Abstract: There is disclosed a system for maintaining content lists. The system includes nodes interconnected by at least one data network. The nodes are organized hierarchically to comprise a root node and at least two child nodes. The root node stores a list of content items expected to be of interest to a particular user; transmits data reflective of an update for a subset of the list to at least one of the child nodes, the subset selected based on at least a predicted future location of the particular user and a geographic location of that child node; and receives data reflective of an update for the subset of the list from at least one of the child nodes. The at least one of the child nodes stores the subset of the list; determines an update for the subset of the list; and transmits data reflective of the update to the root node.

Abstract: Described herein are techniques for identifying anomalous behavior of a monitored entity. Features can be extracted from data related to operation of an entity. The features can be mapped to a plurality of states to generate a state sequence. An observed value of a metric can be compared to an expected value of the metric based on the state sequence.

Abstract: A method for predicting a failure of oilfield equipment based on univariate time series includes providing training data by a sensor. A training data stream comprising the training data is received by a preprocessor. The method further includes extracting training data segments and identifying each training data segment of the training data segments as corresponding to a normal operational state of the first oilfield equipment or a failed state of the first oilfield equipment. The method also includes generating a shapelet-based decision tree and receiving a test data stream from a sensor of second oilfield equipment. The method further includes determining, based on the shapelet-based decision tree, whether one or more test data segments extracted from the test data stream predict a failure of the second oilfield equipment.

Abstract: A method and device determines an optimization solution for an optimization problem. The method includes receiving the optimization problem having cost functions and variables in which each of the cost functions has a predetermined relationship with select ones of the variables. The variables comprise a sub-solution of a spline indicative of a curved path along an estimated trajectory. The method includes generating a first message for each of the cost functions for each corresponding variable based upon the relationship and a second message for each of the variables for each corresponding cost function based upon the relationship. The method includes generating a disagreement variable for each corresponding pair of variables and cost functions measuring a disagreement value between the first and second beliefs. The method includes forming a consensus between the first and second messages until the optimization solution is determined.

Abstract: A computer-implemented system and method of analyzing spatial, temporal and contextual elements of data for predictive decision-making. The computer-implemented method includes receiving a first set of rules and receiving first data and second data including spatial, temporal and contextual elements. The computer-implemented method also includes identifying each rule of the first set for which the received first data and the received second data is a respective candidate. For the identified rules for which the received first data is a candidate, and for the identified rules for which the received second data is a candidate, the respective received first data and received second data is indexed by its temporal, spatial or contextual elements as a function of the identified rules. The computer-implemented method also includes identifying an event as satisfying an identified rule in memory using the indexed first and second data.

Abstract: An assisted method to identify an application component. User interaction with a component of an interactive software component is monitored, locator associated with each aspect of the component is identified, and a reconstructed version of the interactive software application is provided based on pieces of information derived from the response of the user on presented questions. The method is then determining the likelihood of the identification of a candidate component.

Abstract: Method and apparatus for forecasting a characteristic information change. Historical characteristic data in at least one computation period and current incremental data of multiple pieces of first characteristic information corresponding to a pre-estimation model is acquired. The current incremental data is used for indicating a ratio of characteristic data on a day immediately before a forecasting day of each of the multiple pieces to the historical characteristic data in the at least one computation period of each of the multiple pieces of first characteristic information. A first change information on the forecasting day of second characteristic information is determined by a forecasting process using the pre-estimation model based on the historical characteristic data and the current incremental data. Based on the first change information, change pre-estimation information on the forecasting day of the second characteristic information is determined to prompt a user to execute a corresponding operation.

Abstract: Systems and methods are included for adjusting a set of predicted future data points for a time series data set including a receiver for receiving a time series data set. One or more processors and one or more non-transitory computer readable storage mediums containing instructions may be utilized. A count series forecasting engine, utilizing the one or more processors, generates a set of counts corresponding to discrete values of the time series data set. An optimal discrete probability distribution for the set of counts is selected. A set of parameters are generated for the optimal discrete probability distribution. A statistical model is selected to generate a set of predicted future data points. The set of predicted future data points are adjusted using the generated set of parameters for the optimal discrete probability distribution in order to provide greater accuracy with respect to predictions of future data points.

