Reported impact
Business outcome
The exchange gained a working监管科技 platform that improves daily public-opinion analysis efficiency and gives staff earlier warnings on potential capital-market risk events.
- Productivity Improvement
- Risk Reduction
Tencent CloudFinancial ServicesReal-time AnalyticsRisk ManagementAI and Machine LearningData AnalyticsProductivity ImprovementRisk ReductionUndated Tencent CloudTC#0052d9Financial ServicesChinaShenzhen Stock Exchange wanted to monitor fast-moving financial public opinion more effectively and use AI to identify capital-market risks earlier instead of relying on slower manual review of broad internet…4Real-time Analytics|Risk ManagementDeep Learning Event Clustering · Financial Public Opinion Analysis Platform · Knowledge Graph0 0000-00-00 4
Shenzhen Stock Exchange
Real-time Analytics · Risk Management
Shenzhen Stock Exchange wanted to monitor fast-moving financial public opinion more effectively and use AI to identify capital-market risks earlier instead of relying on slower manual review of broad internet information flows.
Solution
Shenzhen Stock Exchange worked with Tencent Cloud to build a financial public-opinion analysis platform for capital-market supervision. The platform ingests large volumes of real-time news and internet opinion data, then applies Tencent Cloud's NLP and knowledge-graph capabilities together with deep-learning event clustering, context analysis, and sentiment analysis. That pipeline deduplicates, classifies, clusters, and analyzes market-related content so staff can quickly isolate negative or sensitive financial signals instead of manually sifting broad information flows. Results are displayed and pushed in personalized ways based on monitoring needs, which lets multiple departments extract daily priority stories, analyze themes, and trigger earlier market-risk warnings. The implementation turns public opinion into a structured regulatory dataset that improves day-to-day efficiency and strengthens the exchange's ability to identify and manage capital-market risk.
Data flow
Internet public-opinion feeds flow into the analysis platform, where NLP, knowledge-graph processing, event clustering, and sentiment analysis deduplicate and classify content before personalized alerts and dashboards present negative or sensitive market signals to monitoring teams.
Solution architecture
- Compute
- NLP Technology Extracts meaning from large volumes of financial text so public opinion can be categorized and analyzed.
- Knowledge Graph Adds relationship context for entities and events appearing in capital-market public opinion.
- Deep Learning Event Clustering Groups related public-opinion events and supports trend and sentiment analysis at scale.
- Serving
- Financial Public Opinion Analysis Platform Acts as the user-facing monitoring system for analysis, visualization, and alert delivery.
Architecture clues
- Deep-learning event clustering, relationship analysis, and sentiment analysis are core algorithms in the stack.
- Outputs are personalized and pushed according to monitoring needs.
- The platform analyzes all-network real-time public-opinion information.
Evidence from the source
Shenzhen Stock Exchange wanted to use NLP and knowledge-graph technology together with Tencent Cloud's big-data strengths to apply regulatory technology to market-risk monitoring. (original: 深交所作为市场的重要参与者，希望利用自然语言处理、知识图谱等人工智能相关技术，结合腾讯云在大数据处理分析上的优势，探索实现监管科技在市场风险监测方面的应用。)
Tencent Cloud jointly built an intelligent financial public-opinion analysis platform that analyzes massive real-time public-opinion information from across the internet. (original: 腾讯云结合在人工智能领域的技术积累...联合打造了智能化的金融舆情分析平台。该平台可对全网海量实时舆情资讯进行分析处理。)
The platform uses deep-learning event clustering, context analysis, and sentiment analysis to deduplicate, classify, cluster, and analyze large volumes of public opinion. (original: 通过基于深度学习的事件聚类、脉络分析、情感分析等算法，实现了海量舆情的去重、分类、聚类、分析等功能。)
The system is used by multiple departments, helps staff quickly extract daily key public-opinion news, and gives earlier warnings on capital-market risk events. (original: 系统在客户多个部门得到实际应用，帮助业务人员快速抽取每日重点舆情新闻，大幅提升日常舆情分析工作效率，帮助业务人员提前预警资本市场风险事件。)
Transparency Evidence & methodology
Review how this reference was scored and trace each normalized claim back to its documented source.
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 clarity20/20Measures whether the customer's operational problem is specific enough to compare.
- Implementation depth25/25Rewards named components, data flow, integrations, and architecture detail.
- Outcome specificity20/20Measures whether the reported benefit is concrete rather than a generic claim.
- Quantified impact0/250 metrics describe measurable impact.
- Deployment scale5/10Rewards evidence of a live or scaled deployment and meaningful integration scope.
Evidence confidence77%
- Source authority20/25The main evidence is an official vendor-published customer story.
- Claim traceability21/2510 of 12 key fields link to a named source.
- Direct evidence20/204 direct source quotes retained.
- Date provenance0/10The publication date has no documented provenance.
- Source transparency8/101 source reference document publisher, URL, authority, retrieval, and supported fields.
- Implementation specificity8/10Rewards source-backed components, data flow, quantified impact, and a specific outcome.
Traceability
Sources & provenance
Field coverage shows which facts each source supports. Dates are shown only when documented by the source.
- https://cloud.tencent.com/customer/szseTencent CloudFirst-party
Shenzhen Stock Exchange customer story
Supports- Customer
- Business problem
- Solution
- Products
- Solution components
- Data flow
- Integrations
- technical area
- use case category
- Business outcome
- outcome category
- Metrics
- Architecture
- evidence quotes
Not separately sourced Industry, Region, Company size. Treat these normalized attributes as lower-confidence until a dedicated source is added.
Related
Similar use cases
In-house Sample Oct 9, 2026 BBVA BBVA's trading desk needs to respond to institutional client requests for bond, interest-rate swap, and foreign-exchange quotes within milliseconds while balancing competitiveness, profitability, portfolio risk, and… within milliseconds Atalaya · Bloomberg · Viriato In-house Sample Apr 16, 2026 UBS Asset Management UBS Asset Management needs to support multi-asset investing decisions across strategy design, tactical asset allocation, portfolio construction, security selection, research, and portfolio implementation while rapidly… Automated trade scheduling · Dendrogram clustering · Execution optimization algorithms 
Google Cloud Sample Archived · Apr 13, 2026 Finhike Finhike needed a cloud platform that could keep a lending stack fast and available in unstable connectivity environments, power real-time risk decisions, and let the team launch country-specific services with minimal… BigQuery · Cloud Logging · Cloud Monitoring