Abstract: A device and computer implemented method. The method includes determining, in a representation of relationships between elements, an element representing a first characteristic of a machine learning pipeline, determining, in the representation, an element representing a second characteristic of the machine learning pipeline depending on the element representing the first characteristic, outputting an output for the element representing the second characteristic, detecting an input, in particular of a user, either determining a parameter of the machine learning pipeline depending on the element representing the second characteristic if the input meets a requirement or not determining the parameter of the machine learning pipeline depending on the element representing the second characteristic otherwise.

Abstract: The present invention uses an agglomerative hierarchical clustering (“AHC”) method for patent clustering. Agglomerative clustering is the most common type of hierarchical clustering used to group objects in clusters based on their similarity. It's also known as Agglomerative Nesting (“AGNES”). The algorithm starts by treating each object as a singleton cluster. Next, pairs of clusters are successively merged until all clusters have been merged into one big cluster containing all objects. The result is a tree-based representation of the objects, known as a dendrogram. This methodology is used in a broad range of applications. In one embodiment, the present invention uses specific requirements of the data in order to create smart ways of choosing which levels are included and which are excluded.

Abstract: The computing device transforms lab data and field data into a first format suitable for execution with a supervised machine learning model to determine an input variable importance for a first set of input variables in predicting a field outcome, generates one or more logical rules of decision metrics, selects the one or more input variables that yields a higher input variable importance, generates one or more pass-fail indicators, combines the one or more pass-fail indicators generates one or more prediction factor rules, transforms the field data and the one or more prediction factor rules into a second format suitable for execution with a model to determine a treatment effect for the one or more prediction factor rules, and selects the prediction factor rule that maximizes the treatment effect of predicting the field outcome of a performance of compounds or biological actives within a range of uncertainty.

Abstract: A computer-implemented method for training a machine-learning method comprises the following steps carried out by computer hardware components: determining measurement data from a first sensor; determining approximations of ground truths based on a second sensor; and training the machine-learning method based on the measurement data and the approximations of ground truths; wherein approximations of ground truths of lower-approximation quality have a lower effect on the training than approximations of ground truths of higher-approximation quality.

Abstract: Embodiments provide methods and systems for processing unstructured and unlabelled data. A method includes generating, by a processor, a structured and unlabelled training dataset from an unstructured and unlabelled dataset. The method includes categorizing the structured and unlabelled training dataset into a plurality of clusters by executing an unsupervised algorithm. Each cluster of a selected set of clusters from the plurality of clusters is labelled with an applicable label from a set of labels. The method includes executing a supervised algorithm to generate a trained supervised model using a labelled training dataset including the set of labels and an input dataset generated from plurality of datapoints present in each cluster of the selected set of clusters. The method includes generating a Labelled Data1 (LD1) by executing the trained supervised model configured to assign applicable label from the set of labels to each datapoint of the structured and unlabelled training dataset.

Abstract: Systems, methods, and programs for privately and securely providing accurate machine learning models to anonymous clients for various applications. Discrete model classes of models are trained on non-anonymous datasets at a centralized server and served to anonymous clients. Clients validate each model against its own localized datasets and retain the most accurate model. Clients improve their model locally through transfer learning on new datasets, and share the updated, anonymized parameters with a centralized computer. The centralized server aggregates and updates model parameters for each respective discrete model class. The improved models may be served to future and existing clients.

Abstract: A computer-implemented method, medium, and system are disclosed. One example computer-implemented method performed by a server includes obtaining training task information from a task party. The training task information includes information about a to-be-pretrained model and information about a to-be-trained target model. A respective task acceptance indication from each of at least one of a plurality of data parties is received to obtain a candidate data party set. The information about the to-be-pretrained model is sent to each data party in the candidate data party set. A respective pre-trained model of each data party is received. A respective performance parameter of the respective pre-trained model of each data party is obtained. One or more target data parties from the candidate data party set is determined. The information about the to-be-trained target model is sent to the one or more target data parties to obtain a target model.