Abstract: Disclosed are MNAR data analysis methods and apparatuses for analyzing user preference data on products. Also, a product recommendation system using the same is disclosed. A data analysis method based on a binomial mixture model comprises defining a binomial mixture model based data generation model for analyzing user preference data on products; defining a missing data mechanism model for explaining observation and missing of user preference data on the products; learning the data generation model and the missing data mechanism model based on observed user preference data on the products; and determining final preferences on products whose preferences are missing based on the learned data generation model and the learned missing data mechanism model.

Abstract: Computer implemented system and method for classifying users is provided. The method includes obtaining a data set from one or more sources corresponding to one or more users; segmenting the data set into segments, each segment comprising one or more data points, wherein each data point is specific and unique to a user; identifying difficult regions from one or more segments; computing a standard deviation of distances between the data points within each of the identified difficult regions for each of the identified difficult regions; selecting a radial basis function (RBF) kernel based on the standard deviation computed for each of the identified difficult regions; generating a support vector machine model on each of the identified difficult regions based on the selected RBF kernel to obtain a hyper plane comprising support vectors and weight assigned to the vectors; and classifying the users into a category based on the hyper plane.

Abstract: Machine learning with model filtering and model mixing for edge devices in a heterogeneous environment is disclosed. In an example embodiment, an edge device includes a communication module, a data collection device, a memory, a machine learning module, and a model mixing module. The edge device analyzes collected data with a model for a first task, outputs a result, and updates the model to create a local model. The edge device communicates with other edge devices in a heterogeneous group, transmits a request for local models to the heterogeneous group, and receives local models from the heterogeneous group. The edge device filters the local models by structure metadata, including second local models, which relate to a second task. The edge device performs a mix operation of the second local models to generate a mixed model which relates to the second task, and transmits the mixed model to the heterogeneous group.

Abstract: A machine learning heterogeneous edge device, method, and system are disclosed. In an example embodiment, an edge device includes a communication module, a data collection device, a memory, a machine learning module, a group determination module, and a leader election module. The edge device analyzes collected data with a model, outputs a result, and updates the model to create a local model. The edge device communicates with other edge devices in a heterogeneous group. The edge device determines group membership and determines a leader edge device. The edge device receives a request for the local model, transmits the local model to the leader edge device, receives a mixed model created by the leader edge device performing a mix operation of the local model and a different local model, and replaces the local model with the mixed model.

Abstract: A method for training a machine learning model for open domain question answering includes receiving trained classifiers for question answering. The received trained classifiers are used to generate a set of candidate answers to a question. Second trained classifiers are used for scoring each of the candidate answers. The scoring indicates a measure of how well each candidate answer answers the question. Using the second trained classifiers for scoring each of the candidate answers includes comparing each candidate answer to a first ground truth corresponding to the question. A set of top-scoring candidate answers is presented to a human operator who marks each as correct or incorrect. The correct candidate answers are treated as additional ground truths for further training the first trained classifiers.

Abstract: Scalable-effort machine learning may automatically and dynamically adjust the amount of computational effort applied to input data based on the complexity of the input data. This is in contrast to fixed-effort machine learning, which uses a one-size-fits-all approach to applying a single classifier algorithm to both simple data and complex data. Scalable-effort machine learning involves, among other things, classifiers that may be arranged as a series of multiple classifier stages having increasing complexity (and accuracy). A first classifier stage may involve relatively simple machine learning models able to classify data that is relatively simple. Subsequent classifier stages have increasingly complex machine learning models and are able to classify more complex data. Scalable-effort machine learning includes algorithms that can differentiate among data based on complexity of the data.

Abstract: Systems and methods for configuring AI algorithms and knowledge sets within an automated messaging system are providing. In some embodiments, a message is received. A subsection of text from the training message is selected. Likewise, a knowledge set is selected. The knowledge set includes probabilistic associations between a term and a category. The terms in the selected subsection of text are compared to the knowledge sets to generate insights and contexts. The insights enable the categorization of the training message. This categorization has an associated confidence value based upon how strongly the terms in the text subsection are associated with the category (per the selected knowledge set). A low confidence value causes the message to be a candidate for training (a training message). Once identified as a training message, it may be displayed to an AI developer for approval or rejection of the categorization.

