Abstract: Technology for training a predictive model is described. A processing device collects digital interview data including features identified from candidate interviews. A model training tool selects a data set of the digital interview data. The data set includes a predicted performance outcome and an actual performance outcome for each of a plurality of candidates. The model training tool determines an error metric for each of the plurality of candidates. The error metric includes a relationship between the predicted performance outcome and the actual performance outcome for each candidate. The model training tool determines a number of candidates whose digital interview data includes a feature corresponding to a protected class. The model training tool normalizes an effect of each candidate on the error metric based on the corresponding protected class and applies the normalized error metric to reduce bias in the predictive model with respect to the protected class.

Abstract: There is disclosed a computer implemented method for training a search ranker, the search ranker being configured to ranking search results. The method comprises: retrieving, by the server, a training dataset including a plurality of training objects; for each training object, based on the corresponding associated object feature vector: determining a weight parameter, the weight parameter being indicative of a quality of the label; determining a relevance parameter, the relevance parameter being indicative of a moderated value of the labels relative to other labels within the training dataset; training the search ranker using the plurality of training objects of the training dataset, the determined relevance parameter for each training object of the plurality of training objects of the training dataset, and the determined weight parameter for each object of the plurality of training objects of the training dataset to rank a new document.

Abstract: A system and methods for suggesting beneficial actions may include generating a first predictive model to estimate a user profile, collecting user data pertinent to a user's circumstance or action at a point in time, collecting a database associating user profiles with sequences of user circumstances and user actions over time for one or more users, and generating a second predictive model to suggest an action or circumstance or a sequence of actions and circumstances to be communicated to a user based upon the estimated user profile and user data and the database of sequences of user circumstances and actions. The system delivers the suggested action or circumstance to a device carried by or worn by a user in the form of advice or a story, using text, speech, images, or video.

Abstract: Systems and methods for determining whether two tree persons in a genealogical database correspond to the same real-life individual. Embodiments include identifying two tree persons in a genealogical database and extracting a plurality of features from both tree persons to generate two vectors. Embodiments also include calculating a plurality of metrics between the two vectors to generate a metric function. Embodiments further include generating feature weights using a recursive process based on training data input by external users, and generating a score by calculating a weighted sum of the metric function being weighted by the feature weights. The generated score may then be compared to a threshold value.

Abstract: A machine learning device which learns fault prediction of one of a main shaft of a machine tool and a motor driving the main shaft, including a state observation unit observing a state variable including at least one of data output from a motor controller controlling the motor, data output from a detector detecting a state of the motor, and data output from a measuring device measuring a state of the one of the main shaft and the motor; a determination data obtaining unit obtaining determination data upon determining one of whether a fault has occurred in the one of the main shaft and the motor and a degree of fault; and a learning unit learning the fault prediction of the one of the main shaft and the motor in accordance with a data set generated based on a combination of the state variable and the determination data.

Abstract: The present invention relates to data analysis whereby a plurality of components are extracted from learning data, each of the plurality of components constituting at least part of the learning data; a component to be utilized for evaluation of the plurality of pieces of evaluation data is selected, from among the plurality of components, on the basis of evaluation information about each of the plurality of extracted components; and the evaluation data is evaluated by utilizing the selected component.

Abstract: The present invention is directed at a system and method for searching and matching content over social networks relevant to a specific individual. In an aspect, the individual relevant content search system provides search results and information that is relevant to the individual's perspective.

Abstract: A network-based enterprise or other system that makes items available for selection to users may implement real-time updates to item recommendation models based on matrix factorization. An item recommendation model may be maintained that is generated from a singular value decomposition of a matrix indicating selections of items by users. A user-specific update to the item recommendation model may be calculated in real-time for a particular user such that the calculation may be performed without performing another singular value decomposition to generate an updated version of the item recommendation model. Item recommendations may then be made based on the user-specific update and the item recommendation model. In various embodiments, the item recommendations may be made in response to an indication or request for item recommendations for the particular user.

Abstract: Providing seating recommendations is provided. Seating recommendations for a current day in an open seating environment are generated based on analysis of previous seat selection information, calendar information, and social network information corresponding to a user and current seat assignments to other users in the open seating environment. A weight for each of the seating recommendations for the current day in the open seating environment is generated based on the analysis of the previous selection information, the calendar information, and the social network information corresponding to the user. The seating recommendations are ordered by weight. A pre-defined top number of the seating recommendations ordered by weight are provided to the user.

