Abstract: A plurality of similar video pairs may be determined based on one or more similarity information types. Each video pair of the plurality of similar video pairs may include a first respective video and a second respective video. For each video pair, one or more similar scene pairs may be determined. Each of the one or more similar scene pairs may include a respective first scene from the first respective video and a second respective scene from the second respective video. An encoder may be trained using a contrastive learning model that contrasts a plurality of similar scene pairs with a plurality of random scenes. The plurality of similar scene pairs may include the one or more scene pairs for each video pair. One or more scene features of one or more other scenes of one or more other videos may be determined using the encoder.

Abstract: Disclosed are systems, methods, and non-transitory computer-readable storage media for managing projects in a content management system. In some embodiments, a content management system can generate a graphical user interface that presents a centralized view of a project. For example, the project can include project members, content items, tasks assigned to project members, communications between project members and activity history for the project. The graphical user interface can present this project data (e.g., project members, content items, tasks, communications, activity, etc.) so that a project member can easily and quickly view multiple aspects of the project.

Abstract: A method comprises reading data from a source database, identifying one or more data types corresponding to the source database, identifying a destination database for the data, and identifying one or more data types corresponding to the destination database. In the method, a destination database model to use in connection with writing the data in the destination database is generated. The generation of the destination database model is based at least in part on the one or more data types corresponding to the destination database, and is performed using one or more machine learning algorithms.

Abstract: A method is disclosed. The method is implemented by a robot engine that is stored as program code on a memory of a system. The program code is executed by a processor of the system, which enables robotic process automations of the robot engine. The processor is communicatively coupled to the memory within the system. The method includes initiating a guided operation of a platform presented by the system and monitoring the guided operation to observe an interaction with the platform or to receive a direct input by the robot engine. The method also includes executing a backend operation with respect to the interaction or the direct input.

Abstract: A corpus of textual data records, labeled by experts as corresponding to a defined characteristic, that comprise descriptions of problems with an item are collected. A language model generates a plurality of n-grams from the corpus. Frequently occurring n-grams are analyzed using a zero-shot learning model to determine similarity to the defined characteristic. N-grams highly similar to the defined characteristic may be selected as defined phrases. N-grams highly similar to another characteristic may also be selected to reduce false positives. The zero-shot model may also be used to determine a weighting factor for each defined phrase for each record. A relevance score is determined for a record by multiplying the weighting factors for each phrase that has a similarity score relative to the record above a threshold based on the expert labeling. The relevancy score may be used to automatically diagnose problems with the item.

Abstract: Disclosed are systems and methods for improving interactions with and between computers in content providing, searching and/or hosting systems supported by or configured with devices, servers and/or platforms. The disclosed systems and methods provide a novel framework that automatically generates and dynamically updates an interactive user interface (UI) that comprises digital information related to multiple processes and operations. The UI provides uniform functionality across platforms, devices and/or services being utilized to view and/or interact with the UI and/or interface objects (e.g., tiles) included therein. The UI provides a dynamic mechanism for assets to be controlled, as well as mechanisms to compare the data of different assets by which certain assets can be subsequently manipulated.

Abstract: Provided is a method, performed by a web browser, for identifying and displaying content, the method including receiving a webpage including text, comparing the text to titles of media content in a media content database, based on the comparison, identifying a subset of text as a match to a title of a matching media content, based on identifying the subset of text, modifying a display of the webpage by inserting a visual indicator into the webpage in proximity to the subset of text, or modifying the display of the subset of text, detecting an interaction of a user-controlled input with the inserted visual indicator or the modified display of the subset of text, and displaying a popup interface over a portion of the webpage, the popup interface displaying additional information about the matching media content and a selectable user-interface element to play the matching media content.

Abstract: The present disclosure is directed to systems and methods for enriching data. Specifically, the systems and methods disclosed enable the enrichment of data via matching, identifying composite data records, and utilizing Reference Source datasets. In one example aspect, Customer data is tokenized and then subsequently transmitted to a third-party Consolidation Platform. The Customer tokens may comprise multiple token records, wherein the multiple token records are displayed in the form of a bitmap. The bitmap may indicate which attributes in a Customer record may be present or absent. The composited Customer token records may then be matched to a Reference Source token set, wherein the matching analysis identifies missing data attributes in the Customer token set that the Customer may or may not already possess. The missing data attributes may be populated and/or updated in a Customer environment based on the Reference Source token set.

