Abstract: A computer implemented method for controlling call capacity in a mobile network. The method includes: activating a mass event mode in a first cell of a first base station, wherein the first cell is a high frequency band cell, and wherein operating in the mass event mode comprises: checking if any low frequency band cells are available in a first sector served by the first cell; and responsive to detecting that one or more low frequency band cells are available, switching, at least some, voice call connections of the users of the first cell to at least some of the available low frequency band cells.

Abstract: According to an embodiment, a computer-implemented method for processing number words based on a word buffer comprises: obtaining a word buffer; filling a number word buffer based on the word buffer by repeatedly performing: obtaining a current mg word from the word buffer, determining whether the current word is a number word, in response to the current word being a number word, determining whether to combine the current word with a subsequent word in the word buffer based at least on a category of the current word and a category of the subsequent word, in response to determining that the current word should be combined with the subsequent word, combining the current word with the subsequent word thus producing a combined word, and adding the combined word to the number word buffer.

Abstract: Example embodiments relate to counteractions for remedying anomalies within a communication network.

Abstract: A computer implemented method for controlling a communications network. It is checked whether amount of handover failures from a first cell to a second cell exceeds a first threshold. Responsive to identifying that the amount of handover failures from the first cell to the second cell exceeds (301) the first threshold, a new cell identifier code is set (306) for the second cell in the communication network.

Abstract: According to an embodiment, a computer-implemented method for managing voice call initiation comprises: performing at least one voice call according to a preconfigured script, wherein the preconfigured script comprises a plurality of steps; obtaining, during the at least one voice call, a time estimate for performing at least one step of the plurality of steps of the preconfigured script; computing, during the at least one voice call, a remaining time estimate for each voice call in the at least one voice call based on the time estimate for performing the at least one step of the plurality of steps of the preconfigured script; and determining whether to initiate a new voice call during the at least one voice call according to the remaining time estimate of each voice call in the at least one voice call.

Abstract: Example embodiments may relate to performance verification in a cellular communication network. A computer-implemented method may comprise: detecting a change in a configuration of a cellular communication network; determining a classification for a network object of the cellular communication network, wherein the classification is indicative of whether performance data obtained prior to the change is applicable for the network object; selecting a performance verification procedure for the network object based on the classification of the network object; and causing execution of the performance verification procedure for the network object.

Abstract: A method for electrical component matching. The method includes receiving an input indicative of a given electrical component for which at least one matching electrical component is required to be identified; inferring specifications of the given electrical component using the input; determining a first set of electrical components from amongst the plurality of electrical components using rule-based cases applied corresponding to the specifications; determining a second set of electrical components from amongst the plurality of electrical components using machine learning; generating raw output data comprising product data of the electrical components of the first set and the second set; and processing the raw output data for generating processed output data.

Abstract: A computer implemented method for identifying a stationary user device of a communications network by obtaining usage data from the communications network; analysing the usage data to check whether a user device fulfils the conditions of a stationary user device; responsive to finding that the user device fulfils said conditions of a stationary user device, concluding that the user device is stationary; and outputting information about the user device being stationary for the purpose of further analysis and/or management of the communications network. The conditions of a stationary user device require that the amount of data transmission to or from the user device exceeds a first threshold, and that the user device has been connected to a predefined maximum number or fewer base stations or cells.

Abstract: A method for securely managing a private wallet. The method includes generating and storing a public key and a private key associated with a digital asset in the private wallet in a dedicated memory hardware of a primary user device, wherein the public key and the private key provide access to the digital asset; extracting a biometric input associated with a user and generating a biometric signature from the extracted biometric input; and linking the generated biometric signature to the private key for adding a security layer to access the private key.

Abstract: Disclosed herein is a computer-implemented method for call security, which includes: receiving a call from a user; identifying an environment of the user during the call using acoustic scene classification; comparing the identified environment to a preconfigured environment whitelist; and in response to at least the preconfigured environment whitelist not comprising the identified environment, performing at least one security policy action.

Abstract: According to an embodiment, a computer-implemented method for performing a computational task using a machine learning model comprises obtaining an indication about a computational task to be performed; obtaining at least one minimum performance threshold for the computational task; obtaining a plurality of machine learning models, wherein each machine learning model in the plurality of machine learning models is associated with at least one performance indicator and at least one resource consumption indicator; choosing a machine learning model out of the plurality of machine learning models based at least on the at least one minimum performance threshold for the computational task, the at least one performance indicator of each machine learning model in the plurality of machine learning models and the at least one resource consumption indicator of each machine learning model in the plurality of machine learning models; and performing the computational task using the chosen machine learning model.

