Amadeus

A method for performing biometric identity validation to confirm identity of a user. The method comprises providing a mobile application configured to be executed on a device of the user, to: register an enrolment data in respect of the user, for enrolling the user for biometric identity validation; when the user device is in proximity of one or more biometric touchpoint devices, enable pairing between the user device and the one or more biometric touchpoint devices to establish, with each of the one or more biometric touchpoint devices, a respective data connection between the user device and the biometric touchpoint devices, the one or more biometric touchpoint devices each comprising a biometric camera. In response to the user presenting at any one of the one or more biometric touchpoint devices to be processed thereby, and the biometric touchpoint device capturing a live image data of the user, the captured live image data is processed to obtain a live biometric data, and a data transfer is enabled to transfer at least the live biometric data or a reference biometric data obtained from the enrolment data, between the biometric touchpoint device that captured the live image data and the device of the user via the established data connection. The identity of the user is confirmed based on a result of a match between the live biometric data and the reference biometric data.

A method and system for deploying a natural language (NL) virtual interaction profile in a dynamic transaction management environment are disclosed. The system includes an Al engine configured to generate virtual electronic profiles based on training datasets of NL dialogue sequences between client devices and agent terminals. The virtual profiles simulate interaction behaviors, enabling iterative dialogues with agent terminals in response to dynamically changing transaction variables. By setting a target number of iteration cycles, the method aims to align interactions with predefined efficiency thresholds, reducing redundant access to transaction management engines and optimizing computational resource allocation. The disclosed system enhances processing efficiency within complex multi-component networks by streamlining interactions and minimizing unnecessary communication cycles.

A method for operating a touchpoint, the method comprising a biometric authentication system: receiving authentication biometric data; associating the authentication biometric data with a person; obtaining a pre-computed risk score associated with the person; determining whether the risk score exceeds an authentication risk threshold; operating the touchpoint to perform biometric authentication using the authentication biometric data in the event that the pre-computed risk score does not exceed the authentication risk threshold; and operating the touchpoint with an enhanced authentication routine in the event that the pre-computed risk score exceeds the authentication risk threshold.

A hierarchical blockchain system is provided. The hierarchical blockchain system comprises: a plurality of blockchains and associated databases having a hierarchical relationship, wherein the plurality of blockchains, amongst hierarchical levels of the hierarchical relationship, are associated via one or more respective identifier types; and one or more computing devices configured to: populate the plurality of blockchains and the associated databases; and validate the plurality of blockchains. The plurality of blockchains are associated with different sets of validation mechanisms. Respective blockchains that are higher in the hierarchical relationship are associated with stricter validation mechanisms and further respective blockchains that are lower in the hierarchical relationship are associated with lighter validation mechanisms. The lighter validation mechanisms are more fault tolerant than the stricter validation mechanisms.

A method of interacting with web sites is provided. The method comprises receiving an input defining a job to be performed and determining one or more tasks on one or more web sites required to perform the job. For each of the one or more tasks, the method further comprises identifying, by a supervisor agent, one or more atomic processes required to perform the task on a web site. And for each of the one or more atomic processes, the method further comprises instructing, by the supervisor agent, a worker agent to perform the atomic process, and determining, by the worker agent, a function call relating to the atomic process for interacting with the web site. The supervisor agent and the worker agent are based on multimodal generative artificial intelligence models. A corresponding assistance system and computer program are provided, too.

A computing system (126) registers peripheral devices (110-1) in communication with a first computing unit (106-1) via local communication links (110-1). Registering peripheral devices (110-1) virtualizes peripheral devices (110-1) at the computer system (126) thereby making peripheral devices (110-1) available for use by computing units (106) in communication with the computer system (126), and wherein registering peripheral devices (110-1) occurs via a peripheral device virtualization application (112-1) installed at the first computing unit (106-1) in communication with the computer system (126). The computing system (126) receives from a second computing unit (106-2), a request for a list (120) of peripheral devices (110-1), and provides back the list (120) of peripheral devices (110-1). The computing system (126) receives, from the second computing unit (106-2), a selection of a peripheral device (110-1), of the peripheral devices (110-1), and enables use of the peripheral device (110-1) at the first computing unit (106-1), by the second computing unit (106-2), via the peripheral device virtualization application (112-1) at the first computing unit (106-1).

Aliveness detection method for determining whether a presented face in respect of a user is a real face, comprising: obtaining an image sequence comprising a plurality of images. Each image comprises left eye image data and right eye image data. Each image in the image sequence being acquired of the presented face under a respective flash setting from a flash setting sequence, the flash settings in the flash setting sequence including at least two different flash setting values. The method further comprises processing the image sequence to detect speckles in the right eye image data and the left eye image data from the image sequence, which are caused by the eyes reflecting a flash applied under a flash setting when acquiring least one image in the sequence, the flash setting for the at least one image being brighter than the flash setting for a preceding and/or a succeeding image. The processing comprises applying a filter to enhance speckle image data corresponding to the speckles in the image sequence relative to non-speckle image data in the image sequence, and/or to suppress the non-speckle image data relative to the speckle image data. If one left eye speckle and one right eye speckle are detected respectively from the left eye image data and the right eye image data in the image sequence, determining whether the detected left and right eye speckles match each other. The method comprises outputting a liveness detection result based at least partially on the determination.

A computerized method, system and computer program of controlling an update strategy of a cache are provided. A plurality of cache updating models applied on data entries of a test cache is analysed, wherein outdating probabilities of data entries of the test cache correspond to outdating probabilities of data entries of the cache. Analysing the plurality of cache updating models thereby comprises determining a value of an evaluation metric for a cache updating model of the plurality of cache updating models, wherein the evaluation metric is based on a target accuracy configurable by a user. Moreover, a cache updating model is selected based on the value of the evaluation metric of the cache updating model and the cache updating model is then applied on the cache.

A method, system, and computer program for cache-based response provision is presented. Responses to requests are stored in a cache, wherein each response is associated with one or more generated embeddings that were generated by at least two different embedding models to at least one input and/or applying the same embedding model on at least two different inputs. When a current request is received, a similarity of one or more current embeddings generated for the current request with the one or more generated embeddings of each cached response is determined. In response to determining that the similarity of the one or more current embeddings with the one or more generated embeddings of at least one response is above a threshold, the response associated with generated embeddings with the highest similarity is returned, whereas otherwise a new response from an original data source and returning the new response.

The present specification provides a multiplatform virtual retail store engine. The specification can have application to client devices with augmented or virtual reality hardware that interact with different platforms with metaverse capabilities. Rich experiences are provided on client hardware while making efficient use of available processing, memory and communication resources. Embodiments discuss the provision of a single retail store model which is dynamically adapted for generation across the plurality of different platforms according to the different metaverse capabilities. Embodiments also discuss include racking of the same user across different accounts on different metaverse platforms.