Abstract: A system for optimal drive configuration using machine learning; the system includes: a data collector configured to collect data and establish correlations among the collected data; a training data set generator configured to compute configuration sets based on the collected data and based on the established correlations, further configured to compute measured success values for the configuration sets, further configured to generate training data sets that include the configuration sets together with corresponding measured success values; a machine learning module, configured to predict predicted success values for calculated configuration sets using the training data sets provided by the training data set generator using machine learning algorithm; and an optimization module, configured to order the calculated configuration sets, including a simulation module, configured to simulate the calculated configuration sets.

Abstract: A series of sequential inputs and a prediction output of a machine learning model, to be analyzed for interpreting the prediction output, are received. An input included in the series of sequential inputs is selected to be analyzed for relevance in producing the prediction output. Background data for the selected input of the series of sequential inputs to be analyzed is determined. The background data is used as a replacement for the selected input of the series of sequential inputs to determine a plurality of perturbed prediction outputs of the machine learning model. A relevance metric is determined for the selected input based at least in part on the plurality of perturbed prediction outputs of the machine learning model.

Abstract: Methods, apparatus, systems, and articles of manufacture are disclosed for composable machine learning compute nodes. An example apparatus includes interface circuitry to receive a workload, instructions in the apparatus, and processor circuitry to at least one of execute or instantiate the instructions to generate a first configuration of one or more machine-learning models based on a workload, generate a second configuration of hardware, determine an evaluation parameter based on an execution of the workload, the execution of the workload based on the first configuration and the second configuration, and, in response to the evaluation parameter satisfying a threshold, execute the one or more machine-learning models in the first configuration on the hardware in the second configuration, the one or more machine-learning models and the hardware to execute the workload.

Abstract: Aspects of the present disclosure involve systems, methods, devices, and the like for auto-labeling clusters generated by machine learning models. In one embodiment, a system is introduced that can perform a series of operations for determining comprehensive labels for clusters output from machine learning methods used to classify data sets. The auto-labeling system may include generating labels determined using a computation of a frequency count, ratio, and coverage. These computations may use feature-based dictionaries which aid in the determination, storage, and analysis of the relevant features useful in labeling the clusters.

Abstract: In some examples, special-purpose machines are provided that facilitate smart copy optimization in a network service or publication system, including software-configured computerized variants of such special-purpose machines and improvements to such variants, and to the technologies by which such special-purpose machines become improved compared to other special-purpose machines that facilitate adding the new features. Such technologies can include special artificial-intelligence (AI), machine-learning (ML), and natural-language-processing (NLP) techniques.

Abstract: Methods and systems, including those employing machine learning, utilizing one or more algorithms for relating the structure of a molecule in a library to its function are described. Embodiments described herein relate structure to function by considering the covalent structure of the molecule, the components of that structure that are common to many molecules in the library, and the properties of those components as they relate to the function in question. Applications include, for example, enhancement and amplification of the diagnostic and prognostic signals provided by peptide arrays for use in analyzing the profile of antibodies in the blood produced in response to a disease, condition or treatment.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for training explainable machine learning models are described. An exemplary method includes obtaining, by sampling without replacement for a plurality of times, a plurality of training datasets from a plurality of historical data records, including a first training dataset and a second training dataset with one or more overlapped historical data records; generating a plurality of histograms respectively corresponding to the plurality of training datasets, in which a histogram of the second training dataset reuses one or more data points corresponding to the one or more overlapped historical data records in a histogram of the first training dataset; training, based on the plurality of histograms, one or more machine learning models corresponding to the one or more user features; and providing personalization based on the one or more machine learning models.

Abstract: An apparatus is disclosed. The apparatus comprises one or more processors to receive trained model update data from each of a plurality of collaborators, execute an auxiliary machine learning model to the trained model update data to generate a risk score for trained model update data associated with each collaborator, apply one or more policies based on the risk scores to generate adjusted trained model update data associated with each collaborator.

Abstract: A method for transmitting a prompt request, including: calculation by a server of a first number of requests to reserve vehicles in a fleet of shared vehicles, in a predetermined geographical area, the calculation of the first number taking into account: the number of reservation requests actually received by the server at a given moment, and/or a number of estimated reservation requests, determination by the server of the geographical positions of the fleet vehicles, calculation of a second number of fleet vehicles that are available in the geographical area, comparison by the server of the first and the second number, if the second number is lower than the first number, identification by the server of the fleet vehicles—which are not available and are in operation; and the geographical position of which is in the geographical area or at a predetermined distance from the geographical area.

