MACHINE LEARNING

VolverVolver

Resultados 71 resultados LastUpdate Última actualización 05/02/2023 [12:08:00] pdf PDF xls XLS

Solicitudes publicadas en los últimos 30 días / Applications published in the last 30 days



Página1 de 3 nextPage   por página


FEDERATED LEARNING IN COMPUTER SYSTEMS

NºPublicación: US2023031052A1 02/02/2023

Solicitante:

INT BUSINESS MACHINES CORPORATION [US]

Resumen de: US2023031052A1

Methods and systems are provided for federated learning among a federation of machine learning models in a computer system. Such a method includes, in at least one node computer of the system, deploying a federation model for inference on local input data samples at the node computer to obtain an inference output for each data sample, and providing the inference outputs for use as inference results at the node computer. The method further comprises, in the system, for at least a portion of the local input data samples, obtaining an inference output corresponding to each local input data sample from at least a subset of other federation models, and using the inference outputs from the federation models to provide a standardized inference output corresponding to an input data sample at the node computer for assessing performance of the model deployed at that computer.

traducir

CROSS IN-DATABASE MACHINE LEARNING

NºPublicación: US2023030608A1 02/02/2023

Solicitante:

SAP SE [DE]

US_2021350254_A1

Resumen de: US2023030608A1

Techniques for implementing cross in-database machine learning are disclosed. In some example embodiments, a computer-implemented method comprises training a machine learning model in a first database instance using a machine learning algorithm and a training dataset in response to receiving a request to train, serializing the trained machine learning model into a binary file in response to the training of the machine learning model, recreating the trained machine learning model in a second database instance using the binary file in response to receiving a request to apply the machine learning model, and generating an inference result by applying the recreated trained machine learning model on the inference dataset in the second database instance.

traducir

MACHINE LEARNING MODEL REGISTRY

NºPublicación: US2023036004A1 02/02/2023

Solicitante:

XIANG CHONGYUAN [US]

US_2021264321_A1

Resumen de: US2023036004A1

Systems and methods to utilize a machine learning model registry are described. The system deploys a first version of a machine learning model and a first version of an access module to server machines. Each of the server machines utilizes the model and the access module to provide a prediction service. The system retrains the machine learning model to generate a second version. The system performs an acceptance test of the second version of the machine learning model to identify it as deployable. The system promotes the second version of the machine learning model by identifying the first version of the access module as being interoperable with the second version of the machine learning model and by automatically deploying the first version of the access module and the second. version of the machine learning model to the plurality of server machines to provide the prediction service.

traducir

SYSTEM AND METHOD FOR AUTOMATED ACCESS REQUEST RECOMMENDATIONS

NºPublicación: US2023035335A1 02/02/2023

Solicitante:

SAILPOINT TECH INC [US]

US_11227055_B1

Resumen de: US2023035335A1

Systems and methods for embodiments of graph based and machine learning artificial intelligence systems for generating access item recommendations in an identity management system are disclosed. Embodiments of the identity management systems disclosed herein may utilize a graph based approach, a machine learning based approach, and hybrid combinations thereof for generating access item recommendations.

traducir

Dynamically Masking Event Processing Requests Using a Machine Learning Model

NºPublicación: US2023035319A1 02/02/2023

Solicitante:

BANK OF AMERICA CORP [US]

Resumen de: US2023035319A1

Aspects of the disclosure relate to a dynamic information masking computing platform. The dynamic information masking computing platform may receive an event processing request from a device corresponding to a first user via a merchant device. The dynamic information masking computing platform may generate masking decision data using a machine learning masking model. The dynamic information masking computing platform may receive a request for account information corresponding to the first user from a device corresponding to a second user. The dynamic information masking computing platform may mask the account information based on the masking decision data. The dynamic information masking computing platform may send the masked account information and commands directing the device corresponding to the second user to display an account interface that includes the masked record.

traducir

AUTOMATED EVALUATION OF PROJECT ACCELERATION

NºPublicación: US2023034554A1 02/02/2023

Solicitante:

ORACLE INT CORPORATION [US]

JP_2020091843_A

Resumen de: US2023034554A1

Systems and methods are provided for predicting the effects of acceleration on a probability of a successful completion of a project. Specifically, one or more machine learning algorithms can be trained to predict the success of a project from a plurality of features, including at least one feature that is a function of an end date of the project. A set of projects can be selected from projects having expected end dates that do not fall within a desired window of time, each project having a first probability of success given the current end date. A second probability is calculated for each project at a machine learning platform that quantifies a chance that the project will be successful if completed within the window of time. A difference between the first probability and the second probability is determined for each project, and the projects are selected according to the difference.

