随着大数据、云计算、人工智能等数字技术的加速演进，各领域智能化、信息化、数字化已成为未来的大势所趋。深地工程作为国家重大战略科技问题，必然面临智能化升级。然而，深部岩体“三高一扰动”的复杂特征给深地工程智能化转型带来严峻的挑战。为实现深地工程与数字技术的高效融合，研究基于“感知−传送−解译−分析−决策”的智能化实践路径，系统回顾了地下工程中智能感知、实时传输、信息解译、数据分析、智能决策等领域的代表性研究进展，并针对性提出了“多感知、快响应、大数据、优方法、精模型、强平台、易推广”的深地工程智能建造发展方向。研究表明：① 前沿的深地工程感知技术包括：光纤传感器、MEMS传感器、计算机视觉、自动化机器人等，待数据采集完毕后，通过兼具配置简单、容错能力强、可移动性好等优点的无线通信协议完成数据的实时响应，以实现深地工程监测数据的精准感知与实时传输；② 深地工程原位监测技术获取的数据类型主要包括图像、波、点云等，对原始数据解译及分析的模型众多，采用新一代的人工智能技术，如：人工神经网络和深度学习技术，可显著提高解译与分析的效率；③ 智能决策系统具备高效的学习能力，能够适应复杂环境下的不确定性，通过循环自主学习，以进行决策问题的智能解答。当前，我国深地工程智能建造的政策与产业体系已基本建立，大量智能建造系统已应用于实践。基于此，从智能感知与信息解译、围岩评价及安全评估、围岩控制与动态修复、平台开发及应用推广等4个方面展望了数智化深地工程的发展方向，进而构建了基于多源信息的深地工程围岩稳定性综合评价与分析系统构想。

With the accelerated evolution of digital technologies such as big data, cloud computing, and artificial intelligence, the trends of intelligence, informatization, and digitization have become imminent across various domains. Deep earth engineering, as a major strategic scientific and technological issue for the nation, is inevitably poised for intelligent upgrades. However, the complex characteristics of “three highs and one disturbance” in deep rock masses pose some severe challenges to the intelligent transformation of deep earth engineering. In order to achieve an efficient integration of deep earth engineering and digital technology, this study focuses on the intelligent practice path based on “perception, transmission, interpretation, analysis, decision”. The representative research progress in intelligent perception, real-time transmission, information interpretation, data analysis, intelligent decision-making and other fields in underground engineering is systematically reviewed, and the targeted development directions for deep earth engineering intelligent development are proposed, including multi perception, fast response, big data, optimal methods, precise models, strong platforms and easy promotion. Research findings indicate that ① The cutting-edge deep earth engineering perception technologies include fiber optic sensors, MEMS sensors, computer vision, automated robots, etc. After data collection is completed, the real-time response of data is achieved through the wireless communication protocols that combine the advantages of simple configuration, strong fault tolerance, and good mobility, in order to achieve an accurate collection and real-time transmission of deep earth engineering monitoring data. ② Deep earth engineering survey technology yields data types such as images, waves, and point clouds. Numerous models for interpreting and analyzing raw data exist. The application of next-generation artificial intelligence technologies, such as artificial neural networks and deep learning, significantly improves the efficiency of interpretation and analysis. ③ The intelligent decision-making system possesses efficient learning capabilities, adapting to the uncertainty in complex environments through cyclic autonomous learning to provide intelligent solutions for decision-making problems. Currently, China’s policies and industrial systems for the intelligent construction in the deep earth engineering have been essentially established, with a plethora of intelligent construction systems already applied in practical settings. Building upon this foundation, the study envisions the development direction of digital deep earth engineering in four aspects: intelligent collection and information interpretation, surrounding rock evaluation and safety assessment, surrounding rock control and dynamic repair, and platform development and application promotion. Furthermore, a comprehensive evaluation and analysis system for surrounding rock stability of deep earth engineering based on multi-source information is constructed.