Abstract: Systems and methods are provided for categorizing signals sensed from receivers into one of a plurality of categories using a machine learning component that obfuscates other characteristics of the signals beyond the categorization of the signal. A set of training signals is generated that includes signals representative of each of a plurality of categories of signals. A machine learning component is trained using the set of training signals so that the machine learning technique can categorize new signals into one of the plurality of categories. The machine learning component is transmitted to one or more receivers so that each receiver can categorize sensed signals into one of the plurality of categories using the machine learning component while obfuscating other characteristics of the sensed signals.

Abstract: A computer-implemented method, apparatus and computer program product for projecting a machine learning model, the method comprising: obtaining a computerized multi-dimensional unsupervised anomaly detection model; obtaining a probability density function of the anomaly detection model; determining samples of the anomaly detection model, based on the probability density function; projecting the samples over at least one dimension set to obtain projected samples; processing the projected samples to obtain decision boundaries of the anomaly detection model over the at least one dimension set; and providing a visual display of the decision boundaries on a display device.

Abstract: A processing unit can successively operate layers of a multilayer computational graph (MCG) according to a forward computational order to determine a topic value associated with a document based at least in part on content values associated with the document. The processing unit can successively determine, according to a reverse computational order, layer-specific deviation values associated with the layers based at least in part on the topic value, the content values, and a characteristic value associated with the document. The processing unit can determine a model adjustment value based at least in part on the layer-specific deviation values. The processing unit can modify at least one parameter associated with the MCG based at least in part on the model adjustment value. The MCG can be operated to provide a result characteristic value associated with test content values of a test document.

Abstract: A method for global data flow optimization for machine learning (ML) programs. The method includes receiving, by a storage device, an initial plan for an ML program. A processor builds a nested global data flow graph representation using the initial plan. Operator directed acyclic graphs (DAGs) are connected using crossblock operators according to inter-block data dependencies. The initial plan for the ML program is re-written resulting in an optimized plan for the ML program with respect to its global data flow properties. The re-writing includes re-writes of: configuration dataflow properties, operator selection and structural changes.

Abstract: A domain-adapted classification system and method are disclosed. The method includes mapping an input set of representations to generate an output set of representations, using a learned transformation. The input set of representations includes a set of target samples from a target domain. The input set also includes, for each of a plurality of source domains, a class representation for each of a plurality of classes. The class representations are representative of a respective set of source samples from the respective source domain labeled with a respective class. The output set of representations includes an adapted representation of each of the target samples and an adapted class representation for each of the classes for each of the source domains. A class label is predicted for at least one of the target samples based on the output set of representations and information based on the predicted class label is output.

Abstract: Technologies for financial data aggregation are described. A financial data analyzer searches for and receives raw data from one or more data sources. An artificial intelligence editor is invoked to determine if the raw data is suitable as enhanced data. If the raw data is not suitable as enhanced data, an artificial intelligence journalist is invoked to modify the raw data to be enhanced data for generating reports.

Abstract: A machine learning method related to these embodiments includes: first generating a pseudo attractor from each of plural series data sets, the pseudo attractor being a set of points in N-dimensional space, each of the points including N values sampled at an equal interval; second generating a series data set of Betti numbers from each of plural pseudo attractors generated in the first generating, each of the Betti numbers being a number of holes for a radius of a N-dimensional sphere in the N-dimensional space; and performing machine learning for each of plural series data sets of Betti numbers generated in the second generating, the series data set of Betti numbers being used as input in the machine learning.

Abstract: Memory facilitation using directed acyclic graphs is described, for example, where a plurality of directed acyclic graphs are trained for gesture recognition from human skeletal data, or to estimate human body joint positions from depth images for gesture detection. In various examples directed acyclic graphs are grown during training using a training objective which takes into account both connection patterns between nodes and split function parameter values. For example, a layer of child nodes is grown and connected to a parent layer of nodes using an initialization strategy. In examples, various local search processes are used to find good combinations of connection patterns and split function parameters.

Abstract: A method for decision-making by an electronic system comprising a plurality of components is provided herein. The components of the system are given tunable voting authority v=[Vmin . . . Vmax], typically [?1 . . . 1]. A singleton officiating member manages the notification and voting process. A current representation of the entire system is stored in the model. The model is a state storage system that tracks the existence and condition of a group of tracked data items, called Entities. The model is managed by the singleton officiating member but may be queried by any component.

