Abstract: Embodiments of the present invention relate to methods, systems, and computer program products for managing a plurality of live comments. A plurality of live comments is obtained for a video, the plurality of live comments being associated with a plurality of fragments in the video, respectively. A plurality of features are extracted from the plurality of live comments, respectively. A knowledge base is generated for the plurality of live comments based on the plurality of features. With these embodiments, the live comments may be managed in an effective way. Further, the knowledge base may provide answers to a user query.

Abstract: A computer implemented method transforms data. Responsive to receiving a data transformation of an input string to an output string, a computer system identifies mappable tokens in the input string that are mappable to the output string. The computer system creates a set of initial mappings for a set of common tokens in the mappable tokens. The set of initial mappings maps the set of common tokens from the input string to the output string. The computer system creates a set of user mappings that maps the mappable tokens from input string to the output string using a user input to the set of initial mappings. The computer system generates program code that transform input strings to output strings using the set of user mappings that maps the mappable tokens from input string to the output string, wherein the program code is used to transform input strings to output strings.

Abstract: Embodiments of the present disclosure relate to a method, system, and computer program product for dynamic update of a computer program in memory. According to the method, one or more processors obtain incremental information, the incremental information specifying an incremental update to at least one section of at least one target function in a computer program. One or more processors identify, based on the incremental information, the at least one target function to be updated from the computer program. One or more processors generate at least one updated copy of the at least one target function by updating the at least one section of the at least one target function based on the incremental information. One or more processors update the computer program based on the at least one updated copy of the at least one target function while the computer program is running.

Abstract: Embodiments for a metadata predictor. An index pipeline generates indices in an index buffer in which the indices are used for reading out a memory device. A prediction cache is populated with metadata of instructions read from the memory device. A prediction pipeline generates a prediction using the metadata of the instructions from the prediction cache, the populating of the prediction cache with the metadata of the instructions being performed asynchronously to the operating of the prediction pipeline.

Abstract: A computer-implemented method according to one embodiment includes receiving a request to perform a transaction in persistent memory at a first node; implementing the transaction within a volatile transaction cache at the first node; determining parity data for the transaction at the first node; sending the parity data from the first node to a parity node; and transferring results of the transaction from the volatile transaction cache to the persistent memory at the first node.

Abstract: A phase change memory (PCM) cell includes an electrode, a heater electrically connected to the electrode, a PCM material electrically connected to the heater, a second electrode electrically connected to the PCM material, an electrical insulator surrounding the PCM material, and a shield positioned between the PCM material and the electrical insulator, the shield comprising a reactive-ion-etching-resistant material.

Abstract: Aspects of the invention include detecting an error alert from a target computer system. In response to detecting the error alert, performance data is then retrieved from the target computer system. A gated recurrent unit (GRU) neural network is used to generate a prediction of a root cause of the error alert based on the performance data. The weights of a reset gate of the GRU neural network are adjusted based on received feedback of the prediction.

Abstract: Methods are presented which include moving a self-stabilizing platform assembly with product disposed on a deck of the self-stabilizing platform assembly. The self-stabilizing platform assembly includes multiple torque-generating devices, a stability control system to control operation of the multiple torque-generating devices, and the deck to support the product being moved. The methods also include adjusting, by the stability control system, operation of one or more torque-generating devices of the multiple torque-generating devices to produce during the moving a stabilization torque within the self-stabilizing platform assembly to facilitate stabilizing the self-stabilizing platform assembly and product during moving of the self-stabilizing platform assembly and product.

Abstract: Methods and systems for similarity-based value-to-column classification are disclosed. A method includes: receiving, by a computing device, a natural language search query; determining, by the computing device, a filtering phrase in the natural language search query using a natural language understanding model; encoding, by the computing device, the filtering phrase; retrieving, by the computing device, a plurality of encoded columns; for each of the plurality of encoded columns, the computing device determining a similarity score based on a similarity between the encoded filtering phrase and the encoded column; and outputting, by the computing device, a column corresponding to an encoded column of the plurality of encoded columns having a highest similarity score.

