Abstract: Embodiments classify a product to one of a plurality of product classifications. Embodiments receive a description of the product and create a first prompt for a trained large language model (“LLM”), the first prompt including the description of the product and contextual information of the product. In response to the first prompt, embodiments use the trained LLM to generate a hallucinated product classification for the product. Embodiments word embed the hallucinated product classification and the plurality of product classifications and similarity match the embedded hallucinated product classification with one of the embedded plurality of product classifications. The matched one of the embedded plurality of product classifications is determined to be a predicted classification of the product.

Abstract: In accordance with an embodiment, described herein are systems and methods for providing a supply chain command center for intelligent procurement assistance, based on an assessment of inventory trends, demand, or other inputs related to the procurement or management of an inventory of items. In accordance with an embodiment, the system can simultaneously optimize for a set of variables related to procurement, by creating time series forecasts of leaf-level independent variables, and performing a simulation within the boundary conditions of historical or expected distributions of each variable, to determine an optimal timing, quantity, location and/or vendor for each order of items that are to be placed in the inventory.

Abstract: In accordance with an embodiment, described herein are systems and methods for generating enterprise forecasts based on an analysis of input variables and direct forecasting. In accordance with an embodiment, the system can use linear regression or other mathematical models or modeling techniques to assess a set of variables related to an enterprise forecast, and their values and rate of change of such values, within a particular forecast window. Based on such assessment, the system can generate an enterprise forecast for that time period, or for a subsequent time period.

Abstract: Embodiments analyze a customer of an organization. Embodiments select the customer and receive historical data corresponding to a plurality of transactions of the customer with the organization, the historical data including, for each of the transactions, a target variable including a number of days of delayed payment for each transaction. Based on the historical data, embodiments determine a cost of a delayed payment from the customer and determine an average delay of payments of the customer. Embodiments convert the cost of delayed payments to a first Z-score and the average delay of payments to a second Z-score. Embodiments then determine a reliability score of the customer comprising determining a Euclidean distance of the first Z-score and the second Z-score.

Abstract: Embodiments predict a target variable for accounts receivable in response to receiving historical data corresponding to a plurality of transactions corresponding to a plurality of customers, the historical data including, for each of the transactions, the target variable. Embodiments segment each of the customers based on the historical data corresponding to each of the customers, the segmenting including determining a variation of the target variable for each customer and, based on the variation, classifying each customer as having a low variation, a medium variation, or a high variation. For each low variation customer, embodiments create a regular ML model without a grace period that is trained and tested using the historical data. For each medium variation customer, embodiments create the regular ML model and create two or more grace period ML models, each grace period ML model adding a different grace period to the target variable.

Abstract: Embodiments predict a target variable for accounts receivable using a machine learning model. For a first customer, embodiments receive a plurality of trained ML models corresponding to the target variable, the plurality of trained ML models trained using the historical data and comprising a first trained model having no grace period for the target variable and two or more grace period trained models, each grace period trained model having different grace periods for the target variable. Embodiments determine a Matthews' Correlation Coefficient (“MCC”) for the first trained model. When the MCC for the first trained model is low, embodiments determine the MCC for each of the grace period trained models, and when one or more MCCs for each of the grace period trained models is higher than the MCC for the first trained model, embodiments select the corresponding grace period trained model having a highest MCC.

Abstract: Embodiments generate a machine learning (“ML”) model. Embodiments receive training data, the training data including time dependent data and a plurality of dates corresponding to the time dependent data. Embodiments date split the training data by two or more of the plurality of dates to generate a plurality of date split training data. For each of the plurality of date split training data, embodiments split the date split training data into a training dataset and a corresponding testing dataset using one or more different ratios to generate a plurality of train/test splits. For each of the train/test splits, embodiments determine a difference of distribution between the training dataset and the corresponding testing dataset. Embodiments then select the train/test split with a smallest difference of distribution and train and test the ML model using the selected train/test split.

Abstract: Methods for producing and extracting geologic hydrogen from rock formations, and related systems, are generally disclosed.

Abstract: A robotic system includes a robotic arm that includes a first joint that connects a first segment to a second segment, the first segment being connected at an end of the first segment opposite the first joint to a shoulder joint of the robotic arm and the second segment being connected at an end of the second segment opposite the first joint to an elbow joint of the robotic arm; and a processor coupled to the robotic arm and configured to receive an end effector trajectory and determine a motion plan to move the end effector through the end effector trajectory, including by using the first joint to vary the distance between the shoulder joint and the elbow joint, as and if needed, to realize the end effector trajectory while using the joints and links other than the first joint in a preferred pose.

Abstract: A system and method for predicting maintenance and providing optimized operational performance in industrial operations on a Metaverse platform, is described. In one aspect, the system implements AI/ML engines for anomaly detection and predictive analytics to control future failures, facilitate planned maintenance, and provide actionable recommendations to control future failures. The system combines data with AR/VR-based digital twin solutions for real-time troubleshooting and maintenance training. The system detects anomalies in industrial assets using sensor and IIoT data and provides predictive analytics for capturing failures and actionable recommendations, provides improved overall equipment effectiveness, enhanced device and system utilization, simulation of processes using data, and prescription uptime plans, achieving superior productivity gains and predictable uptime.

