Abstract: An interactive kiosk includes a display, a microphone, and one or more processors that perform operations including receiving user input provided as a spoken query of a user, receiving user-specific data, querying, by a virtual agent, one or more back-end systems based on the user input, and the user-specific data to provide one or more responses, displaying one or more graphical representations of the one or more responses to the user on the display, the one or more graphical representations depicting at least one product for purchase, facilitating a purchase of the at least one product, and providing instructions to the passenger for physical retrieval of the at least one product within a location.

Abstract: Techniques are described for monitoring the status and transportation of materials. A monitoring platform can employ a distributed ledger system (DLS) and provide a mechanism by which various entities can access information regarding the status of transported materials, and receive alerts regarding issues arising during transport. The platform can also include logic (e.g., smart contract(s)) that executes to perform actions automatically in response to detected issues. Such actions can include remediation actions to compensate a stakeholder in the event of a theft, degradation, or other loss of transported material. The platform can receive sensor data generated by one or more devices that can be present in a vehicle that transports the material, and the data can be analyzed to identify anomalies. Alerts can be generated based on anomalies, and the alert(s) and/or sensor data can be stored on the DLS to be accessible by entities and/or logic.

Abstract: An automation optimization engine is disclosed that provides a closed loop nodal analysis on a process performance tree. By analyzing an observed process and identifying automatable tasks from non-automatable tasks from the observed process, the automation optimization engine then applies machine learning techniques to generate a recommendation report identifying steps for implementing in the observed process to convert the non-automatable tasks into automatable tasks. Optimization is thus achieved to close the loop to further automate the observed process.

Abstract: Direct measurement and simulation of real-time production rates of chemical products in complex chemical plants is complex. A predictive model developed based on machine learning algorithms using historical sensor data and production data provides accurate real-time prediction of production rates of chemical products in chemical plants. An optimization model based on machine learning algorithms using clustered historical sensor data and production data provides optimal values for controllable parameters for production maximization.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for molecular content analysis. One of the methods includes receiving molecular content data that indicates a molecular content of a portion of a batch of sludge; determining, by a machine learning module included in the system using the molecular content data and multiple parameters, a predicted value for a property of the portion of the batch of sludge; and providing the predicted value for the property of the portion of the batch of sludge.

Abstract: A system for assessing a data model includes a data receiver, a model receiver, and a model assessment device. The data receiver receives training data, historical data, and production data. The model receiver receives the data model associated with the historical data and trained using the training data. The historical data includes a first outcome of the data model provided based on an input feature in the production data. The model assessment device identifies a key feature in the production data relative to the input feature based on a target category in the historical data and a statistical distribution of the input feature in the production data. The model assessment device determines a second outcome of the data model based on the key feature. In response to the second outcome being different from the first outcome, the model assessment device determines a veracity score for assessing the data model.

Abstract: A system for auto classification of products includes an entity recognizer and a model selector. The entity recognizer receives training data including an attribute of a product. The model selector selects a feature from the training data using a first statistical model to provide a first feature and a second statistical model to provide a second feature, and trains a probabilistic classifier using the first and the second features for providing a first and a second classification models respectively. Further, the model selector calculates an accuracy score of the obtained classification models for each distinct category in a preset hierarchy of categories and selects a classification model from the obtained classification models based on the accuracy score. The selected classification model has a highest accuracy score for a corresponding category in the preset hierarchy.

Abstract: Examples for enhancing veracity of data are described herein. Data from a repository may be received based on a data receiving rule. From the received data, a first dataset may be generated using statistical modeling. Also, a first data veracity score for the first dataset is generated which is indicative of a degree of usability of the dataset. Another aspect relates to identifying an anomaly in the first dataset, the corrector, for each anomaly, to identify a correction technique from amongst a plurality of correction techniques. Further, a second dataset is generated using the identified correction technique having second data veracity score higher than the first data veracity score.

Abstract: A system may include a federated shipping node. The federated shipping node may receive shipping information for a parcel and determine a new shipping state for the parcel based on the shipping information. The federated shipping node may append the new shipping state to a blockchain. In addition, the federated shipping node may store the new shipping state in an off-chain database. A previous shipping state for the parcel may be replaced with the new shipping state in the off-chain database. To display the real-time information related to the parcel, the federated shipping node may receive the new shipping state from the off-chain database, and send the new shipping state to a device for display. To display the historical information related to the parcel, the federated shipping node may receive previous shipping states from the blockchain, and send the previous shipping states to the device for display.

Abstract: This document describes impact networks that enable stakeholders to measure and take actions to adjust the impact of changes to products and services. In one aspect, a method includes receiving a stakeholder impact graph defining stakeholders. Each stakeholder is a node that is connected to at least one other stakeholder by an impact relationship edge. Data defining a first design perturbation in one or more design properties for a product or service of a first stakeholder is received from the first stakeholder. A determination is made, for one or more second stakeholders of the stakeholders connected to the first stakeholder by a respective impact relationship edge, a respective impact on the second stakeholder caused by the first design perturbation. Data defining a remediation perturbation that adjusts the respective impact of the first deign perturbation on the one or more second stakeholders is received.