traducir

Warning for Frequently Traveled Trips Based on Traffic

NºPublicación: US2023034863A1 02/02/2023

Solicitante:

APPLE INC [US]

US_2019339079_A1

Resumen de: US2023034863A1

Some embodiments of the invention provide a novel prediction engine that (1) can formulate predictions about current or future destinations and/or routes to such destinations for a user, and (2) can relay information to the user about these predictions. In some embodiments, this engine includes a machine-learning engine that facilitates the formulation of predicted future destinations and/or future routes to destinations based on stored, user-specific data. The user-specific data is different in different embodiments. In some embodiments, the stored, user-specific data includes data about any combination of the following: (1) previous destinations traveled to by the user, (2) previous routes taken by the user, (3) locations of calendared events in the user’s calendar, (4) locations of events for which the user has electronic tickets, and (5) addresses parsed from recent e-mails and/or messages sent to the user. In some embodiments, the prediction engine only relies on user-specific data stored on the device on which this engine executes. Alternatively, in other embodiments, it relies only on user-specific data stored outside of the device by external devices/servers. In still other embodiments, the prediction engine relies on user-specific data stored both by the device and by other devices/servers.

traducir

DECISION-MAKING UNDER SELECTIVE LABELS

NºPublicación: US2023034542A1 02/02/2023

Solicitante:

INT BUSINESS MACHINES CORPORATION [US]

Resumen de: US2023034542A1

A computer-implemented method of decision-making using selective labels, includes receiving a conditional success probability value of a feature associated with an entity. A confidence value of the received success probability value is received. A parameter value that is a trade-off between a short-term learning and a long-term utility is selected. A decision is rendered to accept or reject the feature associated with the entity according to a machine learning policy.

traducir

ADJUSTING DEMAND FOR ORDER FULFILLMENT DURING VARIOUS TIME INTERVALS FOR ORDER FULFILLMENT BY AN ONLINE CONCIERGE SYSTEM

NºPublicación: US2023034221A1 02/02/2023

Solicitante:

MAPLEBEAR INC DBA INSTACART [US]

Resumen de: US2023034221A1

An online concierge system allows users to order items within discrete time intervals later than a time when an order was received or for short-term fulfillment when the order was received. To account for a number of shoppers available to fulfill orders during different discrete time intervals and numbers of orders for fulfillment during different discrete time intervals, the online concierge system specifies a target rate for orders fulfilled later than a specified discrete time interval and a threshold from the target rate. A trained machine learning model periodically predicts a percentage of orders being fulfilled late, with an order associated with a predicted percentage when the order was received. The online concierge system increases a price of orders associated with predicted percentages greater than the threshold from the target rate. The increased price of an order is determined from a price elasticity curve and the predicted percentage.

traducir

TECHNIQUES FOR PROVIDING SYNCHRONOUS AND ASYNCHRONOUS DATA PROCESSING

NºPublicación: US2023034196A1 02/02/2023

Solicitante:

ORACLE INT CORPORATION [US]

Resumen de: US2023034196A1

Techniques discussed herein include dynamically providing synchronous and/or asynchronous data processing by a machine-learning model service. The machine-learning model service (“the service”) executes a stream manager application, a web interface, and a machine-learning model via a common container. The stream manager application can obtain input data (e.g., from an input data stream, a partition of an input data stream, etc.) and provide the data to the machine-learning model through the web interface using a local communication channel (e.g., a loopback interface that bypasses local network interface hardware of the computing device on which the model executes). Prediction results from the model may be provided as output data (e.g., to an output data stream, to a partition of an output data stream, etc.).

traducir

COMPUTER-IMPLEMENTED METHOD FOR PROVIDING EXPLANATIONS CONCERNING A GLOBAL BEHAVIOUR OF A MACHINE LEARNING MODEL

NºPublicación: WO2023006705A1 02/02/2023

Solicitante:

SIEMENS AG [DE]