Abstract: Methods, computing systems and computer program products implement embodiments of the present invention that include selecting a training dataset including training instances having respective training features, and applying a classifier to the training dataset, thereby generating a training classification that assigns, to each of the training instances, one of a plurality of categories, the classifier having an expected classification. A classification bias is detected in the training classification relative to the expected classification, and in response to the classification bias, a calibration matrix is defined based on the training features, and the classification bias. A production dataset including production instances is selected, and the classifier and the calibration matrix are applied to the production dataset, thereby generating a production classification quantification that assigns, to each of the production instances, one of the plurality of categories.

Abstract: Information extraction from observed data may be performed. First parameter weights and second parameter weights of a joint discriminative probability distribution may be determined. The joint discriminative probability distribution may be over first variables and second variables and may be conditioned on the observed data. The second variables may be modeled by first-order logic formulas. The first variables may be based on the first parameter weights, and the second variables may be based on the second parameter weights. A first likely output of the first variables based on the first parameter weights and a second likely output of the second variables based on the second parameter weights may be determined.

Abstract: A method for improving a profile analysis of an interpretive framework stored in a memory may include producing and displaying visual stimuli on a computerized device to test visual and visual motor responses of an individual subject in response to the displayed visual stimuli. The method may also include classifying and categorizing digitally measured visual and visual motor responses of the individual subject to the displayed visual stimuli. The method may further include continually modifying parameters of the profile analysis of the interpretive framework corresponding to at least one condition based at least in part on an item analysis corresponding to a pattern of performance determined during the classifying and categorizing of the digitally measured visual and visual motor responses of the individual subject.

Abstract: An algorithm according to an embodiment of the present invention provides for latent signal detection of adverse events. Embodiments infer the presence of adverse drug events from large observational databases housed by the FDA, WHO, and other governmental organizations. The disclosed algorithms do not require the adverse event to be reported explicitly. Instead, the algorithms infer the presence of adverse events through more common secondary effects. In an embodiment, machine learning techniques are used for this purpose.

Abstract: Queue techniques which use a beacon to detect customers. An example queue method includes receiving a message containing an identifier and contact information from a mobile communication device carried by a customer within communication range of a beacon, establishing a position of the customer in a queue, and sending a reply message to the mobile communication device at the contact information containing queue information.

Abstract: The proximity of an arriving guest can be determined and presented to the staff of a hospitality venue. The proximity of an arriving guest to the venue can be calculated using location information received from a GPS-enabled mobile application that executes on the guest's mobile device. The GPS-enabled mobile application can transmit the guest's location to a computer system that can calculate the guest's proximity to a venue based on the guest's location and the location of the venue. Once the proximity of the guest is determined, the proximity can be presented to the venue's staff. Additional information about the guest can also be presented to the staff to assist the staff in greeting the guest and customizing services to the guest's preferences once the guest arrives.

Abstract: An analysis device for time series data from an apparatus to be diagnosed according to the present invention is characterized by being provided with an accumulation device which accumulates sensor data, operation data, or control data, obtained from the apparatus to be diagnosed, while accumulating time information, an algorithm accumulation unit which accumulates algorithms for recognizing behavior of the apparatus to be diagnosed, a behavior recognition unit which recognizes behavior of the apparatus to be diagnosed by use a recognition algorithm, and a specification unit which specifies a behavioral item to be recognized, wherein: a behavior recognition algorithm corresponding to the specified behavioral item to be recognized is selected from the algorithm accumulation unit; sensor data, operation data, or control data to be used by the behavior recognition algorithm is selected from the accumulation device; the start and end times of a selected behavior are recognized by the behavior recognition unit; and

Abstract: A system and method for tracking shipments in a supply chain is provided.

Abstract: A method includes receiving input identifying a dimensional framework and forecasting time period. The method also includes generating a workforce plan based on the dimensional framework and the forecasting time period. The method further includes receiving first data defining a first scenario of the workforce plan, where the first scenario is associated with at least a first turnover assumption, and determining a first set of forecasted headcount values corresponding to the first scenario. The method includes receiving second data defining a second scenario of the workforce plan, where the second scenario is associated with at least a second turnover assumption that differs from the first turnover assumption, and determining a second set of forecasted headcount values corresponding to the second scenario. The method includes generating graphical user interface (GUI) data that includes a comparison of the first set of forecasted headcount values and the second set of forecasted headcount values.