Abstract: Apparatuses, systems, and methods for implementing a multi-driver architecture are described. The multi-driver architecture may include a first driver and a second driver configured to receive an input voltage. A predriver logic circuit may select one of the first driver and the second driver to convert the input voltage into an output voltage. A controller may be connected to the first driver and the second driver, and a switch may be connected between an output terminal of the first driver and the controller. The controller may be configured to control an internal resistance of the switch. In response to the first driver being selected by the predriver logic circuit, the first driver may output the output voltage at a constant impedance level.

Abstract: A system and method for predicting maintenance and providing optimized operational performance in industrial operations on a Metaverse platform, is described. In one aspect, the system implements AI/ML engines for anomaly detection and predictive analytics to control future failures, facilitate planned maintenance, and provide actionable recommendations to control future failures. The system combines data with AR/VR-based digital twin solutions for real-time troubleshooting and maintenance training. The system detects anomalies in industrial assets using sensor and IIoT data and provides predictive analytics for capturing failures and actionable recommendations, provides improved overall equipment effectiveness, enhanced device and system utilization, simulation of processes using data, and prescription uptime plans, achieving superior productivity gains and predictable uptime.

Abstract: A method of identifying causal relationships between time series may include accessing a hierarchy of nodes in a data structure, where each node in the plurality of nodes may include a time series of data. The method may also include identifying a subset of nodes in the plurality of nodes for which causal relationships may exist in the corresponding time series. The method may additionally include generating a model for each of the subset of nodes, where the model may receive the subset of nodes and generate coefficients indicating how strongly each of the subset of nodes causally affects other nodes in the subset of nodes. The method may further include generating a ranked output of nodes that causally affect a first node in the subset of nodes based on an output of the corresponding model.

Abstract: A robotic system, method, and device for controlling operation of a robot is disclosed. The robotic system includes (i) a robot configured to move one or more items within a workspace, (ii) a sensor configured to collect sensor data with respect to the workspace, and (iii) one or more processors. The one or more processors are configured to (a) determine to reset operation of the robot, (b) determine, based at least in part on the sensor data, that a human worker exited a safeguarded space within the workspace, and (c) in response to determining that the human worker exited the safeguarded space, resume operation of the robot.

Abstract: A stack containment fixture is disclosed. The stack containment fixture includes an insertion zone structure including an insertion zone structure and a kitting area structure. The insertion zone structure includes a pair of substantially vertically oriented deflecting arms. each having one or more funnels configured to guide a stack into a position between the deflecting arms as the stack is lowered into the insertion zone structure from above. The kitting area structure is configured to support the vehicle or the stack during kitting operations for items being placed in the vehicle or stack or for items being picked from the vehicle or stack.

Abstract: A method of identifying causal relationships between time series may include accessing a hierarchy of nodes in a data structure, where each node in the plurality of nodes may include a time series of data. The method may also include identifying a subset of nodes in the plurality of nodes for which causal relationships may exist in the corresponding time series. The method may additionally include generating a model for each of the subset of nodes, where the model may receive the subset of nodes and generate coefficients indicating how strongly each of the subset of nodes causally affects other nodes in the subset of nodes. The method may further include generating a ranked output of nodes that causally affect a first node in the subset of nodes based on an output of the corresponding model.

Abstract: Apparatuses, systems, and methods for implementing a multi-driver architecture are described. The multi-driver architecture may include a first driver and a second driver configured to receive an input voltage. A predriver logic circuit may select one of the first driver and the second driver to convert the input voltage into an output voltage. A controller may be connected to the first driver and the second driver, and a switch may be connected between an output terminal of the first driver and the controller. The controller may be configured to control an internal resistance of the switch. In response to the first driver being selected by the predriver logic circuit, the first driver may output the output voltage at a constant impedance level.

Abstract: A method of identifying causal relationships between time series may include accessing a hierarchy of nodes in a data structure, where each node in the plurality of nodes may include a time series of data. The method may also include identifying a subset of nodes in the plurality of nodes for which causal relationships may exist in the corresponding time series. The method may additionally include generating a model for each of the subset of nodes, where the model may receive the subset of nodes and generate coefficients indicating how strongly each of the subset of nodes causally affects other nodes in the subset of nodes. The method may further include generating a ranked output of nodes that causally affect a first node in the subset of nodes based on an output of the corresponding model.

Abstract: In accordance with an embodiment, described herein are systems and methods for use with a computing environment, for providing a determination of model fitness and stability, for model deployment and automated model generation. A model fitness and stability component can provide one or more features that support model selection, use of a model deployability score and deployability flag, and mitigation of model drift risk, to determine model fitness and stability for a particular application. For example, embodiments may be used with analytic applications, data analytics, or other types of computing environments, to provide, for example, a directly actionable risk prediction, in finance applications or other types of applications.

Abstract: Described herein are techniques for identifying highly relevant content for a user to view in the form of KPI cards and providing the relevant view to the user automatically or by suggestion. The KPIs of highest practical and statistical significance are provided when the user accesses the user interface. In some embodiments, when the user is viewing a KPI, other relevant KPIs may be provided for the user to view as suggestions. Further, in some embodiments, the user may be provided with the KPIs of significance based on anomaly detection, and the explanation for the anomaly as well as suggestions for remedying any issues may be provided to the user. The highly informational content can be surfaced through the use of the advanced machine learning algorithms described herein.