System for activating and conducting interaction sessions using physical identification units

Abstract

(Main claim) System for dialogically triggering a structured interaction session between a user and an assistance system, comprising: • at least one physical identifier unit (1), wherein each physical identifier unit (1) has a machine-readable identifier (2) and forms a physical body; • a recognition unit (3), configured to identify one or more physical identifier units (1) placed in a detection area by means of the identifier (2), wherein the recognition unit (3) uses at least one detection modality for evaluating the identifier (2); • at least one audio output unit (4) and at least one audio input unit (4a), and optionally at least one further actuator, selected from an optical display element and a haptic actuator;• a processing unit (5) that is connected to the recognition unit (3), the audio output unit (4) and the audio input unit (4a) via signaling; • a data storage device (6) or a data interface (6) configured to provide a plurality of audio elements, comprising at least speech recordings, soundscapes and / or structural elements; characterized in that the processing unit (5) is configured to activate a session context assigned to the at least one identified physical identifier (1) on the basis of its identification feature (2);• After activating the session context and before the start of an actual interaction session, optionally perform a dialogic pre-configuration process in which a context-dependent request is issued to the user via the audio output unit (4), at least one user response is received, and a recommended configuration for the subsequent interaction session is determined based on the user response, whereby the dialogic pre-configuration process is intended as the system's default behavior and can be skipped or deactivated by a user setting; • subsequently execute a temporally structured, multi-stage interaction workflow with at least two consecutive phases according to the determined configuration;• to generate a session-specific audio composition at runtime during the interaction workflow from the majority of the provided audio elements, wherein the selection, order and / or superimposition of the audio elements is determined depending on the session context, the specific configuration and the current phase of the interaction workflow; • to output the generated audio composition via the audio output unit (4); • wherein the system is configured to allow the interaction session to be conducted without a screen, so that the primary user interaction takes place without a visual display on a graphical screen and without the need for a mobile device; • and wherein the content of the audio composition is not stored in the physical identifier unit (1), but is assembled at runtime from the data storage (6) and / or via the data interface (6) based on the session context and the specific configuration.