Abstract: Systems and methods for generating synthetic data are disclosed. For example, a system may include one or more memory units storing instructions and one or more processors configured to execute the instructions to perform operations. The operations may include receiving a dataset including time-series data. The operations may include generating a plurality of data segments based on the dataset, determining respective segment parameters of the data segments, and determining respective distribution measures of the data segments. The operations may include training a parameter model to generate synthetic segment parameters. Training the parameter model may be based on the segment parameters. The operations may include training a distribution model to generate synthetic data segments. Training the distribution model may be based on the distribution measures and the segment parameters.

Abstract: The present disclosure is directed to a crowdsourced problem-solution directory and a computer implemented, node-based system to inventory problems, needs, and solutions. Within this framework, individuals & teams can use their cognition and reasoning to identify and describe problems, goals, and solutions as well as their respective causal connections, and then use a computer interface to add this information to a shared database. This crowdsourced database will then represent a universal problem-solution object. This tree-like, multidimensional node network serves the purpose to inventory every problem, every goal, and every solution, as well as their casualties, represented as nodal connections.

Abstract: Systems and methods including one or more processors and one or more non-transitory computer-readable media storing computing instructions that, when executed on the one or more processors, cause the one or more processors to perform functions comprising: determining at least one fleet delivery route for delivery of one or more items of one or more orders to one or more locations using a vehicle fleet; dynamically shuffling the at least one fleet delivery route by at least evaluating a cost differential; when the cost differential satisfies a threshold: removing the first order from the source route; inserting the first order into the first other delivery route; and communicating the first order to a first other deliverer associated with the first other delivery route. Additional embodiments are disclosed herein.

Abstract: A method for receiving a historical incident data set with the historical incident data set including a plurality of data records, for each given data record of the plurality of data records, applying a causal analysis algorithm to determine a set of causal factor(s) for the historical instance of an incident corresponding to the given data record to obtain a problems and solutions data set, and automatically, and by machine logic, generating a chatbot based, at least in part, on the problems and solutions data set.

Abstract: Implementations of the present disclosure include actions of receiving search results that are responsive to the search query, the search results being respectively representative of resources, processing one or more triggering rules based on at least one of the search query and the search results, determining, based on processing the one or more triggering rules, that a set of data records is to be displayed in a search results page with the search results, the set of data records including data records that are specific to the user, determining a display prominence of at least one data record in the set of data records, the display prominence indicating a prominence of the at least one data record when displayed in the search results page, and providing the search results and the set of data records for display, the at least one data record being displayed based on the display prominence.

Abstract: The present disclosure is directed to input suggestion. In particular, the methods and systems of the present disclosure can: receive, from a first application executed by one or more computing devices, data indicating information that has been presented by and/or input into the first application; generate, based at least in part on the received data, one or more suggested candidate inputs for a second application executed by the computing device(s); provide, in association with the second application, an interface comprising one or more options to select at least one suggested candidate input of the suggested candidate input(s); and responsive to receiving data indicating a selection of a particular suggested candidate input of the suggested candidate input(s) via the interface, communicate, to the second application, data indicating the particular suggested candidate input.

Abstract: Per-viewer engagement-based video optimization is disclosed. A request for content associated with a first client is received. A model associated with the first client is obtained. The obtained model comprises at least one of behavior and playback preferences of a viewer associated with the first client. The obtained model is used to determine, for the first client, an optimal set of instructions usable to obtain content. A different set of instructions is determined to be optimal for a second client. The optimal set of instructions determined for the client is provided as output. The first client is configured to obtain content according to the optimal set of instructions determined for the first client.

Abstract: A method for training a character for a game is described. The method includes facilitating a display of one or more scenes of the game. The one or more scenes include the character and virtual objects. The method further includes receiving input data for controlling the character by a user to interact with the virtual objects and analyzing the input data to identify interaction patterns for the character in the one or more scenes. The interaction patterns define inputs to train an artificial intelligence (AI) model associated with a user account of the user. The method includes enabling the character to interact with a new scene based on the AI model. The method includes tracking the interaction with the new scene by the character to perform additional training of the AI model.