Abstract: An information processing apparatus includes a processor configured to: acquire information about behavior of a user visiting a restaurant; determine, based on the information about the behavior of the user, whether or not a first condition indicating a predictor of the user leaving the restaurant is satisfied; and determine, in a case where the first condition is satisfied, that a vehicle dispatch request for requesting dispatch of a vehicle to the restaurant is to be made, the vehicle being for movement of the user.

Abstract: Disclosed herein are a method and a system for facilitating seamen ticket booking. The system provides means for the user to specify requirements and book tickets. The system, by contacting associated service providers, identifies suitable flight schedule from an airport which is nearest to the location mentioned by the user. Upon identifying at least one suitable schedule, details of the same are sent to the user, and any other authorized person who may be monitoring the user's actions. Upon getting approval, the system books ticket and send confirmation and other details to the user. The system also provides visa requirement related information to the user, and allows filing of visa request online.

Abstract: A car-hailing method and device, as well as a computer readable storage medium. The method includes receiving a car-hailing instruction and sending a car-hailing notification to a second terminal associated with a first terminal so that the second terminal sends car-hailing information to a target object according to the car-hailing notification. The car-hailing information includes at least a geographical location of the first terminal, user information and a destination.

Abstract: A transportation system including a vehicle hub having a plurality of connection slots, each connection slot accommodating a plurality of vehicles such that the vehicle hub is connected to an interior space of each vehicle through the respective connection slot, the plurality of vehicles being categorized by travel theme, and the plurality of connection slots being grouped by category such that connection slots in a same group are disposed adjacent to each other; and a server to collect passenger information related to travel preferred by passengers, to match the passengers with the connection slots or the vehicles based on the passenger information, and to guide the passengers to the matched connection slots or vehicles.

Abstract: Systems and methods for optimizing multi-modal transportation over a time period are provided. A system includes a simulation system configured to generate simulation data, a servicing system configured to generate servicing data, and a planning system configured to determine a multi-modal transportation itinerary based on the simulation and servicing data. The simulation data can identify a plurality of simulated flights performed in a simulated world corresponding to the real world. The system can determine the impact of scheduling a multi-modal transportation itinerary based on the impact of the multi-modal transportation itinerary on the simulated flights. The servicing data can include a servicing schedule that plans anticipated servicing events based on the impact of the servicing event to the simulated itineraries. Once scheduled, future simulated flights can be generated that account for the multi-modal transportation itinerary and the servicing schedule.

Abstract: The present disclosure provides a method for optimizing transformation of automation equipment in a power distribution network based on reliability, including determining installation states of respective components in the power distribution network and operation criterions for fault isolation, load transfer and fault recovery after a fault occurred in a feeder segment; determining a target function which is a target function for minimizing a total transformation cost of the power distribution network; determining constraint conditions including reliability constraints; establishing an optimization model for evaluating the reliability of the power distribution network based on the reliability constraints in accordance with the target function and the constraints; and solving the established optimization model for evaluating the reliability of the power distribution network based on the reliability constraints to obtain optimal solutions as optimization results of the automation transformation state of the cir

Abstract: A method, computer system, and a computer program product for process optimization is provided. The present invention may include analyzing a business process model comprised of one or more activities. The present invention may include extracting one or more key phrases from one or more event logs, wherein the one or more event logs are based on the business process model. The present invention may include determining a corresponding activity for the one or more extracted key phrases. The present invention may include generating an enriched business process model based on the business process model and one or more derived activities.

Abstract: A method and a system for providing a distributed data architecture are provided. The method includes: defining a scope of a business problem space; identifying solution domains that relate to the defined scope; defining a bounded context that relates to a domain-specific solution for each of the identified solution domains; defining boundaries between the bounded contexts; and using the bounded contexts to define domain models, key entities, relationships, aggregates, applications, application programming interfaces, and events.

Abstract: A work site management system includes: an entry-prohibited area setting unit that sets an entry-prohibited area to prohibit an entry of a manned transport vehicle at a discharging site in a work site; and a notification unit that notifies the manned transport vehicle of the entry-prohibited area.

