Abstract: Systems and methods for implementing a reinforcement machine learning framework for dynamic demand forecasting. A method includes generating estimated booking data for an initial time with a demand model trained using a training set of historical booking data. A variance is detected between the estimated booking data and transient booking data observed at the initial time that exceeds a defined threshold. In response to detecting the variance, a reinforcement learning service is activated. An updated training set including enhanced booking data observed at a subsequent time is created after activating the reinforcement learning service. A parameter of the demand model is updated by training the demand model using the updated training set.

Abstract: The present invention relates to request and messaging technology and in particular to mechanisms of efficiently processing such requests. A computing device receives, from the client, a plurality of requests, the plurality of requests including multiple first requests and multiple second requests, each of the first and second requests comprising request data. The computing device assigns, based on the request data, a respective request processing priority to each of the first and second requests, processes the first requests based on the assigned processing priorities, while the second requests remain pending for processing and determines whether to adapt the priorities of the second requests based on the request data of the second requests and/or response data generated for the multiple first requests.

Abstract: A method of biometric data access in a biometric device environment is provided. The biometric device environment comprises multiple biometric devices, wherein the multiple biometric devices are grouped in multiple biometric device zones and wherein a biometric device zone is associated to one or more biometric databases. The method comprises receiving biometric data of a user and determining an order of one or more of the multiple biometric device zones according to expected access to the biometric data of the user. The method further comprises, in response to a start time being reached, adding the biometric data to one or more of the biometric databases associated to at least a subset of the one or more of the multiple biometric device zones, and, in response to an access progression event, removing and/or adding the biometric data from/to one or more databases associated to a subsequent biometric device zone.

Abstract: A device, system and method for more efficiently controlling client devices to provide common content is provided. A computing device: determines that avatars, associated with client devices interfacing with a virtual platform, are within a given distance of each other and/or located in a common area of the platform; and accesses respective associated data comprising: respective static data associated with users of the devices, and/or respective dynamic data indicative of orientation of the avatars within the platform and/or interactions of two or more of the avatars within the platform. The computing device determines, from the data: avatar subset associated with respective content, the subsets each including two or more of the avatars. The computing device causes respective devices, associated with the subsets, to provide the respective content in association with the subsets, such that two or more of the respective devices associated with a same subset provide respective common content.

Abstract: A device, system and method for secure access to virtual platforms is provided. A computing device establishes a communication session between a client device and a virtual platform, the client device configured to provide rendered scenes of the virtual platform based on scene rendering data generated by the virtual platform. The computing devices accesses disability compensation data indicative of how to compensate for a disability associated with a user of the client device, the disability compensation data anonymized to remove personal identifiable information associated with the user. The computing device adjusts settings of the virtual platform according to the disability compensation data to control the virtual platform to generate the scene rendering data according to the settings as adjusted, such that the client device renders scenes of the virtual platform to replicate the disability for an avatar associated with the user in the virtual platform.

Abstract: A computerized method of estimating resource requirements in an environment is presented. The method comprises a preparation phase and a simulation phase, wherein the preparation phase comprises a machine learning training phase and a clustering phase. The machine learning training phase trains a machine learning model to predict a resource requirement. Thereby, a subset of features is extracted. The clustering phase determines clusters in the subset of features, a correlation coefficient and least one identifying parameter of a distribution of the feature values of the subset of features. Finally, the simulation phase determines a distribution for a feature, selects at least one value for a feature and uses the second machine learning model to estimate a resource requirement in the environment in at least one time period the future.

Abstract: The present disclosure relates to the processing of search results in a distributed computing system, especially at a user terminal. A user terminal comprises a memory storing a probabilistic model to determine validities of search results being outdated after passed time and storing rules to re-compute the search results. The user terminal receives, in response to at least one search request to at least one search platform, at least one search result from the search platform. The user terminal stores the received search results, and in response to a trigger event, locally determines, based on a probabilistic model, that the at least search result is likely invalid. The user terminal locally re-computes the at least one search result using the rules and presents the at least one re-computed search result to the user.

Abstract: A device, system and method for secure assistive handling of electronic content is provided. A computing device trains one or more machine learning engines using account profile(s) as training data, the account profile(s) indicative of previous content selected or accessed in association with the account profile(s). After training the machine learning engine(s), the computing device receives, via one or more of a communication interface and a human-machine interface, criteria for selecting content, and searches for content that meets the criteria, using one or more of the communication interface, the machine learning engine(s), and the human-machine interface. The computing device receives, via one or more of the communication interface and the human-machine interface, the content that meets the criteria, and filters, via the machine learning engine(s), the content to generate filtered content according to the account profile(s). The computing device controls an output device to output the filtered content.