Abstract: A method includes generating a workforce plan including forecasted headcount values associated with a plurality of dimension members of a plurality of dimensions and receiving input to create a first dimension member of a particular dimension of the plurality of dimensions. The particular dimension has an associated dimension level in a hierarchy corresponding to the particular dimension. The method includes storing data associated with the first dimension member to a data store associated with the workforce plan and receiving headcount values associated with a second dimension member that differs from the first dimension member. The method includes generating a graphical user interface (GUI) indicating that the first dimension member is determined to be a potential match for the second dimension member based on the first dimension member being a member of the particular dimension and having the same dimension level as the second dimension member.

Abstract: The application describes parallel solution generation. A data processing apparatus includes a memory including a computer program code, and at least two processors configured to execute the computer program code. The computer program code includes a component program run in parallel on at least two processors to generate solution components compiled in parallel of points, and to store the added solution components in the memory; and a solution program run in parallel on at least two processors to generate a solution by adding one solution component at a time, read from the memory, to the solution based on a key point, and to store the added solution component to the solution in the memory.

Abstract: Providing resources to a customer can include providing a node-relationship model based on a realized service offering. The node relationship model can include an instantiated first resource provided by a resource provider; an instantiated second resource provided by the instantiated first resource; and a plurality of defined relationships among the resource provider, the instantiated first resource, and the instantiated second resource. Providing resources to a customer can include creating a deployment plan for a new service offering based on the node-relationship model.

Abstract: An apparatus for assessing and controlling the quality of a project in a production environment is provided. The apparatus is configured to: receive a first score, wherein the first score comprises a first numerical value associated with a first level of quality, wherein the first level of quality is associated with a first deliverable; receive a second score, wherein the second score comprises a second numerical value associated with a second level of quality, wherein the second level of quality is associated with the first deliverable; and process the first score and the second score to generate a third score.

Abstract: A method, a system and a computer program product for generating a change request object to and associating the generated object with an existing business object are disclosed. A desired update to a first business object is created. The first business object contains a plurality of attributes, where each attribute in the plurality of attributes has a value. Based on the created update, a second business object is generated. The second business object contains at least one change to a value of an attribute of the first business object and a copy of the value of the attribute of the first business object. The value of the attribute in the first business object is compared with a copy of the value of the attribute contained in the generated second business object. Based on the comparison, the second business object is associated with the first business object.

Abstract: A system and method are disclosed for a self-learning supply chain comprising closed-loop feedback monitoring of compliance, levers effectiveness, key assumptions, early warning sensors, and key performance indicators. Self-learning supply chain enables root cause analysis of supply chain execution failures and problems and provides tools to planners to proactively resolve supply chain disruptions.

Abstract: A system and method are provided which allow a user to define a computerized sales and marketing process management system. The system includes a plurality of user-defined stages and identifies retrieved sales and marketing electronic records as belonging to one or more stages by using a set of user-predefined parameters for inclusion of an electronic record in each stage. The system allows a user such as a supervisor to define stage record or activity goals and goal conversion ratios between each stage and provides automated alert feedback to a user such as a salesperson when a goal is not met. A goal determination system allows a supervisor to build individual and sales teams goals dynamically from a starting number of leads or a desired total revenue starting point. Marketing or sales activity goals may also be established and tracked based on a wide variety of user-defined parameters.

Abstract: A command center provides ad-hoc search and navigation through different dimensional topic levels that allow users to better analyze and correlate data. The command center not only generates and displays content and metrics associated with an event, but can also generate and display real-time content and metrics for other topics, products, and/or services related to a currently displayed topic. The command center enables a user to navigate through the different dimensional levels simply by selecting items displayed by a remote control application. The command center also automatically synchronizes the content and metrics for any selected dimension to a same corresponding time period.

Abstract: A goal tracking system including a goal retrieval unit that retrieves a listing of goals, with each goal having at least one prerequisite, and retrieves a listing of completed goals related to a user, a goal analysis unit that compares the completed goal of the user with the prerequisite of the goal and determines if the user is qualified to achieve at least one goal from the listing of goals based on the completed goals of the user.

Abstract: Examples disclosed herein relate to worker task assignment based on correlation and capacity information. For example, a processor may create task assignments for workers based on a comparison of task attributes to worker attributes. The number of workers assigned to a task may be based on the availability of workers assigned. The processor may output information related to the task assignments.

