processing.

  • Cost Reduction
  • Customer Experience
  • Risk Reduction
  • Scalability

Solution

WeBank used Tencent Cloud to build a de-IOE banking architecture that combined cloud infrastructure with AI-based remote identity verification. The platform runs in Tencent Cloud's finance-compliance environment, with TDSQL supporting account and transaction workloads while dedicated lines, VPN, private networking, BGP connectivity, and CDN provide secure low-latency access for customers and institutional exchanges. For onboarding and second-bank-card binding, Tencent YouTu supplies lip-reading liveness detection and facial recognition so users can be verified remotely instead of visiting offline branches. That identity step feeds directly into digital banking workflows, preserving an online service model without dropping core security controls. The result is a cloud-native banking stack that cut account-management cost by 80%, improved response performance, and delivered verification accuracy above 95% with an error rate below one per thousand.

Data flow

Customer account-opening and second-card-binding requests enter WeBank's online channels, Tencent YouTu runs remote liveness and facial-verification checks, verified customer and transaction data are stored in TDSQL, and dedicated lines, VPN, private networking, and CDN keep customer access and institutional data exchange secure and responsive.

Solution architecture

6 components · 3 layers
  1. Compute
    • Tencent YouTu Provides facial recognition and lip-reading liveness detection for remote identity verification.
  2. Storage
    • TDSQL Stores banking data on a financial-grade database platform with multi-site disaster-recovery support.
  3. Serving
    • Private Network Connects cloud resources in an isolated environment for secure banking operations.
    • Dedicated Line Access Links the bank to nearby Tencent Cloud nodes and external institutions with higher-performance network paths.
    • VPN Extends secure connectivity between private-network resources and other environments in the hybrid architecture.
    • CDN Publishes user-facing content to edge nodes so banking users can access services with lower latency and higher success rates.

Architecture clues

  • BGP connectivity spans 17 major domestic ISPs and supports 100 million connections with 6 million concurrent requests.
  • TDSQL is described as supporting daily transaction volumes in the billions with strong synchronous multi-site disaster recovery.
  • The platform was built as a de-IOE, fully cloud-based banking architecture.

Evidence from the source

Cross-region traffic scheduling shortened average public-network latency from 100ms to 20ms and protected stable business operations. (original: 通过跨地域流量调度技术,公网的平均时延从100ms缩短至20ms,保障用户业务的稳定运营。)
TDSQL cut database spending by more than 50% compared with traditional databases and has supported daily transaction volumes in the billions with zero-failure operation for years. (original: 数据库则采用了腾讯云金融级数据库TDSQL,光是这一项支出,相比传统数据库就节约了50%以上的成本。TDSql一直成熟应用于腾讯内部的交易和支付体系中,成功支持日十亿的交易量,支撑了数亿用户多年来0故障运营。)
WeBank quickly launched as the world's first fully cloud-based bank and reduced account-management cost by 80%, while also using facial-verification technology from Tencent Financial Cloud to create innovative online workflows. (original: 微众银行通过腾讯云,构建全新去IOE高扩展性架构,快速开业成为全球首家全云上银行,并降低80%账户管理成本,同时采用金融云的人脸核身等新技术,打造创新的互联网业务流程。)
When users bind a second bank card, Tencent YouTu's lip-reading liveness detection and facial-recognition technology enabled remote identity verification with accuracy above 95% and an error rate below one per thousand. (original: 通过使用腾讯优图独创的结合唇语的活体检测技术以及世界领先的人脸识别技术,银行在用户身份远程识别中达到了95%以上的准确率以及低于千分之一的错误率。)
Transparency Evidence & methodology 100/100 reference value · 85% confidence · 2 sources

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 value100/100
  • 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 impact25/25
    4 metrics describe measurable impact.
  • Deployment scale10/10
    Rewards evidence of a live or scaled deployment and meaningful integration scope.
Evidence confidence85%
  • Source authority20/25
    The main evidence is an official vendor-published customer story.
  • Claim traceability25/25
    12 of 12 key fields link to a named source.
  • Direct evidence20/20
    4 direct source quotes retained.
  • Date provenance0/10
    The publication date has no documented provenance.
  • Source transparency10/10
    2 source references document publisher, URL, authority, retrieval, and supported fields.
  • Implementation specificity10/10
    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. Tencent Cloud

    Webank微众银行

    First-party
    https://cloud.tencent.com/customer/wzyh
    Source type
    Vendor-published customer story
    Supports
    • Customer
    • Region
    • Business problem
    • Solution
    • Products
    • Solution components
    • Data flow
    • Integrations
    • Business outcome
    • Metrics
    • Architecture
    • evidence quotes
  2. WeBank

    2023 Annual Report

    First-party
    https://tctp.tctpwebankcdn.net/owb-admin/data/appsystems/owb-admin/1724837556944-43754.pdf

    The 2023 annual report states: As at 31 December 2023, the Bank had 2,661 employees; the standard mapping classifies 1,000+ employees as Enterprise.

    Source type
    Official annual report
    Supports
    • Company size
Not separately sourced Industry. Treat these normalized attributes as lower-confidence until a dedicated source is added.

Related

Similar use cases

See all like this