Abstract: According to an embodiment, a method for call security, the method comprises: agreeing, by a first party and a second party, about an acoustic fingerprint between the first party and the second party; performing a voice call, by the first party, calling the second party; applying, by the first party, the acoustic fingerprint to the voice call; and detecting, by the second party, the acoustic fingerprint in the voice call.

Abstract: A computer implemented method for controlling a communications network. The method includes obtaining, from the network, cell identifiers, remote electrical tilt, RET, equipment identifiers, link data comprising information about links between cells and RET equipment, and network configuration data, and, from a data storage, network planning data; finding a first cell, if any, missing a link to a RET equipment; searching based on comparing the network configuration data and the network planning data to which RET equipment, if any, the first cell should be linked, and responsive to detecting that the first cell and a first RET equipment should be linked, forming a link between the first cell and the first RET equipment; updating the link data with information comprising the formed link, if any; and using the updated link data in network control operations.

Abstract: A computer implemented method for analysing antenna directions in a communications network. The method includes at least obtaining network related data; calculating a characteristic user direction of a first cell of a first base station; calculating a difference between the characteristic user direction and the antenna azimuth direction of the first cell; and responsive to detecting that the calculated difference is greater than a pre-set threshold angle, indicating an anomaly in the first cell.

Abstract: A method for performing predictive maintenance in a communication network, such as a decentralized communication network includes forming a training dataset using communication and anomaly data of communication nodes in communication network; building predictive maintenance client models and a predictive maintenance server model through machine learning using training dataset; deploying predictive maintenance client models and predictive maintenance server model in plurality of client nodes and server node, respectively; sensing an anomaly by a client node of plurality of client nodes; sending an aggregated information, by client node to server node; and performing a maintenance action by server node based on a decision made by server node on aggregated information. Disclosed also is a system for performing predictive maintenance in a communication network.

Abstract: Disclosed herein is a computer-implemented method for punctuation of text from audio. The method includes obtaining an audio input comprising speech data; identifying a plurality of silent sections in the audio input; grouping the plurality of silent sections into a plurality of groups, where each group in the plurality of groups corresponds to a punctuation mark or a space without a punctuation mark; and associating each silent section in the plurality of silent sections with a punctuation mark or a space according to the grouping of the silent sections, thus obtaining punctuation information.

Abstract: Monitoring network performance relating to an application-level service used by a user by obtaining first monitoring data measuring performance of a home network (11) of the user concerning the application-level service and/or type of a device used by the user, obtaining second monitoring data measuring performance of an operator network (20-40) concerning said application-level service and/or type of a device used by said user, linking the first monitoring data with the second monitoring data so as to obtain combined application-level and/or device type-level monitoring data concerning said particular service used by said particular user, and storing said combined application-level and/or device type-level monitoring data at a data lake (72).

Abstract: Managing a distributed energy storage, DES, arrangement to participate in electric grid balancing, wherein the DES arrangement comprises a pool of nodes. The method is performed by detecting (301) a balancing need for balancing the electric grid either in up direction or down direction; selecting (302) nodes for the balancing need; identifying (303) preferred balancing activity for a plurality of the selected nodes, wherein the preferred balancing activity is node specific, wherein first nodes, if any, have a preferred balancing activity in the same direction with the detected balancing need, and second nodes, if any, have a preferred balancing activity that is opposite to the detected balancing need; starting activation (304) of a balancing activity according to the balancing need for the first nodes, if any, upon detecting the balancing need; and delaying activation (305) of the balancing activity according to the balancing need for the second nodes, if any.

Abstract: A computer implemented method for energy savings management for cells of a sector or a base station of a communication network. The sector or base station has co-located cells that operate on different frequency bands. The method is performed by obtaining a default energy savings plan that calls for fully shutting down at least one of the cells for a first time period and provides a first amount of energy savings; evaluating energy savings achievable by using partial shutdown in cells and determining a second time period of partial shutdown that is needed for achieving the first amount of energy savings; obtaining a third time period that is usable for energy savings actions; and choosing to use partial shutdown in the cells, if the second time period is shorter than the third time period, and else choosing to use the default energy saving plan.

Abstract: A computer implemented method for controlling a pool of energy storages. The energy storages of the pool have capacity limits defining how the energy storages are intended to be used. The method is performed by detecting an exception event; selecting one or more energy storages associated with the detected exception event; and temporarily adjusting at least one capacity limit of the selected energy storages in accordance with the detected exception event.