Absstract of: WO2024218535A1
The disclosure relates to a ML-based method for determining a CCE aggregation level for a UE in a PDCCH. The method comprises obtaining RBS traces. The method comprises training, using first data obtained from the traces, a machine learning model to predict a probability of discontinuous transmission (DTX) "isDTX probability". The method comprises inputting second data obtained from the traces into the machine learning model, obtaining the isDTX probability and expanding the second data with the isDTX probability. The method comprises, for each of a plurality of probability thresholds (PTs) and for each of a plurality of strategies, selecting a data having an isDTX probability greater or equal to the PT and best satisfying the strategy and using the data to train a classifier. The method comprises selecting one classifier and using the classifier for determining the CCE aggregation level for the UE in the PDCCH.
Absstract of: US2024354603A1
Systems and methods are described for identifying and resolving performance issues of automated components. The automated components are segmented into groups by applying a K-means clustering algorithm thereto based on segmentation feature values respectively associated therewith, wherein an initial set of centroids for the K-means clustering algorithm is selected by applying a set of context rules to the automated components. Then, for each group, a performance ranking is generated based at least on a set of performance feature values associated with each of the automated components in the group and a feature importance value for each of the performance features. The feature importance values are determined by training a machine learning based classification model to classify automated components into each of the groups, wherein the training is performed based on the respective performance feature values of the automated components and the respective groups to which they were assigned.
Absstract of: US2024354631A1
Decision Tree Algorithms that learn by training on datasets and models of innovations with Target Variables, Proximal Variables, Nodes, and Parameters to create predictive models.Decision Tree Algorithms can be configured to train on datasets and models of information describing, classifying, and categorizing innovations. Potentially, Decision Tree Algorithms unlock innovations hidden within historical records, specifications, reports, analyses, relationships, adjacencies, applications, products, business models, patent applications, systems, components, lab results, and other information. Subsequently, innovations can be revealed.Furthermore, the insight and learning the Decision Tree Algorithm receives from training on datasets and models of innovations can be used to predict models, areas of focus, and whites spaces, as well as to target untapped opportunities for innovations and developments. Ultimately, Decision Tree Algorithms are configured to parse through datasets and models of innovations to accelerate growth, prioritize investments, and develop new capabilities.In addition to predicting innovations, Decision Tree Algorithms can recommend alternatives, substitutions, modifications, trends, and other signals, using proximal attributes of innovations. Decision Tree Algorithms can reveal anomalies, outliers, and areas for further analysis and, ultimately, prevent attrition.
Absstract of: US2024354550A1
The computer-assisted parallelization of a task capable of being accomplished by a pre-trained machine learning model. Multiple learner models are created by, for each of at least some of the parallel compute resources, selecting one or more characteristics of a learner model based on one or more characteristics of the corresponding compute resource on which the learner model is to run. The learner models are then taught. The teaching occurs such that the learner model is capable of generating a task result when given the task. At task time, the tasks results are then aggregated to generate an aggregated task result. The learner models are thus collectively tailored to run efficiently on the corresponding hardware.
Absstract of: US2024354645A1
Systems, methods, and non-transitory computer-readable media for creating labels for training a machine learning model using a limited dataset. A label creation application receives raw data from a storage device. The raw data includes requests associated with user accounts. The application determines an account type of each of the user accounts. The application generates a raw data set based on account types, requests, and user accounts. The application cleans the raw data set using client feedback data. The feedback data is the limited dataset that includes fraud events associated with user accounts identified by a client. The application extracts a request history for a user account from the raw data that is cleaned. The application generates a training profile for the user account based on the request history. The application creates training labels based on the training profile, and the model is trained by processing the created labels.
Absstract of: US2024354655A1
Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for training a machine learning model. In one aspect, a method comprises: generating a set of candidate batches of model inputs; generating, for each candidate batch of model inputs, a respective score for the candidate batch of model inputs that characterizes: (i) an uncertainty of the machine learning model in generating predicted labels for the model inputs in the candidate batch of model inputs, and (ii) a diversity of the model inputs in the candidate batch of model inputs; and selecting the current batch of model inputs from the set of candidate batches of model inputs based on the scores; and training the machine learning model on at least the current batch of model inputs.
