Abstract: A method can be implemented via execution of computing instructions configured to run at a processor and stored at a non-transitory computer-readable media. The method can include: determining one or more virtual categories associated with a search query by a user. The method can also include: classifying one or more search results for the search query into one or more category groups based on the one or more virtual categories. The method can further include: generating a respective user interface portion for each group of the one or more category groups. The method can additionally include: generating a user interface comprising the respective user interface portion for each group of the one or more category groups. The method can also include: transmitting, via a computer network, instructions to display the user interface on a user device for the user. Other embodiments are disclosed.

Abstract: Systems and methods for providing personalized item recommendations with personalized title are disclosed. In some embodiments, each user and each item of a website is represented as an embedding in a same heterogeneous graph. Based on an anchor embedding representing an anchor item in the heterogeneous graph, a set of items are determined. At least one feature aspect is selected from a set of feature aspects based on at least one implicit intent of a user, each feature aspect characterizing a respective aspect of features common to the set of items. From the set of items, a ranked list of items are generated as recommended items based on the at least one feature aspect. A recommendation title describing the at least one feature aspect is generated for the recommended items. The recommended items and the recommendation title are transmitted to be displayed together with the anchor item to the user.

Abstract: Aspects related to predicting zero-day vulnerabilities using anomaly detection and neural network algorithms are provided. A prediction platform may train an unsupervised algorithm for identifying suspicious packets and a prediction model for generating suspicion scores and behavior patterns based on network traffic information. The platform may segment information of packets of network traffic information into a plurality of segments. The platform may compare the segments with zero-day vulnerability information to identify known zero-day vulnerabilities. The platform may use the unsupervised algorithm to identify suspicious packets that do not correspond to known zero-day vulnerabilities. The platform may generate suspicion scores and behavior patterns for suspicious packets. The platform may further train the prediction model based on behavior patterns associated with certain suspicion scores to generate vulnerability scores.

Abstract: The present disclosure relates to a system (100) and method to facilitate accurate routing of level one (L1) numbers dialed by a user irrespective of the location of the user. The system may include a converge telephony application server (CTAS) (102), associated with a predefined circle, a centralized database accessible by the at least one CTAS (102), a centralized data layer (CDL) server (104) maintaining a mapping table comprising L1 routing information between an ECI and SDCA of the predefined circle. The CTAS may (102) receive one or more predefined request signals from one or more UE (110) by dialling an L1 number based on which the CTAS (102) may generate, a routing control signal for routing the UE (110) communication to a target site or for supplying one or more corresponding handling strategies to the target site.

Abstract: The present disclosure provides a system and a method to facilitate concurrent communication between a user device and a plurality of participating entities. The system may include a network device, which may be associated with a service provider that provides a network service to the user device. The network device may be communicably operational with an external server, where the external server may enable to perform authentication of the user device. The network device may receive input information from the user device, based on which the network device may enable establishing the concurrent communication with the plurality of participating entities. The concurrent communication thus established may not require to sequentially add the participating entities as otherwise required in conventional applications. This may reduce conference establishing time considerably and may also enable to optimize the effective usage of communication time.

Abstract: A system and method for enabling transfer learning-based optimization are provided. The method includes receiving an input indicative of a target optimization task. The target optimization task is associated with an unsolved optimization problem. Similarity between the target optimization task and a source optimization task is determined by applying a predefined similarity checking logic. The source optimization task is associated with a solved optimization problem and a complete optimization history. Complexity scores are computed for the source optimization task and the target optimization task, subject to the outcome of the application of the similarity checking logic, to determine whether the source optimization task is more complex than the target optimization task.

Abstract: Methods, apparatus, and systems are provided for using narrow artificial intelligence (“AI”) to detect and secure confidential data. The methods may include using a camera on a user computer to capture a live camera feed of an area adjacent to the user computer. Methods may include identifying one or more unverified data elements in the captured data. In response to determining an unverified data element, methods may include securing the user computer. Methods may include capturing a screenshot of the user computer screen. Methods may include transmitting data extracted from the screenshot through an object identification algorithm. Methods may include identifying confidential data within the screenshot using a pattern analysis model. Methods may include recreating the screenshot using a narrow AI model. Methods may include blurring the confidential data in the recreated screenshot. Methods may include overwriting the screenshot to display the recreated screenshot on the user computer.