Abstract: Task management techniques which use a beacon to detect mobile communication devices carried by task performers. An example task management method includes receiving by a task management system a message containing a beacon identifier from a mobile communication device carried by a task performer within communication range of a beacon, determining by the task management system a location of the beacon from the beacon identifier, determining by the task management system a task scheduled to be performed at the location, and marking the task as completed by the task management system.

Abstract: A method for optimizing and coordinating people queues is disclosed. In one embodiment, such a method includes determining a set of tasks desired to be performed by a user. This may include determining a set of establishments needed to perform such tasks. The method further includes querying at least one queueing system to determine wait times associated with performing the tasks. Based on the wait times, the method automatically determines an optimized schedule for performing the set of tasks. In certain embodiments, determining an optimized schedule may include determining a shortest time for performing the set of tasks. A corresponding system and computer program product are also disclosed.

Abstract: According to embodiments of the present invention, a process safety management database stored on a server records procedure data structures which may be copied to create job data structures which define an activity or combination of activities that fall under the OSHA definition of “process.” A personnel member performing a step of a covered process under OSHA regulations may use a client application from a client computer to track the progress of those steps, which may be transmitted by a server application to client computers of other personnel members in real-time while each client computer is in a different location. Upon completion of each step of a covered process, the server application may record the job data structure in a fixed state in fulfillment of regulatory certification requirements.

Abstract: A common messaging format can be used for communicating delivery information with a vehicle manufacturer. An intermediary system can be configured to provide an interface for communicating with each of a plurality of different vehicle manufacturer systems that each employ of different messaging format. The intermediary system can also provide a common interface by which the intermediary system communicates with a trucking system so that the trucking system does not need to implement each different interface employed by the different vehicle manufacturer systems. The intermediary system therefore allows a trucking system to more easily deliver vehicles for multiple vehicle manufacturers.

Abstract: A method and system for computing the price for shipping goods. The method includes causing a computer to deliver first information to a user prompting the user to enter at the computer information about a rail transportation service for shipment of goods by one or more railcars. Information about a basic pool of railcars is received and filtered based on one or more filtering criteria to produce a filtered pool of railcars. The computer is then caused to deliver second information to the user prompting the user to select at the computer one or more railcars among the filtered pool of railcars for the shipment of goods. A price for the shipment of the goods is then computed at least in part on the basis of the rail transportation service and the one or more characteristics of the railcars in the filtered pool of railcars selected by the user.

Abstract: An anthology and archiving platform and display system for collectibles is disclosed that includes: at least one imaged and archived, collectible, at least one piece of identifying, or valuation information associated with the at least one collectible, a digital platform system, wherein the system: associates the archived or imaged collectible with the piece of information associated with the collectible, actively identifies at least one piece of additional information associated with the collectible, produces a digital display album, wherein the album is uniquely designed for that collectible, wherein the image and the associated information are displayed. Corresponding methods of using the platform and display system are also disclosed.

Abstract: In one aspect, a method for detecting an object and/or managing an inventory will be described. A motion of an object is detected at a storage structure. One or more images are acquired of at least a part of the object. A direction of the motion of the object is determined An object is identified based on the one or more images. In various embodiments, an inventory for the storage structure is updated based on the motion direction determination and the object identity.

Abstract: A lost item management system and method is provided for matching found items with lost item inquiries provided by customers. An item processing module is configured to accept and store item attributes of the found items as parts of item entries, wherein each of the item entries has a set of the item attributes. An inquiry processing module is configured to accept and store inquiry attributes, corresponding to attributes of the lost items, as parts of inquiry entries. An item matching module is configured to execute a match search comparing the item attributes of the item entries with the inquiry attributes of the inquiry entries and identify possible matches. A monitoring module is configured to actuate the item matching module, in accordance with a schedule, to execute the match search and notify the operator when possible matches are identified by the match search.