Abstract: A method of inverse reinforcement learning for estimating reward and value functions of behaviors of a subject includes: acquiring data representing changes in state variables that define the behaviors of the subject; applying a modified Bellman equation given by Eq. (1) to the acquired data: r ? ( x ) + ? ? ? V ? ( y ) - V ? ( x ) = ? ln ? ? ? ? ( y | x ) b ? ( y | x ) , ? ( 1 ) = ? ln ? ? ? ? ( x , y ) b ? ( x , y ) - ln ? ? ? ? ( x ) b ? ( x ) ,                                                ? ( 2 ) where r(x) and V(x) denote a reward function and a value function, respectively, at state x, and ? represents a discount factor, and b(y|x) and ?(y|x) denote state transition probabilities before and after learning, respectively; estimating a logarithm of the density ratio ?(x)/b(x) in Eq. (2); estimating r(x) and V(x) in Eq.

Abstract: Managing reservations for limited resources such as meeting rooms within a network computing system may include, responsive to receiving a reservation for a meeting room from a requestor, determining, using a processor, availability of meeting rooms for the reservation and determining, using the processor, eligibility of the requestor according to a courtesy score for the requestor. The courtesy score may be determined according to historical usage of the meeting rooms by the requestor. The reservation may be selectively confirmed according to the courtesy score and the availability of the meeting rooms. Further, a particular meeting room may be assigned to the reservation subsequent to the confirming.

Abstract: A system is described that infers that a user will need to complete a trip and selects a transportation service that the user can use to complete the trip. The system predicts a time to request a vehicle associated with the transportation service for completing the trip such that the request has sufficiently high degree of likelihood, of causing the vehicle to arrive at a future location by a final departure time; the final departure time being a latest time at which the user is predicted to need to begin traveling. Responsive to determining that a current time is within a threshold amount of time of the predicted time, the system sends, to a reservation system associated with the transportation service, a reservation request for the vehicle associated with the transportation service for completing the trip.

Abstract: A method and system are provided. The method includes generating a set of workplace predictors of risk relating to accidents, injury, and industrial hygiene, based on at least one employee state that includes at least one of a physical state, a cognitive state, and an emotional state. The method further includes modifying a behavior of a workplace machine by causing a modification to the workplace machine that changes or limits the behavior of the workplace machine, responsive to the set of workplace predictors.

Abstract: A method of acclimatizing a user to a scheduling pattern change includes, in a calendar system implemented by at least one processor, determining an anticipated scheduling pattern change from a current scheduling pattern to a new scheduling pattern for the user; and establishing with the calendar system an acclimatization period to transition the user to the scheduling pattern change.

Abstract: Disclosed are methods for using exponential distribution function to predict project reliability and project risk at a project task level. Based on a project serial model assumption, project reliability and project risk can additionally be predicted at a phase level and at a final project level. The disclosed methods can also be used for predicting project schedule risk, project budget risk, and project supply chain risk. In addition, the disclosed methods provide an exponential distribution function for predicating project variations at a project task level. Based on a project serial model assumption, the disclosed methods can be used to predict project variations at a phase level as well as a final project level. The disclosed methods can also be used to predicting project schedule delays, project budget overages, and project supply chain part delays.

Abstract: Computing systems, methods and tools for managing and optimizing the allocation of enterprise resources by automating employee management decision making to align management decisions made on a local level with the goals of the overall enterprise, global economies and emerging market trends. The computing systems, methods and tools use historical data, objective attributes and subjective feedback at the local level to predict employee progression at specific points in time of an employee's career and the effects particular management decisions may have on the employee as an asset of an enterprise, in order to predict, calculate and select the optimal actions that will further improve the employee's value to the enterprise yielding an optimal return on the investment of resources.

Abstract: A computer-implemented method of creating a workflow application is disclosed, including the steps of presenting a graphical user interface via a display device, receiving a user input specifying a request type representing a framework of information to be provided by an end user for a request to be acted on, receiving a user input specifying a task assignment representing an entity to which a task is assigned, and associating the task assignment with the request type. The method further includes the steps of receiving a user input specifying an action to be performed on the request by the entity to which the task is assigned, associating the action with the task assignment, and presenting a diagram within the graphical user interface to visually represent the request type, task assignment, and action as individual nodes.

