本项目针对ChinaVis挑战赛挑战一的参赛思路以及实现结果进行了整理

MoD Assurance Assessment Build delivered a data-driven assurance assessment build that automates evaluation of project documents against GovS 002 criteria, producing structured ratings, scores, and commentary at scale.

SpeakOutIQ built SpeakOutIQ, a policy decision‑support platform that combines statistical analysis with an interactive dashboard and optional locally hosted AI to translate NDA misuse evidence into clear, policy‑ready insights. The solution is designed to help campaigners and legislators explore harm, reporting behaviour and sector patterns...

Evidence Query Assistant demonstrated a lightweight AI-assisted evidence query approach using ChatGPT to interrogate assurance documents against defined criteria and return clear, traceable answers identifying where evidence exists or is missing.

hack26 is a collaborative hackathon-style event focused on rapidly exploring and prototyping practical data and AI solutions against a defined set of challenges. Teams work within clear challenge boundaries to test ideas, build proof‑of‑concepts and share learning in a short, intensive format.

Local RAG Assurance Engine delivered a fully local, offline-capable assurance analysis engine using retrieval‑augmented generation (RAG) to identify and surface evidence from project documentation and return structured, machine‑readable outputs.

Coding challenge as per doc.

The team developed an AI-enabled risk management solution that integrates SME heuristics with automated evaluation to improve the quality and actionability of project risk registers. The approach combines Microsoft Power Platform components with LLM-driven analysis to identify weak risks and mitigations, prioritise critical issues, and support c...

NDA Harm Evidence Explorer built a policy-facing web application that turns anonymised survey data and survivor testimonies into clear, judge-ready evidence of NDA-linked harm. The solution surfaces patterns across sectors, regions and reporting paths, and generates concise narratives that policymakers can reuse in consultation and briefing mate...

Frontend Mentor Challenge

Project:Hack27 is a community hackathon bringing teams together to design, pitch and judge practical solutions across six defined challenges, with a focus on innovation, clear value and real‑world impact.

Hack25 is a collaborative hackathon-style event focused on rapid experimentation, problem-solving and practical innovation across data, AI and modern digital tooling. Teams explore defined challenges, prototype solutions and share learnings within a short, delivery‑driven format.

PHP MySQL Login System

The team built a rule‑driven risk assessment system that converts SME survey responses into structured, validated heuristics. Using LLMs, fuzzy matching, and human‑in‑the‑loop review, they generate, deduplicate, and govern high‑quality risk and mitigation rules that can be applied consistently across risk registers.

NDA Statistical Evidence focused on rigorous statistical testing of the Speak Out Survey data to establish clear associations between NDA use, reporting outcomes and experienced harm. The team prioritised transparent, reproducible analysis to support credible, evidence‑led policy arguments.

PEAT Document Assessment System developed an interactive assurance evidence assessment solution that applies large language models to analyse project documentation, score maturity, and surface assurance evidence and gaps aligned to recognised governance frameworks.

The team produced a data‑driven risk heuristics analysis pipeline that combines Python analytics with large language model feedback to assess and enrich existing risk registers. Using Jupyter notebooks, they analyse risk and mitigation data, apply SME heuristics via an LLM, and output annotated spreadsheets and summary datasets designed for do...

Sector Risk Lens developed a sector‑level risk analysis that translates NDA misuse and reporting failures into clear, policy‑relevant signals. Using survey data and interpretable modelling, the team highlights where harmful behaviours concentrate and frames results in plain language suitable for non‑technical decision‑makers.

The team built Jim‑E, an interactive AI‑assisted risk review tool that applies SME heuristics to project risk entries. Using a lightweight Streamlit interface and encoded heuristic rules, the solution helps users identify weak risks and mitigations, capture structured feedback, and generate clear audit‑ready reports.