Abstract: Mechanisms are provided to implement a visual analytics pipeline. The mechanisms generate, from an input database of records, a chronology-aware graph data structure of a plurality of records based features specified in an ontology data structure. The chronology-aware graph data structure has vertices representing one or more of events or records based features corresponding to events, and edges representing chronological relationships between events. The mechanisms execute a chronology-aware graph query on the chronology-aware graph data structure to generate a filtered set of vertices and corresponding features corresponding to criteria of the chronology-aware graph query.

Abstract: In response to receiving a request for an identity key from a first entity, an identity key for the first entity is generated. A first request from the first entity to replicate a set of data is received. The generated identity key for the first entity is added to the metadata of the set of data requested to be replicated. A determination is made whether a replication rule exists for the first entity. In response to determining that a replication rule exists for the first entity, the set of data is replicated according to the replication rule for the first entity.

Abstract: Datasets can be synchronized across cloud-based computer environments using computer systems. A data map can be generated for source datasets for a plurality of computing environments, respectively, and an activation function can be determined based on the data map, for simultaneously activating a new dataset of a source system from one of the plurality of computing environments. A generation ID (identification) can be shared from the source system with one or more computing environments of the plurality of the computing environments, in response to receiving the activation function. The new dataset of the source system can be replicated across the one or more computing environments. A data synchronization trigger can be activated, using a synchronization coordinator module of the computer, and the data synchronization can be completed across the plurality of computing environments.

Abstract: Methods for creating a knowledge graph for a video are disclosed. Aspects include obtaining the video, processing the video to extract audio information and video information, and storing the extracted audio information and video information with a timestamp corresponding its occurrence in the video. Aspects also include creating a plurality of groups of the extracted audio information and video information based at least in part on the timestamps and extracting two or more keywords from each of the plurality of groups. Aspects further include identifying a relationship between the two or more keywords based on the extracted audio information and video information and creating a graph having a plurality of nodes and a plurality of links that connect a pair of nodes of the plurality of nodes. Each node corresponds to an extracted keyword and each link corresponds to the identified relationship between the pair of nodes.

Abstract: A marking onto a collaboration board, located in a first location, is detected. The marking includes the creation of one or more content elements on the collaboration board. Responsive to detecting the markings one or more content elements on the collaboration board are analyzed. A first content element of the one or more content elements is classified based on analyzing the one or more content elements. The first content element is classified as a first privileged content element. The first location of the collaboration board is scanned. The scanning is based on the classifying of the first privileged content element. An unauthorized person is identified based on scanning the first location. The unauthorized person is not permitted to view the collaboration board. A security response is performed on the collaboration board regarding the one or more content elements. The security response is performed responsive to identifying the unauthorized person.

Abstract: An example system includes a processor that can receive conversation logs of a dialogue system to be analyzed. The processor can train a predictive machine learning model using a training set of the conversation logs on a selected feature to obtain feature values with associated importance values. The processor can select a number of feature values using a significance score calculated based on the associated importance values. The processor can generate an interactive user interface including the selected number of feature values.

Abstract: An approach for managing data set access based on data set relevance. The approach monitors data set access activities associated with a user. The approach detects access of a first data set by the user. The approach determines a group of data sets associated with the first data set based on a data set mapping associated with the user. The approach recalls one or more data sets of the group of data sets from a slower storage device to a faster storage device.

Abstract: Mechanisms are provided to generate a test dataset for software application development. A baseline mixed reality (MR) environment simulation of an existing process is generated that models applications of an application landscape. A requirement for an application that is to be developed is received and a MR component model is generated to represent the application based on a machine learning computer model processing of the requirements data structure and a knowledge corpus. The MR component model modifies the baseline MR environment simulation, and executes the modified MR environment simulation to simulate the modified MR environment simulation. The simulation is monitored for user input specifying a contextual scenario and context data is collected from the MR component models of the modified MR environment simulation. A test dataset for testing a coded version of the SUD application is generated based on the contextual scenario and the collected data.

