Abstract: A device may determine a number of user equipments (UEs) connected to an inactive site during a first period of time and determine that the inactive site experienced a power outage during a second period of time. The device may determine that the UEs connected to a set of active sites during the second period of time. The device may determine one or more key performance indicator (KPI) changes to one or more KPIs, during the second period of time, for each of the set of active sites. The device may determine a plurality of weights associated with the inactive site experiencing the power outage; determine a set of impacts, of the inactive site, on the one or more KPI changes for the set of active sites based on the plurality of weights; and cause power to be restored to the inactive site based on the set of impacts.

Abstract: Systems and methods may optimize power consumption for RAN devices. A device obtains field data of user equipment (UE) devices for a group of cells during a time interval. The field data includes signal strength measurements. The device computes cell boundaries for each cell based on the field data and predicts signal strength values inside each of the cell boundaries for a future time period. The device computes a cumulative overlap feature and a weighted signal strength feature for each cell of the group of cells during the future time period and generates an energy consumption predictive model that applies the cumulative overlap feature and the weighted signal strength feature for the future time period. The device determines, based on the energy consumption predictive model, optimal cell boundaries that correspond to a reduced energy consumption needed to meet service requirements during the future time period.

Abstract: A method, a device, and a non-transitory storage medium are described in which a test case generation service is provided. The service may include receiving and validating requirement text associated with a prospective test case and/or test script. The service may invoke a remedial procedure when the requirement text is not validated. The service may include selecting multiple types of classification models based on a model profile. The service may include aggregating probability values associated with classifications for sentences, and approving such classification that satisfy a threshold value. The service may further include generating test cases and/or test scripts. The service may generate a schedule for test cases and/or test scripts based on one or multiple criteria values generated by one or multiple predictive models.

Abstract: A system described herein may provide for the use of artificial intelligence/machine learning (“AI/ML”) techniques to generate models for various locations or regions (e.g., sectors) associated with one or more radio access networks (“RANs”) of a wireless network. The system may further use AI/ML techniques to generate interference models to reflect types and/or amounts of channel propagation metrics measured within the RAN. The system may further determine, based on attributes of a given sector, a sector model and/or a channel propagation model associated with the sector. Based on the sector model and/or the determined channel propagation model, one or more actions may be determined in order to enhance channel propagation metrics within the sector, such as at portions of the sector at which increased demand for wireless service is detected.

Abstract: A system described herein may identify a relative feature importance of a set of features in a modeling and/or simulation system. The same set of features may be provided to a group of different models. A relative feature importance of each feature of the set of features may be determined, on a per-model basis, based on comparing outputs of the model with and without particular features of the set of features. A relative feature of each feature may be further be determined on an inter-model basis by identifying features that are commonly ranked highly in the per-model rankings. An iterative process may evaluate the highest ranked, next-highest ranked, etc. features across multiple models. A simulation system may utilize the rankings to more efficiently perform one or more simulations, which may include omitting one or more features of the set of features when performing the simulations.

Abstract: Systems and methods may optimize power consumption for RAN devices. A device obtains field data of user equipment (UE) devices for a group of cells during a time interval. The field data includes signal strength measurements. The device computes cell boundaries for each cell based on the field data and predicts signal strength values inside each of the cell boundaries for a future time period. The device computes a cumulative overlap feature and a weighted signal strength feature for each cell of the group of cells during the future time period and generates an energy consumption predictive model that applies the cumulative overlap feature and the weighted signal strength feature for the future time period. The device determines, based on the energy consumption predictive model, optimal cell boundaries that correspond to a reduced energy consumption needed to meet service requirements during the future time period.

Abstract: A method for summarizing dialogs may include obtaining an agent text stream and a customer text stream, segmenting the agent text stream and customer text stream into sentences, and labeling sentences associated with the segmented agent text stream and the segmented customer text stream. The method may further include extracting sentences from the agent text stream and the customer text stream based upon frequencies of appearance of words and terms of interest; generating an agent summary paragraph based on the extracted sentences from the agent text stream, and generating a customer summary paragraph based on the extracted sentences from the customer text stream. The method may identify keywords associated with each of the agent summary paragraph and the customer summary paragraph.

Abstract: A system described herein may provide for the use of artificial intelligence/machine learning (“AI/ML”) techniques to generate models for various locations or regions (e.g., sectors) associated with one or more radio access networks (“RANs”) of a wireless network. The system may further use AI/ML techniques to generate interference models to reflect types and/or amounts of channel propagation metrics measured within the RAN. The system may further determine, based on attributes of a given sector, a sector model and/or a channel propagation model associated with the sector. Based on the sector model and/or the determined channel propagation model, one or more actions may be determined in order to enhance channel propagation metrics within the sector, such as at portions of the sector at which increased demand for wireless service is detected.

Abstract: A system described herein may provide for the use of artificial intelligence/machine learning (“AI/ML”) techniques to generate models for various locations or regions (e.g., sectors) associated with one or more radio access networks (“RANs”) of a wireless network. The system may further use AI/ML techniques to generate interference models to reflect types and/or amounts of channel propagation metrics measured within the RAN. The system may further determine, based on attributes of a given sector, a sector model and/or a channel propagation model associated with the sector. Based on the sector model and/or the determined channel propagation model, one or more actions may be determined in order to enhance channel propagation metrics within the sector, such as at portions of the sector at which increased demand for wireless service is detected.