Abstract: A method can be implemented via execution of computing instructions configured to run at a processor and stored at a non-transitory computer-readable media. The method can include: determining one or more virtual categories associated with a search query by a user. The method can also include: classifying one or more search results for the search query into one or more category groups based on the one or more virtual categories. The method can further include: generating a respective user interface portion for each group of the one or more category groups. The method can additionally include: generating a user interface comprising the respective user interface portion for each group of the one or more category groups. The method can also include: transmitting, via a computer network, instructions to display the user interface on a user device for the user. Other embodiments are disclosed.

Abstract: Transaction modification based on modeled profiles is described. In an example, transaction data can be received from merchant computing devices associated with merchants associated with a payment processing system. A model can be trained to generate profiles using, as training data, one or more of merchant data, buyer data, or the transaction data. Upon receiving an indication of a particular transaction between a buyer and a merchant, it can be determined that a characteristic of the transaction corresponds to a profile of the generated profiles. Based on the determination that the characteristic corresponds to the profile and the transaction data, a recommendation can be generated for a modification of the transaction to add an item or replace an item.

Abstract: Embodiments of the present disclosure disclose a Radio Unit (RU) comprising a Double Data Rate (DDR) memory unit, a control unit and a Programmable Logic (PL) unit. The PL unit is configured to capture plurality of data packets exchanged between RU and a Distributed Unit (DU) and determine a timestamp and a data size of the captured data packets. Further, the PL unit generates a data packet header comprising timestamp and data size information of the data packets and appends the header to the data packets before transmitting the data packets for storing in DDR memory unit. Thereafter, the control unit retrieves the data packets from the DDR memory unit and generates a Packet Capture (PCAP) data file, which may be used for validating the data packets exchanged between the RU and the DU, without the need of an external logic analyzer.

Abstract: A computer-implemented method of optimizing charging load on electric vehicle chargers and allocating charging connectors to an electric vehicle fleet at a depot, includes mapping occupancy of charging connectors at each charger, and prior to arrival of an electric vehicle at the depot, checking a priority assigned to unoccupied charging connectors, or sorting unoccupied charging connectors based on their priority. If there is a predetermined priority, mapping the electric vehicle to an unoccupied charging connector depending on priority and if the electric vehicle has a predetermined priority requirement, determining a normalized stress metric, selecting an unoccupied charger with lowest normalized stress metric, calculating an allocation of a connector at the charger based on balancing the normalized stress metric during use, allocating the charging connector to achieve balance, and mapping the electric vehicle to the allocated charging connector.

Abstract: A system and method for managing dispatch of vehicle fleet is provided. The method includes receiving information associated with a plurality of blocks to be served by a fleet of vehicles and determining that information of at least one critical block period is unavailable based on the information associated with the plurality of blocks. Further, the method includes determining the at least one critical block period based on at least one block requiring a number of non-EVs greater than an available number of non-EVs in the fleet of vehicles; scheduling the fleet of vehicles for serving the plurality of blocks by reducing a proportion of a number of non-EVs to serve the at least one critical block period; and dispatching the fleet of vehicles for serving the plurality of blocks including the at least one critical block period.

Abstract: A system, method and computer program product for route planning of electric vehicles (EVs) is provided. The method includes receiving a plurality of parameters associated with an EV fleet. The method includes determining a dttr for each route of a plurality of routes based on the route information associated with each EV of the EV fleet. Further, the method includes determining a set of EVs from the EV fleet based on a validity of each EV of the EV fleet and mapping the set of EVs to a set of the routes of the plurality of routes based on the dttr for each route of the plurality of routes. The method also includes scheduling the set of EVs to the set of the routes based on the mapping.

