Aspects are disclosed that facilitate matching a user with a virtual agent. A database of virtual agents is maintained in which each of the virtual agents are remotely located from a property secured by a locking mechanism. A user is authenticated based on user information included in a request to enter the property, and an authenticated user is matched with a host agent of a virtual tour. Here, the host agent is selected from the database of virtual agents, and the virtual tour comprises a remote real time interaction between the user and the host agent while the user physically accesses the property.

A presentation of visual information relates to an accurate identity of a person. Visible data corresponding to the identity is rendered upon a wearable badge associated uniquely with the person. The rendered visible data are augmented dynamically. The augmentation includes adding a conspicuous indication to the rendered visible data, in real time, that an authorized security credential corresponding to the person is exceeded in relation to a presence of the person in a particular location.

An access control system receives a device-specific identifier of a mobile electronic device. A memory device stores the identifier as belonging to a user present in a public zone. An image processing device generates from a camera image produced by a camera a real-time template for facial features of the user present when the user present requests access to an access-restricted zone, and searches user profiles stored in a database for a reference template that matches the real-time template to a specified degree, wherein a user profile is searched only if it is assigned to a present user based on a stored identifier, wherein in the case of a match, the system grants the user access to the access-restricted zone and denies access when there is no match.

Example implementations include a method, apparatus, and computer-readable medium comprising determining, by a processor of a control panel, that a security event has happened, wherein the security event is associated with a user identification or authentication; capturing one or more still images or videos by at least one camera in the control panel subsequent and in response to determining that the security event has happened; and using the one or more still images or videos to perform facial recognition.

A method to implement multifactor authentication of a user may include performing biometric authentication of a person that bears the wearable electronic device and at least one of: performing knowledge-based authentication of the person or presenting an access control token of the wearable electronic device to an access reader that performs token-based authentication of the person. Performing biometric authentication may include receiving a first biometric signal generated by a wearable electronic device and determining a person-specific biometric characteristic of the person therefrom; comparing the person-specific biometric characteristic to a user-specific biometric characteristic of the user determined from a second biometric signal generated when the wearable electronic device was born by the user; and based on the comparing, determining a confidence level that the person is the user to determine a positive or negative authentication of the person as the user.

A controlled access entrance gate, comprising a frame or structure (11) that defines an entry area (I1), an exit area (I2) and a transit area (P) of a user (U), a actuation unit (13), which allows the passage of one or more subjects (U), an electronic control unit (14) and a plurality of sensors or cameras (15, 16). The sensors or cameras (15, 16), which can also be used as an independent kit and can be associated with any type of passage or area to be controlled, are suitable for detecting the data relating to the distance (DT) between each sensor (15, 16) and each subject (U) present in the entry area (11) or in the exit area (I2) or in the passage area (P) and the speed, trajectory and tracking parameters of the subject (U). An electronic control unit (14) receives and processes data through interpolation processes and machine-learning and/or deep-learning algorithms, so as to autonomously learn the characteristics of the passage and predict the forms and probabilistic directions of each subject (U) inside the volume corresponding to the entry (I1) and exit (I2) areas and to the transit area (P) of the passage.

It is an object of the present invention to protect authentication data while ensuring high response performance. An authentication candidate extraction apparatus comprises a biometric information input part that receives biometric information of a to-be-authenticated subject, moving from a first spot to a second spot, acquired at the first spot; a feature information storage part that stores feature information used for authentication of the to-be-authenticated subject; a candidate selection part that selects a feature information candidate to be used for the authentication processing by means of a predetermined secure computation scheme using features extracted from the biometric information acquired at the first spot; and a feature information transmission part that transmits the extracted feature information candidate to an authentication apparatus that performs authentication processing using biometric information of the to-be-authenticated subject acquired at the second spot.

The present disclosure relates to systems and methods of control access to a controlled-access area. In one embodiment the method includes analyzing health data corresponding to a user to determine that the health data satisfies a health standard for an organization controlling the access-controlled location and the health data was captured at a sensing location offsite from the access-controlled location. In one embodiment the method includes determining that the user has authorization from the organization to enter the access-controlled location; and authorizing the user to enter the access-controlled location.

Doorbells can send data to each other to enable a first doorbell user to warn a second doorbell user regarding a suspicious visitor. A first user can indicate a first trait of a visitor via a first remote computing device. The first user can create a user group to enable the members of the user group to use their doorbells to take pictures of suspicious visitors and to send the pictures of the suspicious visitors to other members of the user group.

A method of using image analytics and machine learning in a lock system includes receiving data describing access actions that are performed at an access control device based at least in part on a credential. The data includes, for each access action, a description of the access action, a timestamp, and an image of a person presenting the credential. The data is analysed to identify patterns of access. Facial characteristics of the person presenting the credential are identified. The credential is associated with the facial characteristics. It is detected, based at least in part on facial recognition and the facial characteristics, that the person is proximate to the access control device. An access action is performed at the access control device based on the detecting and the patterns of access, where the facial recognition is used in place of the credential to provide authorization to perform the access action.