Abstract: An embodiment extracts, from an utterance, a goal. An embodiment prompts a large language model (LLM) to select, using metadata describing a plurality of agents, a set of candidate agents from the plurality of agents, each candidate agent in the set of candidate agents corresponding to the goal. An embodiment scores, using metadata of the set of candidate agents, each candidate agent in the set of candidate agents, the scoring resulting in a set of scored candidate agents. An embodiment prompts the LLM to select, using a set of business policy constraints, a next agent from the set of scored candidate agents. An embodiment invokes the next agent, the invoking causing the next agent to perform an action furthering the goal.

Abstract: A demand prediction device is a device predicting a demand quantity for a target product based on a prediction model, and the demand prediction device specifies a similar product to the target product, calculates a base demand quantity for the target product by using the prediction model weighted in accordance with the similar product and a feature of the target product, the prediction model is a model in which two or more types of individual learning models are integrated and a weigh is set for each of the individual learning models, the individual learning model is a model that outputs the demand quantity in accordance with a feature of a product, receives an operation of changing the weight for each of the individual learning models, and calculates a predicted demand quantity for the target product by using the prediction model. The present disclosure can be used to support decision making.

Abstract: To reduce a leakage current of a transistor so that malfunction of a logic circuit can be suppressed. The logic circuit includes a transistor which includes an oxide semiconductor layer having a function of a channel formation layer and in which an off current is 1×10?13 A or less per micrometer in channel width. A first signal, a second signal, and a third signal that is a clock signal are input as input signals. A fourth signal and a fifth signal whose voltage states are set in accordance with the first to third signals which have been input are output as output signals.

Abstract: An operation management method does: acquiring a work plan that mutually associates a farm field F where a work vehicle does work, work content of the work to be done by the work vehicle at the farm field F, and a scheduled work day of the work; determining whether or not a first work plan that needs to be alerted for the work vehicle to do the work as planned in the work plan is present in plural work plans that include the work plan; and notifying work information on the first work plan, when the first work plan is present in the plural work plans.

Abstract: Systems and methods described herein relate to predicting the effect of an intervention via machine learning. One embodiment divides a plurality of units into first and second intervention groups that receive first and second interventions, respectively; identifies, for each unit, k nearest-neighbor units in each of the first and second intervention groups; calculates, for each unit, an outcome under the first and second interventions as first and second weighted averages of the k nearest-neighbor units in the first and second intervention groups, respectively; calculates, for each unit, an intervention effect for that unit as the difference between the outcomes under the first and second interventions; generates a machine-learning-based regression model that models the intervention effects of the units as a function of a set of covariates; and outputs, using the machine-learning-based regression model, a predicted intervention effect for a unit that is outside the plurality of units.

Abstract: A method for predicting a price of any subtractively manufactured part utilizing artificial intelligence at a computing device. The method comprises receiving a part model, identifying at least an element of mechanical part data as a function of the part model, extracting at least an identified element of the mechanical part data, selecting a correlated dataset comprising a plurality of data entries as a function of the extracted element of the mechanical part data, generating at least a part revision datum for the plurality of correlated manufacturing data, determining a pricing datum as a function of the extracted element of the mechanical part data and the correlated manufacturing data, and generating a graphical user interface displaying the mechanical part data and the part revision datum on a user device.

Abstract: A mine site electrification planning apparatus includes a model component to simulate mine site operations under a mine site electrification plan. A simulation control component may provide configuration data to the model component that are descriptive of varying distributions of zero greenhouse gas emitting (ZGHG) mining assets for which the mine site electrification plan is simulated. An optimization control component may identify the configuration data associated with the simulated mine site electrification plan that meets an economic optimization criterion related to physically implementing the mine site electrification plan.

Abstract: Systems and methods, and computer readable media for inventory demand estimation of a region are disclosed. The method receives an item identifier associated with an item for demand estimation. The method may then access overall demand forecast data for the item and identify geographical regions, and evaluate a demand share estimate of the item in the geographical regions. The method may also determine a set of item identifiers associated with a segment of items related to the item and determine the demand estimation for the segment of items. The method may then generate demand estimation of the item at the geographical regions using a Bayesian framework with demand share of the item and demand estimation of the segment of items in a geographical region, and overall demand forecast data for the item as input. The method may use the generated demand estimation at a region to generate demand estimation in other encompassing geographical regions.

Abstract: When inspection data of a process inspection in a production line is input, a machine learning unit 420 of a prediction score calculation device 202 performs machine learning so as to output a prediction score of quality determination of a final inspection. In addition, a prediction score calculation unit 410 outputs a prediction score predicting the quality determination result of the final inspection from the inspection data of the process inspection using a machine learning model that has performed the machine learning. In addition, a threshold value determination unit 440 compares the prediction score calculated by the prediction score calculation unit 410 and determines a threshold value for predicting the quality determination from learning data, the prediction score, and cost data.

Abstract: A system comprising: a skills data store; an employee action data store; at least one hardware processor; and one or more software modules that are configured to, when executed by the at least one hardware processor, retrieve skills data and employee action data from the skills data store and employee action data store, train a classification model, wherein training a classification model comprises performing feature preprocessing, generating an LDA topic vector and TF/IDF Word2Vec similarity scoring, and use AutoML to train ML models, and infer employee skills and levels based on the classification model and employee action data.