Abstract: A data logging method includes: obtaining a data record having an initial size; determining that the initial size exceeds a primary threshold; in response to determining that the initial size exceeds the primary threshold, generating a truncated data record by truncating the data record to a secondary size, wherein the secondary size is smaller than the primary threshold; and storing the truncated data record in a log repository.

Abstract: A device, system and method for providing a hybrid command line is provided. The device provides, at a display screen, a command line in association with a page defined by a document object model that includes metadata defining available natural language (NL) based commands for the device and/or the page. Partial text, received at the command line according to an NL-based format, is used to populate an autocomplete list of NL-based commands, mapped to corresponding server-compatible commands, and filtered by the metadata. An NL-based command is selected from the autocomplete list is provided to a server which converts the NL-based command to a corresponding server-compatible command. Results from the server are provided at the display screen in a graphical format which include graphical selectable options which, when selected, cause corresponding commands to be provided to the server in a server-compatible and/or NL-based format.

Abstract: The present disclosure describes method, apparatus, and computer readable media for dynamically updating a retransmission timeout (RTO) period for data transmissions in a communication system. In an aspect, the method comprises a first step of computing a round-trip time (RTT) period for a successful data transmission between a client and a server in the communication system. The method also comprises a second step of updating the RTO period after the successful data transmission based at least on the computed RTT period. Finally, the method comprises repeating the first and second steps after every Mth successful data transmission, wherein M is an integer with a value greater than 1.

Abstract: The present specification provides a search engine server comprising a network interface, a processor, and a memory for storing and executing programming instructions. These instructions enable the server to establish a conversational session with a client device over a network, determine parameters from the client's request intention, and select nodes representing sources within a full domain, including APIs, databases, and large language models. The server can adjust node selection based on additional parameters and create a query graph with nodes corresponding to identified sources. This graph facilitates the execution of network queries based on the client's request intention, thereby optimizing the data retrieval process across various sources.

Abstract: A method includes receiving, from a client device, a first request to establish a transport-layer connection between the client device and the server, the first request containing a first source port number; in response to receiving the first request, initiating a delay timer and withholding transmission of an acknowledgement to the first request until expiry of the delay timer; receiving from the client device, prior to expiry of the delay timer, a second request to establish the transport-layer connection; determining whether the second request contains a second source port number matching the first source port number; and selecting, based on the determination, a handling action for the second request.

Abstract: A device, system and method for filtering provider objects from one or more provider systems are provided. An intermediation server implements a computing-process flow associated with a client device and one or more provider systems. The server receives, from the client device, during implementation of the computing-process flow, search criteria, and further receives provider objects that meet the search criteria, the provider objects associated with the one or more provider systems. The server applies computer-code content filters to the provider objects, the filters received from one or more computing devices excluded from the computing-process flow. When a given provider object fails to pass all the computer-code content filters, the server removes the given provider object from the provider objects, to generate filtered provider objects, and the server provides, during implementation of the computing-process flow, the filtered provider objects to the client device.

Abstract: A search engine receives a search request and determines a number of initial search results. The initial search results comprise at least one essential data piece and omit at least one non-essential data piece. Later on, a follow-up search request from the client is received which indicates at least one of the initial search results. The search engine computes at least one non-essential data piece for each initial search result indicated in the follow-up search request based on a number of dynamic computation rules and returns the computed at least one non-essential data piece for each initial search result to the client.

Abstract: A method for detecting a current attack in a computerized environment is automatically performed by one or more computerized hosts (50) of the computerized environment. The method comprises generating a signature (22) which is specific for a type of activity in the computerized environment based on historic data (20, 21) of the activity, the signature (22) specifying averaged normalized numbers of occurrences of the activity per time frame of a plurality of recurring time frames. The method further comprises determining a threshold value for the activity based on the historic data of the activity and a statistical measure. The method further comprises monitoring current data of the activity in the computerized environment, and generating an attack detection alert based on determining that the current data of the activity exceeds the threshold value for a current time frame.

Abstract: A method at an aggregator includes: storing previous search results resulting from previous client search requests, and for each previous search result, a previous handling indicator, indicating a relevance of the previous search result to the client; receiving, from the client, a search request containing search parameters; in response to the search request, selecting a subset of previous search results based on correspondence between attributes of the previous search results and the search parameters, and on the previous handling indicators; providing, to a supplier, the search request and auxiliary search parameters corresponding to the selected previous search results and indicating characteristics of the selected previous search results, for generation of current search results at the supplier employing the auxiliary search parameters as inputs; receiving, from the supplier, the current search results generated at the supplier; and returning at least one of the current search results to the client.