Abstract: Data sets for a three-stage predictor can be automatically determined. For example, multiple time series can be filtered to identify a subset of time series that have time durations that exceed a preset time duration. Whether a time series of the subset of time series includes a time period with inactivity can be determined. Whether the time series exhibits a repetitive characteristic can be determined based on whether the time series has a pattern that repeats over a predetermined time period. Whether the time series includes a magnitude spike with a value above a preset magnitude can be determined. If the time series (i) lacks the time period with inactivity, (ii) exhibits the repetitive characteristic, and (iii) has the magnitude spike with the value above the preset magnitude threshold, the time series can be included in a data set for use with the three-stage predictor.

Abstract: In various implementations, a method includes receiving a set of time series data that corresponds to a metric. A seasonal pattern is extracted from the set of time series data and the extracted seasonal pattern is filtered from the set of time series data. A predictive model is generated from the filtered set of data. The extracted seasonal pattern is filtered from another set of time series data where the second set of time series data corresponds to the metric. The filtered second set of time series data is compared to the predictive model. An alert is generated to a user for a value within the filtered second set of time series data which falls outside of the predictive model.

Abstract: Remote computing resource service providers allow customers to execute virtual computer systems in a virtual environment on hardware provided by the computing resource service provider. The hardware may be distributed between various geographic locations connected by a network. The distributed environment may increase latency of various operations of the virtual computer systems executed by the customer. To reduce latency of various operations predictive modeling is used to predict the occurrence of various operations and initiate the operations before they may occur, thereby reducing the amount of latency perceived by the customer.

Abstract: An embodiment of a method for evaluating a schedule for removing a core sample includes generating a model of the core by applying a value of each of the input parameters, one or more of the input parameter values associated with an uncertainty range, and defining a proposed tripping schedule, and performing an evaluation including applying the proposed tripping schedule and a set of expected input parameter values to the model, estimating a core parameter and determining whether the tripping schedule is predicted to be successful by comparing the core parameter to selected core damage criteria. The method also includes iteratively repeating the evaluation, each evaluation being performed using a different combination of input parameter values than any other evaluation, and calculating a probability of success (POS) of the proposed tripping schedule based on a number of evaluations that result in the tripping schedule being predicted to be successful.

Abstract: A predictor management system includes a storage unit 81 and update history management means 82. The storage unit 81 stores, in association with each of a plurality of prediction targets, an update history of a predictor corresponding to the prediction target. The update history management means 82 stores, in response to updating of a predictor, a prediction target of the predictor and an update time of the predictor in the storage unit 81 in association with each other.

Abstract: A method, article comprising machine-readable instructions and apparatus that processes data systems for encoding, decoding, pattern recognition/matching and data generation is disclosed. State subsets of a data system are identified for the efficient processing of data based, at least in part, on the data system's systemic characteristics.

Abstract: There is provided a method for implementing an algorithm for forming, or synthesizing, quantum circuits on a system capable of performing the quantum circuit synthesis by using a deterministic walk (i.e. a pseudo-random walk with a random or pseudo-random starting point). In one implementation, the deterministic walk is performed using a parallel search algorithm. In an implementation of the parallel search algorithm, a user utilizes a programming language to write instructions for a compiler. Then, a meet in the middle approach is utilized to separate the circuit into two halves. Next, the parallel search technique is used to find a claw, or a pair, which satisfies the circuit analysis. Subsequently there is the production of a result and/or a synthesis of the circuit if the pair is found.

Abstract: A system rapidly produces training cases for machine based learning by automatically creating training cases from a database of historical data. The system determines a plurality of attributes relevant to each of the training cases. The system identifies a first attribute of the plurality of attributes as an issue, and a second attribute of the plurality attributes as a response to the issue. The system identifies a plurality of cohort members from the database of historical data, where each cohort member comprises cohort member attributes that match a subset of the plurality of attributes. The system analyzes the cohort member attributes of each of the plurality of cohort members to identify the most frequent responses to the issue. The system creates the training cases where each training case comprises the issue and the most frequent responses. The system then trains a machine based learning system using the training cases.