EP_4125009_PA

Resumen de: WO2023006705A1

Computer-implemented method for providing information concerning a global behaviour of a machine learning model (f) trained with measured sensor data representing technical parameters of a technical system (20) and used to evaluate the technical system, comprising - receiving (Ml) the machine learning model (f) and measured sensor data (x) of the technical system (20) - generating (M2) a number (N) of synthetic sensor data (z) by a synthetic data generator (36), - predicting (M3) labels (L) for the synthetic sensor data (z) and the measured sensor data (x) by the result of the machine learning model (f) when processing the synthetic sensor data (z) and the measured sensor data (x) as input data, - training (M4) a surrogate model based on the synthetic sensor data (z) and measured sensor data (x) and the predicted labels, wherein the surrogate model (g) is intrinsically interpretable and provides an explanation of the global behaviour of the machine learning model (f), - calculating (M5) an agreement accuracy (ACC) indicating the similarity of a result of the surrogate model (g) compared to a result of the machine learning model (f) both processing the same synthetic sensor data (z) and the same measured sensor data (x), - outputting (M6) to a user interface (33) the trained surrogate model (g) and the agreement accuracy (ACC).

traducir

TRUST RELATED MANAGEMENT OF ARTIFICIAL INTELLIGENCE OR MACHINE LEARNING PIPELINES IN RELATION TO THE TRUSTWORTHINESS FACTOR EXPLAINABILITY

NºPublicación: WO2023006193A1 02/02/2023

Solicitante:

NOKIA TECH OY [FI]

EP_4125012_PA

Resumen de: WO2023006193A1

There are provided measures for trust related management of artificial intelligence or machine learning pipelines in relation to the trustworthiness factor "explainability". Such measures exemplarily comprise, at a first network entity managing artificial intelligence or machine learning trustworthiness in a network, transmitting a first artificial intelligence or machine learning trustworthiness related message towards a second network entity managing artificial intelligence or machine learning trustworthiness in an artificial intelligence or machine learning pipeline in said network, and receiving a second artificial intelligence or machine learning trustworthiness related message from said second network entity, wherein said first artificial intelligence or machine learning trustworthiness related message is related to artificial intelligence or machine learning model explainability as a trustworthiness factor out of trustworthiness factors including at least artificial intelligence or machine learning model fairness, artificial intelligence or machine learning model explainability, and artificial intelligence or machine learning model robustness, said second artificial intelligence or machine learning trustworthiness related message is related to artificial intelligence or machine learning model explainability as said trustworthiness factor, and said first artificial intelligence or machine learning trustworthiness related message comprises a first information element inc

traducir

TRUST RELATED MANAGEMENT OF ARTIFICIAL INTELLIGENCE OR MACHINE LEARNING PIPELINES

NºPublicación: WO2023006188A1 02/02/2023

Solicitante:

NOKIA TECH OY [FI]

Resumen de: WO2023006188A1

There are provided measures for trust related management of artificial intelligence or machine learning pipelines. Such measures exemplarily comprise, at a first network entity managing artificial intelligence or machine learning trustworthiness in a network, transmitting a first artificial intelligence or machine learning trustworthiness related message towards a second network entity managing artificial intelligence or machine learning trustworthiness in an artificial intelligence or machine learning pipeline in said network, and receiving a second artificial intelligence or machine learning trustworthiness related message from said second network entity, wherein said first artificial intelligence or machine learning trustworthiness related message includes at least one criterion related to an artificial intelligence or machine learning trustworthiness aspect.

traducir

PROPENSITY MODELING PROCESS FOR CUSTOMER TARGETING

NºPublicación: US2023032739A1 02/02/2023

Solicitante:

DELL PRODUCTS L P [US]

Resumen de: US2023032739A1

In one aspect, an example methodology implementing the disclosed techniques includes receiving a historical customer dataset, the historical customer dataset reflective of pre-purchase, purchase, and post-purchase stages of a consumption process of a plurality of customers and identifying a plurality of first features, the plurality of first features derived from the historical customer dataset. The method also includes generating a first training dataset from the plurality of first features, training a first machine learning (ML) model using the first training dataset, and determining, using the first ML model, a plurality of second features. The method further includes generating a second training dataset from the plurality of second features and training a second ML model using the second training dataset, wherein the second ML model is trained to output propensity predictions for the plurality of customers.

traducir

MACHINE LEARNING PIPELINE FOR PREDICTIONS REGARDING A NETWORK

NºPublicación: US2023031889A1 02/02/2023

Solicitante:

JUNIPER NETWORKS INC [US]

US_2022004897_A1

Resumen de: US2023031889A1

This disclosure describes techniques that include using an automatically trained machine learning system to generate a prediction. In one example, this disclosure describes a method comprising: based on a request for the prediction: training each respective machine learning (ML) model in a plurality of ML models to generate a respective training-phase prediction in a plurality of training-phase predictions; automatically determining a selected ML model in the plurality of ML models based on evaluation metrics for the plurality of ML; and applying the selected ML model to generate the prediction based on data collected from a network that includes a plurality of network devices.

