Abstract: Store a subscription dataset for each tenant of a multi-tenant system, each of the subscription datasets having a common data format native to the system, the subscription datasets including billing data and not behavioral data. Determine primary features from a particular subscription dataset. Derive secondary features from the primary features. Generate a churn prediction model based on the primary features and the secondary features. Obtain a second subscription dataset, the second subscription dataset comprising billing data that is more recent than the particular subscription dataset. Identify, using the particular churn prediction model and the second subscription dataset, one or more subscribers as a churn-risk. Report the one or more subscribers identified as a churn-risk.

Abstract: An objective of the present invention is to promote efficiency improvement of a business by a mobile device. A business analysis server that analyzes a business in a mobile device system conducting the business by controlling a mobile device on the basis of a scenario includes a control unit, and a storage unit including a business index value database that manages a business index value indicating an effect of the business and a business index value history database that manages a change in the business index value as time-series data. The control unit receives scenario execution information when a business index value is designated, analyzes a correlation between the business index value and the scenario by referring to the business index value history database and the scenario execution information, extracts a target scenario whose correlation value with the business index value satisfies predetermined conditions, and generates a correction scenario.

Abstract: One example operation may include retrieving meeting participant profiles associated with meeting participants and meeting topics assigned to a scheduled meeting set to occur at a scheduled meeting time for a time duration, creating the meeting, at the scheduled meeting time, with a number of meeting intervals, collectively which comprise the time duration of the meeting, and each of the meeting intervals are assigned a respective different meeting topic among the meeting topics, assigning the participant profiles to one or more of the meeting intervals, automatically initiating a start to the meeting at the scheduled meeting time, without any of the meeting participants being connected to the meeting via their respective computing devices, and creating one or more of audio and video content based on one or more of the meeting topics and one or more meeting data files.

Abstract: Improvement of work is instructed based on an analysis result obtained by combining data having different timescales. A productivity improvement support system includes a time scale setting unit configured to, when 4M data having different time scales acquired from a target device contains data that satisfy a condition for detecting a state fluctuation, switch time scale of the 4M data to time scales according to a state fluctuation, a loss analysis calculation unit configured to analyze a production loss factor by using analysis model data in which the production loss factor of the target device when the condition is satisfied is determined, and a recommended work selection unit configured to select a recommended work when the production loss factor occurs from one or a plurality of recommended works by using recommended work data stored in association with the production loss factor.

Abstract: One example method of operation may include identifying a plurality of active project files in a database, identifying one or more deliverables included in the plurality of active project files, performing a simulation test based on a current set of allocated resources and a current set of deadlines associated with each of the one or more deliverables to determine whether the one or more deliverables will fail, determining the one or more deliverables includes one or more failed project risk metrics indicating that the one or more deliverables will fail to be completed by a corresponding deadline among the current set of deadlines, selecting one or more of the active project files which does not have a failed project risk metric, and reallocating resources, from the one or more of the active project files which does not have a failed project risk metric, to one or more of the active project files which has one or more failed project risk metrics.

Abstract: One example method of operation may include identifying a topics to apply to a meeting having a defined time window, creating meeting time intervals corresponding to the topics, transmitting meeting invites to user accounts identified as potential meeting attendees, identifying when the user accounts were active in the meeting, and determining the user accounts fulfilled a topic fulfillment obligation of one or more of the topics based on a user account presence during one or more of the meeting intervals.

Abstract: An automated method for determining a complexity of a task. The method includes extracting data from the plurality of historical support tickets to generate training data. The method trains a complexity model to predict a complexity value of a task associated with a support ticket using the training data. The method predicts, using the complexity model, the complexity value of a new task associated with a new support ticket.

Abstract: A system for validating data includes a digital touch point associated with an organization having an element and a quality assurance (QA) module for monitoring the digital touch point. The system includes a quality control (QC) algorithm associated with the QA module, which is executed against the new element to determine if one or more discrepancies exist between current data for the new element and expected data for the new element. The system includes a tangible error report that captures one or more discrepancies between the current data and the expected data for the new element. The QA module has the ability to modify the request to call to eliminate the one or more discrepancies.

Abstract: Methods, apparatus, and processor-readable storage media for automatically identifying and correcting erroneous process actions using artificial intelligence techniques are provided herein. An example computer-implemented method includes discovering, during execution of a given process, one or more process action variants by processing data related to the given process using at least a first set of artificial intelligence techniques; categorizing at least a portion of the discovered process action variants into one or more groups based at least in part on historical process-related data and at least one density-based clustering algorithm; determining at least one resolution action in response to at least a portion of the one or more discovered process action variants by processing data pertaining to the one or more groups using at least a second set of artificial intelligence techniques; and performing the at least one determined resolution action.

Abstract: A computerized-method for generating a machine-learning model to determine genuineness of customer feedback to filter-out, non-genuine agent recording segments from evaluation. The computerized-method includes generating a Genuineness Opinion Score (GOS) model. The generating of GOS model includes: (a) a data manipulation phase; (b) a data visualization and analysis phase, and (c) a feature augmentation phase for sorting the variables in a set of unique and relevant variables into two categories: estimated variables and anticipated variables. The estimated variables are used for calculation of a GOS of an interaction that is received in a contact center and the anticipated variables are used for calculation of a threshold of said GOS.