Abstract: A method, computer system, and a computer program product for securing visible data is provided. The present invention may include encrypting an on-screen data rendered on a display of an endpoint device. The present invention may also include authenticating an external decryption device within a periphery defined by the endpoint device. The present invention may further include decrypting the encrypted on-screen data on the authenticated external decryption device.

Abstract: Mechanisms are provided to improve an output of a trained machine learning (ML) computer model based on label co-occurrence statistics. For a corpus, label vector representations of the knowledge data structures are generated. Co-occurrence scores for each pairing of labels, across the label vector representations, are generated. A vector output of the ML computer model is received and a knowledge driven reasoning (KDR) computer model is configured with threshold(s) and delta value(s) specifying condition(s) of a co-occurrence of a first label in the output with a second label in the plurality of labels which, if present, causes the delta value(s) to be applied to modify a probability value associated with the second label in the output of the ML computer model. The KDR computer model is executed on the output of the ML computer model to modify probability value(s) in the output.

Abstract: A level of classification for each piece of data of one or more pieces of data is determined. A layer of encryption for each piece of data of the one or more pieces of data is determined. A type of encryption for each piece of data of the one or more pieces of data is determined. Other mechanisms applied to each piece of data of the one or more pieces of data is determined. A first constant for the layer of encryption, a second constant for the type of encryption, a third constant for the other mechanisms applied is determined. A risk factor for each piece of data of the one or more pieces of data is determined.

Abstract: A method, computer program product, and computer system are provided. A microservice formats a request to a process management microservice and to another microservice to perform an operation on behalf of the microservice. The process management microservice validates the requested operation. Based on the requested operation being valid, process management sends the requested operation to the other microservice. The process management microservice updates the microservices registry with a status of the microservice and the other microservice. The microservice and the other microservice update their respective local status registries.

Abstract: Techniques for generating a set of Deep Learning (DL) models are described. An example method includes training an initial set of DL models using the training data, wherein a topology of each of the DL models is determined based on the parameters vector. The method also includes generating a set of estimate performance functions for each of the DL models in the initial set based on the set of edge-related metrics, and generating a plurality of objective functions based on the set of estimated performance functions. The method also includes generating a final DL model set based on the objective functions, receiving a user selection of a selected DL model from the final DL model set, and deploying the selected DL model to an edge device.

Abstract: A method, computer system, and a computer program product for anomaly detection is provided. The present invention may include converting business process logs into a graphical data structure. The present invention may include generating an optimized graph encoding for anomaly detection using an unsupervised machine learning model. The present invention may include computing an anomaly score for each activity of the business process log using a process aware metric based on feature representation. The present invention may include labeling each of the one or more data points with a high anomaly score.

Abstract: Revising a delivery route for a user based on, at least, identified disruptions is provided. A computer device identifies delivery parameters for a delivery, wherein the delivery parameters include (i) a delivery route from a shipping location to a delivery location, and (ii) one or more delivery constraints. The computing device displays the delivery route on a graphical user interface (GUI), wherein the GUI is configured to be interacted with by one or more users. The computing devices receives from a user via the GUI, a definition of an environmental disruption. The computing device generates a revised delivery route, wherein the revised delivery route modifies the delivery route to avoid the environmental disruption while satisfying the one or more delivery constraints. The computing device displays the revised delivery route on the GUI.

Abstract: Systems, methods, and computer programming products for dynamically managing the uninstallation and/or re-installation of software applications stored or accessed by a computing system, including mobile devices. Management of the applications by the system can be periodically managed automatically or based on recommendations. Management of applications being uninstalled or reinstalled may be determined based on a rate a user accesses the application and/or data published or accessible by an application storefront, such as user reviews, storefront rankings, user feedback and uninstallation rates of the applications by other users. Applications experiencing a decreased level of average user satisfaction below a predetermined threshold can be proposed for deletion or automatically deleted. Replacement of underperforming or unsatisfactory applications with alternative applications having similar functionality but a higher rate of user satisfaction can be recommended or installed.