Abstract: According to some embodiments, a data acquisition computer may receive a first task request, including a data source communication identifier, from a back-end application. The data acquisition computer may perform a first data acquisition process and determine indications of: when the data source expects to return to a normal operating condition, a quality of service received by the data source from a service provider, and a quality of service performed by the back-end application server. The back-end application server might generate and transmit the task request, for example, a first pre-determined period of time after an event associated with the data source. The back-end application server may also detect that a second pre-determined period of time after the event has occurred and facilitate a second data acquisition process including at least one rating within a scale of ratings provided by the data source.

Abstract: Systems and methods for connecting an operator at a worksite are disclosed. One method includes receiving telematics data relating to a machine operating at a worksite using a data standard, receiving operator condition data relating to an operator of the machine using the data standard, wherein the operator condition data comprises one or more of nutritional data, health data, activity data, and sleep data, determining an operation state based at least on the telematics data and the operator condition data, and generating a response based at least on the determined operation state, wherein the response is configured to be transmitted used the data standard.

Abstract: Systems for controlling autonomous vehicles are disclosed. Using one or more location detection resources, the system can receive vehicle data from an autonomous vehicle as the autonomous vehicle progresses towards a pickup location of a requesting user and receive requester data from a mobile computing device of the requester. The system can determine when the autonomous vehicle and the requester are at or within a threshold distance of the pickup location. Subsequently, the system can instruct the autonomous vehicle to perform one or more non-driving operations to facilitate use of the autonomous vehicle by the requester.

Abstract: A project management system manages a project by continuously monitoring each phase of the project to greatly increase the probability that all required deliverables are produced while adhering to project constraints. The project management system tracks and displays the progress being made and the current status of each deliverable in the project to enable users to easily view and understand the overall project progress along with risks and issues associated with the project in one centralized system The project management system also performs project portfolio management by evaluating individual projects based on various business valuation criteria to correlate the impact of the individual projects to the strategic goals of the business. Accordingly, the project management system provides a system enabled centralized governance framework that enables the users to efficiently plan and manage any type of project.

Abstract: A method, computer program product and a computer system is provided. A processor receives a change request. A processor identifies a category of the change request. A processor identifies at least one available resource with a characteristic that matches a criterion as dictated by the change request. A processor determines a technical lead-time for a first available resource of the at least one available resources. A processor determines an administrative lead-time based, at least in part, on the category of the change request. A processor generates a total lead-time for the first available resource based, at least in part, on the technical lead-time and the administrative lead-time. A processor sends a solution to a requestor of the change request, based, at least in part, on the total lead-time for the first available resource and the category of the change request.

Abstract: Disclosed is a method of and system for managing service requests. The method may include determining, with a processor, a Service Level Agreement (SLA) target associated with each service request of a plurality of service requests. Additionally, the method may include determining, with a processor, a target delivery time corresponding to each service request of the plurality of service requests. A target delivery time of a service request may be determined based on each of an origin time and a SLA target associated with the service request. Furthermore, the method may include determining, with a processor, a priority value corresponding to each service request of the plurality of service requests. The priority value corresponding to a service request may be determined based on at least one of the origin time of the service request and the target delivery time of the service request.

Abstract: The present disclosure introduces methods and systems for tracking pieces of wellsite equipment. Such tracking includes receiving first identification information and first location information for a first module associated with a first piece of wellsite equipment at a first location, receiving second identification information for a second module associated with a second piece of wellsite equipment at the first location, and determining a tracking event associated with the second piece of wellsite equipment based on the first identification information, the first location information, and the second identification information. A utilization state associated with the second piece of wellsite equipment is then determined based on at least the tracking event.

Abstract: A method of reallocating inventory in a fulfillment network is disclosed herein. The fulfillment network can include a plurality of distribution centers. An allocation plan can be created in a one of a variety of different manners, where the allocation plan involves allocating an item to one or more distribution centers in the fulfillment network. Thereafter, the allocation plan can be analyzed for feasibility. If the allocation plan is not feasible, each distribution center in the allocation plan can be analyzed to determine if using the distribution center is feasible. If the distribution center cannot be used, another distribution in the same cluster of distribution centers is examined for feasibility. This process is repeated for each distribution center in the allocation plan. Once an alternative allocation plan has been developed in this maimer, items can be allocated. Existing inventory can be taken into account in the allocation plan.