Abstract: Extracting data from traffic logs using regular expressions. A traffic log is received from a network device. A characterization of an extraction of data from the traffic log is determined. The traffic log is parsed by applying a first regular expression to the traffic log according to the characterization of the extraction of data from the traffic log to generate parsed data. Data is extracted from the traffic log by applying a second regular expression to the parsed data according to the characterization of the extraction of data from the traffic log to generate extracted data.

Abstract: Systems and methods include receiving a functional integrated circuit design and generating a plurality of place and route (PnR) layouts based on the received functional integrated circuit design and one or more integrated circuit floorplans may be generated. One or more fuzzy logic rules may be applied to analyze attributes associated with each of the generated PnR layouts, and a PnR layout of the plurality of PnR layouts having an area utilization complying with the one or more fuzzy logic rules may be generated.

Abstract: In a video processing method, a video frame sequence comprising a moving target is obtained. According to the video frame sequence and by processing circuitry of a neural network model, a motion state feature representing the moving target is obtained. The motion state feature is expressed in a time sequence of the video frame sequence. A result of matching between the motion state feature of the moving target and a motion state feature of a designated target is obtained. The moving target is determined as the designated target in response to a similarity between the motion state feature of the moving target and the motion state feature of the designated target being greater than a threshold. According to the motion state feature of the moving target and by using a classifier, a probability that the moving target pertains to an action category corresponding to the designated target is obtained.

Abstract: Embodiments disclosed herein describe systems, methods, and products to generate dynamic event trees that may be generated with ease and rapidly reconfigured. A computer may provide, e.g., through a web service, a user interface for a user (e.g., a trainer) to retrieve and customize event nodes from an event node database. The computer may also provide an event tree template where the user may simply drag and drop event nodes and use the dynamic event sequencers to generate hierarchical interconnections between the event nodes to generate a dynamic event tree. The computer may further execute a machine learning model that may recommend one or more event nodes. The computer may continuously train the machine learning model based upon the dynamic event tree and based upon whether the user has accepted the recommended event node.

Abstract: Methods, systems, and computer program products for providing a contextual dialogue framework over dynamic tables are provided herein. A computer-implemented method includes maintaining a context space for a natural language conversation of a user, wherein the context space comprises a dynamic set of one or more tables used for processing at least one query of the natural language conversation; obtaining an additional table associated with an additional query of the natural language conversation; discovering one or more implicit links between the additional table and the dynamic set of tables; updating the context space with the one or more implicit links; and answering the additional query based at least in part on the updated context space.

Abstract: The present disclosure provides methods and apparatuses for probabilistic procedure planning for generating a plan based on a goal relating to an end state. In some embodiments, a method includes receiving a request from a user to generate an action plan comprising T intermediate actions between a start state and the end state. The method further includes constructing an input query matrix based on T, the start state, the end state, positional encodings, and pseudo-random noise information. The method further includes generating, using a machine learning transformer decoder, the action plan based on the input query matrix and a plurality of learnable vectors. The method further includes providing the action plan to the user. The action plan indicates a probability distribution of a plurality of distinct action sequences, to be performed by the user, that transform the start state to the end state.

Abstract: A method for identifying an assignment of phase lines of an electrical distribution grid to connections of an electrical device capable of unbalanced-load operation, wherein the device is connected to a plurality of phase lines of the electrical distribution grid, includes setting target parameters assigned to an unbalanced load profile at each of the connections of the electrical device, detecting a temporal profile of a measurement parameter on each of the plurality of phase lines using a detection circuit, comparing the detected temporal profiles of the measurement parameters with the target parameters of the unbalanced load profile for each of the plurality of phase lines, respectively, and identifying the assignment of the phase lines to the connections on the basis of the comparison.

Abstract: With respect to an information processing device which anonymizes data composed of records including one or more items through statistical processing, the information processing device includes a memory, and a processor configured to classify respective records constituting the data into one or more first sets, based on masking target items, a dictionary, and a selected hierarchy level indicating a hierarchy level selected in the tree structure for each of the masking target items, classify the respective records into one or more second sets with respect to a number of records belonging to each of the one or more first sets, and calculate a number of records of each of the one or more second sets and a ratio of records belonging to each of the one or more second sets to the records, and display the ratio in each hierarchy level of each of the masking target items.