Abstract: A computer-implemented method and a system for providing passenger information performing the tasks of sending, from a passenger electronic device (110), personal data, device geolocation and device time-stamp information; obtaining the passenger itinerary and confirming passenger identity, by a managing unit (206), based upon a match between the personal data, passenger electronic device geolocation and time-stamp; information contained in the obtained passenger itinerary; accessing to updated air traffic information relevant to the passenger upon confirming the passenger identity and sending, by the managing unit (206), a passenger report comprising flight status information for display on the passenger electronic device (110).

Abstract: A method of managing a rebooking of a purchased flight ticket by iteratively querying network resources using software modules for data used for matching an alternative flight ticket. The method comprises designating a purchased flight ticket of a flight comprising purchased flight legs, gathering purchased flight data by identifying values each of one of flight leg parameters of each flight leg, in each of matching iterations, querying at least one flight leg database for a match indicative of an alternative flight ticket based on the purchased flight data, in each iteration, when the match is found, estimating a rebooking advisability rank while taking into account a cancellation fee of one or more of the purchased flight legs, and when the rebooking advisability rank is above a threshold forwarding to the user a notification about the alternative flight ticket.

Abstract: An apparatus operation plan creation device according to an embodiment includes a power generation quantity predictor, a power demand predictor, a hot water demand predictor, an estimator, a decider, a calculator, and a plan creator. The power generation quantity predictor predicts a quantity of power generation. The power demand predictor predicts a quantity of power demand. The hot water demand predictor predicts a quantity of hot water demand. The estimator estimates a quantity of power generation by a fuel cell based on a predicted value of a quantity of hot water demand. The decider decides a quantity of power storage of a storage battery.

Abstract: A method, system and computer program product for operating an expert system. Technical prescriptive domains and business prescriptive domains containing one or more templates are accessed, where each template defines an intention, goal or constraint. Furthermore, each technical prescriptive domain defines a generic optimization problem and each business prescriptive domain extends a technical prescriptive domain and defines a more specific business problem. A structure of data is received and analyzed with the technical prescriptive domains and business prescriptive domains to identify technical and/or business prescriptive domains that match the received structure set of data in data structure and/or semantic terms.

Abstract: A method, system and computer program product for generating an optimization model. A prescriptive model including a structured set of data and instance(s) of templates of a technical and/or business prescriptive domain is received, where the instances of the templates define goals and/or constraints for the structured set of data. The business prescriptive domain extends the technical prescriptive domain defining a generic optimization problem and the business prescriptive domain defines a more specific business problem. The prescriptive model is translated into a technical prescriptive model using a set of mapping rules to translate the instance(s) of the templates of the business prescriptive domain into instance(s) of the templates of the technical prescriptive domain from which the business prescriptive domain extends. Furthermore, the technical prescriptive model is translated into an optimization model, where the optimization model is solved.

Abstract: Systems and methods for use in enabling multiple management activities for a business entity through a domain model are disclosed. One exemplary method includes receiving, in response to a user input, a change to a domain model. The domain model is representative of technology associated with a business entity, and the domain model defines multiple layers, each associated with one of infrastructure, a plurality of services, and/or a plurality of business products of the business entity. Each layer includes multiple assets. And, the domain model further defines at least one relationship between one of the multiple assets in one layer and at least one of the multiple assets in a different layer. The method further includes updating the domain model based on the change and exposing the updated domain model to multiple different management activities of the business entity.

Abstract: Systems and methods are described herein for learning an entity's trust model and risk tolerance. An entity's trust score may be calculated based on data from a variety of data sources, and this data may be combined according to a set of weights which reflect an entity's trust model and risk tolerance. For example, an entity may weight data of a certain type more heavily for certain types of transactions and another type of data more heavily for other transactions. By gathering data about the entity, a system may predict the entity's trust model and risk tolerance and adjust the set of weights accordingly for calculating trust scores. Furthermore, by monitoring how entities adjust weights for different transaction types, default weighting profiles may be created that are customized for specific transaction types. As another example, an entity's trust score, as reported to a requesting entity, may be adjusted based on that requesting entity's own trust model, or how “trusting” the requesting entity is.

