Skip to content

Requirements

The system requirements for the Individual Experience AI Engine, written in line with ISO/IEC/IEEE 29148:2018 and traced to visitor user stories.

Requirements are the agreed contract for what the engine must do and how well. They are written so that everyone, from historians and site curators to engineers, reads the same expectation, and so progress can be checked objectively.

Each requirement follows a consistent shape, [Condition] [Subject] [Action] [Object] [Constraint], for example "When signal X is received, the system SHALL store event X within 2 seconds." Mandatory items use SHALL; optional ones use SHOULD or MAY. Every requirement is grounded in a visitor user story (off-site visitor preparing a trip, on-site visitor, remote virtual visitor, organised group), which keeps it traceable from motivation to implementation.

Two categories. Full definitions live in the deliverable's Appendix B; descriptions below.

Functional, data and storage

ID Description
WP5-DATA-01 On consent at registration, store optional visitor info (nationality, place of birth, age range, knowledge level) to a relational DB
WP5-DATA-02 On interaction with a platform, persist the interaction event to an event store
WP5-DATA-03 On processing text, MAY determine emotional valence via sentiment analysis
WP5-DATA-04 On estimating a user state, store the inferred state with contextual metadata
WP5-DATA-05 On ingesting content and generating embeddings, persist vectors to a vector DB

Functional, behavior

ID Description
WP5-FR-01 With no profile data, provide a generic curated experience
WP5-FR-02 Support filtering and recommendation by preferred language
WP5-FR-03 Compute similarity between visitor profile and stored prisoner / diary-writer profiles (demographic and knowledge-level)
WP5-FR-04 Present content related to the visitor's live physical location (on-site)
WP5-FR-05 Present content matching profile characteristics (nationality, age, gender, visit history)
WP5-FR-06 Retrieve an item's context by querying the KG semantic structure
WP5-FR-07 Perform fuzzy string and semantic matching to connect imprecise inputs to KG entities
WP5-FR-08 Estimate user states (attention, engagement, satisfaction, emotional reaction) in real time
WP5-FR-09 On focused exploration, offer semantically dissimilar suggestions to encourage discovery
WP5-FR-10 On an adaptive action, log the triggering state, affected content, timestamp, and rationale
WP5-FR-11 MAY provide KG-based justifications (for example "shared location and event")

Non-functional

ID Description
WP5-NFR-01 Deliver contextual suggestions within 1 second of the triggering interaction
WP5-NFR-02 Complete user-state estimation and availability within 1 second of an interaction

The implemented endpoints and the online serving design that target these latencies are in Online serving model.