Abstract: An application for creating an editing a knowledge graph for document retrieval and exploration. The application may create a data structure, arranged as a directed acyclic graph (DAG), based on user input indicative of categories within a taxonomy and documents within an information repository. The DAG may have a top-level node, interior nodes, and leaf nodes. Interior nodes correspond to taxonomic classifications and point to other interior nodes or leaf nodes. Leaf nodes have corresponding interior nodes and include links to one or more documents in the information repository. The application permits editing of nodes, but does so in a way that preserves links to the arrangement of nodes prior to the editing. The application also permits traversal of nodes of the data structure via a user interface in which a representation of a given node includes an indication of one or more possible paths for reaching the given node.

Abstract: Computationally efficient and accurate methods of fitting black box simulation data to obtain Linear Parametrically Varying models useful for design of thermal management systems are disclosed. The Linear Parametrically Varying models may be used in dynamic simulations to determine temperatures in thermal systems. A computer-implemented model is run at a plurality of fixed values of the scheduling parameter to obtain output responses to excitations of the input at the fixed values of the scheduling parameter. LTI representations are fit to the output responses, the LTI representations having state-space variables characterized by negative real poles. Coefficient matrices of the LTI representations are updated, and an LPV-ROM representation is generated.

Abstract: Disclosed implementations provide executable models, such as artificial intelligence models that can be owned, traded, and used in various execution environments. By coupling a model with a strictly defined interface definition, the model can be executed in various execution environments that support the interface. Coupling the model with a non-fungible cryptographic token allows the model and other components to be owned and traded as a unit. The tradeable composite units have utility across multiple supported execution environments, such as video game environments, chat bot environments and financial trading environments. Additionally, the interface allows for the creation of pipelines and systems from multiple complementary composite units.

Abstract: One variation of a method for modeling neurological development includes: aggregating electroencephalography (EEG) data that comprise multiple EEG signals of each user in a set of users, EEG signals of each user recorded on multiple distinct dates, the set of users comprising a plurality of users of various known neurological statuses; identifying a synchronization pattern trend within the EEG data of the set of users; and correlating the synchronization pattern trend with neurological development within the set of users.

Abstract: A new product development system may provide, to one or more client devices and server devices, one or more tools to enable development of a new product. The new product development system may receive current project data identifying a current project for developing the new product, historical project data identifying historical projects for developing historical products, and industry data associated with the new product. The new product development system may process the current project data, the historical project data, and the industry data, with a machine learning model, to identify one or more variables for a predictive model and may process the one or more variables, with the predictive model, to predict a predicted success rate of the current project. The new product development system may perform one or more actions based on the predicted success rate of the current project.

Abstract: Provided herein are exemplary embodiments including a secure intelligent networked architecture for real-time precision care plan remote support including a secure intelligent data receiving agent having a specialized hardware processor and a memory, the secure intelligent data receiving agent configured to automatically receive a digital data element over a network from a Bluetooth® equipped peripheral device, the digital data element representing an output in response to a predetermined plan, the secure intelligent data receiving agent caching the digital data element within a non-relational database for short term storage and the secure intelligent data receiving agent configured to process the digital data element using a serverless compute functionality and configured with logic for anomaly detection.

Abstract: A method for determining a trajectory function to represent an aging state trajectory for at least one electrical energy storage unit of one or more devices includes determining uncertainty-containing model values of aging states of the at least one electrical energy storage unit, cleaning error-containing model values of the determined uncertainty-containing model values, determining the aging state trajectory based on the cleaned model values, and determining the trajectory function based on the determined aging state trajectory.

Abstract: Techniques for providing an enhanced search to generate a feed based on a user's interests are disclosed. In some embodiments, a system/process/computer program product for providing an enhanced search to generate a feed based on a user's interests includes receiving a plurality of interests associated with a user, searching online content including one or more websites (e.g., news or other content websites, social networking sites, and/or other online content) based on the plurality of interests associated with the user, receiving a plurality of web documents (e.g., links to websites, social networking sites, and other online content) based on the search for online content, ranking the plurality of web documents based on a document score and a user signal, and generating a content feed that includes at least a subset of the plurality of web documents based on the ranking.