Abstract: A transportation service improvement for a user by reflects the degree of dissatisfaction of the user on the operation of a vehicle. In a transport service system that provides a service of operating a transport resource to transport a user, a third management device acquires a numerical value representing dissatisfaction of the user, a first management device gives a point corresponding to the dissatisfaction and stores a point for each of users in a first database, the point being usable for executing a request for the operation of the transport resource, and the third management device receives a request from the user and changes a plan of the operation of the transport resource based on the request and the status of the operation of the transport resource that is managed by a second database in exchange for the point given to the user that is managed by the first database.

Abstract: A method and an apparatus for creating a workflow, the method being performed by a computing device, and including obtaining a log file generated while a user performs a task, parsing each of a plurality of events recorded in the log file, and creating an activity sequence to correspond to an order of the events, grouping a plurality of partial sequences extracted from the activity sequence, and creating a plurality of activity groups to correspond to each of a plurality of different repetitive tasks included in the task and creating the workflow of at least one activity group among the plurality of activity groups.

Abstract: A method (200) for configuring a workflow is described. The method (200) comprises initiating (202), by a workflow engine (122), a task in the workflow and identifying (210), by a rule engine (124), at least one upcoming task in the workflow based on data associated with at least one parameter of the task. The method (200) further comprises determining (212), by a task engine (126), at least one additional parameter of the identified at least one upcoming task and obtaining (214), by the task engine (126), data associated with the at least one additional parameter. The method (200) further comprises completing (216), by the task engine (126), the task based on the data associated with the at least one additional parameter.

Abstract: A system for predicting a particular intended action of a guest on a resort property is provided, the system including a server configured to connected to and to receive data from a mobile device of the guest or via camera images of the guest; a plurality of interaction devices, each of the interaction devices being configured to connect to the mobile device when the guest is within a particular distance of a respective interaction device and/or capture digital images of the guest, wherein the server is configured to obtain guest information from the respective interaction device; and a processor configured, based on the guest information, to make a prediction of the guest's intended action or destination; and to initiate a business workflow within the resort property based upon the prediction of that guest's intended action or destination.

Abstract: Techniques for solving asset synthesis by integrating asset synthesis instances into a historical, virtual, or predicted workflow within an organization. The integration facilitates improving a parameter of the synthesis, such as cost or time. The result is a system that improves productivity in an organization and improves accuracy of workflow completion prediction within the organization.

Abstract: A system and method analyzes computer actions to identify computer-based processes (e.g. computer-user interactions) which are automation candidates. A data gathering process executed by a processor on a computer may collect low-level user action information or items, each low-level user action information or item including for example an input type description, a user name, and screen window information. At a computer sequential pattern mining may be applied to determine a set of subprocesses, each subprocess including a series of low-level user actions, each user action associated with a user action vector, and each subprocess associated with a subprocess vector generated from user action vectors associated with (typically generalized) low-level user actions comprised in the subprocess. The subprocess vectors may be grouped or clustered to create processes. For each process, an automation score may be calculated using the actions in the subprocesses in the process.

Abstract: Systems and methods for recommending merchant actions include a physical merchant location having a plurality of beacon devices. A system provider device receives a plurality of first location information from the plurality of beacon devices that is collected from a customer beacon communication device that is associated with a customer. The system provider device also receives a plurality of second location information over the network from the plurality of beacon devices that is collected from a merchant beacon communication device that is associated with an asset of the merchant. The system provider device analyzes the plurality of first location information and the plurality of second location information to determine at least one merchant action recommendation related to the customer and the asset of the merchant and provides the at least one merchant action recommendation over the network for display on a display device.

Abstract: A system and method for determining a likelihood of future success of a business includes obtaining one or more sets of data associated with the business from one or more sources, storing the one or more sets of data in at least one database, retrieving the one or more sets of data from the at least one database and analyzing the one or more sets of data to determine a likelihood of future success of the business, and displaying to a user the likelihood of the success of the business.

