US-20260126851-A1 - METHOD AND APPARATUS FOR INITIATING AN ACTION

US20260126851A1US 20260126851 A1US20260126851 A1US 20260126851A1US-20260126851-A1

Abstract

An apparatus comprises a first sensor ( 101 ) and second sensor ( 103 ) arranged to determine a first and second set of properties for entities being devices or persons, the sets being determined in accordance with different sensor modalities. A first processor ( 105 ) determines directions between entities and a second processor ( 107 ) determines an orientation of an entity. A first detector ( 109 ) detects a bi-directional information exchange link between a first person and another entity out of a plurality of possible bi-directional information exchange links between entities in response to the directions and the at least one orientation. An initiator ( 111 ) initiates an action in response to the detection of the bi-directional information exchange link. The detection of the bi-directional information exchange link is in response to the first set of properties and the second set of properties.

Inventors

Christiaan Varekamp
Arnoldus Werner Johannes Oomen

Assignees

KONINKLIJKE PHILIPS N.V.

Dates

Publication Date: 20260507
Application Date: 20251230
Priority Date: 20211007

Claims (20)

1 . An apparatus comprising: a first sensor, wherein the first sensor is arranged to determine a first plurality of properties for a plurality of entities; a second sensor, wherein the second sensor is arranged to determine a second plurality of properties for the plurality of entities; a processor circuit, wherein the first processor circuit is arranged to determine directions between at least two entities of the plurality of entities, wherein the processor circuit is arranged to determine at least one orientation of at least one entity of the plurality of entities in response to the first plurality of properties; a detector circuit, wherein the detector circuit is arranged to detect an information exchange link in response to the directions and the at least one orientation, wherein the information exchange link exists between a first entity of the plurality of entities and a second entity of the plurality of entities, wherein the information exchange link is a real world audiovisual communication link, wherein the real world audiovisual communication link enables information to be exchanged from the first entity to the second entity, an initiator circuit, wherein the initiator circuit is arranged to initiate an action in response to the detection of the information exchange link, wherein the detector circuit is arranged to detect the information exchange link in response to the first plurality of properties and the second plurality of properties.
2 . The apparatus of claim 1 , wherein the first plurality of properties is determined in accordance with a first sensor modality; wherein the second plurality of properties is determined in accordance with a second sensor modality, wherein the second sensor modality is different from the first sensor modality.
3 . The apparatus of claim 1 , wherein the real world audiovisual communication link enables information to be exchanged from the second entity to the first entity
4 . The apparatus of claim 1 , wherein the at least one orientation comprises a orientation of the first entity.
5 . The apparatus of claim 1 , wherein the directions comprises a first direction, wherein the first direction is between the first entity and the second entity, wherein the detector circuit is arranged to determine the information exchange link in response to the first direction.
6 . The apparatus of claim 1 , wherein the directions comprises a first direction, wherein the first direction is between the first entity and the second entity, wherein the detector circuit is arranged to determine the information exchange link in response to a detection that an orientation of the first entity aligns with the first direction.
7 . The apparatus of claim 1 , wherein the at least one orientation comprises an orientation of the second entity.
8 . The apparatus of claim 1 , wherein the directions comprises a first direction, wherein the first direction is between the first entity and the second entity, wherein the detector circuit is arranged to determine the information exchange link in response to a criterion, wherein the criterion comprises a requirement that an orientation of radiation of information from the second entity to the first entity is aligned with the first direction.
9 . The apparatus of claim 1 , wherein the directions comprises a first direction, wherein the first direction is between the first entity and the second entity, wherein the detector circuit is arranged to determine the information exchange link in response to a criterion, wherein the criterion comprises a requirement that a view direction of the first entity is aligned with the first direction.
10 . The apparatus of claim 1 , further comprising the detector circuit, wherein the detector circuit is arranged to detect a trigger action by the first entity, wherein the initiator circuit is arranged to initiate the action in response to the trigger action.
11 . The apparatus of claim 8 , wherein the detector circuit is arranged to detect the trigger action as a communication by the first entity over the information exchange link.
12 . The apparatus of claim 2 , wherein the first sensor modality is a vision modality, wherein the second sensor modality is an audition modality.
13 . The apparatus of claim 1 , wherein the first entity is a person, wherein the second entity is a person.
14 . The apparatus of claim 1 , wherein the detector circuit is arranged to detect the information exchange link in response a first detection and a second detection, wherein the first detection comprises detecting that a pose for the first entity and a pose for the second entity meet a match criterion, wherein the second detection comprises detecting that a sound from at least one of the first entity and the second entity meet a sound criterion.
15 . The apparatus of claim 1 , wherein the action is an action of the second entity.
16 . The apparatus of claim 2 , wherein the first sensor modality and the second sensor modality are different modalities, wherein the first sensor modality and the second sensor modality selected from the group consisting of Vision, Audition, Tactition, Ultrasound, Infrared, Radar, and Tag detection.
17 . A method comprising: determining a first plurality of properties of a plurality of entities, wherein the first plurality of properties is determined in accordance with a first sensor modality; determining a second plurality of properties of the plurality of entities, the second plurality of properties is determined in accordance with a second sensor modality, wherein the second sensor modality is different from the first sensor modality; determining directions between at least two entities of the plurality of entities; determining at least one orientation of at least one entity of the plurality of entities in response to the first plurality of properties; detecting an information exchange link in response to the directions and the at least one orientation, wherein the information exchange link exist between a first entity of the plurality of entities and a second entity of the plurality of entities wherein the information exchange link is a real world audiovisual communication link, wherein the real world audiovisual communication link enables information to be exchanged from the first entity to the second entity, initiating an action in response to the detection of the information exchange link, wherein the detection of the information exchange link is in response to the first plurality of properties and the second plurality of properties.
18 . The apparatus of claim 17 , wherein the real world audiovisual communication link enables information to be exchanged from the second entity to the first entity
19 . A computer program stored on a non-transitory medium, wherein the computer program when executed on a processor performs the method as claimed in claim 17 .
20 . The method of claim 17 , wherein the at least two entities comprise a first entity and a second entity, wherein at least one of the directions is a direction between the at least one entity to the second entity.