Abstract: Methods, apparatus, and systems are provided for using narrow artificial intelligence (“AI”) to detect and secure confidential data. The methods may include using a camera on a user computer to capture a live camera feed of an area adjacent to the user computer. Methods may include identifying one or more unverified data elements in the captured data. In response to determining an unverified data element, methods may include securing the user computer. Methods may include capturing a screenshot of the user computer screen. Methods may include transmitting data extracted from the screenshot through an object identification algorithm. Methods may include identifying confidential data within the screenshot using a pattern analysis model. Methods may include recreating the screenshot using a narrow AI model. Methods may include blurring the confidential data in the recreated screenshot. Methods may include overwriting the screenshot to display the recreated screenshot on the user computer.

Abstract: A method, computing system, and computer-program product for robust optimization of charging of a plurality of electric vehicles scheduled for charging at a charging station is provided. The charging station includes a plurality of chargers. In an embodiment, the method includes obtaining vehicle data and station data. Based thereon, it is determined if a set of EVs from amongst the plurality of EVs has failed to achieve a pre-defined target SoC, after a pre-defined charging duration. If the set of EVs has failed to achieve the pre-defined target SoC, a target power is computed. Further, the method includes adjusting at least one of the maximum power of each charger associated with charging of each EV from the set of EVs and the maximum power of the set of EVs as per the target power, to reach the target SoC of the set of EVs.

Abstract: The present disclosure provides a system and a method that facilitate establishment of an effective machine to machine (M2M) communication in a network. The system and method may provide a series of instructions to provide an efficient and effective communication between two or more machines without loss of information through a converge telephony application server (CTAS) operatively coupled to a next generation telecommunication network.

Abstract: The present disclosure provides a system and a method to facilitate concurrent communication between a user device and a plurality of participating entities. The system may include a network device, which may be associated with a service provider that provides a network service to the user device. The network device may be communicably operational with an external server, where the external server may enable to perform authentication of the user device. The network device may receive input information from the user device, based on which the network device may enable establishing the concurrent communication with the plurality of participating entities. The concurrent communication thus established may not require to sequentially add the participating entities as otherwise required in conventional applications. This may reduce conference establishing time considerably and may also enable to optimize the effective usage of communication time.

Abstract: The present disclosure relates to a system (100) and method to facilitate accurate routing of level one (L1) numbers dialed by a user irrespective of the location of the user. The system may include a converge telephony application server (CTAS) (102), associated with a predefined circle, a centralized database accessible by the at least one CTAS (102), a centralized data layer (CDL) server (104) maintaining a mapping table comprising L1 routing information between an ECI and SDCA of the predefined circle. The CTAS may (102) receive one or more predefined request signals from one or more UE (110) by dialling an L1 number based on which the CTAS (102) may generate, a routing control signal for routing the UE (110) communication to a target site or for supplying one or more corresponding handling strategies to the target site.

Abstract: A system and method for block scheduling for an electric vehicle are provided. The method includes obtaining route information including designated routes and their distances in a defined operation period for the EV, and battery information including a consumption factor and a charging rate for a battery of the EV. The method further includes adding dummy routes representative of a predefined charging time period for the battery in the defined operation period. The method further includes defining a dummy factor having a first value for each of the designated routes for the energy being consumed, and a second value for each of the dummy routes for the energy being replenished. The method further includes determining a schedule for the designated routes and the dummy routes for the EV using an optimization model having constraints for the route information, the battery information and the dummy factor.

Abstract: Systems, methods, and computer program products are provided for monitoring network processing using node analysis. The method includes receiving node operation information relating to a node command from one or more nodes. The one or more nodes are grouped into a cluster. The method also includes determining one or more node characteristics based on the node operation information. The method further includes comparing the node characteristic(s) of the node command to expected node characteristic(s). The method still further includes determining a node outage likelihood. The node outage likelihood indicates the likelihood the given node will experience a node outage. The method also includes determining a cluster node operation plan. The cluster node operation plan is configured to determine the nodes of the cluster that must be in operation in an event of the node outage of the given node.