Abstract: A method and system determining node order fulfillment performance considering cancelation costs. The method includes receiving a current order for fulfillment node assignment and calculating a cancelation ratio of a node of a plurality of nodes by dividing orders canceled due to back order from the node by orders scheduled from the node collected from a pre-assigned time period. The method also includes determining a cancelation cost of the node based on the cancelation ratio of said node. The method then includes automatically generating a node order assignment based on the determined cancelation cost for fulfillment of a current order.

Abstract: A predictive engine on a computer environment comprising a shared pool of configurable computing resources is executed to perform a predictive analysis on data pipelined into the computer environment, the data received from a plurality of sources and in a plurality of different formats, the predictive engine generating a network level cost information based on the predictive analysis on a dynamic and continuous basis. Asynchronous communication comprising the network level cost information from the predictive engine is received and a set of candidate nodes for order fulfillment is generated based on the network level cost information and a defined distance between the set of candidate nodes and a target destination. An optimization engine on the computer environment is invoked that filters the set of candidate nodes. A number of fulfillment nodes that meet one or more of a constraint and preconfigured rule is output.

Abstract: The present disclosure relates generally to the field of retail supply networks. In one specific example, mechanisms are provided to model markdown-avoidance savings for omni-channel fulfillment in retail supply networks. In various embodiments, systems, methods and computer program products are provided.

Abstract: A method and system for evaluating node fulfillment capacity in node order assignment. The method includes receiving a current order for node order assignment. The method also includes retrieving data of each node from a plurality of nodes, the retrieved data comprising current capacity utilization, capacity of a current day and capacity of a future day. The method then includes determining a probability of backlog on an expected ship date of each node, the probability of backlog being based on the retrieved current capacity utilization. Further, the method includes automatically converting the probability of backlog, backlog cost, and labor cost of each node into a capacity utilization cost of the each node using a capacity utilization cost model defining a set of predetermined capacity utilization threshold values. Then, the method includes automatically calculating a fulfillment cost of each node of the current order by adding a plurality of costs.

Abstract: A shipping option cost matrix may be generated based on the postal address codes, the carrier transit time data and the shipment rate cards. Responsive to receiving an order, the generated shipping option cost matrix may be searched in real-time to determine least costly delivery option, based on order information, the order information comprising a scheduled fulfillment center, destination, expected delivery date and weight of a shipment.

Abstract: A method and system for considering customized capacity utilization cost in node order fulfillment. The method includes receiving by a customized capacity utilization cost module an electronic record of a current order. The method includes retrieving data of a plurality of nodes and calculating an actual capacity utilization. The method includes automatically converting the actual capacity utilization of each node of the plurality of nodes and a predetermined maximum amount of cost to balance capacity utilization across the plurality of nodes into a customized capacity utilization cost, and transmitting the customized capacity utilization cost to an order fulfillment engine. The method includes receiving by the order fulfillment engine the current order, the processing cost data, and the customized capacity utilization cost. The method includes automatically calculating a fulfillment cost and identifying a node-order assignment with the lowest fulfillment cost.

Abstract: Data content delivery and validation in a computer environment may provide a file system in the computer environment, the file system subdivided into unique folder locations per content type, each of the unique folder locations representing a content type folder. The file system is monitored for changes to a content type folder. An occurrence of a manifest file in the content type folder may be detected, the occurrence of the manifest file ensuring that all files in a package of files associated with the manifest file have arrived. Content of the manifest file may be analyzed to check validity of the files. A content package registry may be queried to determine a base job for processing a given content type associated with the package of files, and the base job may be run to process the package of files.

Abstract: A historical scenario and historical decisions made in the historical scenario are received. The historical decisions represent a set of decision variables of an objective function. A random set of decision variables having different values than the set of decision variables are generated. To determine a weight setting associated with multiple objectives of the objective function, a number of inequalities are built and solved with an assumption that, for an optimization that minimizes the objective function, the objective function having the set of random decision variables has a larger value than the objective function having the set of decision variables. The receiving, the generating and the building steps may be repeated to determine multiple sets of weight settings. The multiple sets of weight settings are searched to select a target weight setting for each of the multiple objectives. The target weight setting may be automatically and continuously learned.

Abstract: Methods, systems, and computer program products for parsing objects are provided herein. A method includes producing a plurality of versions of an image of an object derived from an input, wherein each version comprises one of one multiple resolutions of said image of said object; computing an appearance probability at each of a plurality of regions on the one or more lowest resolution versions of said plurality of versions of said image for at least one attribute for said object; determining a configuration of the at least one attribute in the one or more lowest resolution versions based on at least the appearance probability in each of the plurality of regions; and outputting said configuration.

Abstract: A system comprises an input component, a feature extractor, an object classifier, an adaptation component and a calibration tool. The input component is configured to receive one or more images, and the feature extractor is configured to extract features for one or more objects in the one or more images, the extracted features comprising at least one view-independent feature. The object classifier is configured to classify the one or more objects based at least in part on the extracted features and one or more object classification parameters, and the adaptation component is configured to adjust the classification of at least one of the objects based on one or more contextual parameters. The calibration tool is configured to adjust one or more of the object classification parameters based on likelihoods for characteristics associated with one or more object classes.