Absstract of: US2024354575A1
Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for training a machine learning model. In one aspect, a method comprises: generating a set of candidate batches of model inputs; generating, for each candidate batch of model inputs, a respective score for the candidate batch of model inputs that characterizes: (i) an uncertainty of the machine learning model in generating predicted labels for the model inputs in the candidate batch of model inputs, and (ii) a diversity of the model inputs in the candidate batch of model inputs; and selecting the current batch of model inputs from the set of candidate batches of model inputs based on the scores; and training the machine learning model on at least the current batch of model inputs.
Absstract of: WO2024220902A1
Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for training a machine learning model. In one aspect, a method comprises: generating a set of candidate batches of model inputs; generating, for each candidate batch of model inputs, a respective score for the candidate batch of model inputs that characterizes: (i) an uncertainty of the machine learning model in generating predicted labels for the model inputs in the candidate batch of model inputs, and (ii) a diversity of the model inputs in the candidate batch of model inputs; and selecting the current batch of model inputs from the set of candidate batches of model inputs based on the scores; and training the machine learning model on at least the current batch of model inputs.
Absstract of: WO2024220262A1
The computer-assisted parallelization of a task capable of being accomplished by a pre-trained machine learning model. Multiple learner models are created by, for each of at least some of the parallel compute resources, selecting one or more characteristics of a learner model based on one or more characteristics of the corresponding compute resource on which the learner model is to run. The learner models are then taught. The teaching occurs such that the learner model is capable of generating a task result when given the task. At task time, the tasks results are then aggregated to generate an aggregated task result. The learner models are thus collectively tailored to run efficiently on the corresponding hardware.
Absstract of: WO2024220098A1
Methods, systems, and apparatus, including computer programs encoded on computer storage media, for determining elements of a shipping network. One of the methods includes obtaining environmental input data, wherein the environmental input data includes weather forecast data; providing the environmental input data to a circulation model; and providing output environmental condition from the circulation model to a machine learning model trained to generate a route for a ship.
Absstract of: WO2024219125A1
Problem To generate a fair rule model with essentially necessary rules. Solution The present invention involves: determining an exclusion target from a first rule that does not include a condition of a first attribute and a second rule including the condition of the first attribute, on the basis of a fairness score that is regarding the first rule and is a first proportion of data that, among data satisfying a condition of the first rule, satisfies the condition of the first rule including a second attribute, and a fairness score that is regarding the second rule and is a second proportion of data that, among data satisfying a condition of the second rule including the first attribute, satisfies the condition of the second rule including the first attribute and the second attribute; and generating a machine learning model including a rule other than the rule, which is the exclusion target, from among a plurality of the rules.
Absstract of: WO2024219067A1
Problem To suppress any decline in the accuracy of a fair rule model. Solution In the present invention, a machine learning device: identifies a first attribute having a higher correlation with a protection attribute than a threshold among a plurality of attributes; identifies a first correlation between the first attribute and an objective variable; executes a process of comparing, with the first correlation, a condition pertaining to the first attribute in a first rule including the first attribute among a plurality of rules including one or more attributes among the plurality of attributes, with the plurality of attributes taken as explanatory variables for the objective variable; and generates a machine learning model including a rule excluding the first rule from the plurality of rules on the basis of a result of the comparison process.
Absstract of: AU2024227034A1
The present disclosure provides systems and methods that may advantageously apply machine learning to accurately manage and predict inventory variables with future uncertainty. In an aspect, the present disclosure provides a system that can receive an inventory dataset comprising a plurality of inventory variables that indicate at least historical (i) inventory levels, (ii) inventory holding costs, (iii) supplier orders, or (iv) lead times over time. The plurality of inventory variables can be characterized by having one or more future uncertainty levels. The system can process the inventory dataset using a trained machine learning model to generate a prediction of the plurality inventory variables. The system can provide the processed inventory dataset to an optimization algorithm. The optimization algorithm can predict one or more inventory management parameters that result in a particular probability of achieving a target service level while minimizing a cost. The optimization algorithm can comprise constraint conditions.