Abstract: The present disclosure discloses a system for integrated view of customer information using a unique combination of Light Weight Master Data Management (LWMDM), Internet of Things/Sensor Data, Social Listening and Foundational Analytics to provide actionable insights to the consuming application. The system enables enterprises to eliminate redundant data points and integration steps and get to a more unified view of customer within a short time line as compared to a multi-year implementation of a full-fledged MDM, Data Warehouse (DW) and Analytical solutions. Further, the system also integrates the enterprise administrative Applications, Portals, Customer Service and Social Media in real-time. The system further provides data quality and integrity across various internal systems, big data analytics along with social listening and sensor information and provides actionable insights on customer life time value, retention, marketing strategies, and determines risk scores to arrive at product pricing.

Abstract: Disclosed herein is a conditioning system for nutritional substances. The conditioning system obtains information regarding the nutritional substance to be conditioned, the desired conditioning, and the desired properties, including nutritional content, of the conditioned nutritional substance, and dynamically controls the conditioning in response to this information optimize the organoleptic properties of the conditioned nutritional substance, while minimizing any detrimental changes to the nutritional content.

Abstract: Remote management techniques which allow existing workflows to remain intact and manager responses to workflow tasks to be completed on or off-site using a mobile communication device, such as a smartphone or tablet. An example remote management method includes receiving a workflow task from a local management system by a workflow management system, sending a message by the workflow management system to a mobile communication device carried by a manager requesting that the manager respond to the workflow task, receiving a manager response from the mobile communication device by the workflow management system, and providing the manager response to the local management system by the workflow management system.

Abstract: The present disclosure provides an improved network for tracking and managing mobile workers, which includes storing, tracking, and managing information associated with mobile workers and projects. The mobile workers may use a mobile communications system, such as a mobile device, to log their project with associated data, after which the data can be uploaded in real-time or stored locally until connectivity is available to the platform. Business owners or managers and individuals can review work performance and automatically create required business reports. The mobile worker may use the mobile device to clock in and out of each project through a worker presence verification method that may include obtaining an image/photograph or video of the worksite, location data (e.g., global positioning (GPS) coordinates), and a timestamp to ensure that the mobile worker is at the worksite and working on the appropriate project.

Abstract: A method is provided for generating a software application. In some embodiments, a user may be prompted to provide organizational arrangement data relating to a contract and/or process data relating to a contract operation to be performed pursuant to the contract. At least one database may be automatically generated to store the organizational arrangement data, and code for software may be automatically generated to facilitate performance of the contract operation. The software may be adapted to present a user interface for a case workflow specified by a case definition for a case under the contract.

Abstract: A method and system for providing a graphical position hierarchy and associated data sets is described. The method includes receiving a graphical position hierarchy model, analyzing nodes of the position hierarchy model to discern branches and leafs thereof, associating incumbent information with the nodes, where the incumbent information pertains to resources such as employees, contracting services, consulting, and other data and attributes related to the position hierarchy model, and displaying the model to a user thereof. Nodes of a position hierarchy may include incumbents, or may be placeholder position nodes, with no incumbents, allowing the user to model the position hierarchy according to organization needs before associating or allocating resources thereto. The method provides options for users to analyze the effect of changes to the position hierarchy on organizational resource allocation and costs in order to assess, optimize, and monitor the impact of such changes on the organization.

Abstract: Systems, methods, and devices are disclosed herein for implementing a referral processor. Systems include a profile data aggregator configured to aggregate data from at least one data source and generate candidate profile data based, at least in part, on the aggregated data. Systems include a connectivity metric generator configured to identify at least one connection between at least one candidate and at least one employee based on the candidate profile data. The connectivity metric generator may be configured to generate at least one connectivity metric based on the identified at least one connection. Systems include a referral processing engine configured to return the at least one candidate and the at least one employee as a result. The referral processing engine may be further configured to generate messages based on the at least one connectivity metrics. The messages may be configured to automate a referral of the at least one candidate.

Abstract: Disclosed herein are systems, methods, and devices for generating connectivity metrics associated with a referral processor. Methods may include identifying a first plurality of candidates based on a plurality of search parameters, and identifying a plurality of social connections associated with the first plurality of candidates and a first plurality of employees. Methods may also include generating at least one connectivity metric associated with the first plurality of candidates based on the plurality of social connections, where the at least one connectivity metric characterizes a strength of at least one social connection between a candidate of the first plurality of candidates and an employee of the first plurality of employees. The methods may also include receiving a selection of at least one candidate and at least one employee, the selection being based, at least in part, on the at least one connectivity metric.