Abstract: A method for device monitoring includes: providing a plurality of fleet measurement data for at least one device, where the plurality of fleet measurement data includes a number of fleet device data measurements “Nfleet;” providing a plurality of device measurement data for a monitored device, where the plurality of device measurement data includes a number of monitor device data measurements “Ndata;” determining a fleet distribution “Fdist” determined as a distribution of differences between consecutive measurements of the plurality of fleet measurement data; determining a device distribution “Ddist” determined as a distribution of differences between consecutive measurements of the device measurement data; determining an effective number of data measurements “Neff” and determining a probability of failure of the monitored device, the determining including utilising the fleet distribution “Fdist,” the device distribution “Ddist,” the number of monitor device data measurements “Ndata,” and the effective numbe

Abstract: The present invention provides a computer system providing an advice on communication. The computer system (100) of the present invention is configured to receive characteristics of a plurality of users (S501), to mutually compare the characteristics of two users out of the plurality of users (S502), and output an advice on communication between the two users on the basis of the comparison of the characteristics of the two users (S503).

Abstract: A method for managing mainframe billable resources for a plurality of mainframe environments is provided. The method includes receiving a job file from a user, the job the including a batch file relating to a mainframe job and a mainframe task; identifying an override statement in the job file; determining, based on a result of the identifying, a mapping strategy according to a predetermined criterion, the mapping strategy relating to a mapping of the job file to a billing entity identifier; authorizing the job file based on the billing entity identifier and a logon identifier corresponding to the user; mapping the job tile to the billing entity identifier based on the determined mapping strategy; recording, in a memory, information relating to the mapping; and executing, in a mainframe environment, the job tile.

Abstract: Generating employee retention insights is provided. An analysis is performed, using an artificial intelligence component, of data in a completed digital off-boarding form corresponding to a particular employer and a type of a particular employee leaving the particular employer and information in data feeds from a plurality of different data sources. Insights are generated, using the artificial intelligence component, into employee retention for the type of the particular employee corresponding to the particular employer based on the analysis of the data in the completed digital off-boarding form and the information in the data feeds from the plurality of different data sources. A set of action steps are generated, using the artificial intelligence component, based on the insights and the data in the completed digital off-boarding form. One or more of the set of action steps are performed automatically.

Abstract: The Profit Enhancer Analysis aka The Profit Enhancer aka The PEA is a cloud-based predictive model diagnostic business and productivity Software as a service (SaaS) tool for customer relationship management. The software application decodes data entered using proprietary calculations and algorithms to provide a detailed, customized assessment of a clients business performance. It offers the user insight to be able to understand client historical behavior trends and is used as a new client qualifier as well as an identifier of specific performance gaps of a company as well as overall health of the company. Through the use of The Profit Enhancer Analysis, the user will have further the ability to send proposals immediately after a consultation and have insight and details to evaluate product performance, service performance and department performance of a client.

Abstract: A method and system for dynamically deploying a module of a manufacturing operations management application across a plurality of layers. A MOM application has a plurality of modules organized in a hierarchical architecture, wherein each module is independently deployable in at least two layers of the plurality of layers; for each module and for each layer wherein the module is deployable, defining a set of production parameters relevant for recommending a layer for module deployment; defining for each module a layer-deploying function, having as input variables values of the production parameter sets for the module and having as output variable a recommended layer wherein the module is to be deployed; and, upon request, for a specific module and for a specific time-point, calculating the recommended deploying layer with the layer-deploying function by using values of the input variables at the requested specific time-point.

Abstract: The disclosure herein describes generating and presenting a benchmark to a target entity. A peer group of entities associated with the target entity is determined based on at least one attribute of the target entity. Behavior data of the target entity and behavior data of the entities of the peer group is identified and the behavior data of the entities of the peer group is transformed using adjustment values, wherein the transformed behavior data differs from corresponding behavior data of the entities of the peer group by less than an accuracy threshold. Benchmark data of the benchmark associated with the behavior category is generated based on the behavior data associated with the target entity and the transformed behavior data associated with the entities of the peer group and the benchmark data of the benchmark is presented as a benchmark visualization via a user interface.

Abstract: Some embodiments provide a non-transitory machine-readable medium that stores a program executable by a device. The program identifies a set of visualizations associated with the user. The program further determines, for each visualization in the set of visualizations, a score associated with changes in the visualization. The program also determines a subset of the set of visualizations based on the set of scores. The program further provides to the user notifications associated with the subset of the set of visualizations.