Abstract: A method for summarizing dialogs may include obtaining an agent text stream and a customer text stream, segmenting the agent text stream and customer text stream into sentences, and labeling sentences associated with the segmented agent text stream and the segmented customer text stream. The method may further include extracting sentences from the agent text stream and the customer text stream based upon frequencies of appearance of words and terms of interest; generating an agent summary paragraph based on the extracted sentences from the agent text stream, and generating a customer summary paragraph based on the extracted sentences from the customer text stream. The method may identify keywords associated with each of the agent summary paragraph and the customer summary paragraph.

Abstract: A method for summarizing dialogs may include obtaining an agent text stream and a customer text stream, segmenting the agent text stream and customer text stream into sentences, and labeling sentences associated with the segmented agent text stream and the segmented customer text stream. The method may further include extracting sentences from the agent text stream and the customer text stream based upon frequencies of appearance of words and terms of interest; generating an agent summary paragraph based on the extracted sentences from the agent text stream, and generating a customer summary paragraph based on the extracted sentences from the customer text stream. The method may identify keywords associated with each of the agent summary paragraph and the customer summary paragraph.

Abstract: A method for summarizing dialogs may include obtaining an agent text stream and a customer text stream, segmenting the agent text stream and customer text stream into sentences, and labeling sentences associated with the segmented agent text stream and the segmented customer text stream. The method may further include extracting sentences from the agent text stream and the customer text stream based upon frequencies of appearance of words and terms of interest; generating an agent summary paragraph based on the extracted sentences from the agent text stream, and generating a customer summary paragraph based on the extracted sentences from the customer text stream. The method may identify keywords associated with each of the agent summary paragraph and the customer summary paragraph.

Abstract: Systems, apparatuses, methods, and computer programs for overprovisioning resources are disclosed. Resource usage statistics may be gathered for a plurality of client virtual machines (“VMs”). Statistical characteristics of resource usage by the plurality of client VMs may be calculated. It may also be determined which of the plurality of client VMs requesting resources to allocate resources to, as well as an amount of the resources to allocate, in a given time slot based on the calculated statistical characteristics.

Abstract: A method and apparatus of providing a user with a customized user interface is disclosed. One example may include generating a window display area based on at least one predefined user preference, and displaying the window display area in a specified location of the user. The method may also include prompting the user to select at least one particular application that may be associated with the window display area, and prompting the user to customize the window attributes by modifying the window display area. Other operations may include saving the customized window display area in a memory of a computing device once the user has completed the customizing of the window attributes.

Abstract: A computer device may include a memory storing instructions and processor configured to execute the instructions to obtain a text file generated based on a communication session; select topics for classifying communication sessions; and apply one or more trained machine learning models to the obtained text file to determine one or more most likely topics for the communication session. The processor may be further configured to apply regular expression binary classifiers, each associated with a different topic, to the obtained text file to determine a likelihood the communication session is associated with a particular topic; select a topic for the communication session based on the determined one or more most likely topics and the determined likelihood the communication session is associated with the particular topic; and classify the communication session based on the selected topic.

Abstract: The present application describes performing a user initiated search query comprising receiving user input comprising description details of at least one desired object, retrieving a plurality of objects from a database sharing one or more of the description details of the user input, retrieving an image of the at least one desired object based on one or more of the plurality of objects, generating a contour of the image and comparing the generated contour with other related contours of other images stored in the database, displaying all of the available contours of all of the images that match the generated contour, receiving a selection of one of the available contours from the user and performing the search query based on the user selected contour.

Abstract: A computer device may include a memory storing instructions and processor configured to execute the instructions to obtain a text file generated based on a communication session; select topics for classifying communication sessions; and apply one or more trained machine learning models to the obtained text file to determine one or more most likely topics for the communication session. The processor may be further configured to apply regular expression binary classifiers, each associated with a different topic, to the obtained text file to determine a likelihood the communication session is associated with a particular topic; select a topic for the communication session based on the determined one or more most likely topics and the determined likelihood the communication session is associated with the particular topic; and classify the communication session based on the selected topic.

Abstract: Systems, apparatuses, methods, and computer programs for overprovisioning resources are disclosed. Resource usage statistics may be gathered for a plurality of client virtual machines (“VMs”). Statistical characteristics of resource usage by the plurality of client VMs may be calculated. It may also be determined which of the plurality of client VMs requesting resources to allocate resources to, as well as an amount of the resources to allocate, in a given time slot based on the calculated statistical characteristics.

Abstract: Certain aspects of the present disclosure relate to a technique for processing data based on touch events on a touch sensitive device. A first touch event is detected indicating a selection of a value for an attribute using a touch input device from a first portion of a touch sensitive display screen of the touch sensitive device. A second touch event is detected indicating a change in position of the touch input device from the first portion to a second portion of the touch sensitive display screen of the touch sensitive device. In response to detecting the second touch event, a query is determined for searching a database based on the value for the attribute.

Abstract: Certain aspects of the present disclosure relate to a technique for determining a valid sequence of touch events on a touch sensitive device. A first sequence of touch events is received, a proximity between any two touch events of the first sequence of touch events being greater than a proximity threshold. A second sequence of touch events is received. The touch events from the first and the second sequence are combined if a time difference between the first and the second sequence of touch events is below a time threshold and a proximity between the first and the second sequence of touch events is less than the proximity threshold. A valid sequence of touch events is determined if a combined pressure of the first and the second sequence of touch events is greater than a pressure threshold.