Embodiments of the present disclosure may include a method for credit underwriting, the method including receiving a dataset of user details. Embodiments may also include creating a convolutional neural network (CNN) with the dataset of user details. In some embodiments, the convolutional neural network organizes at least a portion of the dataset of user details into a layered and weighted dataset. Embodiments may also include creating an enriched layered and weighted dataset. Embodiments may also include executing a back-propagation operation to remove at least a portion of the layered and weighted data from the layered and weighted dataset. Embodiments may also include receiving a plurality of enriched layered and weighted datasets.

Methods, systems, and computer program products for optimization of query processing in a data federation system using priority queuing techniques are provided. Priority queuing techniques may include generating a query vector corresponding to a query, comparing the query vector to historical query vectors to determine similarity, determining an expected processing time for the query based on the determined similarity, and inserting the query into a priority ordered queue at a particular position based on the expected processing time.

A method for performing biometric recognition in a system in which biometric information is distributed and stored in a plurality of databases includes extracting biometric information of a user, generating a plurality of biometric information segments by dividing the extracted biometric information, calculating distances between pre-stored biometric information template segments for each of the plurality of databases and a corresponding one of the plurality of biometric information segments, and detecting a biometric information template matching the biometric information by using the calculated distances.

Methods and systems for determining at least one candidate user for a license plate number (LPN) are described herein. A set of license plate recognition (LPR) events that correspond to the LPN and a set of access events of a plurality of users may be obtained. One or more associated events for each respective user of the plurality of users may be determined. A confidence score for each respective user may be determined based on the one or more associated events for the respective user. At least one candidate user for the LPN may be identified based on the confidence score. An indication that the at least one candidate user is a candidate for the LPN is output. Methods and systems for determining at least one candidate license plate number for a user are also described herein. Additional related methods and systems are described herein.

A method includes receiving a selection of a first change to a project in a first repository of a plurality of repositories and identifying one or more attributes of the first change to the project. The method further includes identifying a second change to the project in the plurality of repositories in view of the one or more attributes of the first change and performing an action in view of identifying the second change to the project.

Methods and systems are disclosed for dynamically conducting messaging campaigns, responsive to customer events. A set of parameters for a messaging campaign includes an initial schedule for providing a set of messages from a set of data objects. Responsive to a customer event associated with a first customer, an adjusted schedule is generated for providing the set of messages to the first customer. The adjusted schedule differs from the initial schedule in a timing for providing at least a first message, where the first message is scheduled to be provided at an adjusted timing proportionate to a time period between the customer event and a first milestone event. The first message is generated from a first data object and transmitted to the first customer, in accordance with the adjusted schedule.

The present disclosure describes methods, systems, and computer program products for enabling advanced analytics with large datasets. One computer-implemented method includes receiving, by operation of a computer system, a dataset of multiple data records, each of the plurality of data records comprising one or more features and a target variable; selecting key features among the one or more features based at least on relevance measures of the one or more features with respect to the target variable; dividing the dataset into multiple subsets; for each of the multiple subsets, identifying a number of clusters and respective centroids of the number of clusters based on the key features; identifying a number of final centroids based on the respective centroids of the number of clusters for the each of the number of subsets, the number of final centroids being respective centroids of a number of final clusters; and for each data record in the multiple subsets, assigning the data record to one of the number of final clusters based on distances between the data record and the number of final centroids.

System (100) comprising several edge computing devices (ECD), each comprising a sensor (S); a memory (M); a Central Processing Unit, CPU; and digital communication interface (IF), for communication across a network (NW).

The invention is characterised in that each edge computing device is arranged with a respective interpreting software function, arranged to execute on said CPU and to interpret computer code, received via said digital communication interface and stored in said memory, according to a query language having a predetermined syntax; in that said syntax is arranged to define queries the results of which are streams of data; in that a first such software function is arranged to pose a first query to a second edge computing device (120), in that a second such software function of said type is arranged to, in response thereto, generate and communicate a second stream of data; in that the first software function is arranged to preprocessing said second stream so that it adheres to a predefined global data ontology, and to perform a first calculation using said second stream.

The invention also relates to a method.

A data processing method and apparatus, and a device are provided. In this application, a plurality of data processing modules may collaboratively process data. Data output by each data processing module is stored in a data set, the data set includes a plurality of pieces of data, each piece of data carries one index, and the index indicates a data processing module that generates the data. A first data processing module in the plurality of data processing modules may obtain, from the data set, first data carrying a first index, where the first index indicates a data processing module that generates the first data. Then, the first data processing module processes the first data to generate second data carrying a second index, where the second index indicates the first data processing module. Then, the first data processing module stores the second data into the data set.

Techniques described herein perform implement a query using a synthetic time series (STS), for example applying an STS on time series data to obtain an answer to the query. In an embodiment, a method receives a times series and query relating to the time series. The method translates the query into a synthetic time series. The method executes a reduce operation on the STS and the time series. The method then returns the result of the operation as an answer to the query. A result of the reduce operation is returned as an answer to the query.