In the industrial pre-training of large language models (LLMs), large-scale web content extraction faces a critical trade-off: rule-based methods sacrifice quality for efficiency, while model-based methods do the opposite. As a result, existing solutions deployed at scale often lead to significant data quality degradation and corpus loss. To address this challenge, which we faced directly at Ant Group, this paper introduces HiParse, a hierarchical adaptive web parsing framework deployed in production. The core of HiParse is to abstract this multi-dimensional challenge into a ''PESO'' (Precision, Efficiency, Scope, Overhead) evaluation model, quantifying parser capabilities and parsing requirements from a ''supply-demand'' perspective. The framework integrates a hybrid parser system and uses a lightweight decision engine to dynamically route different web pages to the optimal parsing strategy. Comprehensive experiments show that HiParse not only achieves superior parsing quality (9.03/10 score) but its direct output corpus, with only 30 billion tokens, also improved the average performance of a downstream LLM on 11 benchmarks by 7.6%. Furthermore, the framework has proven its high throughput, cost-effectiveness, and alignment with business parsing demands under real industrial loads. HiParse provides a high-fidelity, scalable, and cost-effective data solution for enterprise-level LLM pre-training. All the relevant models in the paper will be open source soon.

With extending applications of digital surveillance video, the fast browsing technique for surveillance video has become a hot spot in the domain. As one of the most important supporting technologies, region of interest (ROI) information coding is a necessary part of fast browsing framework for surveillance video. Therefore, a novel coding method of object region flags and successful application of object mapping flags for the scalable browsing of surveillance video are proposed in this paper. This object region flags coding method includes both intra-frame coding and inter-frame coding, wherein, the former eliminates the redundancy in spatial domain by improving the scanning mode of region flags, the latter eliminates the redundancy in temporal domain, which cuts coding cost obviously and provides essential supports for video synopsis browsing of surveillance video.