Cyberspace maps facilitate the understanding of complex, abstract cyberspace. Due to the exponential growth of the Internet, the complexity of cyberspace has escalated dramatically. Traditional cyberspace maps are primarily for professionals and thus remain challenging for non-professionals to interpret. Ordinary users often find themselves overwhelmed by the vast amount of information and the complexity of cyberspace. This renders traditional visualization tools inadequate for the general public, thereby highlighting the urgent need for more intuitive and accessible representations. This study uses the metaphor of cyberspace as a familiar geographical space to simplify the understanding of its internal relationships. Based on Autonomous System (AS) connectivity data, a “node-link” model is created to illustrate cyber interactions and dependencies, forming a foundation for analysis. The GMap algorithm visualizes AS connectivity data of countries, converting it into an intuitive map that clearly illustrates the cyber composition and dynamics. Cyber potential and national influence are considered to enhance map practicality and accuracy. A cyber-geography metaphor model integrates scientific and geographical elements, improving readability. The optimized GMap algorithm includes a holisticcyberspace strength index, showing both connectivity and relative country strength in cyberspace. This metaphorical approach aims to reduce information complexity, making cyberspace more comprehensible to the general public.

Multimodal large language models (MLLMs) have demonstrated promising potential in addressing real-world vision-language tasks. However, existing MLLMs exhibit relatively limited capabilities in understanding street view images, struggling to achieve multi-level semantic understanding and spatial reasoning for region-level fine-grained inference in street view images, which to some extent limits their potential in geospatial artificial intelligence (GeoAI). This study constructs an instruction fine-tuning dataset to guide MLLMs in learning spatial knowledge and scene features from street-view images, called SVGPT-Instruct. This large-scale dataset for street view understanding encompasses 430K instruction samples and 110K street view images. Ultimately, we propose the StreetViewGPT, an MLLM-based method for street view image scene perception and reasoning. The StreetViewGPT is capable of uniformly handling various street view image tasks, including time estimation (TE), weather recognition (WR), scene classification (SC), spatial distance estimation (SDE), and scene graph generation (SGG). The experimental results show that in the TE, WR, and SC tasks, the accuracy of StreetViewGPT improved by 1.33%, 21.68%, and 18.83% respectively compared to the suboptimal model. In the SDE task, the accuracy of predictions falling within the three error tolerance intervals of [75%, 125%], [50%, 150%], and [25%, 175%] reached 88.3%, 97.7%, and 99.5%, respectively, which improved by 78.2%, 78.7%, and 58.6%. In the SGG task, Recall and Mean Recall reached 16.09% and 6.84%, respectively, which improved by 12.49% and 5.4% compared to Qwen2-VL. It demonstrates that StreetViewGPT possesses multi-level semantic understanding and spatial reasoning capabilities, ranging from global semantic perception at the image level to fine-grained reasoning at the region level. The proposed method enhances the recognition and cognition capabilities for spatial scenes in street view images, offering positive implications for smart city perception and autonomous driving navigation research.

Constructing more effective maps for robots has gained increasing attention in the domain of cartography and GIS (geographic information science). Existing task-relevant mapping methods in robotics relies predominantly on the semantic dimension, neglecting the temporal and spatial dimensions that are fundamental to cartographic theory. Inspired by thematic cartography, we propose a novel task-relevant online incremental map construction method that enforces spatiotemporal and semantic consistency. Continuous sensor streams are encoded into structured segments that are characterized by temporal, spatial, and semantic features. A three-channel association mechanism computes a joint task-relevant conditional distribution, which drives an Agglomerative Information Bottleneck module to filter and cluster task-relevant quasi-objects. Subsequently, a Multi-Dimensional Association Cost Matching strategy unified with Exponential Moving Average smoothing integrates complementary spatiotemporal and semantic costs into a single optimization objective, establishing a long-term consistent incremental map maintenance mechanism. Experiments on indoor RGB-D datasets across three scene scales demonstrate that the proposed method significantly outperforms the baseline Clio method, achieving improvements of 18.9% in F1 score, 9.1% in accuracy, and 49.9% in precision. It enables compact, robust, and task-relevant online incremental construction of 3D Scene Graph, effectively enhancing temporal continuity, spatial adjacency, and semantic consistency in map construction and maintenance.