Jean Martins

Jean Martins, Leonid Mokrushin, Marin Orlic

Intent-based networking promises to revolutionize telecommunications network management by enabling operators to specify high-level goals rather than low-level configurations. The TM Forum Intent Ontology (tio) provides a standardized vocabulary for expressing network intents, yet lacks formal validation mechanisms to ensure intent correctness before its admission. We present tio-shacl, the first comprehensive SHACL (Shapes Constraint Language) validation framework for the TMF Intent Ontology. Our contribution includes 56 node shapes and 69 property shapes across all 15 tio v3.6.0 ontology modules, a reusable constraint library with 25 parameterized SPARQL-based constraint components, and novel validation patterns for recursive logical operators, quantity-based constraints, and cross-expectation relationships. We pursued 100% vocabulary coverage (87 classes, 109 properties, 72 functions), cross-implementation compatibility across three major SHACL engines, and validation accuracy on a corpus of 133 test cases. tio-shacl is publicly available under MIT license at https://github.com/EricssonResearch/tio-shacl and enables automated syntactic and semantic validation of network intents, addressing a critical gap in the field.

Jean Martins, Leonid Mokrushin, Marin Orlic et al.

Intent-based automation for 6G envisions networks steered by high-level goals rather than low-level configurations. Existing LLM-based approaches translate natural language into plausible intent representations but typically omit what production deployment requires: grounding in actual service catalogs, formal validation, and cross-layer decomposition. We address this with an agentic workflow comprising three coupled reasoning layers: (i) grounding the translation in a semantic service catalog that exposes TMF compliant service specifications; (ii) validation of the RDF intent via SHACL structural checking against the TMF Intent Ontology; and (iii) decomposition that selects a CFSS profile via constraint satisfaction over QoS capability envelopes, then covers its infrastructure requirements with RFSS profiles via weighted set cover. Across 930 benchmark runs over six GPT-4.1/5 models, the workflow achieves 97% success in structured mode and 90% on average across natural-language scenarios, with 100% correct rejection of infeasible requests. Grounding LLM context in catalog capability metadata reduces adversarial hallucinations by 26 percentage points; larger gains than scaling model size alone.