Abstract: A set of inputs from a plurality of inputs are selected based on a user identifier of a user. The set of inputs are apportioned and recombined to produce one or more grouped inputs. The one or more grouped inputs are input to one or more machine learning models to provide individualized information output by the one or more machine learning models to the user.

Abstract: A computerized method of estimating resource requirements in an environment is presented. The method comprises a preparation phase and a simulation phase, wherein the preparation phase comprises a machine learning training phase and a clustering phase. The machine learning training phase trains a machine learning model to predict a resource requirement. Thereby, a subset of features is extracted. The clustering phase determines clusters in the subset of features, a correlation coefficient and least one identifying parameter of a distribution of the feature values of the subset of features. Finally, the simulation phase determines a distribution for a feature, selects at least one value for a feature and uses the second machine learning model to estimate a resource requirement in the environment in at least one time period the future.

Abstract: AI-based orchestration. In an embodiment, a recommendation engine is applied to a data pipeline representing company accounts. Engagement metric(s) are calculated based on activity data associated with the company accounts, and predictive model(s) are applied to the activity data and/or firmographic data associated with the company accounts to generate predictive output. A tactic recommendation model is applied to orchestration features, comprising the engagement metric(s) and predictive output, to generate recommended tactic(s). In addition, a contact recommendation model is applied to contact data to generate recommended contact(s). The recommended tactic(s) are combined with the recommend contact(s) to generate an orchestration, comprising recommended action(s), to be executed.

Abstract: Provided is a method and an apparatus for processing a logistics order task, an electronic device, and a computer medium. The method for processing the logistics order task includes: detecting a quantity of an item on a shelf, the item being associated with a positioning task having been received; determining a time for receiving the positioning task; determining, based on the quantity of the item and/or the time for receiving the positioning task, whether the shelf meets a scheduling condition; and transporting the shelf that meets the scheduling condition to a sorting workstation directed by the positioning task.

Abstract: Aspects of the disclosure relate to intelligently aggregating data using a convolutional network quantum processor. Using an artificial intelligence model, a computing platform may identify dependencies derived from a consumer request and corresponding values. For each configuration of dependency and corresponding value, the computing platform may determine a likelihood of success. The computing platform may alter the configurations and may determine a likelihood of success for each altered configuration. The computing platform may train a convolutional network to analyze the consumer request using the configurations, the altered configurations, and/or corresponding likelihoods of success. The convolutional network may generate a function that describes the dependencies derived from the consumer request. Using a quantum processing model, the computing platform may analyze different states of the function in parallel and may determine whether to approve or deny the consumer request based on the analysis.

Abstract: A system and method are disclosed for immersive guidance using a supply chain execution platform. The method comprises monitoring and receiving input comprising user interaction and user input signals, detecting a user intent within a supply chain execution environment from the user input signals, determining associated focus prompts and action prompts, displaying immersive guidance to the user comprising a visual prompt using augmented reality and updating the immersive guidance based on real-time user action updates received from one or more sensing devices. The method further comprises where the user intent further comprises a series of prompts for the user that guide the user through completion of one or more tasks and where the focus prompts are determined based on eye cornea reflection tracking and facial expressions.

Abstract: A scheduling method using a knowledge graph (KG) performs following steps by a processor: obtaining an initial scheduling solution of the production system; converting the initial scheduling solution into triples to form the KG, each triples includes two entities and a relationship of the production system, the two entities indicate two production resources; embedding triples into a vector space to generate embedded vectors by a KG embedding technique; generating embedded vector combinations according to the embedded vectors and computing a distance of each of embedded vector combinations; and performing a scheduling algorithm to generate a target scheduling solution according to the embedded vector combinations, and providing reference information when the scheduling algorithm generates a schedule of a station, wherein the reference information comprises at least one of the embedded vector combinations associated with the station, and the distance corresponding to said at least one embedded vector combinatio

Abstract: Application, in a single software instrument, of AI and advanced statistics methods for monitoring and analyzing quality problems over the whole lifecycle of a product is provided. A method based on web scraping techniques and AI for monitoring the product out of the warranty period is also provided.

Abstract: One example method is performed at a far edge device and includes collecting data with one or more IoT (Internet of Things) devices, feeding the data to a feedback loop that includes multiple stages, running the feedback loop, providing learning information, comprising output from one or more of the stages of the feedback loop, to a central manager by way of a learn interface, accessing learning information generated by one or more other far edge devices, and updating the feedback loop using the learning information generated by the one or more other far edge devices.

Abstract: Examples of the present disclosure describe systems and methods for monitoring services provided by a service provider to a consumer using a smart contract architecture. In one example, smart contract terms are provided to a DeFi application running on a blockchain, and a smart contract (e.g., a SLA smart contract) is constructed on the blockchain. Once the service provider begins providing service to the consumer, the system may monitor the service performance of the service. If the service performance dips below a certain agreed-upon threshold based on the smart contract, a trigger event may occur. Additionally, the analysis of the service performance data may indicate a service deficiency, wherein a remedial action is suggested to the service provider to be applied. The service deficiency and remedial action may be stored on the blockchain for future review.