Abstract: Aspects of the disclosure relate to enhancing hybrid traditional neural networks with liquid neural networks for cyber security and offense protection. A computing platform may receive a request to access enterprise organization data. The computing platform may compare the current request to previous requests to determine whether a similar request was previously processed. If a similar request was not previously processed, the computing platform may flag the request as a threat and may analyze the request. The computing platform may extract data from the request and may use the extracted data to generate rules, threat detection algorithms, and training models. The computing platform may use the rules, threat detection algorithms, and training models to train a deep learning neural network to identify and handle threats to an enterprise organization.

Abstract: The present invention is directed to a brand value growth and retention system for brand drugs commercialized by brand drug advertisers through a brand drug's lifecycle during patent exclusivity and after loss of exclusivity. The brand value growth and retention system iteratively analyzes combined computational models of consumer, healthcare provider retailer and payor segment data to produce brand drug promotional campaigns that are predictive with modifying parameters that transform the promotional campaigns over time. As a result, the brand drug promotional campaign generates an increased number of brand drug purchases while predicting the point where incremental promotional campaign investments produce a diminishing number of incremental brand drug purchases.

Abstract: Technologies for determining healthcare relationships include a healthcare insight computing device communicatively coupled to multiple patient data providers. The healthcare insight computing device is configured to determine one or more relationships between received data and previously received patient data associated with one or more patients. The healthcare insight computing device is further configured to correlate the ingested data as a function of the determined relationships and enrich the correlated patient data to form a new data element. Additionally, the healthcare insight computing device is configured to transmit the new data element to a raw data cluster such that visual representations of the data elements of the raw data cluster and the relationships there between can be displayed. Additional embodiments are described herein.

Abstract: One example method includes receiving, from an entity, a proposed entry for a ledger, where the ledger is shared and accessible by multiple users and includes a whitelist and a blacklist, determining, or assigning, a credibility score and rate limiter value for the entity, comparing the credibility score and rate limiter value with respective credibility score and rate limiter value thresholds, determining that the credibility score and rate limiter value meet or exceed the respective credibility score and rate limiter value thresholds, and submitting the proposed entry to the ledger.

Abstract: A chat bot capable of seamlessly acquiring, in response to user input in a chat session, information necessary for an appropriate chat scenario for assisting the user from an external system and dynamically generating a chat scenario. Accordingly, the chat bot control device includes an external data acquisition unit for acquiring, in a chat session between a user and a chat bot, chat scenario creation data for generating a chat scenario from a predetermined external system based on a first input from the user; a scenario generation unit for generating, based on the chat scenario creation data, a first chat scenario that specifies transitions of a dialogue between the user and the chat bot using predetermined scenario conversion logic that defines a chat scenario generation pattern; and a scenario execution unit for executing the first chat scenario in the chat session.

Abstract: Systems and methods are disclosed for triggering an update to a machine-learning model upon detecting that a distribution of particular (e.g., recently collected) input data set is sufficiently different from a distribution training input data set used to train the model. The distributions may be determined to be sufficiently different when a classifier can identify to which distribution individual data elements belong (e.g., to at least a predetermined degree). An update to the machine-learning model can include morphing weights used by the model and/or retraining the model.

Abstract: A method for detecting a two-qubit correlated dephasing error includes accessing a signal of a quantum system, where the quantum system includes a plurality of qubits. Every qubit has a nonzero rate of dephasing and some qubits have a nonzero rate of correlated dephasing. The signal further includes information about a matrix that includes diagonal elements and off-diagonal elements. The off-diagonal elements of the matrix are 2s-sparse. The method further includes performing randomized measurements of the off-diagonal elements of the matrix and recovering the matrix based on a direct measurement of the diagonal elements of the matrix.

Abstract: A method may include determining an action associated with field development planning or asset management of an oilfield based on a policy or value function and a state, simulating a reward of the action using information identifying the action and the state as inputs, generating an experience record based on executing the simulation, wherein the experience record identifies the simulated reward associated with the action and a current state or resulting state, storing the experience record in an experience buffer, wherein the experience buffer stores a plurality of previously generated experience records, updating the policy or value function based on the information stored in the experience buffer, selecting an action related to the field development planning based on the updated policy, and displaying information representing the action.