Abstract: Embodiments train data analytics models by fitting that is distributed computationally and from a data storage point of view to produce an equivalent model to that achieved by sequential fitting. For example, a method may include performing a first pass on an untrained model at a first node, repeatedly transmitting the model to a next node and training the data analytics model at the next node until the data analytics model has been trained by at least a portion of the plurality of processing nodes. There may be a plurality of models that need to be fitted on the dataset and that may be independent or may result from varying and choosing different combinations of model structure, model meta-parameters that are not learned through training, and training algorithm parameters. Embodiments may provide the capability for training multiple models simultaneously by performing the single-model fitting process on different successions of nodes.

Abstract: The disclosed embodiments illustrate method and system of processing data by a computing device for training a target domain classifier. The method includes extracting one or more first features and one or more second features from a first target instance, associated with a target domain. The method further includes predicting a first label for the received first target instance based on the one or more first features by utilizing a trained first classifier associated with a set of labeled source instances, wherein the predicted first label is assigned to the first target instance when a first score of the predicted first label exceeds a first pre-specified threshold. Further, the method includes updating a set of labeled target instances associated with the target domain based on the labeled first target instance, wherein the updated set of labeled target instances is utilized to train the target domain classifier.

Abstract: The structure of an untagged document can be derived using a predictive model that is trained in a supervised learning framework based on a corpus of tagged training documents. Analyzing the training documents results in a plurality of document part feature vectors, each of which correlates a category defining a document part (for example, “title” or “body paragraph”) with one or more feature-value pairs (for example, “font=Arial” or “alignment=centered”). Any suitable machine learning algorithm can be used to train the predictive model based on the document part feature vectors extracted from the training documents. Once the predictive model has been trained, it can receive feature-value pairs corresponding to a portion of an untagged document and make predictions with respect to the how that document part should be categorized. The predictive model can therefore generate tag metadata that defines a structure of the untagged document in an automated fashion.

Abstract: An experience-aware anomaly processing system and a method for an experience-aware anomaly processing system are provided. The experience-aware anomaly processing system comprises an anomaly detection module configured to receive geographic location data with corresponding time information of a target object, and analyze target object behavior based on the geographic location data with corresponding time information of the target object; a user feedback module configured to receive user feedback from a user and model user feedback behavior when the user receives an alarm message indicating the target object is abnormal; and a decision module configured to receive user setting from the user, and make a detection decision through fusing target object behavior information corresponding to the target object behavior, user feedback behavior information corresponding to the user feedback behavior, and the user setting.

Abstract: A problem of finding unknown associations between ‘concepts’ in a given text corpus is addressed. A new framework for computing and visualizing the association between concepts using the generic association measures and the public knowledge available in data sources such as Wikipedia. Indirect association analysis extends the utility of the proposed framework to a broader class of association mining applications including the interesting area of new hypothesis generation.

Abstract: A system and method are described herein for improving content-based (CB) filtering to find other items similar to a particular item. For example, the system and method can operate to (1) collect ground truth from users, experts or non-experts for a subset of items in a library; (2) build similarity model(s) against the collected ground truth and evaluate this/these similarity model(s) for generalizability to all items in the library, and (3) build recommendations for users based on knowledge elicited from the users themselves, combined with the similarity scores in the built similarity model(s).

Abstract: Methods and systems for selecting a selected-sub-set of features from a plurality of features for training a machine learning module, the training of the machine learning module to enable classification of an electronic document to a target label, the plurality of features associated with the electronic document. In one embodiment, the method comprises analyzing a given training document to extract the plurality of features, and for a given not-yet-selected feature of the plurality of features: generating a set of relevance parameters iteratively, generating a set of redundancy parameters iteratively and determining a feature significance score based on the set of relevance parameters and the set of redundancy parameters. The method further comprises selecting a feature associated with a highest value of the feature significance score and adding the selected feature to the selected-sub-set of features.

Abstract: Among other things, data is received representing a case for which an output premise is to be generated. The received data is processed to generate the output premise for the case. The processing includes both analytical processing and statistical processing. The analytical processing in the statistical processing are managed so that the output premise depends on results of the analytical processing that have been affected by the statistical processing, or on results of the statistical processing that have been affected by the analytical processing, or on both.