Absstract of: US2024353827A1
A computer-implemented method for providing information concerning a global behavior of a machine learning model trained with measured sensor data representing technical parameters of a technical system and used to evaluate the technical system, including, receiving the machine learning model and measured sensor data generating a number of synthetic sensor data by a synthetic data generator, predicting labels for the synthetic sensor data and the measured sensor data by the result of the machine learning model when processing the synthetic sensor data and the measured sensor data as input data, training a surrogate model based on the synthetic sensor data and measured sensor data and the predicted labels, calculating an agreement accuracy indicating the similarity of a result of the surrogate model compared to a result of the machine learning model, outputting to a user interface the trained surrogate model and the agreement accuracy.
Absstract of: US2024353812A1
A system includes a processing device, operatively coupled to the memory device, to perform operations comprising obtaining a plurality of sensor values associated with a deposition process performed, according to a recipe, in a process chamber to deposit film on a surface of a substrate. A machine-learning model is applied to the plurality of sensor values. The machine-learning model is trained based on historical sensor data of a sub-system of the process chamber and task data associated with the recipe for depositing the film. An output of the machine-learning model is generated that is indicative of a suspected failure of the sub-system and a corrective action is generated based on the suspected failure of the sub-system.
Absstract of: AU2022409327A1
A system for controlling multicomputer interaction with deep learning is disclosed that includes a controller system that is configured to generate one or more first user-controllable avatars on an interaction field, where the first avatars include movement controls and prompt functionality that is controllable by a first user to cause the first avatar to generate a prompt. A client system is configured to generate a second user-controllable avatar on the interaction field, where the second avatar includes movement controls and response functionality that is controllable by a second user to cause the second avatar to generate a response to the prompt. A deep learning processing system is configured to receive the prompt and the response and to process the prompt and the response to generate a score and to assign the score to one of two or more categories associated with the second user.
Absstract of: US2024311548A1
The present disclosure provides a computer implemented method and system for generating an algebraic modelling language (AML) formulation of natural language text description of an optimization problem. The computer implemented method includes generating, based on the natural language text description, a text markup language intermediate representation (IR) of the optimization problem, the text markup language IR including an IR objective declaration that defines an objective for the optimization problem and a first IR constraint declaration that indicates a first constraint for the optimization problem. The computer implemented also includes generating, based on the text markup language IR, the AML formulation of the optimization problem, the AML formulation including an AML objective declaration that defines the objective for the optimization problem and a first AML constraint declaration that indicates the first constraint for the optimization problem. The computer implemented method and system of the present disclosure improves the accuracy in generating an AML formation of an optimization problem than is possible with known solutions, thereby improving the operation of a computer system that applies the computer implemented method.
Absstract of: WO2023111658A1
A method (700) for distributed machine learning, ML, using a set of N CDs. The method includes obtaining first topology information, wherein, for each CD included in the set of N CDs, the first topology information identifies other CDs included in the set of N CDs to which the CD is connected, thereby identifying a set of CD pairs. The method also includes obtaining first network state information, wherein, for each CD included in the set of N CDs, the first network state information comprises a network state vector for the CD, wherein the network state vector for the CD comprises, for each other CD to which the CD is indicated as being connected by the first topology information, a determined network state value. The method further includes determining a consensus weight matrix (W) using the obtained first network state information and the first topology information.
Absstract of: US2024339191A1
A method and system for predicting a selected treatment regimen for a subject. Baseline data for a subject diagnosed with neovascular age-related macular degeneration (nAMD) is received. A plurality of predictor inputs is formed for an outcome predictor using the baseline data and regimen data for a plurality of treatment regimens. The plurality of predictor inputs comprises a different predictor input for each of the plurality of treatment regimens. A plurality of treatment scores is generated for the plurality of treatment regimens via the set of outcome predictor using the plurality of predictor inputs. One of the plurality of treatment regimens is selected as a selected treatment regimen for the subject based on the plurality of treatment scores.