Abstract: Multi-mode video event indexing includes determining a quality of object distinctiveness with respect to images from a video stream input. A high-quality analytic mode is selected from multiple modes and applied to video input images via a hardware device to determine object activity within the video input images if the determined level of detected quality of object distinctiveness meets a threshold level of quality, else a low-quality analytic mode is selected and applied to the video input images via a hardware device to determine object activity within the video input images, wherein the low-quality analytic mode is different from the high-quality analytic mode.

Abstract: An approach that detects locations of hazardous conditions within an infrastructure is provided. This approach uses satellite imagery, GIS data, automatic image processing, and predictive modeling to determine the location of the hazards automatically, thus optimizing infrastructure management. Specifically, a hazard detection tool provides this capability. The hazard detection tool comprises a detection component configured to: receive visual media containing asset location data about a set of physical assets, and hazard location data about potential hazards within a vicinity of each of the set of physical assets. The detection component further receives graphical information system (GIS) data containing asset location data about each of the set of physical assets.

Abstract: A system and computer program product for tracking and monitoring assets along a transport route. The system includes at least one receiver for receiving asset identifications transmitted from the assets, where each asset transmits its own asset identification. The receiver also receives physical location coordinates of each of the assets. A plurality of cameras is dispersed along the transport route for transmitting camera images of the assets. The system further includes a server coupled to the receiver and cameras. The server is configured to recognize the assets in the camera images, to correlate the asset identification from the receiver with recognized assets in the camera images, and to correlate the physical location coordinates of each of the assets with physical location coordinates of the cameras. The system monitors the visual appearance of the assets, and keeps track of whether or not they have sustained physical damage.

Abstract: A hierarchical multi-stage model of asset failure risk for complex heterogeneously distributed physical assets is built. The hierarchical multi-stage model considers heterogeneity of failure patterns for the assets. At least one data stream is analyzed to determine whether the hierarchical multi-stage model needs to be updated due to a change in the failure patterns. If the analysis indicates that the hierarchical multi-stage model needs to be updated, the hierarchical multi-stage model is dynamically updated to obtain an updated hierarchical multi-stage model.

Abstract: Predicting operational changes in a multi-detector environment includes generating, via a computer processing device, a factor matrix for each univariate time series data in a set of sparse time series data collected from data sources, identifying a subset of the time series data as a feature selection based on application of a loss function, and generating a predictive model from the subset of the time series data.

Abstract: An invention for identifying a spatial location of an event within video image data is provided. Disclosed are embodiments for detecting an object and obtaining trajectory data of a trajectory of the object within the video image data from a sensor device; converting the trajectory data into a contour-coded compressed image; generating, based on the trajectory data, a searchable code that contains a set of locations traversed by the trajectory of the object within the video image; associating the searchable code with the contour-coded compressed image in a database; and returning, in response to a query having a selected location that corresponds a location of the set of locations in the searchable code, an image of the trajectory data corresponding to the object based on the contour-coded compressed image in the database.

Abstract: An invention for identifying a spatial location of an event within video image data is provided. Disclosed are embodiments for detecting an object and obtaining trajectory data of a trajectory of the object within the video image data from a sensor device; converting the trajectory data into a contour-coded compressed image; generating, based on the trajectory data, a searchable code that contains a set of locations traversed by the trajectory of the object within the video image; associating the searchable code with the contour-coded compressed image in a database; and returning, in response to a query having a selected location that corresponds a location of the set of locations in the searchable code, an image of the trajectory data corresponding to the object based on the contour-coded compressed image in the database.

Abstract: Predicting operational changes in a multi-detector environment includes generating, via a computer processing device, a factor matrix for each univariate time series data in a set of sparse time series data collected from data sources, identifying a subset of the time series data as a feature selection based on application of a loss function, and generating a predictive model from the subset of the time series data.

Abstract: Techniques for performing foreground analysis are provided. The techniques include identifying a region of interest in a video scene; detecting a static foreground object in the region of interest; and performing a foreground analysis based on tracking information to determine whether the static foreground object is abandoned or removed.

Abstract: An approach for generating a coding schema for identifying a spatial location of an event within video image data is provided. In one embodiment, there is a spatial representation tool, including a compression component configured to receive trajectory data of a trajectory of an object for an event within video image data; generate a lossless compressed contour-coded blob to encode the trajectory data of the trajectory of the object for the event within video image data; generate a lossy searchable code of the trajectory of the object for the event within the video image data; convert a region of interest within the video image data to a lossy query code, the region of interest corresponding to a sub-section of a visual display output of the video image data; and compare the lossy query code to the lossy searchable code within a relational database to identify a corresponding lossless trajectory data of the trajectory of the object for the event within the video image data.