Abstract: A method includes using a computational network to learn and predict time-series data. The computational network is configured to receive the time-series data and perform transformation-invariant encoding of the time-series data. The computational network includes one or more encoding layers. The method also includes feeding back future predictions of the time-series data through inertial adjustments of transformations. The inertial adjustments preserve the invariants in the computational network. The computational network could further include one or more pooling layers each configured to reduce dimensionality of data, where the one or more pooling layers provide the transformation invariance for the encoding.

Abstract: A method and system for providing an enriched root cause of an incident using machine-generated textual data. The method includes extracting, from a dataset including machine-generated textual data for a monitored environment, a plurality of features related to a root cause of an incident in the monitored environment; generating a suitability score for each of a plurality of insights with respect to the incident based on the extracted features and a suitability model, wherein the suitability model is created based on a training set including a plurality of training inputs and a plurality of training outputs, wherein each training output corresponds to at least one of the plurality of training inputs; and selecting at least one suitable insight based on the generated suitability scores.

Abstract: Aspects relate to a computer implemented method for resolving abnormal contention on a computer system. The method includes detecting, using a processor, abnormal contention of a serially reusable resource caused by a first process, wherein the abnormal contention includes the first process blocking the serially reusable resource from a second process that is waiting to use the serially reusable resource. The method includes collecting, in a computer storage medium, resource data in a serialized resource history database and analyzing the resource data associated with the serially reusable resource and adjusting, using the processor, resource allocation for the first process of the serially reusable resource based on the resource data. The method also includes processing, using the processor and the serially reusable resource, the first process based on the resource allocation and releasing, using the processor, the serially reusable resource by the first process in response to the first process completing.

Abstract: A method for access control to a digital event is disclosed. The method may include receiving, from a first client device, a request to purchase an electronic ticket for a digital event. The method may further include sending an event identifier to the first client device. The method may also include receiving an access request to access the digital event, wherein the access request includes the event identifier and a password. The method may include identifying a second client device that is currently accessing the digital event. The method may further include sending a message to the second client device indicative of the access request received from the first client device. The method may include receiving authorization from the second client device to initiate a transfer of access to the digital event from the second client device to the first client device.

Abstract: A vehicle sharing system includes a vehicle having interior transceiver modules associated with different passenger seating areas and a vehicle computing system (VCS) including a processor and a memory in communication with the modules and programmed to detect occupancy status of each seating area based on signals from the modules and to communicate the occupancy statuses to a remote server to facilitate scheduling of ride-sharing passengers for a specified seating area of the vehicle. The reserved seating location may be used to align the seating location/door with a passenger during pick-up, adjust vehicle accessory settings associated with the reserved seating location, and activate a visual indicator to direct the passenger to the assigned/reserved seating location.

Abstract: A notification server, notification method and notification program to perform watch over a person to be watched who uses on-demand transportation. A transceiver part receives boarding/alighting information comprised of a date and time of boarding/alighting, a stopping point of a vehicle and a name of a boarding person or a name of alighting person transmitted from an information terminal apparatus mounted on a shared vehicle, and a notification information generating part acquires a notifying destination associated with the received name of the boarding person or the name of the alighting person from a notifying destination storage part and generates notification information addressing to the acquired notifying destination, and a transceiver part transmits the generated notification information.

Abstract: A method and apparatus for selecting travel related services. The method includes the step of determining a plurality of travel related services that a consumer of such services can select for their own use. Each service has a start and end date. The services are stored in a database from which they are published to consumers. Consumers may then select the services of interest to them. Should a consumer not be able to use the selected service within its start and end date, the consumer may make the service available to other consumers for selection. An associated apparatus is provided to implement the process.

Abstract: The present disclosure relates to systems and methods for determining a predicted distribution of future transportation service time point. The systems may perform the methods to obtain historical service time points of transportation service requests occurred in a predetermined region; determine a variance of the historical service time points; determine a predicted distribution of future transportation service time point in the predetermined region based on the variance; and store the predicted distribution in a database.

Abstract: A method of generating a domain-specific graphical process studio is provided. The method includes performing initialization and/or an update of a generated domain-specific process studio (GDPS); combining a domain specification and a GDPS template; displaying a freshly generated GDPS instance; providing a way for a user to select a domain to work in via a user interface; receiving data from the user regarding new diagrams that have been created or existing saved diagrams that have been selected from one or more centralized repositories; receiving data regarding collaboratively edited diagrams from one or more users; and/or receiving updates from monitoring infrastructure populating the process diagram and the various version numbers being shown in the diagrams received.