Abstract: An intelligent real-time 360° enterprise performance management system and 6-step methodology, which provides an integrated way to evaluate the performance and effectiveness of specific ‘business components’ within organizations (e.g., internal functions, internal processes, and stakeholder relationships). The system serves as a highly scalable, customizable, and context-aware Unified Enterprise Performance Management Application Platform (UEPMAP) that automates static and dynamic real-time and asynchronous business intelligence gathering from employees, customers, suppliers, business partners and other key stakeholders; analyses structured and unstructured feedback data; identifies strengths and weaknesses for each business component by way of SWOT analysis; develops prioritized action plans, supported by an adaptive neuro-fuzzy inference system (ANFIS) in order to address weaknesses identified within business components.

Abstract: A system for determining a labor flexibility level for a document management system that meets a performance level of a full-flexibility level and is within one or more threshold limits includes a document management system having a plurality of print production devices, an electronic device in communication with the document management system, and a computer-readable storage medium having one or more programming instructions. The document management system is associated with a plurality of operators who each possess one or more skill sets for operating one or more of the print production devices.

Abstract: A system and method for managing grants is provided. A method includes multiple entities associated with a grant, each having an instance of a grant management application. Each instance of the grant management application includes the capability to receive disparate fiscal, human resource, and program data associated with the grant, and to compare the combined data to a goal of the grant to determine the entity's performance to the goal. The combination of instances of the grant management application allows for a complete roll-up of individual entity's performance into a total performance for the funder of the grant and according to the funder's specifications.

Abstract: Mechanisms are provided for assisting medical practitioners to achieve incentive goals. The mechanisms generate a patient registry comprising a plurality of patient registry records where each patient registry record is associated with a corresponding patient and comprises personal and medical information about the corresponding patient. The mechanisms evaluate a registry of incentive goals for a medical practitioner based on the patient registry to determine an incentive goal whose criteria the medical practitioner has not yet met. The mechanisms determine an action to be performed by one or more patients to meet the criteria of the incentive goal and analyze the patient registry to identify a set of patients to perform the action. The mechanisms then generate an output identifying the set of patients.

Abstract: A system and method for generating and scoring leads for senior living communities, which collects and processes event and attribute data for seniors, senior living communities and staffers, and presents filtered and scored lists of potential senior residents and potential job applicants to senior living community operators. The matching, filtering and scoring of leads is based on early indicators of imminent senior care need, the communities' demographic and event qualifiers for candidates, the demographic traits of the current populations of the senior living communities, and weights assigned to the demographic qualifiers, event qualifiers and demographic traits by the senior living communities or system operator. Embodiments of the present invention can also be used by senior care seekers and job seekers to identify and score compatible senior care living communities based on demographic qualifiers, event qualifiers and weights provided by the senior care seekers, the job seeker, or system operator.

Abstract: Mechanisms are provided for matching patients with care providers. Patient information for a current patient, from at least one patient information source, is analyzed and a medical need of the current patient is determined. Patient information for a plurality of other patients associated with a plurality of care providers is analyzed and, for each care provider in the plurality of care providers, a measure of strength for a type of medical care corresponding to the at least one medical need is determined, based on results of the analysis of patient information for the plurality of other patients associated with the care provider. At least one care provider is selected for inclusion in a care team for the current patient based on the determined strengths of each care provider in the plurality of care providers. A care team data structure comprising information about the at least one care provider is output.

Abstract: In some embodiments, apparatuses and methods are provided herein useful to locating containers with low inventory in a shopping facility. Some of these embodiments include systems for identifying and determining the location of containers in a low inventory condition in shopping facilities, the system comprising: a container configured to hold merchandise items in a shopping facility; a light sensor disposed in the container, the light sensor calibrated to detect an ambient light level and to respond when the detected ambient light level exceeds a predetermined ambient light threshold; and a control circuit operatively coupled to the light sensor and configured to transmit a signal indicating a low inventory condition when the light sensor determines the detected ambient light level exceeds the predetermined ambient light threshold.

Abstract: The present disclosure provides methods and systems for the storage, ordering, listing, and delivery of products. Warehousing and delivery fulfillment systems are provided. Also provided are methods of warehousing and delivery fulfillment.