traducir

TEA IMPURITY DATA ANNOTATION METHOD BASED ON SUPERVISED MACHINE LEARNING

NºPublicación: US2023030210A1 02/02/2023

Solicitante:

KUNMING UNIV [CN]

CN_113569967_A

Resumen de: US2023030210A1

A tea impurity data annotation method based on supervised machine learning is provided. In particular, a feature vector of tea and impurity is first extracted by using a traditional image processing method, each element in the feature vector then is added with a corresponding annotation bit, a training dataset and a test dataset subsequently are divided by using a manual discrimination method, and afterwards data annotation is performed on each feature element in the test dataset. The manual method and the supervised machine learning method are combined, which can improve the accuracy and ensure the work efficiency.

traducir

METHOD FOR WATERMARKING A MACHINE LEARNING MODEL

NºPublicación: US2023029578A1 02/02/2023

Solicitante:

NXP B V [NL]

Resumen de: US2023029578A1

A method is provided for watermarking a machine learning model used for object detection. In the method, a first subset of a labeled set of ML training samples is selected. Each of one or more objects in the first subset includes a class label. A pixel pattern is selected to use as a watermark in the first subset of images. The pixel pattern is made partially transparent. A target class label is selected. One or more objects of the first subset of images are relabeled with the target class label. In another embodiment, the class labels are removed from objects in the subset of images instead of relabeling them. Each of the first subset of images is overlaid with the partially transparent and scaled pixel pattern. The ML model is trained with the set of training images and the first subset of images to produce a trained and watermarked ML model.

traducir

SYSTEMS AND METHODS FOR FORECASTING MACROECONOMIC TRENDS USING GEOSPATIAL DATA AND A MACHINE LEARNING MODEL

NºPublicación: US2023029983A1 02/02/2023

Solicitante:

SCHNEIDER ECONOMICS LLC [US]

WO_2021207518_A1

Resumen de: US2023029983A1

A system for forecasting macroeconomic trends using geospatial data and a machine learning model. The system may include a server computing device in communication with a user computing device via a network, the server computing device comprising a processor and a memory, the memory storing computer-executable instructions which are executed by the processor to: obtain images from a satellite imagery catalog; determine Normalized-Difference Built-Up Index (NDBI) values of one or more zones between various bands of the images; determine an average of the NDBI values for each zone; seasonally adjust the average NDBI values; obtain economic data from external sources; generate a stationarity dataset based on the adjusted NDBI values and the economic data; generate a statistical relationship model based on the stationarity dataset and economic activity of each zone; and forecast a macroeconomic trend based on the statistical relationship model and the current satellite imagery data.

traducir

DYNAMIC ACTION IDENTIFICATION FOR COMMUNICATION PLATFORM

NºPublicación: US2023029697A1 02/02/2023

Solicitante:

SALESFORCE COM INC [US]

Resumen de: US2023029697A1

A method that includes monitoring, by a communication service that is a participant to a channel of a communication platform, multiple inputs to the channel by other participants to the channel, where the communication service is configured to execute one or more machine learning models and access one or more external data platforms that are linked to the channel. The method may further include identifying, by the communication service and based on processing of an input by the one or more machine learning models, an action associated with a first external data platform, where the action is identified from a set of actions that are associated with the first external data platform and preconfigured for the communication platform. The method may further include triggering, by the communication service and based on identifying the action, execution of the action using data from the first external data platform.

traducir

FEDERATED MIXTURE MODELS

NºPublicación: US2023036702A1 02/02/2023

Solicitante:

QUALCOMM TECH INC [US]

BR_112022011012_PA

Resumen de: US2023036702A1

Aspects described herein provide a method of processing data, including: receiving a set of global parameters for a plurality of machine learning models; processing data stored locally on an processing device with the plurality of machine learning models according to the set of global parameters to generate a machine learning model output; receiving, at the processing device, user feedback regarding machine learning model output for the plurality of machine learning models; performing an optimization of the plurality of machine learning models based on the machine learning output and the user feedback to generate locally updated machine learning model parameters; sending the locally updated machine learning model parameters to a remote processing device; and receiving a set of globally updated machine learning model parameters for the plurality of machine learning models.