Abstract: Apparatus for assessing threat to at least one computer network in which a plurality of systems (301, 302, 303, 304, 305, . . . 30n) operate is configured to determine predicted threat activity (13), to determine expected downtime of each system in dependence upon said predicted threat activity, to determine loss (12A, 12B, 12C, 12D, 12E, . . . , 12m) for each of a plurality of operational processes (31A, 31B, 31C, 31D, 31E, . . . 31m dependent on the downtimes of the systems, to add losses for the plurality of processes so as to obtain a combined loss (12SUM) arising from the threat activity.

Abstract: A system for generating operational metrics data for a medical care facility includes a first camera and an operational metrics device. The first camera generates digital images of a first detection area. The operational metrics device includes an optical code detector, a medical object detector, and an operational metrics generator. The optical code detector generates optical code detection data indicative of the presence or absence of optical codes within each of the digital images. Each of the optical codes is disposed on a respective medical object. The medical object detector generates medical object detection data indicative the presence or absence of each medical object within the first detection area. For each medical object, the operational metrics generator generates operational metrics data based at least partially on a determined amount of time that each medical object was present within the first detection area.

Abstract: Embodiments of the invention are directed to a system, method, or computer program product for generating communicable linkages that collectively provide a cloud-based dynamic credential selection and implementation system. The system generates a user profile containing user preferences, historic trends, and user resources based on information collected from a user and user associated accounts. The dynamic credential selection and implementation system is triggered by the user signaling the system of a proposed transaction. The system requests updated resource characteristics from resource managers. The user profile, resource characteristics and transaction characteristics are evaluated and ranked by the dynamic credential selection and implementation system before completion of the transaction, which in some embodiments requires user approval of the selected resource.

Abstract: Examples of the disclosure provide a system and method for entity-specific inventory optimization. An inventory optimization module obtains inventory data for an individual entity at a given time, including variance date codes associated with an individual item, and identifies at least one item of a plurality of items that exceeds an inventory threshold based on the inventory data. An elasticity estimation module receives the identified item from the inventory optimization module, identifies a value response curve for the identified at least one item based at least in part on entity-cluster data, generates an entity-specific elasticity value for the item, and generates an inventory optimization recommendation based on the generated entity-specific elasticity value and the variance date codes of the inventory data.

Abstract: A reminder system is provided. The system provides a user-friendly interface to a user's existing email, and in some embodiments to the user's document management, calendar and other systems, in order to ensure that an appropriate user is notified when action should be taken, and also provides notation to the user indicating the appropriate course of action to be taken. The system provides a calendaring feature where a supervisor or manager can determine the workload of a group of workers for an upcoming time period. The system provides an easily accessible and traceable database of information pertaining to a project checklist, document, a client name, a client matter number, a document type, or other customizable fields in order for a user to search and sort the information for their own use.

Abstract: A system, medium, and method including receiving input data relating to an employee, the input data including a plurality of sentences of descriptive language regarding the employee's performance; processing the input data to determine sentences of refined textual data; determining a category for each of the sentences of the refined textual data from a plurality of categories, each of the plurality of categories being different from each other and relating to a particular type of performance evaluation characteristic; generating, based on the refined textual data and the determined category for the sentences of the refined textual data, a plurality of summary sentences reflective of the input data; and generating a summarization of the employee's performance, the summarization including an ordered listing of the plurality of summary sentences.

Abstract: A method and a system are provided for role-based auto-selection of employees for trainings associated with skills required in a project. The method comprising receiving a request for the project. The method may extract one or more current skills of one or more employees based on the received request. The method for a required role in a project may further determine, a proficiency gap between the one or more required skills and the one or more current skills for each of the one or more employees. The method for a required role in a project may prioritize the one or more required skills for each of the one or more employees based on the determined proficiency gap. The method may select a set of employees from the one or more employees for one or more skill-based trainings.

