This paper provides a direct understanding of the labour-saving threats embedded in decarbonisation pathways. It starts with a mapping of the technological innovations characterised by both climate change mitigation/adaptation (green) and labour-saving attributes. To accomplish this, we draw on the universe of patent grants in the USPTO since 1976 to 2021 reporting the Y02-Y04S tagging scheme and we identify those patents embedding an explicit labour-saving heuristic via a dependency parsing algorithm. We characterise their technological, sectoral and time evolution. Finally, after constructing an index of sectoral penetration of LS and non-LS green patents, we explore its correlation with employment share growth at the state level in the US. Our evidence shows that employment shares in sectors characterised by a higher exposure to LS (non-LS) technologies present an overall negative (positive) growth dynamics.

中文翻译：

---

绿色专利中的省力启发式方法：自然语言处理分析


本文提供了对脱碳途径中嵌入的节省劳动力的威胁的直接理解。它首先对以气候变化缓解/适应（绿色）和节省劳动力属性为特征的技术创新进行了映射。为了实现这一目标，我们借鉴了自 1976 年至 2021 年以来美国专利商标局报告 Y02-Y04S 标记方案的专利授权范围，并确定了那些通过依赖关系解析算法嵌入了显式节省劳动力的启发式方法的专利。我们描述了他们的技术、行业和时间演变。最后，在构建了 LS 和非 LS 绿色专利的行业渗透指数后，我们探讨了它与美国州一级就业份额增长的相关性。我们的证据表明，以 LS（非 LS）技术敞口较高为特征的行业的就业份额总体上呈现出负（正）增长动态。