Abstract: It is provided a method for determining intent to open a door. The method is performed by an intent determiner. The method comprises: obtaining an image of a physical space near the door; determining a position and orientation of a person in the image by providing the image to an image machine learning model, wherein the image machine learning model is configured to determine position and orientation of a person in the image, wherein the image machine learning model is configured to determine a stick figure of the person based on the image; adding a data item, comprising an indicator of the position and an indicator of the orientation, to a data structure; determining based on the data structure, whether there is intent of the person to open the door; and repeating the method until an exit condition is true.

Abstract: It is provided a method for handling access rights for access to a physical space (16a-g), comprising: communicating (40) with a credential (2) of a user (5), based on short-range wireless communication; determining (42) that the credential (2) does not currently have access rights to access the physical space (16a-g); finding (44) a communication address to a superior (6) to the user (5); generating (46) an increased-access request message, comprising a link that, when activated, adds a first access role to the user (5); sending (48) the increased-access request message to the address of the superior (6); receiving (50) an indication that the superior has activated the link, adding the first access role to the user (5); and granting (52) access for the user (5) to the physical space (16a-g).

Abstract: According to a first aspect, it is provided a method for processing an input media feed for monitoring a person. The method is performed by a media processing device comprising a media capturing device. The method comprises the steps of: obtaining an input media feed using the media capturing device; providing the input media feed to a local artificial, AI, intelligence engine, to extract at least one feature of the input media feed; and transmitting intermediate results comprising the extracted at least one feature to train a central AI model, while refraining from transmitting the input media feed. The local AI engine forms part of the media processing device. The intermediate results comprise a label of the extracted at least one feature. The label is obtained from an end result of another local AI engine.

Abstract: A method for alerting difference in user sentiment of a user using a door. The method is performed in a user analysis device. The method comprises: receiving sensor data from at least two sensors of different sensor types, the sensor data comprising data relating to a user in the vicinity of a door; determining, based on the sensor data, a first user sentiment prior to using the door; determining, based on the sensor data, a second user sentiment after using the door; deriving a difference in user sentiment between the first user sentiment and the second user sentiment; detecting that the difference in user sentiment is greater than a threshold; and generating an alert signal, indicating that the difference in user sentiment is greater than the threshold.

Abstract: A method for providing non-visual guidance for passing through a door. The method being performed by a guidance device. The method comprises: determining that a person is near the door and that non-visual guidance is to be provided to the person; determining an indication of location of the person in relation to the guidance device or the door; and providing non-visual guidance to the person for passing through the door, wherein the non-visual guidance is based on the indication of location.

Abstract: It is provided a method for handling access rights for access to a physical space (16a-g), comprising: communicating (40) with a credential (2) of a user (5), based on short-range wireless communication; determining (42) that the credential (2) does not currently have access rights to access the physical space (16a-g); finding (44) a communication address to a superior (6) to the user (5); generating (46) an increased-access request message, comprising a link that, when activated, adds a first access role to the user (5); sending (48) the increased-access request message to the address of the superior (6); receiving (50) an indication that the superior has activated the link, adding the first access role to the user (5); and granting (52) access for the user (5) to the physical space (16a-g).

Abstract: It is provided a method for providing training data for a machine learning model for monitoring a person based on video data. The method is performed by a training data provider (1). The method comprises: obtaining (40) a data feed of the person, wherein the data feed comprises a series of images that preserves a privacy of the person; generating (42) fake video data of a fictive person, such that a face of the fake video data is a computer-generated face; combining (44) the data feed with the fake video data, resulting in training data; and providing (46) the training data for training the machine learning model.

Abstract: According to a first aspect, it is provided a method for processing an input media feed for monitoring a person. The method is performed by a media processing device comprising a media capturing device. The method comprises the steps of: obtaining an input media feed using the media capturing device; providing the input media feed to a local artificial, AI, intelligence engine, to extract at least one feature of the input media feed; and transmitting intermediate results comprising the extracted at least one feature to train a central AI model, while refraining from transmitting the input media feed. The local AI engine forms part of the media processing device. The intermediate results comprise a label of the extracted at least one feature. The label is obtained from an end result of another local AI engine.