Abstract: Computerized systems are provided for automatically determining action items of an event, such as a meeting. The determined action items may be personalized to a particular user, such as a meeting attendee, and may include contextual information enabling the user to understand the action item. In particular, a personalized action item may be determined based in part from determining and utilizing particular factors in combination with an event dialog, such as an event speaker's language style; user role in an organization; historical patterns in communication; event purpose, name, or location; event participants, or other contextual information. Particular statements are evaluated to determine whether the statement likely is or is not an action item. Contextual information may be determined for action items, which then may be provided to the particular user during or following the event.

Abstract: Methods and systems for generating a recovery scheduling solution in response to a scheduling disruption are disclosed.

Abstract: Systems and methods for training models to improve fairness.

Abstract: Techniques described herein are directed to e-commerce tags in multimedia content. In an example, multimedia content is received and item-recognition techniques are performed to identify one or more items referenced in the content. An interactive element is generated that indicates information about a given referenced item, and that interactive element is displayed while the multimedia content is output. Selection of the interactive element may cause a purchasing user interface to be displayed with item and/or or payment information prepopulated based at least in part on identified attributes of the item and/or user preferences determined from historical purchase data associated with the user.

Abstract: Systems and methods are provided herein for altering a start time of an event based on indicia of how late event attendees will be for the event that are retrieved from location applications corresponding to each attendee of the attendees. For example, a media guidance application may determine a start time of an event, a location of the event, and attendees of the event. The media guidance application may determine location applications corresponding to the attendees. The media guidance application may query the location applications for arrival times of each attendee. The media guidance application may calculate a plurality of differences between each of the arrival times and the start time of the event. Based on the plurality of differences, the media guidance application may delay the start time of the event.

Abstract: A method, apparatus, system, and computer program code for forecasting a data anomaly to a supply chain. A plurality of data records is identified for a plurality of entities. The data records include import records and export records. The data fields in the data records are categorized into generic field types. The generic field types include numeric fields, categorical fields, and date fields. For each of the plurality of entities, an entity-specific model is constructed for forecasting imports and exports based on the generic field types. The entity-specific model for each of the plurality of entities is combined into a global supply chain model. Based on the global supply chain model, a data anomaly is forecast to a supply chain that is associated with a particular entity.

Abstract: A system for facilitating construction of a deck comprises a server, a client computer, and a database. A user inputs, through a graphical user interface on the display of the client computer, a configuration for the deck. The server receives the deck information from the client computer and determines, based on information in the database and the deck information, a parts list and instruction information. The instruction information includes information on the alterations to the parts needed to construct the deck. The parts list and the instruction information may be displayed on the user interface.

Abstract: A construction management system includes: a current topography data acquisition unit configured to acquire current topography data indicating a current topography of a construction site; a design topography data acquisition unit configured to acquire design topography data indicating a design topography of the construction site; a construction plan data calculation unit configured to calculate construction plan data including earth cutting plan data and earth banking plan data by collating the current topography data with the design topography data; and a construction plan data output unit configured to output the construction plan data to an output device. The construction plan data output unit causes an output device to output at least two of the design topography data, the cutting plan data, and the banking plan data in parallel.

Abstract: Aspects described herein relate to a flexible order fulfillment management system that utilizes predefined fulfillment workflows including common business processes. By utilizing predefined workflows including common business processes, the order fulfillment management system is able to drive store-based fulfillment programs efficiently as multiple fulfillment workflows may utilize the same common business processes and a single fulfillment management system may operate workflows in parallel. In addition, such an order fulfillment management system may also be more easily adapted for different retail store environments as the system allows a designer to easily create or modify a fulfillment workflow by selecting predefined common business processes or creating any additional custom business processes.

Abstract: Machine learning based method for multilabel learning with label relationships is provided. This methodology addresses the technical problem of alleviating computational complexity of training a machine learning model that generates multilabel output with constraints, especially in contexts characterized by a large volume of data, by providing a new formulation that encodes probabilistic relationships among the labels as a regularization parameter in the training objective of the underlying model. For example, the training process of the model may be configured to have two objectives. Namely, in addition to the objective of minimizing conventional multilabel loss, there is another training objective, which is to minimize penalty associated with the prediction generated by the model breaking probabilistic relationships among the labels.

