Recent advances in knowledge graphs show great promise to link various data together to provide a semantic network. Place is an important part in the big picture of the knowledge graph since it serves as a powerful glue to link any data to its georeference. A key technical challenge in constructing knowledge graphs with location nodes as geographical references is the matching of place entities. Traditional methods typically rely on rule-based matching or machine-learning techniques to determine if two place names refer to the same location. However, these approaches are often limited in the feature selection of places for matching criteria, resulting in imbalanced consideration of spatial and semantic features. Deep feature-based methods such as deep learning methods show great promise for improved place data conflation. This paper introduces a Semantic-Spatial Aware Representation Learning Model (SSARLM) for Place Matching. SSARLM liberates the tedious manual feature extraction step inherent in traditional methods, enabling an end-to-end place entity matching pipeline. Furthermore, we introduce an embedding fusion module designed for the unified encoding of semantic and spatial information. In the experiment, we evaluate the approach to named places from Guangzhou and Shanghai cities in GeoNames, OpenStreetMap (OSM), and Baidu Map. The SSARLM is compared with several classical and commonly used binary classification machine learning models, and the state-of-the-art large language model, GPT-4. The results demonstrate the benefit of pre-trained models in data conflation of named places.

Recent developments in Web Service and Semantic Web technologies have shown great promise for the automatic chaining of geographic information services (GIService), which can derive user-specific information and knowledge from large volumes of data in the distributed information infrastructure. In order for users to have an informed understanding of products generated automatically by distributed GIServices, provenance information must be provided to them. This paper describes a three-level conceptual view of provenance: the automatic capture of provenance in the semantic execution engine; the query and inference of provenance. The view adapts well to the three-phase procedure for automatic GIService composition and can increase understanding of the derivation history of geospatial data products. Provenance capture in the semantic execution engine fits well with the Semantic Web environment. Geospatial metadata is tracked during execution to augment provenance. A prototype system is implemented to illustrate the applicability of the approach.

Geospatial data provide an important basis for urban governance, resource management, disaster assessment, and public health analysis by linking spatial locations, attribute information, and dynamic processes. However, complex geospatial analysis still requires substantial expertise in spatial databases, spatial SQL, and GIS computation tools. Although large language model-based Text-to-SQL methods have lowered the barrier to natural language-driven data querying, most existing approaches rely on single-step SQL generation and remain unstable for spatial tasks that involve attribute retrieval, spatial relationship evaluation, geometric operations, and statistical aggregation. To address this limitation, this paper proposes a Code Generation-Driven Query–Computation Separation Framework (CGD-QCSF). The framework is based on the separation of query and computation, and decomposes complex geospatial analysis into a staged execution process. CGD-QCSF coordinates intent understanding, schema pre-filtering, planning, execution state management, SQL generation, and spatiotemporal computation. A structured planner and an execution state manager coordinate task decomposition, capability-aware routing, and evidence-based recovery. A SQL Code Generation Agent (SCGA) handles database access, attribute filtering, and intermediate data extraction, while a Spatiotemporal Computation Agent (STCA) performs out-of-database spatial computation and statistical aggregation in an isolated Python sandbox. We construct a benchmark of 200 tasks, covering easy, medium, and hard spatial tasks. In the main experiment with Qwen3.7-Plus as the foundation model, CGD-QCSF achieves a Strict Structured Accuracy (SSA) of 90.5%. Removing the Planner reduces SSA to 84.5%, while removing the STCA reduces it to 70.5%. The ablation experiments show that removing either the Python sandbox or the Planner Agent degrades performance on complex tasks. These results indicate that CGD-QCSF extends complex geospatial analysis from single-step SQL generation into a multi-staged execution process. By explicitly separating query and computation, the framework reduces interference between spatial computation logic and database schema information, thereby improving the stability and success rate of natural language-driven geospatial analysis.