Abstract: A search device updates positions and momentums of a plurality of virtual particles, for each unit time from an initial time to an end time. The search device, for each unit time, calculates, for each of the particles, a position at a target time of a corresponding particle, calculates, for each of a plurality of nodes, a first accumulative value by cumulatively adding positions at the target time of two or more particles corresponding to outgoing two or more directed edges, calculates, for each of the nodes, a second accumulative value by cumulatively adding positions at the target time of two or more particles corresponding to incoming two or more directed edges, and calculates, for each of the particles, a momentum at the target time of a corresponding particle based on the first accumulative value and the second accumulative value.

Abstract: The present invention relates to a relation-enhancement knowledge graph embedding method and system, wherein the method at least comprises: performing collaborative coordinate-transformation on entities in the knowledge graph; performing relation core enhancement by means of relation-entropy weighting, so as to endow entity vectors with strong relation property; building an interpretability mechanism for a knowledge graph embedding model, and accounting for effectiveness and feasibility of the relation enhancement by proving convergence of the knowledge graph embedding model; and using a dynamic parameter-adjusting strategy to perform learn representation learning of to the vectors in the knowledge graph, and configuring deviation control to ensure accurate embedding.

Abstract: The present disclosure is directed to method for controlling an autonomous or human-driven vehicle that can include receiving, via a processor a vehicle communication indicative of a traffic flow parameter, and determining, based on the vehicle communication, a driver behavior characteristic, determining, via the processor and based on a historic driver behavior record, a driver performance characteristic, generating, via the processor, a first speed assignment and a lane assignment and associated with the vehicle and causing to transmit a first speed and lane assignment message to the vehicle. The system uses enhanced sensing technology within a connected environment to observe vehicle speeds and other vehicle patterns to ingest real-time, road network patterns of vehicle behavior, manages traffic through simulation, and sends messages to dynamic lane management controls such as signage, V2V communication, etc.

Abstract: Methods, computer-readable media, software, and system may generally build and quantify mobility patterns based on user location data, both at an individual level and an aggregate level. The system may determine the origin and destination data for each trip taken by a user. The system may then define areas of mobility using a mobility graph built from the data. The graph may include nodes and edges. In some examples, the nodes are constructed from the origins and destinations of the trajectories using spatial clustering techniques. Further, the edges between nodes may be constructed based on the trips between them, such as two nodes are connected by an edge if there is at least one trip between them. The edges may be given different weights based on trip frequencies. The system may then determine a region of mobility using the generated mobility graph and data clustering techniques.

Abstract: Provided herein are systems, methods, and computer readable medium for entering, identifying, and aggregating data for analysis data in an electronic device, wherein the data are from a plurality of multi-participant surveys.

Abstract: Systems and methods for processing documents based on a cardinal graph convolution network by generating cardinal graph representations representing words as single nodes with edges connected between neighbouring nodes in four cardinal directions. Features tensors are generated for nodes of the cardinal graph representation and the cardinal directions are encoded to generate an adjacency tensor having node neighbour indices. Entries of the adjacency tensor are transformed into a one-hot encoding of the node neighbour indices. Neighbourhood feature tensors are created over node indices and the features in each block may be scaled, convolved and reduced into new feature tensors.

Abstract: Systems and methods for a machine learning system to learn a new skill without catastrophically forgetting an existing skill and to continually learn in a self-supervised manner during operation, without human intervention.

Abstract: Cognitive determination of whether a message is suitable for sending over a data communications network can include extracting tokens from the message prior to transmitting the message. One or more intended recipients of the message can be determined from the tokens. A machine learning classification model corresponding to the one or more recipients of the message can be selected. The machine learning classification model can be constructed based on tokens extracted from prior messages, which are combined to create a plurality of documents for training the machine learning classification model. The one or more tokens extracted from the message can be classified using the machine learning classification model. An alert message can be generated in response to determining based on the classifying that the message is unsuited for sending.

Abstract: Individual nodes of a plurality of nodes can be fixed to the architectural structure and associated with a different segment of a plurality of segments of a first model of an architectural structure. Positional data associated with the nodes can be received. A structural change to the architectural structure can be estimated based on a comparison of positional data associated with the nodes. A second model representing the architectural structure as modified by the structural change can be generated. The second model can be generated based on (i) the first model and (ii) the estimated change to the architectural structure.