Abstract: A method for scheduling servers within a food-serving establishment or other business environment using a point-of-sale system based on a fairness processing module. The system includes a tablet, configured to receive a food order, and a computer having a transceiver, memory, and processor. The transceiver receives information about the food order from the tablet including payment and gratuity information. The memory stores payment and gratuity information along with information related to tables statistics and server-table assignments. The computer uses the fairness processing module to provide a preliminary recommendation of a first server from a group of servers for a non-routine scheduling assignment. The fairness processing module is based on a total amount of gratuities the first server has earned during a relevant period of time as compared to a total amount of gratuities earned by other servers in the group of servers.

Abstract: A real-time trade resource management system is shown. In a construction site having one or more points of ingress/egress a tracking assembly at each point of ingress/egress is used to determine when workers are first and last observed on the site. Each worker on the site is assigned to a specific contract for the construction project. A server, computer readable medium, and method for managing trade resources is described.

Abstract: A calendar conflict resolving method, system, and non-transitory computer readable medium, include processing a request for an event for a time slot of a calendar to correlate the requested event with user data, comparing the requested event with a scheduled event to determine a conflict between the scheduled event and the requested event, and resolving the conflict between the requested event and the scheduled event according to a set of rules, the set of rules being based on the user data.

Abstract: A method for providing a typical load profile of a vehicle includes computing dwell times and maximum load stops, wherein a maximum load stop indicates a stop having a largest load on a route for a trip using route information and vehicle scheduling information based on automatic vehicle location data, computing one or more trip load profiles by identifying a load progression rate by performing a local regression procedure dividing the route into subsections such that the loads between adjacent subsections can be represented by a linear function on input of the computed maximum load, the computed dwell times, and maximum load stops, and constraining the identified load progression rate to an admissible value by evaluating the rate load progression with regard to historical dwell times and the computed maximum load stops. The method further includes computing the typical load profile based on load profiles of computed trips.

Abstract: A first terminal determines a collection date of a somatic cell based on a desired collection date and a collectable date transmitted by a second medium; and outputs the collection date to a first medium. A second terminal outputs the collectable date to the second medium; and determines an acceptance date based on the collection date transmitted by the first medium and a production period of an iPS cell transmitted by a third medium. A third terminal determines the production period based on the collection date and a producible period, and determines a shipment date based on the production period and stockable location and period transmitted by a fourth medium; and outputs the production period to the third medium. A fourth terminal outputs the stockable location and period to the fourth medium; and determines stock location and period based on the production period and the stockable location and period.

Abstract: A server-implemented method for automatically registering an asset tag in a database is disclosed. One or more asset tag collision reports are received from at least one mobile device connected to the server, each report including a tag identifier of the asset tag that is wirelessly broadcast by the asset tag. A location of the asset tag is determined based on the one or more received asset tag collision reports. A first asset is selected from a set of unregistered assets that are identified as being deployed in the indoor facility based on determining that there is a match between the location of the asset tag and location information associated with the first asset. The asset tag is then registered in association with the first asset in the database.

Abstract: Systems and methods for monitoring worker movement within a warehouse setting are provided. According to one implementation, a wearable apparatus comprises an audio unit configured to receive audio input signals from a user and convey audio output signals to the user. Also, the wearable apparatus includes a step count unit configured to detect walking movements of the user.

Abstract: Some embodiments include receiving a plurality of items available for purchase; aggregating the plurality of items into a menu; populating a first interface configured for ordering; receiving an order; requesting delivery quotes to deliver the order to the customer; receiving the delivery quotes to deliver the order to the customer; populating a second interface with information defining the order, requesting confirmation of the order and selection of a delivery network to deliver the order to the customer; populating the second interface with at least one of cost and time from the delivery quotes; receiving a confirmation of the order and a selection of a delivery network to delivery network; notifying the customer of the confirmation and an estimate of a time for delivery of the order; facilitating delivery of the order to the customer using the delivery network; and processing payment for the order and payment for delivery.

Abstract: Disclosed are methods for managing inventory in e-commerce. A method may be provided that may include segmenting a quantity of a specific product in inventory into a plurality of inventory leases having a smaller quantity of the specific product. A lease management server may distribute at least one inventory lease. At least one of the specific products may be selected by the inventory management server for reservation. A rate of selection of the specific products from each of the respective inventory leases may be determined. The determined rate of selection may be analyzed to determine when the quantity in the respective inventory lease will reach a minimum quantity in the respective inventory lease. An indication of when a request for a new inventory lease is to be sent to the lease manager server may be provided.