Abstract: Methods and apparatuses are described for intelligent imputation of missing data in a machine learning (ML) dataset comprised of a plurality of features. Each feature includes a plurality of values, where at least a portion of the values for one or more features are missing. A server analyzes the ML dataset to generate characteristics of the missing values in the ML dataset. The server selects an imputation algorithm for filling in the missing values based upon the identified characteristics. The server determines a computing environment in which the imputation algorithm is executed based upon one or more of a size of the ML dataset or the selected algorithm. The server generates code that comprises instructions for executing the imputation algorithm on the ML dataset in the computing environment. The server integrates the code into an ML platform that executes the code to assign replacement values to the missing values.

Abstract: A system may measure a response associated with a sample to an excitation. The system may compute, using the measured response and the excitation as inputs to an inverse model or a predetermined predictive model, model parameters on a voxel-by-voxel basis in a forward model with multiple voxels that represent the sample. The predetermined predictive model was trained using training data for different excitation strengths, different measurement conditions, or both. The forward model may simulate response physics occurring within the sample to a given excitation, and the model parameters may include magnetic susceptibilities of the multiple voxels. Moreover, the system may determine an accuracy of the model parameters by comparing at least the measured response and a calculated predicted value of the response using the forward model, the model parameters and the excitation. When the accuracy exceeds a predefined value, the system may provide the model parameters as an output.

Abstract: A system and method are provided for monitoring events in process management systems. The method is executed by a device having a communications module and includes obtaining first event data from a plurality of process management systems, each process management system being associated with a corresponding process flow; asynchronously from obtaining the first event data, providing second event data for at least two of the plurality of process management systems, to a monitoring tool, the second event data for the at least two process management systems being generated from a same client interacting with the at least two process management systems; and in response to providing the second event data to the monitoring tool, initiating at least one action to be executed.

Abstract: Devices, methods, and systems are provided for analyzing lung imaging data. A server computing device receives imaging data of a lung over a network from a client computing device and analyzes the imaging data to identify lung, airways, and blood vessels, segment the lung into lobes, subtract airways, calculate volumes, calculate emphysema scores, identify fissure locations, calculate fissure completeness scores. A reconstruction of the fissures indicating locations where the fissures are incomplete and a report comprising fissure scores, volumes, and emphysema scores are created.

Abstract: Exemplary embodiments of the present disclosure provide a method, apparatus, and computer-readable medium for sharing. An exemplary method includes receiving, by a user equipment (UE) having a plurality of connections, a description, and determining, by the UE, a correspondence between the description and the plurality of connections. The method further includes providing, by the UE, an option to share a subset of the plurality of connections that have a correspondence above a predetermined threshold.

Abstract: The present disclosure describes systems and methods for computer-moderated collaborative estimation among a population of human participants using a plurality of networked computing devices. A query (e.g., estimation prompt) may be presented to participants for collecting collaborative responses. The population of users may each set an initial estimation response to the prompt during an initial estimation time period, which is then followed by a collaborative estimation time period (during which all users are asked to produce an updated estimation response to the same prompt). A forbidden deadband region defines an area around each participant's initial estimation that the participant must move their variable slider out of in order for their slider to register as part of the collaborative real-time process. In some embodiments, a participant is not shown initial estimation responses of other participants until the participant has moved their slider out of the forbidden deadband region.

Abstract: One or more computing devices, systems, and/or methods for content recommendation based upon continuity and grouping information of attributes are provided herein. User interaction data specifying whether users interacted with content items, user attributes of the users, and content attributes of the content items is obtained. A data structure is populated with the user interaction data. The data structure is modified by inserting a set of sub-fields into the data structure for a user attribute. A sub-field is populated with a value representing an option of the user attribute. The set of sub-fields are an encoding of continuity information and grouping information representing options for the user attribute. The data structure is processed using machine learning functionality to generate a model. The model is utilized to generate a prediction as to whether a user will interact with a content item.

Abstract: A system and method perform assessments of technical systems or institutions by applying one or more standards of practice to one or more entities. The system and method may apply those one or more standards of practice in a distributed piece-meal fashion allowing less trained personnel to accomplish more assessments with lower cost and in less time.