Abstract: A system and method are disclosed for solving a supply chain planning problem modeled as a linear programming (LP) problem. Embodiments include receiving a matrix formulation of at least a portion of the LP problem representing a supply chain planning problem for a supply chain network, generating an image based on the matrix formulation to identify connected components, partitioning the matrix formulation based, at least in part, on the connected components constraint into at least two partitions, formulating an LP subproblem from each of the at least two partitions, and solving the LP subproblems to generate a global solution to the supply chain planning problem.

Abstract: Methods and devices for decommissioning micro-climate sensors for generating product flow data for each of a plurality of items of sale flowing through a supply chain are disclosed. An example device may include an opening for receiving at least one micro-climate sensor and a space for storing the sensor. The device may further include a plurality of sensors operative to detect a presence of the at least one micro-climate sensor, and a sensor decommission circuit to generate a decommission command value in response to detection of the at least one micro-climate sensor.

Abstract: One example method of operation may include identifying a proposed meeting summary, processing proposed meeting summary content of the proposed meeting summary to identify topics to apply to a meeting, identifying profiles matching one or more of the topics, transmitting meeting invites to user accounts linked to the profiles, receiving one or more confirmations from the user accounts confirming attendance at the meeting, initiating the meeting at a scheduled time, and forwarding an initial topic summary to each user account during a beginning of the meeting.

Abstract: Aspects of the disclosure relate to a machine learning based decentralized business planning system. A computing platform may identify an event likely to impact one or more business operations. Subsequently, the computing platform may receive, for the event, data from one or more sources of data. Then, the computing platform may generate a data structure including a plurality of nodes, where the plurality of nodes corresponds to the received data. Then, the computing platform may authenticate, by utilizing a distributed ledger-based verification system, the plurality of nodes. Subsequently, the computing platform may perform, based on business rules applicable to the one or more business operations, analytics on the plurality of authenticated nodes. Then, the computing platform may generate, based on the analytics, a contingency plan to mitigate the impact to the one or more business operations, and may provide, via an interactive graphical user interface, the contingency plan.

Abstract: One example method of operation may include identifying project files in a database, identifying one or more active project files and one or more inactive project files from the project files, retrieving one or more of the inactive project files, identifying one or more project risk metrics associated with the one or more inactive project files, and determining potential project risk metrics associated with the one or more active project files based on the one or more project risk metrics associated with the one or more inactive project files.

Abstract: One example method of operation may include identifying a plurality of project files stored in a database, determining current project scores assigned to the plurality of project files, selecting a lowest scored project file with a lowest assigned project score, identifying one or more types of resources assigned to the project file with the lowest score, identifying the highest scored project file and the types of resources assigned to the highest scored project file, determining whether any of the types of resources assigned to the highest scored project file match any of the types of resources assigned to lowest scored project, and when one or more types of resources assigned to the highest scored project file match the types of resources assigned to the lowest scored project, assigning one or more of the matched resources of the highest scored project file to the lowest scored project.

Abstract: Methods and systems for determining cyber security related projects to implement. Cyber security related projects used to protect entity assets can be identified. A return on investment for each cyber security related project can be determined. An optimization programming problem algorithm can be solved to remove project redundancies. Cyber security related projects to implement can be determined.

Abstract: One example method of operation may include identifying a proposed meeting summary, processing proposed meeting summary content of the proposed meeting summary to identify topics to apply to a meeting, creating the meeting to include meeting time intervals, assigning one or more of the topics to one or more of the meeting time intervals, identifying profiles of user accounts matching one or more of the topics, assigning the user accounts, with profiles matching one or more of the topics, to one or more of the meeting time intervals with assigned ones of the topics which match the profiles of the user accounts, transmitting meeting invites to the user accounts, and initiating the meeting at a scheduled time.

Abstract: Methods to update a database and forward a communication are disclosed. A method to update a database may include a service provider device receiving a first communication in one of a plurality of communication formats, the first communication including unknown content that is interpretable by the service provider device. The service provider device may parse the first communication to discover a request to modify a schedule of a plurality of events stored in the service provider database. The service provider device may modify the schedule in accordance with the request. The service provider device may send a second communication indicating that the schedule has been modified in accordance with the request or seeking information required to complete the modification.

Abstract: Various examples are directed to systems and methods for managing a warehouse. For example, a set of candidate routes through the warehouse may be generated based at least in part on graph data describing a plurality of nodes comprising a depot node, and a plurality of internode paths. Orders may be assigned to routes from the set of candidate routes to minimize a total duration for the routes. A set of tasks may be generated, where a first task of the set of tasks comprises a route and an order of the plurality of orders matched to the route. Tasks from the set of tasks may be assigned to picking agents to minimize a duration of the longest task from the set of tasks.