Abstract: A computer-implemented method, a computer program product, and a computer system for log anomaly detection. A computer receives a windowed log of incoming raw log messages. A computer compares statistical distribution metrics of entities in the windowed log with a statistical distribution extracted from a real-time statistical model for the entities. In response to the statistical distribution metrics being statistically different from the statistical distribution extracted from the real-time statistical model for the entities, a computer tags the windowed log as an entity anomaly. A computer computes a distance between an average word embedding vector in the windowed log and a statistical distribution extracted form a real-time statistical model for word embeddings. In response to the distance being greater than a predetermined threshold, a computer tags the windowed log as a word embedding anomaly. A computer sends to a user an alert with an anomaly severity level.

Abstract: A computer-implemented method, a computer program product, and a computer system for log anomaly detection. A computer receives a windowed log of incoming raw log messages. A computer compares statistical distribution metrics of entities in the windowed log with a statistical distribution extracted from a real-time statistical model for the entities. In response to the statistical distribution metrics being statistically different from the statistical distribution extracted from the real-time statistical model for the entities, a computer tags the windowed log as an entity anomaly. A computer computes a distance between an average word embedding vector in the windowed log and a statistical distribution extracted form a real-time statistical model for word embeddings. In response to the distance being greater than a predetermined threshold, a computer tags the windowed log as a word embedding anomaly. A computer sends to a user an alert with an anomaly severity level.

Abstract: Embodiments of the present invention provide a system, method and computer program product for forecasting a time series based on actuals and a plan. A method comprises generating a first and a second sequence of segments that rise and fall alternately based on a first and a second sequence of data values over time, respectively. The first and second sequence of data values represent actual data for an ongoing project and estimated data for a planned project, respectively. The method further comprises aligning at least one segment of the second sequence of segments with at least one segment of the first sequence of segments, and adjusting the estimated data by replacing at least one segment of the second sequence of segments with a scaled version of at least one corresponding aligned segment of the first sequence of segments. The scaled version maintains an estimated total for the planned project.

Abstract: Embodiments of the present invention provide a system, method and computer program product for forecasting a time series based on actuals and a plan. A method comprises generating a first and a second sequence of segments that rise and fall alternately based on a first and a second sequence of data values over time, respectively. The first and second sequence of data values represent actual data for an ongoing project and estimated data for a planned project, respectively. The method further comprises aligning at least one segment of the second sequence of segments with at least one segment of the first sequence of segments, and adjusting the estimated data by replacing at least one segment of the second sequence of segments with a scaled version of at least one corresponding aligned segment of the first sequence of segments. The scaled version maintains an estimated total for the planned project.

Abstract: Embodiments of the present invention provide a system, method and computer program product for forecasting a time series based on actuals and a plan. A method comprises generating a first and a second sequence of segments that rise and fall alternately based on a first and a second sequence of data values over time, respectively. The first and second sequence of data values represent actual data for an ongoing project and estimated data for a planned project, respectively. The method further comprises aligning at least one segment of the second sequence of segments with at least one segment of the first sequence of segments, and adjusting the estimated data by replacing at least one segment of the second sequence of segments with a scaled version of at least one corresponding aligned segment of the first sequence of segments. The scaled version maintains an estimated total for the planned project.

Abstract: Embodiments of the present invention provide a system, method and computer program product for generating a succinct approximate representation of a time series. A method comprises determining at least one peak data value and at least one trough data value of an input series comprising a sequence of data values over time. The input series is partitioned into multiple segments comprising at least one rising segment that rises to a peak data value and at least one falling segment that falls to a trough data value. A sequence of segments that rise and fall alternately is generated based on the segments. A sequence of totals representing a succinct approximate representation of the input series is generated. Each total comprises a sum of data values for a corresponding segment of the sequence of segments.

Abstract: Tracking of brand followers utilizing social media history and generation of directed advertising. A computing device receives a brand for market analysis, the brand having a brand account on a social media platform. Social media history is received regarding social media habits of social media users. A distribution of brand followers is determined among social media users following the brand account. One or more clusters are generated for viewing market segmentation regarding the brand for market analysis. Brand data is received regarding a plurality of brands having brand accounts on the social media platform, follower profiles for brand followers of the plurality of brand accounts, and social media information for the followers of the plurality of brand accounts. An influencer analysis is generated. Historical follower profiles are received. A historical distribution analysis is generated. A market analysis is generated. Directed advertising is generated based upon the market analysis.

Abstract: A computer program product that includes a computer useable storage medium to store a computer readable program that, when executed on a computer, causes the computer to perform operations, including operations to incorporate an entity specification into a business process in response to an input by a user, determine a multifunction printer (MFP) from a heterogeneous mix of MFPs for implementation of the business process, and generate an executable to execute on the MFP. The entity specification describes an element of a document and is associated with the business process. The MFP has an associated executable language and a graphical user interface (GUI) specification. The executable conforms to the executable language and the GUI specification, is generated from the entity specification and the business process, and performs the business process when executed by the MFP.

Abstract: A system for generating an optimal set of tasks to be performed includes an interface to receive from a user first and second processes and a priority criterion defining an objective of the first and second processes and a process converter configured to convert the first and second processes into tasks that make up the first process and the second process. The system further includes a task network modeler configured to determine relationships between the tasks and to generate a task network comprising the tasks of the first and second processes, the task network representing the relationships between the tasks of the first and second processes. The system further includes an optimization unit configured to generate, based on the priority criterion, an optimal set of tasks in the task network to be performed.