Abstract: An example system includes a processor to receive a query. The processor can retrieve ranked candidates from an index based on the query. The processor can re-rank the ranked candidates using a Bidirectional Encoder Representations from Transformers (BERT) query-question (Q-q) model trained to match queries to questions of a frequently asked question (FAQ) dataset, wherein the BERT Q-q model is fine-tuned using paraphrases generated for the questions in the FAQ dataset. The processor can return the re-ranked candidates in response to the query.

Abstract: The invention relates to a water level prediction system for a dam. The system includes a water level prediction module which is configured to (a) receive time series data, which relates to a water level of the dam, in real-time; and (b) predict, in real-time, a future water level of the dam by processing the received time series data in one or more predictive models/formula(s)/algorithm(s). The one or more predictive models/formula(s)/algorithm(s) may include a recurrent neural network (RNN) or RNN model/algorithm which is configured/trained to predict, in real-time, a future water level of the dam by using the received time series data in the RNN or RNN model/algorithm. The water level prediction module may also include at least one statistical model/algorithm which is configured/trained to predict, in real-time, a future water level of the dam by using the received time series data in the statistical model/algorithm.

Abstract: A method and system may input telemetry into a data structure. The telemetry may comprise a plurality of measurement results or other data collected from remote network nodes. Subscriber use metrics may be determined from the telemetry. From the use metrics and habits of the subscriber, user characteristics may be determined. A likelihood of service cancellation, based on the user characteristics, may be estimated in an embodiment. In another embodiment, a likelihood of receiving an inquiry from the subscriber at a subscriber support center may be estimated. Service enhancements may be proactively provided to the subscriber, based on the telemetry, the subscriber use metrics and the user characteristics in advance of service cancellation or receiving the inquiry. Last mile equipment may provide telemetry. The last mile equipment may include set top boxes, cellular phones, tablets and the like.

Abstract: Methods, computer-readable media, software, and apparatuses may retrieve, from an industry standard setting scoring system and for a vulnerability, a temporal score based on a pre-revision version of a scoring system, and predict, based on a machine learning model and based on the temporal score for the vulnerability, an updated temporal score based on a post-revision version of the scoring system. A mitigating factor score, indicative of a mitigation applied to the vulnerability by an enterprise organization, may be determined. A risk score may be generated for each vulnerability, as a composite of the updated temporal score and the mitigating factor score. The risk scores for vulnerabilities in a collection of vulnerabilities may be aggregated to determine an enterprise risk score for the enterprise organization. In some instances, the enterprise risk score may be displayed via a graphical user interface.

Abstract: Methods and systems for detecting and correcting anomalies include detecting an anomaly in a cyber-physical system, based on a classification of time series information from sensors that monitor the cyber-physical system as being anomalous. A similarity graph is determined for each of the sensors, based on the time series information. A subset of the sensors that are related to the classification is selected, based on a spectral embedding of the similarity graphs. A corrective action is performed responsive to the detected anomaly, prioritized according to the selected subset.

Abstract: Provided is a system and method for automated recommendation of new features for addition to an item based on user-generated feedback. In one example, the method may include receiving, via a user interface, a search query associated with an object, retrieving user-generated content that describes the object based on the received search query, identifying, via a machine learning model, one or more features to be added to the object based on the retrieved user-generated content, and outputting identifiers of the one or more features to be added to the object via the user interface.

Abstract: The present disclosure discloses a data mining method, a data mining apparatus, an electronic device and a storage medium, relates to the technical field of the Internet, and in particular to the Internet big data processing technology. The method includes: acquiring a current article to be mined; obtaining information values required for each data identification strategy of multiple data identification strategies from the current article, and each data identification strategy is used for identifying a preset type of data; identifying a data type of the current article according to the information values required for each data identification strategy to obtain a data type identification result; and determining whether the current article belongs to any preset type of data according to the data type identification result.

Abstract: The invention relates to a control system for controlling a brake, a steering and/or a drive of an autonomous or automated vehicle. This involves an artificial-intelligence-based first control apparatus being monitored by virtue of a criticality of a driving situation being determined on the basis of simple calculation values, wherein a specific criticality of the driving situation, or an inappropriate reaction by the first control apparatus to the driving situation, can result in changeover to a second control apparatus that undertakes the control of the vehicle on the basis of a deterministic calculation rule.