Abstract: Mechanisms are provided for scheduling a workload in a cloud computing system. A cloud affinity factor (CAF) computer model is trained, via a machine learning process based on a training dataset comprising static characteristics of a workload binary for a workload, and dynamic characteristics corresponding to historical performance data for the workload, such that the trained CAF computer model predicts a performance classification for a given workload binary. The trained CAF computer model processes a new workload to generate a performance classification for the new workload. Cloud affinity factor(s) are generated based on the performance classification for the new workload. Node affinity and dispatch rule(s) are applied to the cloud affinity factor(s) to select one or more nodes of the cloud computing system to which to dispatch the workload. The workload is then scheduled on the selected one or more nodes.

Abstract: Methods, systems, and computer program products for auto-discovery of reasoning knowledge graphs in supply chains are provided herein. A computer-implemented method includes obtaining a spatiotemporal query related to a demand of at least one product in a supply chain; analyzing the spatiotemporal query to identify one or more parameters affecting the demand of the at least one product, wherein the one or more parameters comprise at least one of one or more climate parameters and one or more disruptive event parameters; generating a knowledge graph comprising information indicating an impact on the demand of the at least one product for at least a portion of the one or more parameters; and outputting, to a user interface, an explanation of a predicted demand forecast for the at least one product based at least in part on the knowledge graph.

Abstract: Methods, systems, and computer program products for facilitating user selection using trend-based joint embeddings are provided herein. A method includes obtaining a selection of an item in an online catalog; determining a compatible item of the plurality of items at least in part by providing the selected at least one item and at least one previously selected item corresponding to the user to a trend-based machine learning model, wherein the trend-based machine learning model is trained on historical data associated with the item in the online catalog and fine-tuned based on current trend data from multiple data sources; receiving feedback in response to outputting the at least one compatible item; identifying one or more attributes related to the at least one compatible item based on the feedback; and using the trend-based machine learning model to determine at least one additional compatible item based on the one or more attributes.

Abstract: An approach is provided in which the approach receives an image that includes multiple image points and constructs a plane in the image based on a first subset of the plurality of image points. The approach identifies a second subset of the image points that belong to the plane and are not part of the first subset of image points, and removes the first subset of image points and the second subset of image points form the image points. The approach annotates the remaining subset of image points in the image.

Abstract: Methods, computer program products, and systems are presented. The method computer program products, and systems can include, for instance: predicting an exhibited sentiment of a certain user on being presented one or more candidate education segment, wherein the predicting is in dependence on historical sentiment parameter values of one or more user on being exposed to presented educational content, the historical sentiment parameter values being stored in a data repository, wherein the presented education segments comprise digital media content adapted for playing by a digital media player; selecting at least one of the one or more candidate education segment in dependence on a result of the predicting so that a selected at least one of the one or more candidate education resulting from the selecting is personalized for the certain user; and presenting to the certain user the selected at least one of the one or more candidate education segment.

Abstract: A method and system of training a spoken language understanding (SLU) model includes receiving natural language training data comprising (i) one or more speech recording, and (ii) a set of semantic entities and/or intents for each corresponding speech recording. For each speech recording, one or more entity labels and corresponding values, and one or more intent labels are extracted from the corresponding semantic entities and/or overall intent. A spoken language understanding (SLU) model is trained based upon the one or more entity labels and corresponding values, and one or more intent labels of the corresponding speech recordings without a need for a transcript of the corresponding speech recording.

Abstract: Machine-learning-based determination of event stability is provided to facilitate loose coupling of event coordination systems. The method includes training a machine learning model to determine stability of events of an event coordination system based on a plurality of attributes of the events, and using the machine learning model to determine an event stability for an event of the event coordination system. Further, the method includes comparing the determined event stability for the event to a stability threshold, and determining that the event is a stable event based on the event stability extending the stability threshold. Based on determining that the event is the stable event, the stable event is propagated from the event coordination system to another event coordination system.