Abstract: A method for supply chain management using mobile devices with a server on an electronic data network includes receiving identifying information for a product transmitted from a mobile device via the network, the server being periodically updated with product recall data. The server queries a traceability server via the network for master data and event data related to the product using the identifying information. The server processes the recall data, master data, and event data to produce product data which is output to the mobile device.

Abstract: A Package Security Device senses delivery person's terminal device (or called mobile computer), triggers a camera to monitor the delivered package. When an unknown animal or a person approaches to the package, it captures and stores images, and generates warning sounds. The device can also send receipt confirmation message to the delivery person's terminal device, and/or the shipping company's data center as well as the package recipient through wireless communication.

Abstract: An unmanned aerial vehicle (UAV) may be used to deliver a package. The UAV may include a communication interface configured to receive a request to transport a package. The UAV may also include a navigation unit configured to direct the UAV to the package. The UAV may further include a sensor configured to determine one or more physical characteristics of the package. The UAV may also include an acceptance unit configured to accept the package for transport in response to the one or more physical characteristics satisfying a set of criteria.

Abstract: A package room system may include at least one shelf, at least one sensor configured to sense items on the at least one shelf, at least one data entry device, and at least one computer coupled to the at least one sensor and the at least one data entry device. The at least one computer may be configured to receive data concerning a package from the at least one data entry device, detect, from data from the at least one sensor, a location of the package on the at least one shelf, notify a recipient of receipt of a presence of the package and the location of the package, and detect, from data from the at least one sensor, removal of the package from the at least one shelf.

Abstract: Navigation data to a first location on a delivery route for a first delivery is sent to a navigation components of a delivery vehicle. Upon receipt of a notification that the first delivery to the first location is canceled, the availability of a backup delivery is determined. The location of each of a pre-determined set of potential buyers is compared to the current location of the delivery vehicle, and in real-time, a consumption of resources is calculated for a backup delivery and the return the one or more items to a designated return location. A determination of whether the backup delivery to a particular potential buyer is favorable as compared to the return the one or more items to the designated return location and, if favorable, navigational instructions are transmitted in real-time to the delivery vehicle to deliver the one or more items to the particular potential buyer.

Abstract: To propagate compliance and governance (C&G) policies, a parser including natural language processing is used to deconstruct a set of organization C&G policies from a set of C&G documents to identify and record a parsed set of categorized C&G policies. A configuration parameter analyzer deconstructs and parses a plurality of C&G configuration parameters of an application program to identify and record a set of application C&G configuration parameters each comprising a purpose and a unit of measure. A reconciliation arranger receives the set of categorized C&G policies and the set of application C&G configuration parameters and maps the categorized C&G policies for the correct purpose and the unit of measure to the respective application C&G configuration parameters. The reconciliation arranger propagates and secures the application program with the respective set of mapped application C&G configuration parameters from mapped C&G policies.

Abstract: An approach for a veterinary management system server that enables management of a practice, vendors, pet, and pet owner information while gathering metrics and providing reports in addition to providing marking services to the practice and vendors.

Abstract: In a method for determining an area milled by at least one construction machine or at least one mining machine by means of a milling drum (2) by means of working a predetermined area in several milling trajectories by at least one machine (1), determining the length of the milling trajectories along which a milling operation has taken place by evaluating the continuous machine positions, adding up the previously milled partial areas taking into account the length of the milling trajectory and the installed width of the milling drum (2), wherein the partial area currently milled along the milling trajectory is checked, either continuously or subsequently, for overlapping or multiple overlapping with any previously milled partial areas, and any partial areas which overlap are deducted, as overlapping areas, from the added-up previously milled partial areas, the total added-up partial areas milled minus the total overlapping areas established give the milled area.