Abstract: Systems and methods of processing items. Items in a distribution network or process may be scanned at every handling point in the distribution network, and each scan is recorded in a central repository. The scan information can be used to generate real-time access to data, analytical tools, predictive tools, and tracking reports.

Abstract: A system for an iPS cell bank includes a terminal and a server. The terminal receives and sends a production request including a desired collection date of a somatic cell and a customer ID to the server. The server stores a collectable date for collecting the somatic cell, a producible period for producing an iPS cell, and a location and a stockable period for stocking the iPS cell; and determines: a collection date based on the desired collection date and the collectable date; a production period based on the collection date and the producible period; an acceptance date of the somatic cell based on the collection date and the production period; a stock location and a stock period based on the production period, the stockable location, and the stockable period; and a shipment date of the iPS cell based on the production period, the stockable location, and the stockable period.

Abstract: A method and system for cold chain monitoring of perishable goods, includes at least one environmental sensor to monitor at least one environmental parameter, a wide area network interface to communicate with a wide area network, a controller to log a plurality of readings from each of the at least one environmental sensors and to transmit at least one data signal associated with the plurality of readings to the wide area network via the wide area network interface.

Abstract: A system and method for tracking a container may include a memory; a communication unit; a location unit adapted to determine a location of the container, a power source; and a controller configured to: use the communication unit to report a location of the container to a server. A container may include sensors for sensing at least one of: a temperature, a motion, a pressure, a humidity, an acceleration, a velocity, an opening of the container and a presence of specific objects in the container and a controller included in the container may be adapted to autonomously send a message to the server based on input from the sensors.

Abstract: Described herein are various embodiments of a system for tracking interests in content using a distributed data store. By being “distributed,” there may be multiple different copies of the data store that each hold a portion or all of the data of the data store, with the different copies being continuously, periodically, or occasionally synchronized to ensure that data held in one matches the data held in another, but with no copy of the data store being treated as the official or canonical copy of the data store. The distributed data store may track the interests regarding the content in particular ways, including through storing information identifying the content and identifying interests in the content. The distributed data store may be used to track interests in media, such as to track ownership, management, or royalty interests in media like songs, to provide a mechanism for “Digital Rights Expression” (DRE).

Abstract: A system comprises a first client device, a second client device, a data store, one or more information sources communicatively coupled to a network, and a server communicatively coupled to the first client device, the second client device, the data store, and the network. The first client device can receive a first set of user input data from a first user and the second client device can receive a second set of user input data from a second user. The server can search the one or more information sources for first secondary information associated with the first set of user input data and for second secondary information associated with the second set of user input data. The server can apply a matching model based on the first set of user input data, the second set of user input data, the first secondary information, and the second secondary information.

Abstract: A referral system is provided with an on-line social network system. The referral system accesses a member profile representing an employee of a certain company. For each job posting that represents a job at the target organization, the referral system generates a presentation score that reflects the likelihood of the employee referring someone from their network for the job represented by that job posting. The referral system uses respective presentation scores generated for the job postings to determine which of these job postings are to be selected for inclusion into a referral UI for presentation to the employee.

Abstract: Methods, apparatus, systems, and computer-readable media are provided for increasing dimensionality of data structures associated with filling positions. In some implementations, a prediction of desired experience for a given position to be filled may be used to increase the dimensionality of a searchable data structure that represents the given position. For example, the predicted desired experience may be incorporated into a searchable field of the data structure. Among other things, increasing the dimensionality of the data structure may facilitate more granular searching of positions and guided creation of new positions to be filled. In some implementations, a predicted desired experience may be used to notify a user posting a new position whether a specified desired experience corresponds to a predicted desired experience.

Abstract: Example career data analysis systems and methods are described. In one implementation, a processing system receives data associated with a career path and receives data associated with a candidate's career history. The processing system determines at least one of a suggested career position or a suggested salary associated with the candidate based on the data associated with the career path and the data associated with the candidate's career history.