Abstract: A system and method are disclosed that utilizes an artificial intelligence based virtual proxy node. The virtual proxy node includes an intent resolution model and communicates between a smart audio device and at least one secondary device, wherein the at least one secondary device is configured to be controlled by a smart audio device or smart hub. The virtual proxy node tracks interactions between the smart audio device and the at least one secondary device to derive historical and context data from the tracking interactions. The virtual proxy node uses the historical and context data to predict which secondary device will be successful in responding to the user input command and broadcasts the input command to the virtual proxy node associated with one of the at least one secondary device. The virtual proxy node includes an intent resolution model trained by historical and context data.

Abstract: A method for managing network service response times by a client device is provided. The client device determines whether a network service of a service provider is reachable or active and determines a service response time of the service provider. The client device communicates to the service provider a request to establish a conditional connection based on an average accept service time of a connection and a maximum service response time.

Abstract: An approach for dynamically transitioning mobile client devices from one location to another within edge computing is disclosed. The approach includes retrieving locations for near edges and far edges and collecting one or more SCC (security compliance center) rules. The approach includes identifying edge access from one or more client devices and determining mobility pattern associated with the edge access. The approach includes determining edge recommendation based on the mobility patterns and applying the edge recommendation.

Abstract: Systems, computer-implemented methods, and computer program products that facilitate vulnerability and attack technique association are provided. According to an embodiment, a system can comprise a memory that stores computer executable components and a processor that executes the computer executable components stored in the memory. The computer executable components can comprise a map component that defines mappings between vulnerability data representing a vulnerability of a computing resource and attack data representing at least one attack technique. The computer executable components can further comprise an estimation component that analyzes the mappings to estimate a probability that the vulnerability will be exploited to attack the computing resource.

Abstract: Systems, computer-implemented methods, and computer program products to aggregate classifier result are provided. According to an embodiment, a system can comprise a memory that stores computer executable components and a processor that executes the computer executable components stored in the memory. The computer executable components can comprise a fractal dividing component that can train classifiers with fractally defined disjoint and non-disjoint subsets of training data comprising data with a first label and data with a second label. Further, the system can include training component that can train the group of classifiers with the fractally defined disjoint and non-disjoint subsets of training data. A fractal aggregating component can be included to generate a unified result of the classifiers by fractally aggregating results of classification by the ones of the classifiers, based on the subsets.

Abstract: A computer-based method, system, and computer program product for automatically identifying significant events for food traceability. The method may comprise receiving a series of events from an agriculture supply chain entity, automatically determining, at a machine learning model of an event analysis module, one or more events in the series having a significance for food traceability greater than a threshold, and automatically reporting the one or more events to a ledger.

Abstract: A computer-implemented method and a computer system establish network slices within a physical network having a plurality of network elements. The method includes receiving a request to instantiate a network slice at a network element. The method also includes determining a performance metric of the network element. The method further includes delaying instantiation of the requested network slice within the network element in response to determining that the performance metric of the network element is below a threshold. The method also includes instantiating the requested network slice within the network element in response to determining that the performance metric of the network element is at or above the threshold. Finally, the method includes deactivating the requested network slice in response to determining that the performance metric of the network element is below the threshold at a time subsequent to instantiating the requested network slice.

Abstract: One or more computer processors establish a geofence surrounding a display having a plurality of pixels capable of change based on one or more display capabilities. The one or more computer processors monitor for a change in at least one pixel of the plurality of pixels. The one or more computer processors identify a photosensitive user within the established geofence. The one or more computer processors responsive to the at least one pixel change associated with the display, calculate a photosensitivity score utilizing a model trained for one or more photosensitive conditions associated with the photosensitive user. The one or more computer processors adjust the display to show a change on the at least one pixel based on the calculated photosensitivity score.

Abstract: An optical module includes an optoelectronic assembly and a heat spreader. The optoelectronic assembly includes a flat, rigid substrate, an array of electrical contacts positioned on a first portion of the substrate, and an optoelectronics assemblage that is electrically connected to the array of contacts and is positioned apart from the array of electrical contacts. The heat spreader is comprised of a thermally conductive material and comprises a second portion that is structurally connected to the first portion and a third portion that is thermally connected to the optoelectronics assemblage.

