A Scenario-Knowledge-Driven Pipeline for Just-in-Time Assistance

2026-09-15

AI Summary

研究提出一种基于场景知识的管道，通过配置感知、约束大语言模型推理和形成分级干预提案来解决自助服务终端用户无声挣扎时的即时辅助问题。

Abstract

Detecting a silently struggling kiosk user is only the first step; deciding whether, when, and how to help depends on scenario knowledge usually buried in model weights and thresholds. We propose a scenario-knowledge-driven pipeline: a single scenario knowledge document, human-authored and version-controlled, configures sensing, constrains LLM reasoning, and shapes a graded intervention proposal. Narration, assistance-need assessment, and proposal are kept separate for independent audit. As proof of concept, we replay two recorded kiosk sessions offline, chosen before the runs for their struggle evidence and retrospective detail. Both cases support what the design promises: checkable reporting and measured escalation. Across 95 updates, every sentence of the append-only narration cites the primitive events underlying it, and the rule layer detects 12 of 13 and 7 of 7 annotated struggle episodes under a strict criterion. The assessor de-escalates on recovery and reaches the top rung exactly once, under maximally converging evidence. At the decisive help-seeking turn, narration, assessment, and the participants' retrospective accounts converge. The appropriateness of these interventions, the pipeline's restraint on sessions without struggle, and the document's transfer to a new scenario frame the agenda.

Problem

• scenario knowledge
• just-in-time assistance
• kiosk user
• struggle detection
• intervention proposal

Innovation

• scenario-knowledge-driven
• pipeline
• just-in-time assistance
• LLM reasoning
• graded intervention proposal