evidoria

← Voltar à navegação

Boa prática Importada

ClassifAI e Survey Assist — o Pipeline de IA do ONS do Reino Unido que Reduziu para Metade o Tempo de Codificação de Ocupações

Reino Unido · Newport · Ver o perfil de Reino Unido

Evidência: Observacional / pré-pós Top 7% 87/100 · Pergunte a Evidence Copilot sobre esta prática

O ONS do Reino Unido criou o ClassifAI, de código aberto, para codificar texto de inquéritos em classificações oficiais, reduzindo para metade o tempo de codificação de ocupações num grande inquérito laboral, e testa agora o Survey Assist sob registo público de transparência.

-50% %
Reduction in occupation-coding processing time on ASHE
~90,000 households
Households potentially covered by Survey Assist once deployed (annual, once deployed)
~2.25 million instances
Survey instances Survey Assist could cover annually (annual, once deployed)
ClassifAI e Survey Assist — o Pipeline de IA do ONS do Reino Unido que Reduziu para Metade o Tempo de Codificação de Ocupações

Detalhes

Maturidade
Em expansão
Promotor
UK Office for National Statistics (ONS) - Data Science Campus
Período
2023-present
Palavras-chave
official statistics, government data science, labour statistics

Contexto

National statistics offices spend significant staff time manually coding survey respondents' free-text answers into standard classifications such as the Standard Occupational Classification (SOC) and Standard Industrial Classification (SIC), a bottleneck as survey volumes grow. The UK's Office for National Statistics (ONS) Data Science Campus built ClassifAI, an open-source Python package that combines semantic search over previously coded examples with retrieval-augmented generation.

Objetivos

ClassifAI aims to assign free text automatically to classifications including SOC, SIC, COICOP and their international equivalents (ISCO, ISIC). Building on the same pipeline, the ONS is separately piloting 'Survey Assist' on the Transformed Labour Force Survey, using AI-generated follow-up questions to sharpen SIC/SOC coding.

Atividades

ClassifAI, according to the ONS's own account, is now coding labour market data in production, including a large-language-model application used on the Annual Survey of Hours and Earnings (ASHE). Survey Assist, which could cover around 90,000 households (about 2.25 million survey instances a year) once deployed, was published on 30 October 2025 under the UK's Algorithmic Transparency Record Standard (v3.0), documenting its pilot status, data flows, human clerical review and a planned evaluation against gold-standard coded data.

Resultados

The ONS's own account states that the large-language-model application built on ClassifAI halved processing time for occupation coding on ASHE. Survey Assist, the newer follow-up-question tool, has not yet published accuracy or consistency results, as testing was still under way through 2025.

Conclusões

The Survey Assist Transparency Record sets a materially higher public-transparency bar than most comparable AI deployments in this dataset, but the well-evidenced part of the impact claim remains limited to the ASHE processing-time figure, with Survey Assist itself still unproven in production.

Implementação
Custo indicativo
Médio (50 mil–500 mil €)
Tempo até resultados
Médio (1–3 anos)
Equipa e competências
ONS Data Science Campus (in-house team, Newport)

Condições de sucesso

  • Open-source (MIT-licensed) codebase enabling reuse and scrutiny
  • Retrieval-augmented generation over a library of previously coded examples
  • Publication under the UK Algorithmic Transparency Record Standard (v3.0)
  • Human clerical review retained alongside the AI-generated codes

Modos de falha comuns

  • Survey Assist has no published accuracy or consistency results yet; testing was still under way through 2025

Habitualmente financiado por

National / regional programmes

Vias de financiamento indicativas para práticas deste tipo — verifique sempre os avisos abertos e as regras de elegibilidade de cada programa.

Kit de replicação

Artefactos reutilizáveis desta prática — tal como publicados pelas suas fontes.

Implementa esta prática? Reivindique-a — implementadores verificados obtêm um contacto público na página e podem propor correções.

Fontes de dados

De onde foi obtida a informação desta prática, e quando.

Anexos

Práticas semelhantes que podem ser úteis