Description

CROSS-REFERENCE TO PRIOR APPLICATIONS This application is a continuation of U.S. application Ser. No. 18/698,073, filed on Apr. 3, 2024 which is the U.S. National Phase application under 35 U.S.C. § 371 of International Application No. PCT/EP2022/074999, filed on Sep. 8, 2022, which claims the benefit of EP Patent Application No. EP 21201493.0, filed on Oct. 7, 2021.These applications are hereby incorporated by reference herein. FIELD OF THE INVENTION The invention relates to an apparatus and method for initiating an action based on detection of links between entities, and in particular, but not exclusively, to initiating an action based on man-machine interactions. BACKGROUND OF THE INVENTION Human-machine interactions are becoming increasingly prevalent, and many new applications based on or utilizing interactions between humans and machines are being developed. For human to machine interactions voice control is getting increasingly important and popular as it may provide a more efficient and user friendly interaction in many practical situations. It may often, e.g. in critical environments such as hospital environments, provide contactless operation and a simpler user interface (less physical buttons). As an example, an increasing number of devices that interact with humans are becoming part of home or professional environments. Indeed, homes and offices increasingly comprise a number virtual or voice assistants that can be interfaced with by users using voice commands and queries. Examples include home assistant devices such as Amazon Alexa, Apple Siri, Microsoft Cortana and Google Assistant that have become widespread in many homes and offices. In addition, voice assistants or direct human interfaces may be implemented in appliances and other devices, such as televisions, radios, etc. Such devices may often be operated and accessed by different people at different times and may often be used in environments where multiple people are present at the same time, such as home and office spaces. Another example is in the health industry where a large number of devices may often be present in the same room. For example, in an operation theatre, a large number of devices may be present and used to monitor the health and biological condition of the patient and for providing information to the health professional, such as specifically the surgeon, specialists, nurses, etc. Further, a relatively large number of people may dynamically be interacting with the devices with the interactions between people and devices often changing fast and quite substantially. It is therefore of increasing importance in many scenarios that human machine interaction is efficient, robust, and practical when used in dynamic environments in which multiple people and multiple devices may be present. However, most current systems tend to be focused on a direct link between one person and a single device where the device itself interacts directly with a single person to detect command and requests. However, whereas such an approach may be efficient in many scenarios and applications, it may also have a number of disadvantages and may not be optimal in environments with multiple devices and people. An improved approach would be advantageous in many scenarios. In particular, an approach that allows improved operation, increased flexibility, reduced complexity, facilitated implementation, an improved user experience, a more reliable, more robust interaction or operation, reduced computational burden, wider applicability, facilitated operation, and/or improved performance and/or operation would be advantageous. SUMMARY OF THE INVENTION Accordingly, the Invention seeks to preferably mitigate, alleviate or eliminate one or more of the above mentioned disadvantages singly or in any combination. According to an aspect of the invention there is provided an apparatus comprising: a first sensor arranged to determine a first set of properties for a plurality of entities in a real-world environment, the first set of properties being determined in accordance with a first sensor modality, each entity of the plurality of entities being a person or a device; a second sensor arranged to determine a second set of properties for the plurality of entities, the second set of properties being determined in accordance with a second sensor modality, the second sensor modality being different from the first sensor modality; a first processor arranged to determine real-world directions between entities of the plurality of entities; a real-world direction between two entities being a direction from one entity of the two entities to another entity of the two entities in the real-world environment; a second processor arranged to determine at least one real-world orientation of an entity of the plurality of entities in response to the first set of properties; a first detector arranged to detect a real-world bi-directional information exchange link existing between a fir