Abstract: Methods, systems, and apparatus, including computer programs encoded on computer-storage media, for obtaining inventory data associated with a product or service; generating, using the inventory data, a monotonically increasing function indicative of cumulative demand; predicting future inventory events using the monotonically increasing function and a machine learning model that includes survival curve analysis; in response to predicting future inventory events using the monotonically increasing function of data and survival curve analysis, generating an instruction configured to procure one or more items of inventory; and transmitting the instruction to an inventory system.

Abstract: Aspects of the present disclosure provide systems, methods, and computer-readable storage media that support ontology driven processes to generate digital twins using a partially automated process. To generate the digital twin, an ontology may be obtained and used to generate a multi-layer probabilistic knowledge graph as a digital twin. A first layer may include a domain ontology knowledge graph that is generated based on the ontology. A second layer may include a probabilistic ontology graph model that is automatically generated based on the domain ontology knowledge graph. A third layer may include a decision optimization model that represents decisions that optimize variable(s) included in the second layer. The digital twin based on this multi-layer probabilistic knowledge graph may enable improved querying of semantic information, probability distributions, and decision information from a single model without requiring a user to be trained in probability theory to set up the digital twin.

Abstract: In some implementations, a robot controller may receive a list of a set of items based on one or more orders. The robot controller may determine a set of locations relative to a reference location, a set of weights, and a set of volumes associated with the set of items. The robot controller may receive a weight constraint and a size constraint associated with a robotic device. The robot controller may pack a group of items, consisting of a subset of the set of items, based on minimizing a total distance associated with the group based on the set of locations and satisfying the weight constraint and the size constraint based on the set of weights and the set of volumes. The robot controller may transmit instructions to the robotic device to retrieve the subset of the set of items in the group.

Abstract: Example computer-implemented methods, media, and systems for improving experience and performance of applications over 5G networks are disclosed. One example computer-implemented method includes establishing multiple signaling message quality of service (QoS) flows of an application over a communications network. Multiple data message QoS flows of the application are established over the communications network. The multiple signaling message QoS flows are sent to a user device through an ultra-reliable low latency communication (URLLC) slice over the communications network. The multiple data message QoS flows are sent to the user device through an enhanced multimedia broadband (eMBB) slice of the communications network. The multiple signaling message QoS flows are mapped to first multiple data radio bearers (DRBs). The multiple data message QoS flows are mapped to second multiple DRBs.

Abstract: Aspects of the present disclosure provide systems, methods, and computer-readable storage media that support ontology driven processes to generate digital twins having extended capabilities. To generate the digital twin, an ontology may be obtained and modified to define additional types of data, such as events and metrics, for incorporation into the digital twin. The ontology, once modified, may be instantiated as a knowledge graph having the additional types of data embedded therein. The embedded data may be used to convert the knowledge graph to a probabilistic graph model that may be queried to extract information from the digital twin in a probabilistic manner. Additionally, multiple ontologies may be utilized to create a digital twin-of-digital twins, which enables more complex digital twins to be generated (e.g., digital twins of entire ecosystems), and enables new insights and understanding of the various components and interactions between the components of the ecosystem.

Abstract: The present disclosure relates to systems, methods, and products for optimization of a chromatography purification process using a physics-informed neural network. The method includes inputting a plurality of process parameters into the physics-informed neural network to obtain a predicted output; calculating a loss function based on a set of governing equations, as set of constraints, and the predicted output; determining whether the physics-informed neural network is convergent based on the calculated loss function; in response to the physics-informed neural network being convergent, exporting the physics-informed neural network; and in response to the physics-informed neural network not being convergent: updating a plurality of weights in the physics-informed neural network, and inputting the plurality of process parameters to the physics-informed neural network for a next convergence iteration to calculate the loss function and determine whether the physics-informed neural network is convergent.