Abstract: The accuracy of unsupervised anomalous sound detection is improved. An anomalous sound generation unit 12 generates a pseudo-anomalous sound by associating a sound obtained from a predetermined device with a probability distribution followed by a sound obtained from a desired device group. A threshold value setting unit 13 sets a threshold value so that all anomaly scores calculated from the pseudo-anomalous sound are determined to be anomalous. A parameter update unit 14 uses an obtained normal sound and an obtained anomalous sound, or a threshold value and a value based on the obtained anomalous sound, to update a parameter so to reliably determine an anomalous sound as anomalous and minimize the probability of determining a normal sound as anomalous.

Abstract: A unique implementation of a machine learning application for suggesting actions for a user to undertake is described herein. The application transforms a history of user behavior into a set of models that represent user actions given a set of parameters. These models are then used to suggest that users in a payments or banking environment take certain actions based on their history. The models are created using the DensiCube, random forest or k-means algorithms.

Abstract: Methods and systems for software analysis include determining a similarity score for an ordered input set and at least one ordered cluster set that represents a distance between the ordered input set and the at least one ordered cluster set. It is determined that he ordered input is similar to a first cluster of the at least one ordered cluster set, based on the similarity score. The ordered input set is merged to the first cluster of the at least one cluster set to generate a merged set that preserves an ordering of the ordered input set and the first cluster. Software analysis is performed using the merged set.

Abstract: An agent device that receives state information regarding a state of a vehicle from the vehicle, and receive a question from a user as question information; performs inference processing for the received question information and the received state information in order to infer an intent of the question; and acquires a response to the question based on the inferred intent.

Abstract: Configurations are disclosed for presenting virtual reality and augmented reality experiences to users. The system may comprise an image capturing device to capture one or more images, the one or more images corresponding to a field of the view of a user of a head-mounted augmented reality device, and a processor communicatively coupled to the image capturing device to extract a set of map points from the set of images, to identify a set of sparse points and a set of dense points from the extracted set of map points, and to perform a normalization on the set of map points.

Abstract: A method of transforming data including receiving data in a first language specific form, converting the data in the first language specific form to a language agnostic form, storing the data in the language agnostic form, converting the data in the language agnostic form to at least one second language specific form and exporting, on demand, the data in at least one of the at least one second language specific form.

Abstract: In one aspect, computer-implemented method may include, while a battery pack is charging, receiving, from sensors, measurements associated with the battery pack. The battery pack includes cells. The method may include separating the measurements into separate profiles for the cells, wherein the separate profiles include data pertaining to current, voltage, temperature, or some combination thereof. The method may include identifying, using the separate profiles, features, generating a training dataset by reducing the features based on a mean-comparison technique, a minority scaling technique, or both, and generating a trained machine learning model using the training dataset including the reduced features as labeled input and true lithium plating occurrence statuses as labeled output. The method may include predicting, using the trained machine learning model, an occurrence of lithium plating by inputting subsequently received data into the trained machine learning model.

Abstract: Aspects include receiving a document and classifying at least a subset of the document as having a first type of data. Features are extracted from the document. The extracting includes initiating processing of the at least a subset of the document by a first processing engine that was previously trained to extract features from the first type of data. The extracting also includes initiating processing of a remaining portion of the document not included in the at least a subset of the document by a second processing engine that was previously trained to extract features from a second type of data. The first type of data is different than the second type of data. Features are received from one or both of the first processing engine and the second processing engine. The received features are stored as features of the document.

Abstract: Disclosed herein are systems and methods for intelligent generation and display of insights using information in a data repository. For example, disclosed herein are methods for generating and displaying insights using initial data from a data repository, and intelligently/automatically proposing, generating, and displaying further insights using previously-generated insights.

Abstract: A method and associated system for providing artificial intelligence (AI) services. The method includes receiving an unfulfilled AI service request from a user interacting application operating on an operating system of a first user device. If the first AI service module in the first user device can process the unfulfilled request, processing the unfulfilled service request to generate and provide a fulfilled request and to the user interacting application. If the first AI service module cannot process the unfulfilled request, then transmitting the unfulfilled request to a second device with a second service module or a cloud AI service module generate a fulfilled AI service request. Then, transmitting the fulfilled AI service request to the user device, then to the user interacting application. The AI modules may operate across many different operating systems and types of devices. Updates from one AI modules may be pushed to other AI modules.