Abstract: In an approach for suggesting an item to pack, a processor receives an indication that a user is packing a first item of luggage, wherein the indication includes information about a trip. A processor generates a packing list based on the information about the trip. A processor receives a request to link the first item of luggage and a second item of luggage for the trip. A processor links the first and second items of luggage such that contents of each item of luggage are jointly compared to the packing list. A processor receives, via a short-range point-to-point communication reader of the first item of luggage, a signal from a short-range point-to-point communication device operably affixed to a first item. A processor identifies the first item based on the signal. A processor determines that the first item is an item of the packing list.

Abstract: A method includes receiving, at an inventory monitoring device and from a system including shelf inventory sensor devices that each include cameras and distance sensors positioned to monitor shelf spaces, camera image data and distance sensor data from the shelf inventory sensor devices. Types of items stored on shelf spaces and a number of items stored on the at shelf spaces are determined based on the camera image data. A current used volume of the shelf spaces is identified based on distance sensor data, and a notification is sent to a device associated with the supplier in response to a determination that the current used volume is lower than a predetermined threshold.

Abstract: This disclosure relates generally to inventory management, and more particularly to allocating pallet locations to items in a distribution center. In one embodiment, the method includes receiving an input including an item identifier. Based on the item identifier, a load distribution information is accessed. Based on the load distribution information associated with the item and one or more allocation parameters associated with the one or more pallet locations, one or more pallet locations from amongst a plurality of pallet locations are determined. The one or more allocation parameters are indicative of the availability of pallets at the one or more pallet locations in real-time. At least one pallet location is selected from amongst the one or more pallet locations based on a location identifier associated with the at least one location, for accommodating the item. The location identifier is indicative of prioritization of the pallet location for accommodating the item.

Abstract: A method for equipping the packaging (11) of an article (10), packaged ready for sale, with additional information intended for the end buyer of the article, that includes: (a) providing the article (10) packaged ready for sale; (b) providing an information carrier (14) provided with the additional information; (c) determining a location on or at the packaging (11), at which the information carrier (14) is to be placed; (d) placing the information carrier (14) at the predetermined location on or at the packaging (11) of the article packaged (10) ready for sale, in such a manner that the information carrier (14) remains at this location; and (e) providing the article (10), provided with the information carrier (14), for further processing.

Abstract: The present disclosure provides a system and method of live inventory management. The system includes a plurality of bins that include a plurality of specifically located level sensors and a controller that aggregates the data from the sensors to push to the host server, which ascertains the inventory state of the bins and generates alerts when the bins require replenishment. The method includes the step of automatically generating alerts for replenishment based upon the data from the plurality of level sensors.

Abstract: A computer based system for taking the physical inventory of liquids dispensed in full and partially full containers. A database stores images of containers and their associated volumes. The containers to be inventoried are identified by a user and input to a computer at a graphical user interface (GUI) input/output. A computer causes the display of an image of the container and a sliding level indicator at the GUI. The level indicator is slidable along the image. The computer calculates a volume of liquid remaining in the container as a function of the position of the level indicator along the image of the container.

Abstract: The invention is an electronic identification system that integrates with consumer purchased products for management of data in digital form by way of an interconnected computing system, network, and/or mobile device. The system utilizes a scanning system and coded labels that facilitate a uniform identification of goods within a sales setting or within a household. Such a system would enable the use of SMART technology systems in household appliances, warehouses and retail such that the system implements mobile applications and interfacing through a high-speed network.

Abstract: A business method and system for executing the method that involves gathering merchandise orders at a show in the home of a hostess. The method compiles the merchandise orders while maintaining a relationship between each individual order and information pertaining to the guest making the order. The guest information maintains an association with the order throughout the method such that each order made at the show may be individually packaged and labeled, obviating the need for the hostess to sort the ordered items upon receiving them from a warehouse. The system stores records of all purchased items and maintains a running inventory of each item, accessible by the consultants so they may warn customers of potentially low inventories. The database also facilitates returns and exchanges of purchased items.