Abstract: A secure communication tunnel between user space software and a client device can be established. A private session key can be communicated from the user space software to a network communication device via an application programming interface. Outbound session packets can be communicated from the user space software to the network communication device. The network communication device can generate encrypted outbound session packets by encrypting the outbound session packets using the private session key; communicate to the client device, via the secured communication tunnel, the encrypted outbound session packets; receive, by the network communication device from the client device, via the secured communication tunnel, inbound session packets; generate decrypted inbound session packets by decrypting the inbound session packets using the private session key; and communicate the decrypted inbound session packets.

Abstract: An example operation may include one or more of establishing a communication channel between a sending system and a receiving system, executing an oblivious transfer protocol between the sending system and the receiving system via the established communication channel, wherein the oblivious transfer protocol provides the receiving system with a functional encryption key based on a data vector of the receiving system without the sending system learning the data vector, committing to the functional encryption key using a cryptographic commitment and signing the functional encryption key commitment with a digital key of the receiving system, and storing the signed functional encryption key commitment to a blockchain.

Abstract: Methods, computer program products, and/or systems are provided that perform the following operations: determining a pacing requirement for host requests based on one or more thresholds; setting a pacing delay level based on the one or more thresholds in response to the determination of the pacing requirement; and implementing a memory request flow for a host request based on the pacing requirement and the pacing delay level.

Abstract: Deployment updates in multivendor cloud environments are provided by obtaining, from an administrative user, deployment objectives for a network deployment; identifying currently deployed infrastructure in the network deployment; identifying information sources to provide information for evaluating candidates for additional infrastructure to include in the network deployment to meet the deployment objectives; performing a cognitive computing analysis based on the deployment objectives to identify a configuration of the network deployment that includes the additional infrastructure selected from the candidates provided by the information sources; and providing the administrative user with the configuration.

Abstract: A computer-implemented method is provided that includes accessing candidate text and a candidate pair including first and second phrases, substituting the first and second phrases into cause-effect patterns to generate variant sentences. An artificial intelligence model is leveraged to determine respective probabilities that the variant sentences are inferred from the candidate text, calculate a statistical measure of the respective probabilities, and assess the calculated statistical measure to ascertain whether the first and second phrases possess a causal relationship or non-causal relationship to one another. A knowledge base including one or more pairs of cause-effect phrase pairs is populated with the first and second phrases possessing the causal relationship. A computer system and a computer program product are also provided.

Abstract: An example operation may include one or more of receiving a request for blockchain information from a user device, acquiring blockchain data from a plurality of blockchains which are actively operating and available for joining, determining an amount of trust for each blockchain among the plurality of blockchains based on acquired blockchain data of the respective blockchain, and outputting a list identifying the plurality of blockchains where each blockchain on the list comprises a trust indicator indicating a determined amount of trust for the respective blockchain.

Abstract: Systems and techniques that facilitate background monitoring of eye health are provided. In various embodiments, a system can comprise a sensor component of a device. In various aspects, the sensor component can detect one or more physical characteristics associated with an entity. In various embodiments, the system can further comprise a diagnostic component of the device. In various instances, the diagnostic component can estimate in a background of the device a health condition of an eye of the entity based on the one or more physical characteristics. In various cases, estimating the health condition in the background of the device can facilitate real-time monitoring of the eye health of the entity without interrupting the entity's normal use of the device.

Abstract: Techniques regarding discovering configuration information for one or more computer applications are provided. For example, one or more embodiments described herein can comprise a system, which can comprise a memory that can store computer executable components. The system can also comprise a processor, operably coupled to the memory, and that can execute the computer executable components stored in the memory. The computer executable components can comprise a configuration component that can discover configuration information associated with a containerized computer application. The configuration information can be characterized by a set of environment attributes extracted by querying a source code of the containerized computer application.

Abstract: In an approach for optimization of integer arithmetic expressions implemented as a Boolean logic circuit, a processor converts arithmetic operators in an arithmetic expression into adders. A processor identifies a topological order of the adders. A processor merges the adders based on the topological order into a multi-operand adder. A processor converts the multi-operand adder to a compressor tree and a two-operand adder. A processor performs the arithmetic expression based on the converted multi-operand adder.