Abstract: Aspects of the present disclosure provide systems, methods, and computer-readable storage media that support ontology driven processes to create digital twins that extend the capabilities of knowledge graphs. A dataset including an ontology and domain data corresponding to a domain associated with the ontology is obtained. A knowledge graph is constructed based on the ontology and the domain data is incorporated into the knowledge graph. The knowledge graph is exploited to derive random variables of a probabilistic graph model. The random variables may be associated with probability distributions, which may include unknown parameters. A learning process is executed to learn the unknown parameters and obtain a joint distribution of the probabilistic graph model, which may enable querying of the probabilistic graph model in a probabilistic and deterministic manner.

Abstract: The present disclosure relates to systems, methods, and products for adaptive design and optimization using a physics-informed neural network (PINN). The system includes a non-transitory memory and a processor. The processor executes instructions to cause the system to: input collocation points and design parameters into the PINN to obtain an output; calculate a loss function based on a set of governing equations and the output; determine whether the PINN is convergent based on the calculated loss function; in response to the PINN being convergent, export the PINN; and in response to the PINN not being convergent: determine whether to resample the collocation points; determine an optimum number of collocation points; determine a set of optimal network parameters for adjusting the PINN; and input the collocation points and the set of optimal network parameters to the PINN for a next iteration.

Abstract: A method and device for automatically generating personalized smart contracts is disclosed. The method includes identifying a plurality of asset attributes associated with a current asset within a blockchain network. Each of the plurality of asset attributes are compared with each of a plurality of asset clusters to compute a cluster similarity score, when a plurality of assets within the blockchain network do not include the current asset. The method includes identifying an asset cluster that has the highest cluster similarity score and which is also above a predefined threshold. Similarity scores are then computed for each of the set of assets within the asset cluster. At least one asset from the set of assets is then identified based on the associated similarity scores. A current smart contract template is generated based on at least one smart contract template associated with the at least one asset.

Abstract: A method and device for generating data services from heterogeneous systems is disclosed. The method includes generating an asset data model for a parent asset based on at least one data attribute associated with the parent asset. The method further includes populating the asset data model with at least one sub-asset associated with each of the at least one data attribute and at least one event associated with the at least one sub-asset and the at least one data attribute. The method includes creating a plurality of role hierarchies across multiple organizations associated with the parent asset. The method further includes associating a plurality of stakeholders with each of the plurality of role hierarchies. The method includes associating data contracts with each of the plurality of stakeholders and each of the at least one sub-asset based on the plurality of role hierarchies and the asset data model.

Abstract: A method and device for generating data services from heterogeneous systems is disclosed. The method includes generating an asset data model for a parent asset based on at least one data attribute associated with the parent asset. The method further includes populating the asset data model with at least one sub-asset associated with each of the at least one data attribute and at least one event associated with the at least one sub-asset and the at least one data attribute. The method includes creating a plurality of role hierarchies across multiple organizations associated with the parent asset. The method further includes associating a plurality of stakeholders with each of the plurality of role hierarchies. The method includes associating data contracts with each of the plurality of stakeholders and each of the at least one sub-asset based on the plurality of role hierarchies and the asset data model.

Abstract: According to examples, system control may include accessing a plurality of procedures to control an operation of a system to prevent an occurrence of a fault in the system and/or a reduction of an output of the system. A highest ranked procedure may be learned from the plurality of procedures to control the operation of the system to prevent the occurrence of the fault in the system and/or the reduction of the output of the system. Real-time data associated with the system may be accessed. Further, the operation of the system may be controlled by applying the highest ranked procedure to prevent the occurrence of the fault in the system and/or the reduction of the output of the system.

Abstract: A method and device for tracing issues in an end-to-end process is disclosed. The method includes identifying a plurality of stakeholders involved in the end-to-end process and a plurality of vectors associated with each of the plurality of stakeholders, determining a plurality of parameters associated with each of the plurality of vectors for each of the plurality of stakeholder, comparing values associated with each of the plurality of parameters with corresponding threshold values for each of the plurality of stakeholders, collating deviation information associated with at least one of the plurality of parameters based on the comparing on a distributed ledger network, evaluating a resultant product or service obtained after the end-to-end process based on predefined quality standards, and upon evaluating, tracing an issue and a location of the issue in the end-to end process using the deviation information collated on the distributed ledger network.