Abstract: Systems and methods for determining a predicted brain health of a first user and providing individualized health recommendations to the first user based at least in part on an artificial neural network trained on previously existing anatomical and functional neuroimaging information, behavioral information, self-reported information, and other types of information of a plurality of users. The artificial neural network may be capable of determining a predicted benchmark of brain health of the first user's information when compared with the previously existing users' information and storing the first user's anatomical and/or functional neuroimaging information, behavioral information, self-reported information, and other types of information in a database such that the artificial neural network can be re-trained based on the new information of the first user. The first user can be notified of his or her brain health and receive individualized health recommendations.

Abstract: A method, system and computer readable medium for generating a cognitive insight comprising: receiving data, the data comprising a plurality of examples, each of the plurality of examples comprising an input object and a desired output value, at least some of the plurality of examples being based upon feedback from a user; performing a machine learning operation on the data, the machine learning operation comprising performing an augmented gamma belief network operation, the augmented gamma belief network operation producing an inferred function based upon the data; and, generating a cognitive insight based upon the cognitive profile generated using the inferred function generated by the augmented gamma belief network operation.

Abstract: A method, system and computer readable medium for generating a cognitive insight comprising: receiving information regarding a temporal sequence of events; performing a temporal topic machine learning operation on the temporal sequence of events; generating a cognitive profile based upon the information generated by performing the temporal topic machine learning operation; and, generating a cognitive insight based upon the cognitive profile generated using the temporal topic machine learning operation.

Abstract: Described herein is a technique capable of optimizing a timing of a maintenance process. According to one aspect of the technique of the present disclosure, there is provided a method of manufacturing a semiconductor device including: (a) transferring a substrate to a process chamber, and performing a substrate processing; (b) receiving maintenance reservation information of the process chamber wherein a maintenance timing at which the process chamber enters into a maintenance enable state is determined by the maintenance reservation information; and (c) continuously performing the substrate processing after the maintenance reservation information is received in (b) until the substrate processing in the process chamber related to the maintenance reservation information is completed, stopping one or more substrates including the substrate from being transferred into the process chamber, and thereafter setting the process chamber to the maintenance enable state.

Abstract: Techniques for detecting and correcting anomalies in computer-based reasoning systems are provided herein. The techniques can include obtaining current context data and determining a contextually-determined action based on the obtained context data and a reasoning model. The reasoning model may have been determined based on one or more sets of training data. The techniques may cause performance of the contextually-determined action and, potentially, receiving an indication that performing the contextually-determined action in the current context resulted in an anomaly. The techniques include determining a portion of the reasoning model that caused the determination of the contextually-determined action based on the obtained context data and causing removal of the portion of the model that caused the determination of the contextually-determined action, to produce a corrected reasoning model.

Abstract: A computer-implemented method of performing queries using Artificial Intelligence (AI) database embeddings includes the operations of generating a plurality of vector embeddings describing a training data from a database for training a machine learning model. A test vector embedding is generated from the plurality of vector embeddings based on training data for unseen data from one or more rows of the database. One or more vectors from the plurality of vector embeddings describing the training data that are a closest match to the test vector embedding are identified. A task is determined based upon the unseen data. The determined task is performed using the trained machine learning model.

Abstract: A method for performing correlation-based parking availability estimation is provided. The method includes retrieving a plurality of parking availability correlation models, wherein each of the parking availability correlation models estimates parking availability for a target parking block based on parking availability for one or more other parking blocks; selecting a subset of the parking availability correlation models, wherein the subset comprises parking availability correlation models that estimate parking availability of the target parking block based on parking availability for one or more other parking blocks for which current parking availability is known; selecting a parking availability correlation model from the subset based on a model quality indicator associated with each parking availability correlation model; and estimating parking availability for the target parking block based on the selected parking availability correlation model.

Abstract: Implementations are directed to methods for providing an enhanced encounter via a holographic virtual assistant, including detecting, by one or more processors, an encounter request from a user, selecting a first encounter including a first holographic representation and a first dialog output, providing the first encounter for presentation to the user on the holographic virtual assistant, receiving, from the user, a first user reaction, the first user reaction including a first user dialog input and a first user engagement input, and training, using the first user reaction, a conversational goal model.