Abstract: In some possible implementations, a device may include one or more memories and one or more processors, communicatively coupled to the one or more memories, to: receive a document that includes a plurality of clauses relating to two or more entities; identify a selected clause, of the plurality of clauses, based on a characteristic of the selected clause; determine a domain-specific language (DSL) unit based on the selected clause, the DSL unit identifying the two or more entities and values associated with the selected clause, identified by the selected clause, associated with the two or more entities; automatically generate a smart contract based on the DSL unit, the smart contract being configured to enforce a condition or action, of the values, between the two or more entities; and perform an action based on the smart contract.

Abstract: A device may receive data associated with a benefit manager organization. The data may relate to a performance of the benefit manager organization and hardware resources associated with the benefit manager organization. The device may process the data using a technique after receiving the data. The device may map the data to a benefit manager operating model based on processing the data. The benefit manager operating model may identify a functional area or a sub-area of another benefit manager organization. The device may perform an analysis of the data based on mapping the data to the benefit manager operating model. The device may identify a deficiency related to the performance of the benefit manager organization. The device may perform an action to positively impact the performance of the benefit manager organization based on identifying the deficiency. The action may reduce the deficiency.

Abstract: A device may receive user input data identifying a canvas, API documents, or tagged assets for an application to be generated, a requirements document for the application, and asset data identifying reusable assets and components for the application. The device may process the user input data, the requirements document, and the asset data, with a first model, to extract entity data and intent classification data. The device may parse the API documents to generate structured data identifying API endpoints, a request API model, and a response API model. The device may process the structured data to generate an API layer. The device may process the canvas to identify UI objects and to map the UI objects to UI elements. The device may generate code for the application based on the asset data, the entity data, the intent classification data, the API layer, and the UI elements.

Abstract: A system and method for dynamic risk assessment is disclosed. The system may include a data warehouse, an output device and a processor including a data capturer, a process engine and a rules engine. The data capturer may capture information pertaining to a plurality of risk factors associated with an infection risk corresponding to a plurality of data elements in an environment. The plurality of data elements may pertain to at least one of a space and a person in the space. The process engine may include at least one of a space risk profiler and a person risk profiler. The process engine may determine a risk score and a risk profile associated with the person and the space. Based on the risk profile, the processor may perform at least one of an automatic identification of a mitigation to reduce the infection risk and an automated generation of an alert.

Abstract: An Artificial Intelligence (AI) based user intent analyzer system analyzes a received user query to determine an intent of the user query and enables execution of processes on a backend system based on the user intent. The user query is divided into a plurality of portions and the portions with extraneous information are discarded. The remaining portions are parsed with a plurality of parsers. The output from the plurality of parsers is processed for extraction of the entities, entity attributes, verbs, and verb arguments. The entities and verbs are further filtered using knowledge graphs and the remaining entities and verbs are mapped to sub-intents using intent mapping rules retrieved from the knowledge graphs. The sub-intents are mapped to the final intent using process rules associated with the process to be executed by the backend system in response to the user query.

Abstract: Implementations of the present disclosure include providing, by a security platform, graph data defining a graph that is representative of an enterprise network, the graph comprising nodes and edges between nodes, a set of nodes representing respective assets within the enterprise network, each edge representing at least a portion of one or more lateral movement paths between assets in the enterprise network, determining, for each asset, a criticality of the respective asset to operation of a process, determining a lateral movement path between a first node represented by a first asset and a second node represented by second asset within the graph, determining a path value representative of a criticality in preventing an attack through the lateral movement path, and providing an indication of the path value representative of the criticality in preventing an attack through the lateral movement path.

Abstract: Methods, systems, and apparatus for solving optimization tasks. In one aspect, a system includes one or more classical processors and one or more quantum computing resources, wherein the one or more classical processors and one or more quantum computing resources are configured to perform operations comprising receiving input data comprising data specifying a computational task to be solved; processing the received input data using a first quantum computing resource to generate data representing a reduced computational task, wherein the reduced computational task has lower dimensionality that the computational task; and processing the data representing the reduced computational task to obtain a solution to the computational task.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for natural language control of web browsers. The methods, systems, and apparatus include actions of obtaining a query from a user, determining a likely intent and an entity from the query, determining an action and script metadata based on the likely intent and the entity, compiling scripts based on the action and the script metadata, and providing the scripts to a web browser for execution.

Abstract: A closed-loop natural language query pre-processor and response synthesizer architecture accepts natural language queries and dynamically synthesizes query results. The query results may be in the form of data stories. The architecture identifies, selects, and composes candidate response elements into a coherent and meaningful query result. The architecture also implements an adaptable delivery mechanism that is responsive to connection bandwidth, query source preferences, query source characteristics, and other factors. Feedback from multiple sources adapts the architecture for handling subsequent queries.

Abstract: Embodiments provide for prediction and mitigation of network faults. Information associated network nodes may be compiled and used to generate network analytical records (NARs). A first model may be executed against the NARs to predict faults associated with one or more nodes of the network. Tickets are generated for predicted faults and stored in a ticket database. The tickets may be analyzed to predict executable actions to mitigate the faults associated with each ticket. To analyze the tickets, ticket data may be compiled and used to generate ticket analytical records (TARs). A second model may be executed against the TARs predict actions to resolve the predicted faults. The predicted actions may be executed to mitigate the impact that the faults have on the network, which may include preventing the faults entirely (e.g., via preventative maintenance) or minimizing the impact of the faults via use of the predicted actions.