Abstract: According to examples, steam breakthrough detection and prevention for a steam assisted gravity drainage (SAGD) well may include accessing real-time data associated with the SAGD well. Parameter values associated with an operation of the SAGD well may be determined based on the real-time data associated with the SAGD well. A potential of occurrence of steam breakthrough may be determined based on an analysis of selected parameter values from the parameter values associated with the operation of the SAGD well. A procedure to prevent the occurrence of the steam breakthrough may be determined based on an application of hypothetical parameter values associated with the operation of the SAGD well to an engineering analysis model associated with the SAGD well. Further, the operation of the SAGD well may be controlled based on the procedure to prevent the occurrence of the steam breakthrough.

Abstract: The system may receive a group of project requirements from a client for development of a software application. The system may identify the client based on the received group of project requirements. The system may to determine, based on the group of project requirements of the client, a past project requirement submitted by the client or another client or created previously as a generic project requirement and corresponding to a first project requirement of the group of project requirements. The system may determine information created or used for the past project requirement. The system may create information for a second project requirement of the group of project requirements. The system may generate a prototype of the software application based on the information created or used for the past project requirement and the information created for the second project requirement. The system may output the prototype.

Abstract: A transportation system may store a standard time of arrival table including standard time of arrivals for fixed stops and waypoints or geo-sections. Delay of a vehicle reaching a fixed stop is determined and may be used to determine an estimated time of arrival to a destination on the route. Delay may be determined in response to traversing the waypoints or geo-sections on the route, and the estimated time of arrival may be updated according to the delay at each waypoint or geo-section.

Abstract: A request to perform a transaction is detected. Based on the request to perform the transaction, one or more factors related to a context in which the transaction is being requested are determined. Based on the one or more factors, one or more parameters for authenticating a user that requested performance of the transaction are determined. The user that requested performance of the transaction is authenticated based on the determined one or more parameters for authenticating the user that requested performance of the transaction. Based on to authenticating the user that requested performance of the transaction, performance of the requested transaction is allowed.

Abstract: A method for controlling a sensor may be performed by a mobile device including a processor and a memory. The method may include receiving raw data from the sensor, classifying the raw data into a context value, interpreting the context value into a higher-level context, receiving a predicted context based on the higher-level context, and controlling the sensor based on the predicted context. Controlling the sensor may include controlling a frequency at which raw data is received from the sensor, or an on/off state of the sensor. Control of the sensor may also be based on both the higher-level context and the predicted context.

Abstract: A method and system for reducing demand on a power grid through demand side management includes receiving assigned priorities from a customer for smart appliances and for appliances plugged into sockets of one or more smart plugs of the customer, the assigned priorities indicative of a customer-preferred sequence for disconnection of, or adjustment of power to, the appliances from the power grid. The system determines whether to disconnect or adjust power to at least one of the appliances of the customer; and selects at least one of the appliances according to the assigned priorities to reduce demand on the power grid. The system sends one or more commands, the one or more commands indicative to the one or more smart plugs to disconnect or adjust power to the selected at least one of the appliances based on selecting at least one of the appliances.

Abstract: Intelligent application back stack management may include generating a first back stack for activities of an application that have been executed by a device that executes the application. The first back stack may include a back stack size limit. A further back stack may be generated for selected ones of the activities of the application if a total number of the activities of the application and further activities of the application exceeds the back stack size limit. The first back stack may be an in-memory back stack for the device that executes the application, and the further back stack may include an external on-device back stack for the device that executes the application and/or a Cloud storage based back stack. Intelligent application back stack management may further include regenerating an activity of the selected ones of the activities that is pulled from the further back stack.