Abstract: A computer system for enforcing a workflow, the computer system comprising: a computer store comprising: a set of actions; a plurality of data objects each comprising a specification identifying one or more of the set of actions for operation on the data object; and a plurality of stakeholder objects each being associated with (a) one or more of the data objects and (b) one or more of the set of actions; a user terminal coupled to the computer store and configured to provide a user with access to one or more data objects associated with a stakeholder object corresponding to that user; and a computer processor configured perform at least part of a workflow comprising a sequence of first and second actions by: operating a first action of the set on a first data object of the plurality; in response to a first user accessing the first data object at the user terminal, causing the user terminal to present to the first user one or more second actions identified by the first data object and associated with a first s

Abstract: Aspects of the present disclosure relate to generating a graphical output of characteristics of a person. A server accesses information about a person, the information comprising one or more of: a public social networking service profile of the person, information submitted by the person, an assessment of the person, and data published by the person. The server determines, based on the accessed information, one or more characteristics of the person. The server provides a graphical output related to the one or more characteristics.

Abstract: Aspects of the present disclosure relate to releasing content interaction statistics while preserving privacy. A server receives a request for statistics about user interaction with content items. The server accesses, in response to the request for statistics, a user-content interaction log that stores data representing interactions of users with content items. The server generates, using the user-content interaction log, a user-content interaction data set grouping users according to the user features and grouping content items according to the content features. The server preprocesses the user-content interaction data set to limit activity of each user with each content item in the user-content interaction data set. The server computes statistics, using the preprocessed user-content interaction data set, regarding interactions of users having a specified user feature with content items having a specified content feature.

Abstract: A plurality of data items can be managed using a processor. The plurality of data items can be contributed by a plurality of applications. The plurality of data items can include at least scheduled events, scheduled tasks and previous activities. Information corresponding to at least the scheduled events, scheduled tasks and previous activities can be presented. The plurality of data items can be managed based on knowledge and meaning of content of the plurality of data items.

Abstract: A system and method are provided for automatically estimating a repair cost for a vehicle. A method includes: receiving, at a server computing device over an electronic network, one or more images of a damaged vehicle from a client computing device; performing image processing operations on each of the one or more images to detect external damage to a first set of parts of the vehicle; inferring internal damage to a second set of parts of the vehicle based on the detected external damage; and, calculating an estimated repair cost for the vehicle based on the detected external damage and inferred internal damage based on accessing a parts database that includes repair and labor costs for each part in the first and second sets of parts.

Abstract: A cost calculating device mounted on a vehicle to calculate repair cost for damage includes a number of pressure sensors, at least one flaw detector, and a processor. The pressure sensors detect changes in pressure value in collisions. The processor acquires the pressure values from each of the pressure sensors and determines whether a pressure value is greater than a preset value. The flaw detector detects damage data if the acquired pressure value is greater than the preset value. The processor further determines a damage ratio according to the damage data and a pre-stored data for undamaged vehicle, and determines a repair cost according to the damage ratio and a pre-stored table recording a relationship between different damage ratios and repair costs. A cost calculating method is also provided.

Abstract: A device maintenance apparatus includes a device information storage storing information of a device and one or more maintenance items associated with the information of the device, an acquirer configured to acquire the information of the device, and a display configured to display the acquired information of the device and an operator receivable of an operation for executing, with respect to the device, at least one maintenance item among the one or more maintenance items associated with the acquire information of the device and stored in the device information storage.

Abstract: Wireless-enabled kiosk systems and associated methods for recycling and performing other processes with mobile phones and other electronic devices are described herein. In various embodiments, the present technology includes systems and methods for wirelessly connecting a consumer-operated kiosk with an electronic device to facilitate processing (e.g., purchasing) the device. In some embodiments, the present technology includes using a wireless link to identify a device, evaluate a device, resolve device issues to enable purchase of the device, locate a device, etc. Various other aspects of the present technology are described herein.

Abstract: Some embodiments enable one or more processors coupled to one or more storage devices to perform the following steps: receive a first request to conduct a financial transaction from a first user; in response to the request, receiving money in the form of a first currency from the first user; create a cryptographically secure coin, wherein the coin comprises a unique string that is associated with the first user; deliver the cryptographically secure coin to the first user.

Abstract: Systems and methods that provide improved security and scalability in digital token exchange are disclosed. In one example, a system may receive from a requester one or more old cryptographically signed tokens each including a shared class and denomination. After validating the previously issued Value Tokens, the system may sign newly issued Value Tokens having the shared class and send them to the requester as a swap for the previously issued Value Tokens. Some tokens have intrinsic value while other coded Value Tokens require reference to a record of valid tokens to validate them. The system allows tokens of one type to be swapped for tokens of the other type, but issues intrinsic Value Tokens only as a swap for coded Value Tokens.