Abstract: Systems and methods are provided for creating and managing a data integration workspace. The workspace may comprise one or more views of data (or datasets) stored in or accessible by the system. Models may be generated and updated based on the plurality of datasets and presented via a graphical user interface. Feedback received via a graphical user interface presenting a model may be used to annotate an underlying dataset associated with the model. Responsive to a modification of the underlying dataset or the rules for using the underlying dataset to generate the model, other related datasets and/or models may be automatically updated accordingly. Templates associated with one or more types of users may be defined. Each template may comprise one or more specific models related to a specific type of user.

Abstract: A denial-of-service detection system includes a denial-of-service detection subsystem coupled to a plurality of storage systems via a network. The denial-of-service detection subsystem receives current first storage system data for each of a plurality of different storage system operating metrics from a first storage system included in the plurality of storage systems.

Abstract: The pull-type searching system provides an effective and efficient way to navigate deals and assist the user in identifying a deal for selection. The pull-type searching system further enables identification of one or more alternative deals to present to the user when no deals are identified for the selected search criteria. The pull-type searching system includes a method and apparatus. The method includes communicating ordered selectable search criteria, the search criteria including one or more categories, subcategories and deal types based on a user profile or available deals, or redemption goals. The method further includes receiving a selection from the search criteria and searching a deals database for results associated with the selection. Further, the method includes communicating the results associated with the selection, one or more alternative categories, or one or more alternative deals. A similar apparatus is provided.

Abstract: Methods and apparatus related to determining additional features for a user task entry of a user based on a user habit of the user. For example, one or more aspects of a user task entry of a user may be compared to one or more aspects of a user habit of the user to determine a correlation measure between the task entry and the user habit. If the correlation measure satisfies a threshold, one or more additional features of the user task entry may be determined based on the user habit. For example, the user habit may include one or more trigger indicators that indicate an actual entry or anticipated entry of the user into the user habit, and one or more of the trigger indicators may be utilized to determine task trigger indicators for the user task entry.

Abstract: The present disclosure provides an operation adjustment method and system for metro trains in a delay scenario. The method includes: acquiring basic parameters, current delay information and current online train information in a metro system; determining a detaining position of a departing train and an operation strategy of a waiting train according to the acquired; determining a next state of a running train according to the detaining position, the operation strategy, and the acquired; and optimally configuring an available rolling stock resource of the metro system according to the next state of the running train and operation data. The present disclosure can automatically adjust the operation diagram according to the delay information and reasonably change the operation plan of the rolling stock, so as to reduce influences of the delay on passengers and improve the actual fulfillment rate of the operation diagram.

Abstract: The present disclosure is for systems and methods for connecting offline machine learning training systems with online near-real time machine learning scoring systems. It is not trivial to connect an offline training environment with an online scoring environment. For example, offline training environments are usually static and contain large amounts of historical data that is needed for the initial training of models. Once trained, the model algorithms are then migrated into an online scoring environment for transactional or event based scoring. This migration effectively breaks the connection between the data in the offline environment and the model now running in the online environment. When new or shifting data occurs in the online environment, the static model running in the online environment goes unaltered to the changing inputs. The present disclosure solves the issues that are caused by the break in the offline and online environments.

Abstract: A computer system for recommending merchants to a candidate cardholder is provided. The computer system includes a memory device in communication with a processor. The processor is programmed to receive transaction information for a plurality of cardholders from a payment network. The transaction information includes data relating to purchases made by the cardholders at a plurality of merchants, the purchases satisfying a first criteria. The processor receives candidate cardholder preference information for at least one of the merchants input by the candidate cardholder. The computer system determines a merchant rank for each merchant based on the received transaction information and the candidate cardholder preference information, and determines a neutral merchant rank for each merchant based on the received transaction information and neutral cardholder preferences of the plurality of cardholders.

Abstract: Techniques for generating a user interface (UI) for a public safety user are provided. An event trigger may be received at a computing device associated with a public safety user. The event trigger may be associated with a public safety event. Historical interaction with at least one UI object by the public safety user when handling previous event triggers of the same type as the received event trigger may be determined. The historical interaction may be retrieved from a historical UI interaction data store. UI objects that the public safety user may interact with to handle the received event trigger may be identified based on the determined historical interaction. A UI may be generated to handle the received event trigger, the UI to handle the received event trigger including the identified UI objects.