Abstract: A non-transitory processor-readable medium stores code representing instructions to be executed by a processor. The code stored in the medium includes code to cause the processor to receive a first signal indicating a quantity of an item listed on a website of a first marketplace from a set of marketplaces. The item is listed on a website of each marketplace from the set of marketplaces. The code stored in the medium includes code to cause the processor to change, based on the first signal, an inventory parameter associated with the item from a first value to a second value. The code stored in the medium includes code to cause the processor to send, to a device of each marketplace, a second signal indicating the updated inventory parameter such that the item remains listed on the web site of each marketplace until the second value is zero.

Abstract: In some embodiments, systems, apparatuses and methods are provided herein that provide control over the delivery of products. In some embodiments, a product delivery control system comprises: a customer authorization system configured to receive, from a customer who ordered a product, an authorization to associate one of one or more delegates, designated by the customer, to receive products on behalf of the customer; a delegate tracking system configured to identify when a first delegate of the one or more delegates is within a geographic threshold distance of an originally specified receiving location where the product ordered by the customer is scheduled to be received; and a delivery authorization system configured to communicate an authorization to a first user interface unit associated with the first delegates that authorizes the first delegate to receive the product at the receiving location on behalf of the customer.

Abstract: A delivery management system comprises a communication device that receives a notification of a communication established between an unmanned aerial vehicle (UAV) that delivers a payload and a delivery box constructed and arranged to receive the payload from the UAV when the UAV is a predetermined distance from the delivery box and moving in a direction toward the delivery box, the communication including an identity of the UAV; a verification device that processes the notification and validates the identity of the UAV; and an instruction generator that generates an instruction to the delivery box to open the delivery box in response to the verification device validating the identity of the UAV and a determination by the communication device that the communication is established between the UAV and the delivery box. The communication device includes an autolocker communication device that outputs the instruction to the delivery box.

Abstract: A method includes coordinating delivery by a selected delivery agent to a delivery recipient. A geographical receiving location for a delivery recipient is determined. A delivery agent, of a plurality of potential delivery agents, is identified and selected that is capable of delivering a specific product to the delivery recipient at the geographical location for the delivery recipient, in which the identifying includes analyzing planned geographical routes for each of the plurality of potential delivery agents to determine the delivery agent. A network communications address of the delivery recipient is determined and an electronic communication exchange is established between an entity responsible for providing the product to the delivery recipient and the network communications address of the delivery recipient. The specific product is assigned for delivery to the delivery recipient based on the communications exchange.

Abstract: A system for securely controlling the flow of network traffic between item processing facilities is described. An intra-facility network at a first facility is provided for collecting operational information from equipment at the first facility. A central collection server gathers operational information from multiple facilities. The central collection server identifies a portion of the operational information corresponding to a second facility and routes only this portion of the operational information to the second facility thereby reducing the network traffic and securing the release of information that is related to the receiving facility.

Abstract: A system for executing shipments based on physical trade documents includes a document intake machine comprising a document scanner and a data extractor. The document intake machine receives a physical trade document associated with a shipment of goods from an entity. The document scanner scans the physical trade document to create an electronic file. The data extractor identifies shipment information from the electronic file. A trade executing machine receives the shipment information from the document intake machine and compares the shipment information to a shipment condition. If the shipment information matches the shipment condition, the trade executing machine issues shipment instructions according to the shipment information and communicates a notification message to the entity indicating that the physical trade document was processed according to the shipment information.

Abstract: Product order and shipping information received via email messages is automatically aggregated for ready user review. Once the user is authenticated, authorization to access their email mailbox is obtained and the email message headers of their entails are analyzed to identify those messages of interest. The bodies of the email messages of interest are parsed to extract the product order and shipping information which is stored and presented for display to the user typically grouped by individual product thus greatly simplifying user review of orders. The aggregated product order and shipping information can be augmented with additional information such as shipping status, delivery status, a product image, and/or a last date that the product can be returned.

Abstract: A data processing system (X) is adapted to confront an offer (O) and a demand (D), in particular in the field of transportation of travelers or goods. The system (X) receives requests corresponding to new offers/demands, formulated by users (Cx) of the data processing system and data corresponding to offers/demands not yet satisfied from a plurality of secondary data processing servers (A, B, C, E) themselves adapted to confront an offer and a demand. After receiving a request corresponding to a new offer/demand formulated by a user (Cx) of the data processing system (X), the system (X) verifies if there is an offer/demand (OA, DA, OB, DB, OC, OB, DB) not yet satisfied, received from a secondary data processing server (A, B, C, E) or transmitted previously by a user of the data processing system, that can respond to the request.