Abstract: A method and system to test, monitor, and share revenue associated with third-party software applications operating on mobile devices over a network operator's wireless network. An application may be tested by the mobile application monitoring system to simulate the expected load of the application on a mobile device and the wireless network utilized by the mobile device, and to determine any services utilized by the application. Based on the simulation, the system determines a compensation arrangement under which revenue associated with the application will be shared between the network operator and the application provider. In some embodiments, the compensation arrangement is determined from a variable reward table. Revenue is shared inversely with an application's impact on customers and on the network operator.

Abstract: Systems and methods for processing mobile transactions include determining an indication to make a payment by a user to a payee; responsive to determining the indication, identifying, from a payment account associated with the user, a plurality of payment instruments; determining a first payment instrument in the plurality of payment instruments based at least in part on a first reward associated with making at least a portion of the payment using the first payment instrument; and generating a payment instrument alert to inform the user to make the payment using the first payment instrument.

Abstract: Online transactional processing systems, methods, and computer program products for processing an alternative method of electronic payment (AMOP) in online transactions. A mass storage memory device hosts a database that stores data for transforming one or more virtual payment forms into data that relates to one or more AMOP's. Each of the one or more virtual payment forms stored in the database is compatible with a legacy system of a merchant. In response to receiving, in relation to an online transaction with the merchant, data that relates to an AMOP, the data that relates to the AMOP is transformed to create a virtual payment form that is compatible with the legacy system of the merchant. The virtual payment form is then transmitted to the legacy system of the merchant for processing, and data for transforming the virtual payment form into data relating to the AMOP is stored in the database.

Abstract: Commercial accounts should be set up by ITunes and other providers of digital sound and video for businesses to sell the products within stores, avoiding the inefficiency of preloaded MP3 players and increasing the availability of these products to those without Internet access or with not enough bandwidth.

Abstract: Disclosed is a system for validating point of access customer subscription status and brokering intermediary billing adjustments. Customers can register into a water filter network. When at a food service provider location, a subscriber, when ordering water, can receive water filtered by network company's filter systems in a water storage container having a unique optical machine code that can be scanned using a smartphone application to verify the customer's subscription status via water filter manufacturer's database server. Filtered water from company's water dispensing apparatus is provided to a valid subscriber for free, while the unregistered subscriber will be required to pay full retail price for said bottle of water. The amount of water received by the validated subscriber will be deducted from the retail service bill of the service customer and the volume of water dispensed is deducted from a monthly bill of the food service provider.

Abstract: Voice recognized data analysis and corrective action systems and methods are disclosed. An example disclosed method includes analyzing a transcript of an order to identify menu items within the transcript. The example method also includes removing words from the transcript that are not identifies as menu items. Additionally, the example method includes formatting, with a first format, the transcript to separate and highlight the identified menu items when the transcript is displayed on a screen.

Abstract: Protection of POS terminals is enabled by multi-pronged security apparatus that includes: initializing the POS terminal and storing a profile of the terminal, and thereafter monitoring for any change in the POS terminal environment; inserting a bait into the memory (e.g., RAM) of the POS terminal, and monitoring the bait, such that when it is detected that the bait has been read, an indication of potential intrusion is issued; and providing communication channel between a monitoring center and plurality of POS systems, so that whenever an indication of potential intrusion is issued by a terminal, it is sent to the monitoring center and the monitoring center alerts the administrators of the participating POS systems, and the affiliated merchants about identified attacks to enable a response or removal of compromised terminals from service, including but not limited to temporary payment transactions blocking.

Abstract: Multiple different non-financial loyalty currencies held by different issuers are used by a consumer as financial tender for a transaction with a merchant. Each issuer pays to a primary issuer the financial currency value of the non-financial loyalty currencies being held in return for a corresponding reduction of the balance of non-financial loyalty currency. For each reduced balance, the primary issuer adds an equivalent primary loyalty currency to a primary loyalty account for the consumer. The primary issuer pays the merchant for the transaction in financial currency and makes an equivalent reduction in the balance of the primary loyalty currency. The financial value of each loyalty currency may be dependent upon its use in a transaction with a competitor of a merchant supplying loyalty currency to the consumer.