Abstract: Methods and systems are disclosed for scheduling a task of a user based on a cyber-physical-social (CPS) context of activities. The present disclosure is directed to increasing the efficiency of performing tasks by grouping tasks with the same or similar task CPS contexts so that they are performed in conjunction with one another. A stream of user activities is received that encompasses the CPS context, tasks are identified and classified based on a CPS context model. The CPS model is trained using CPS context and annotations for identified tasks as input to create classes of tasks. The classes of tasks from the model are used to group similar tasks. The present disclosure enables users to receive recommendations on clustering tasks with the same or similar contexts based on an online tool, a location, and collaborators to be performed together to improve productivity.

Abstract: An approach is provided that transmit a first set survey questions to a user with each of the first set questions corresponding to a primary survey goal. Survey answers are then received from the user. A cognitive system is then used to determining an affinity level between the user and the primary survey goal. If the affinity level reaches a threshold, then a second set of questions is transmitted to the user with these questions also corresponding to the primary survey goal. However, if the first affinity level fails to reach the threshold, then the second set of questions are based on a secondary survey goal and these questions are transmitted to the user.

Abstract: A machine learning (ML) process can include teaching, with a teaching set, a first ML algorithm to generate one or more machine-predicted results. One or more weights can be generated based on the one or more machine-predicted results and the teaching set. A second ML algorithm can be generated based on the one or more weights. Via the second ML algorithm, one or more machine-learned results can be generated. A description of one or more candidates can be received. Based on the one or more machine-learned results, a respective likelihood of interest in a CCG class of positions for each of the one or more candidates can be generated. A respective communication can be transmitted to each of a subset of the one or more candidates open to the respective likelihood of interest in the CCG class of positions for the subset above a threshold.

Abstract: Systems and methods of automated personalized guidance include the evaluation of interaction content data. At least one automated guidance is assigned to an agent based upon the evaluation. The automated guidance is defined by at least one interaction type and at least one guidance trigger. Interaction content data is monitored to identify instances of the interaction type and the guidance trigger. Upon identification of the interaction type and the guidance trigger, the automated guidance is automatically provided. The automated guidance is then evaluated based upon the interaction content data.

Abstract: A system and a method for connecting a tutor with a student in real time. Initially, the system receives a student profile. Further, the system receives a question from the student. Furthermore, the system synthesizes the question based on a set of predefined machine learning model. Subsequently, the system determines a cohort of the students from the set of the cohort of the students. The cohort of the students is determined based on the one or more parameters related to the question. Further, the system identifies a tutor assigned to the cohort of the students. Subsequently, the system notifies the tutor in real time. Further, the system receives an acknowledgement from the tutor within a predefined time. Finally, the system connects the tutor with the student in real time when the acknowledgement is the positive acknowledgement.

Abstract: Described are a system, method, and computer program product for generating and applying a predictive wait time estimate using predictive modeling. The method includes receiving initial transaction data representative of a plurality of transactions between a plurality of transaction accounts and at least one merchant. The method also includes generating, for each subinterval, training data including at least one of the following: service rate during the subinterval, number of transactions during the subinterval, total transaction value during the subinterval, mean transaction value during the subinterval, year, month, day of week, or any combination thereof. The method further includes generating a predictive model that generates an output of arrival rate for an input of at least one time parameter. The method further includes generating the predictive wait time estimate for a designated time.

Abstract: A method for analyzing survivability of an infrastructure link includes determining an optimal path arrangement of the infrastructure link between two geographic locations; and determining a risk index associated with the determined optimal path arrangement based on one or more quantified cost factors and one or more quantified risk factors associated with the determined optimal path arrangement. The risk index represents a survivability of the infrastructure link.

Abstract: A central system, or server, may store information for determining the schedules of drivers. For example, the information may include loads assigned to the drivers, training, lunch breaks, time off, and/or other commitments. The central system may centrally store the information to efficiently and conveniently determine and update schedules. The central system may allow drivers and/or carriers to manage driver onboarding, training, compliance, scheduling, work assignment, and reporting, as well as build monthly, weekly, and daily schedules. The central system may also automate matching drivers to loads, balances work distribution, reduce human errors, and assist in audits.

Abstract: A system and method for dispatching haul trucks includes a production planner configured to operate based on a production plan. The production planner computationally defines production arcs for transferring material from loading tools to dump sites, computationally develops one or more possible return arcs for each production arc, compiles a set of possible return arcs, and computationally selects a sub-set of the possible return arcs to command a real time dispatcher.

Abstract: Methods, apparatuses, and systems for scheduling tasks to field professionals include: storing, in a database, a plurality of records reflecting characteristics associated with completing a set of technical services, wherein information in each record is derived from historical experience of completing each of the technical services; receiving a request for a new technical service associated with a location; and assigning a field professional to perform the new service having determined from information in the database a likelihood that the field professional will complete the new technical service in a single on-site visit at the location.