Abstract: This disclosure is directed to a procurement server for processing one or more requisition requests from various client devices. The procurement server determines whether there is an approver that can approve of the various requisition requests. The procurement server performs this determination by evaluating one or more requisition expressions, which include various expression attributes associated with corresponding condition operators. To expedite such processing, the procurement server builds an expression index corresponding to the various requisition expressions, where the expression index includes various nodes and associations between nodes. Each node represents a unique value assignable to the expression attributes of the various requisition expressions. When the nodes of the expression index are traversed, the last node in the traversal yields an approver that can approve the requisition request. The expression index requires less memory and time to evaluate than the various requisition expressions.

Abstract: The invention is related to the system and information management processes among multiple databases that are updated online and interact according to instantaneous evaluation of the information.

Abstract: A machine may be configured to generate recruitment leads based on targeted content. For example, the machine causes a presentation of an item of digital media in a user interface of a first device associated with a member of a social networking service. The member may be targeted for the presentation of the item of digital media. The machine, based on the presentation of the item to the member, accesses an event message pertaining to an interaction by the member with the item of digital media. The machine, based on the event message, identifies an indication of interest by the member in a content of the item. The machine generates a communication pertaining to the interest by the member in the content of the item. The machine transmits the communication to a second device associated with a recruiter.

Abstract: An improved system and method for sourcing and matching candidates to jobs is provided. In an embodiment, a user client may receive a notification having a link to an online application that includes information identifying a job for which a candidate was rejected. The user client may send a request to a job server to run an online application to search for job matches to the job profile for which the candidate was rejected, and a search may also be made for job matches to the candidate profile. A combined list of job matches to the candidate profile and job matches to the job profile for which the candidate was rejected may be ranked. A short list of ranked job matches may be served to a user client which may send a request to a company server to apply for a job on the short list.

Abstract: A computer implemented method, computer program product and system for predicting an outcome of the execution of a schedule. The schedule, endogenous data relating to one or more activities or the schedule, and exogenous data relating to one or more activities or the schedule is processed in accordance with a machine learning algorithm-generated prediction model to predict at least one of: a performance measure, and a final condition that may result from executing the one or more activities according to the schedule.

Abstract: Disclosed are a method and a device for counting events in a calendar. The method includes: obtaining a subject calendar by acquiring a subject of a calendar and time of a subject event; sending a request for acquiring a subject event to a server, the request for acquiring a subject event carrying a subject of the subject calendar and time of a subject event; receiving subject event information returned by the server, the subject event information being acquired by the server according to the subject of the subject calendar and the time of the subject event; and adding the subject event information into corresponding time of the subject calendar.

Abstract: A method, a computer readable storage medium and an apparatus for generating a combined calendar are described. In formation of at least two calendars are received, each of which includes several events that is associated with at least one attribute. The attributes of the events are compared. Events are considered identical when they have at least one identical attribute. A common visual representation of the at least two calendars are generated. The identical events are represented as a single calendar object in the common visual representation.

Abstract: A mobile terminal including a display unit; and a controller configured to display a watch object on the display unit, the watch object including at least one of a plurality of schedule information or a plurality of applications. The controller is configured to transmit time information with respect to a first region in the watch object and application information set to correspond to the first region to a wearable device, when there is a schedule information transmission input to the first region. Further, the controller is configured to synchronize schedule information related to the watch object with another application or a web screen and to display the schedule information related to the watch object in a synchronized state.

Abstract: The moving and arrival time at each destination during movement to destinations can be visualized in an easily understandable manner and the moving time can be adjusted. A portable device that displays action plan information which involves a movement within an arbitrary period and/or execution support information of the action plan which involves the movement includes: a display unit, a display control unit, and a spatiotemporal action diagram display control unit. The display control unit displays a time coordinate axis on the display unit, displays the action plan information, which involves the movement along the time coordinate axis, and displays speed information of all movements included in the action plan information at an arbitrary time simultaneously. The spatiotemporal action diagram display control unit receives an input for correcting the speed information of the movement.