Abstract: The technology described herein relates to, among other aspects, a system for connecting multiple applications and extracting work related data from these applications. The technology further harmonizes and transforms the work related data into a common model that operates across different disparate systems. In doing so, the technology can manage a digital footprint created by an individual as they work across multiple applications (e.g., Software-as-a-Service (SaaS) cloud applications).

Abstract: Provided is a system, method, and computer program product for predicting product temperatures. The system includes at least one processor programmed or configured to collect, from temperature probes, temperature data of the plurality of different perishable products during a time period, collect, from at least one environmental sensor, environmental data of the at least one environment during the time period, generate a machine-learning model based on the temperature data and the environmental data, collect second environmental data from the at least one environmental sensor and/or from a separate data source while at least one package of at least one perishable product is in the at least one environment, and generate a predicted temperature of the at least one perishable product based on inputting the second environmental data into the machine-learning model.

Abstract: Training and risk management system and method are provided to improve team performance during trainings by simulating events for reducing risk to business. The system comprises computer simulation subsystem for simulating events in space and time for training, team performance measurement subsystem for evaluating the performance of the participants and computer vision subsystem for monitoring the participants' activities. A risk management platform contains a comprehensive asset list as required to build scenarios for risk simulations and allow access to other subsystems. Team performance can be continuously improved by feedback of the evaluation.

Abstract: A software application for use with mobile computing devices (e.g. smart phones and tablets) by financial planning experts in the field. The software application would be downloaded to the agent's computing device and will have constant communication to a remote server for processing and sending results to the expert's computing device. The expert will hand their computing device to the client who will then use the software application to input data relevant to their financial position. The central server will receive that data and send back alert results which will help to guide the discussion of financial planning.

Abstract: System, methods, and devices for measuring the performance of a component of a communications network recently installed by a technician using proactive network maintenance parameters, and further assessing the installation performed by the technician.

Abstract: Technology for a computer system that uses unsupervised machine learning (ML) for determining employment training opportunities that individuals can take to make the individuals better suited to fill skill gaps that exist in an enterprise (for example, a company that manufactures commercial products or provides commercial services). Some embodiments include remediation techniques. Some embodiments include a solutions-oriented toolset.

Abstract: Methods, systems, and apparatus for obtaining solutions to train and driver recovery problems using quantum computation. In one aspect, a method includes receiving data representing a train and driver recovery problem, wherein the train and driver recovery problem comprises a task of recovering from a disruption to a planned train and driver schedule; generating, based on the data representing the train and driver recovery problem, a quadratic unconstrained binary optimization (QUBO) formulation of the train and driver recovery problem, wherein the QUBO formulation excludes variables that relax constraints on driver duties; obtaining data representing a solution to the train and driver recovery problem from a quantum computing resource, wherein the data representing the solution to the train and driver recovery problem comprises an adjusted train and driver schedule; and initiating an action based on the obtained data representing a solution to the train and driver recovery problem.

Abstract: A method for workforce scheduling by a computer system is provided. The method includes receiving a first workforce schedule describing initial assignments of a plurality of workers to a plurality of shifts, each shift comprising one or more work activities, each work activity comprising an activity and a time interval, and storing the first workforce schedule in a memory. The method also includes receiving a cell size associated with each activity, and determining a quantity of workers in each work activity associated with each activity in the first workforce schedule. The method further includes determining cell size violations by dividing the quantity of workers assigned to each work activity by the cell size for the activity associated with the work activity. The method also includes modifying the first workforce schedule to minimize cell size violations, resulting in a second workforce schedule, and storing the second workforce schedule in the memory.

Abstract: A system for centralized status monitoring in a multidomain network. The system includes at least one processor and at least one memory device storing instructions that when executed configure the processor to perform operations. The operations include establishing connections with domains, receiving a first request from a first domain to initiate a monitoring operation, and generating a new entry in a status table stored in a first database. The operations also may include receiving a second request from the second domain to update the monitoring operation and, in response to receiving the second request, updating the new entry in the status table by modifying the status field. The operations may also include applying a monitor operation in response to receiving a third request from a monitoring engine and generating an alert comprising entries in the status table in which the status field matches the category status.