Abstract: An example operation includes one or more of detecting, by a processor of a transport, an exit on a road, calculating, by the processor of the transport, a probability that the transport is not prepared to exit, requesting, by the processor of the transport, at least one other transport proximate to the transport to alter its speed if the probability exceeds a threshold, and responsive to a detecting of an altering of the speed by the at least one other transport, triggering the transport to exit the road.

Abstract: A system and methods for generating and applying learning agents in simulated environments, in which an agent simulation is selected, one or more agent goals are received, and agents are created which are individual instances of the agent simulation with each agent having at least one of the agent goals, wherein the agents are used in the execution of an environment simulation which dynamically changes based on the collective behavior of the agents.

Abstract: Systems and methods may make exchanging data in a neural network (NN) during training more efficient. Exchanging weights among a number of processors training a NN across iterations may include sorting generated weights, compressing the sorted weights, and transmitting the compressed sorted weights. On each Kth iteration a sort order of the sorted weights may be created and transmitted. Exchanging weights among processors training a NN may include executing a forward pass to produce a set of loss values for processors, transmitting loss values to other processors, and at each of the processors, performing backpropagation on at least one layer of the NN using loss values received from other processors.

Abstract: Methods, systems, and apparatus, including computer-readable media, for automated idle environment shutdown. In some implementations, activity of a server environment is monitored over a period of time. A measure of user-initiated activity of the server environment is determined based on the monitored activity of the server environment over the period of time. The level of user-initiated activity over the period of time is determined to be less than a threshold level. In response to determining that the level of user-initiated activity over the period of time is less than the threshold level, shut down of the server environment is initiated.

Abstract: Workers often forget to enter clockings indicating when they have arrived or left work or transferred between work activities. Various embodiments provide a system that predicts the risk of potential missed worker clockings and delivers alerts to the workers and/or their managers when that risk is high. The system analyzes historical data to find previous instances of missed clockings at an organization, extracts feature information regarding the context of the missed clockings, and calibrates a missing clocking risk model. The model is then used in either an online or batch mode to predict the risk of workers missing upcoming scheduled clockings. Based on these risk scores and system configurations, alerts are generated for employees and managers reminding them about the upcoming clockings and lowering the amount of missed clockings and subsequent remedies.

Abstract: A processing system may obtain a customer identifier at a first retail location of a telecommunication network service provider, determine a recency factor of the identifier, obtain an identification of items of interest to the customer, and determine whether the customer has visited a second retail location of the provider within a time period prior to the customer being at the first retail location. The processing system may then apply, to a fraud detection machine learning model, a plurality of factors comprising: a quantity of items of interest, a value of the items, a factor associated with whether the customer has visited the second retail location within the time period, and the recency factor, where the fraud detection machine learning model outputs a fraud indicator value, determine that the fraud indicator value meets a warning threshold and present a warning to a device at the first retail location.

Abstract: The disclosed embodiments provide a system for processing data. During operation, the system obtains a feature configuration for a feature. Next, the system obtains, from the feature configuration, an anchor containing metadata for accessing the feature in an environment. The system then uses one or more attributes of the anchor to retrieve one or more feature values of the feature from the environment. Finally, the system provides the one or more feature values for use with one or more machine-learning models.

Abstract: Systems and methods are disclosed that provide contextual tracking information to tracking sensor systems to provide accurate and efficient object tracking. Contextual data of a first tracking sensor system is used to identify a tracked object of a second tracking sensor system.

Abstract: Systems and methods for analyzing user behavior patterns to detect compromised computing devices in an enterprise network are provided. According to one embodiment, an enforcement engine running on a network security device, identifies top users of a network exhibiting a suspicious behavior relating to login failures by determining a first set of users having a number of login failure events during a given time duration exceeding a threshold. The enforcement engine identifies from the first set of computers associated with the top users, a second set of computers exhibiting a suspicious behavior relating to new connections exceeding a threshold. The enforcement engine classifies a third set of computers, representing a subset of the second set exhibiting a suspicious behavior relating to consecutive new connections, as compromised source computers when their respective new connections are in a sequence that results in a Shannon entropy measure exceeding a threshold.