Absstract of: WO2023113657A1
A method (100) is disclosed for managing a wireless device that is operable to connect to a communication network, wherein the communication network comprises a Radio Access Network (RAN), and wherein the wireless device has available for execution a Machine Learning (ML) model that is operable to provide an output, on the basis of which a RAN operation performed by the wireless device may be configured. The method, performed by a RAN node of the communication network, comprises, on fulfilment of a trigger condition, causing an ML model Assurance Information, MAI, Request to be sent to the wireless device (110), the MAI Request comprising an indication of the ML model to which the MAI Request relates. The method further corpses receiving, from the wireless device, an MAI Response, wherein the MAI Response comprises ML model characteristic information generated by the wireless device using the ML model (120), and configuring the RAN operation performed by the wireless device according to the received MAI Response (130).
Absstract of: EP4451281A1
The present disclosure describes a method, apparatus, and computer readable medium for anonymizing medical records using a combination of deep learning and smart templatization. The method comprises performing tokenization on an input medical record comprising one or more sentences to generate tokenized data and generating one or more templatized sentences by performing templatization on the tokenized data, where performing the templatization comprises replacing one or more known patterns in the tokenized data with predefined patterns. The method further comprises identifying one or more PHI sentences from the templatized sentences using a trained classifier, each PHI sentence may comprise one or more PHI. The method further comprises identifying the PHI in the medical record by processing the identified PHI sentences using a trained model and generating an anonymized medical record by anonymizing the identified PHI in the input medical record.
Absstract of: WO2024213270A1
Embodiments relate to providing explainable classifications with abstention using client agnostic machine learning models. A technique includes classifying, by a processor, a record with a label using a machine learning model, the machine learning model abstaining from classifying a given record in response to the given record being outside of a scope of an information technology (IT) domain. The processor generates an explanation of a decision by the machine learning model to classify the record with the label and displays the explanation in a human readable form.
Absstract of: WO2024213269A1
Embodiments relate to providing explainable classifications with abstention using client agnostic machine learning models. A technique includes inputting, by a processor, records to a machine learning model, the records being associated with an information technology (IT) domain. The technique includes classifying, by the processor, the records with labels using the machine learning model, the machine learning model abstaining from classifying a given record in response to the given record being outside of a scope of the IT domain.
Absstract of: AU2024220148A1
A computer-implemented method of training a classification model includes the steps of obtaining, by at least one computer, a plurality of historical resistance trends from a plurality of installed rectifier sites and rectifier site metadata for each installed rectifier site of the plurality of installed rectifier sites; labelling each historical resistance trend of the plurality of historical resistance trends as one of a plurality of historic resistance trend classifications; and, inputting into a machine learning algorithm the historical resistance trends and the rectifier site metadata of the plurality of installed rectifier sites to train the classification model to output a predicted resistance trend classification in response to rectifier site metadata input into the model.
Nº publicación: AU2023287586A1 17/10/2024
Applicant:
EVERGREEN FS INC [US]
EVERGREEN FS, INC
Absstract of: AU2023287586A1
Systems and methods for predicting crop diseases in a crop field using machine learning are disclosed. The method includes first receiving one or more ambient weather parameters related to environmental conditions around the crop field from an environmental sensor. Next, determining a disease risk indicator associated with the disease and the crop field based on the one or more ambient weather parameters, using a disease risk machine learning module trained on historical weather data from a weather database. Then, receiving a pathogen incidence indicator related to the presence of a pathogen around the crop field from a pathogen sensor, where the pathogen is associated with the disease. Finally, generating a disease score based on the disease risk indicator and the pathogen incidence indicator, where the disease score represents the severity of the disease around the crop field.