Abstract: Disclosed are methods and systems for identifying and visualizing the patterns of work transfers for service delivery using financial data. Within a service firm, work is often transferred from one delivery center to another, which results in additional costs and delays in service delivery. To control unnecessary work transfers, sustained patterns of work transfer are identified so that steps can be taken to limit their occurrence. The disclosed methods and systems analyze the relations among the costs transferred from one location to another.

Abstract: A method includes obtaining, by a processor, a representation of a first process and dividing the first process into tasks that make up the first process. The method includes determining relationships between the tasks and generating a task network comprising the tasks of the first process. The task network represents the relationships between the tasks of the first process. The method further includes receiving a priority criterion defining an objective and generating, based on the priority criterion, an optimal set of tasks in the task network to be performed.

Abstract: Embodiments of the present invention provide a system, method and computer program product for selecting representative models. A method comprises generating a first data model representing a first aggregation level, and generating multiple additional data models. Each additional data model represents a lower aggregation level than the first data model. For each additional data model, a corresponding score is determined. For each lower aggregation level, a corresponding combined score is determined based on two or more highest scoring additional data models representing the lower aggregation level. The method further comprises reporting a second aggregation level and a set of data models. The second aggregation level is a lower aggregation level having the highest combined score over all other lower aggregation levels. The set of data models comprises two, or more, highest scoring additional data models representing the second aggregation level.

Abstract: Embodiments of the present invention provide a system, method and computer program product for extrapolating a time series. A method comprises receiving multiple sequences of data values over time. Each sequence of data values is partitioned into a corresponding plurality of segments comprising at least one rising segment that rises to a peak data value of the sequence of data values and at least one falling segment that falls to a trough data value of the sequence of data values. For each sequence of data values, a corresponding sequence of segments that rise and fall alternately is generated based on a corresponding plurality of segments for the sequence of data values. An aggregated sequence of segments is generated by aggregating each sequence of segments generated. The aggregated sequence of segments represents a typical model for the sequences of data values.

Abstract: Embodiments of the present invention provide a system, method and computer program product for forecasting a time series based on actuals and a plan. A method comprises generating a first and a second sequence of segments that rise and fall alternately based on a first and a second sequence of data values over time, respectively. The first and second sequence of data values represent actual data for an ongoing project and estimated data for a planned project, respectively. The method further comprises aligning at least one segment of the second sequence of segments with at least one segment of the first sequence of segments, and adjusting the estimated data by replacing at least one segment of the second sequence of segments with a scaled version of at least one corresponding aligned segment of the first sequence of segments. The scaled version maintains an estimated total for the planned project.

Abstract: Embodiments of the present invention provide a system, method and computer program product for generating a succinct approximate representation of a time series. A method comprises determining at least one peak data value and at least one trough data value of an input series comprising a sequence of data values over time. The input series is partitioned into multiple segments comprising at least one rising segment that rises to a peak data value and at least one falling segment that falls to a trough data value. A sequence of segments that rise and fall alternately is generated based on the segments. A sequence of totals representing a succinct approximate representation of the input series is generated. Each total comprises a sum of data values for a corresponding segment of the sequence of segments.

Abstract: Disclosed are methods and systems for identifying and visualizing the patterns of work transfers for service delivery using financial data. Within a service firm, work is often transferred from one delivery center to another, which results in additional costs and delays in service delivery. To control unnecessary work transfers, sustained patterns of work transfer are identified so that steps can be taken to limit their occurrence. The disclosed methods and systems analyze the relations among the costs transferred from one location to another.

Abstract: A system for generating an optimal set of tasks to be performed includes an interface to receive from a user first and second processes and a priority criterion defining an objective of the first and second processes and a process converter configured to convert the first and second processes into tasks that make up the first process and the second process. The system further includes a task network modeler configured to determine relationships between the tasks and to generate a task network comprising the tasks of the first and second processes, the task network representing the relationships between the tasks of the first and second processes. The system further includes an optimization unit configured to generate, based on the priority criterion, an optimal set of tasks in the task network to be performed.

Abstract: A method includes obtaining, by a processor, a representation of a first process and dividing the first process into tasks that make up the first process. The method includes determining relationships between the tasks and generating a task network comprising the tasks of the first process. The task network represents the relationships between the tasks of the first process. The method further includes receiving a priority criterion defining an objective and generating, based on the priority criterion, an optimal set of tasks in the task network to be performed.

Abstract: A computer-implemented method that includes incorporating an entity specification into a business process in response to an input by a user is described. The entity specification describes an element of a document and is associated with the business process. The computer-implemented method also includes determining a multifunction printer (MFP) from a heterogeneous mix of MFPs for implementation of the business process. The MFP has an associated executable language and a graphical user interface (GUI) specification. The computer-implemented method also includes associating the entity specification with an element of the GUI specification. The computer-implemented method also includes generating, from the entity specification and the business process, an executable that conforms to the executable language and the GUI specification and performs the business process when executed by the MFP. The computer-implemented method also includes deploying the executable to the MFP.

Abstract: Systems and methods for adapting an existing call flow wherein the call flow further comprises an associated data set, comprising: activating the existing call flow, the existing call flow generating a series of questions designed to obtain information from a caller; determining if an exception condition has occurred; allowing a user to activate an exception call flow in response to the exception condition; retaining the data set associated with the call flow when the exception condition occurred; adapting the data set such that the call flow addresses the exception condition; analyzing the adapted data set to determine if it is unique; and, modifying the existing call flow to incorporate the adapted data set if the adapted data set is unique.