traducir

CLOUD INFRASTRUCTURE PLANNING ASSISTANT VIA MULTI-AGENT AI

NºPublicación: US2023036747A1 02/02/2023

Solicitante:

AT&T INTELLECTUAL PROPERTY I L P [US]

US_2020336388_A1

Resumen de: US2023036747A1

Cloud infrastructure planning systems and methods can utilize artificial intelligence/machine learning agents for developing a plan of demand, plan of record, plan of execution, and plan of availability for developing cloud infrastructure plans that are more precise and accurate, and that learn from previous planning and deployments. Some agents include one or more of supervised, unsupervised, and reinforcement machine learning to develop accurate predictions and perform self-tuning alone or in conjunction with other agents.

traducir

PRIVACY PRESERVING MACHINE LEARNING VIA GRADIENT BOOSTING

NºPublicación: US2023034384A1 02/02/2023

Solicitante:

GOOGLE LLC [US]

CN_114930357_PA

Resumen de: US2023034384A1

This describes a privacy preserving machine learning platform. In one aspect, a method includes receiving, by a first computing system of multiple multi-party computation (MPC) systems, an inference request including a first share of a given user profile. A predicted label for the given user profile is determined based at least in part on a first machine learning model. A predicted residue value for the given user profile indicating a predicted error in the predicted label is determined. The first computing system determines the first share of the predicted residue value for the given user profile based at least in part on the first share of the given user profile and a second machine learning model. The first computing system receives, from a second computing system of the MPC computing systems, data indicating the second share of the predicted residue value for the given user profile.

traducir

PEDESTRIAN INTENT YIELDING

NºPublicación: US2023031375A1 02/02/2023

Solicitante:

WAYMO LLC [US]

CN_115688552_PA

Resumen de: US2023031375A1

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, that determine yield behavior for an autonomous vehicle. An agent that is in a vicinity of an autonomous vehicle can be identified. An obtained crossing intent prediction characterizes a predicted likelihood that the agent intends to cross a roadway during a future time period. First features of the agent and of the autonomous vehicle are obtained. An input that includes the first features and the crossing intent prediction is processed using a machine learning model to generate an intent yielding score that represents a likelihood that the autonomous vehicle should perform a yielding behavior due to the intent of the agent to cross the roadway. From at least the intent yielding score, an intent yield behavior signal is determined and indicates whether the autonomous vehicle should perform the yielding behavior prior to reaching the first crossing region.

traducir

PEDESTRIAN INTENT YIELDING

NºPublicación: EP4124530A1 01/02/2023

Solicitante:

WAYMO LLC [US]

CN_115688552_PA

Resumen de: EP4124530A1

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, that determine yield behavior for an autonomous vehicle. An agent that is in a vicinity of an autonomous vehicle can be identified. An obtained crossing intent prediction characterizes a predicted likelihood that the agent intends to cross a roadway during a future time period. First features of the agent and of the autonomous vehicle are obtained. An input that includes the first features and the crossing intent prediction is processed using a machine learning model to generate an intent yielding score that represents a likelihood that the autonomous vehicle should perform a yielding behavior due to the intent of the agent to cross the roadway. From at least the intent yielding score, an intent yield behavior signal is determined and indicates whether the autonomous vehicle should perform the yielding behavior prior to reaching the first crossing region.

traducir

TRUST RELATED MANAGEMENT OF ARTIFICIAL INTELLIGENCE OR MACHINE LEARNING PIPELINES IN RELATION TO THE TRUSTWORTHINESS FACTOR EXPLAINABILITY

Nº publicación: EP4125012A1 01/02/2023

Solicitante:

NOKIA TECHNOLOGIES OY [FI]

Resumen de: EP4125012A1

There are provided measures for trust related management of artificial intelligence or machine learning pipelines in relation to the trustworthiness factor "explainability". Such measures exemplarily comprise, at a first network entity managing artificial intelligence or machine learning trustworthiness in a network, transmitting a first artificial intelligence or machine learning trustworthiness related message towards a second network entity managing artificial intelligence or machine learning trustworthiness in an artificial intelligence or machine learning pipeline in said network, and receiving a second artificial intelligence or machine learning trustworthiness related message from said second network entity, wherein said first artificial intelligence or machine learning trustworthiness related message is related to artificial intelligence or machine learning model explainability as a trustworthiness factor out of trustworthiness factors including at least artificial intelligence or machine learning model fairness, artificial intelligence or machine learning model explainability, and artificial intelligence or machine learning model robustness, said second artificial intelligence or machine learning trustworthiness related message is related to artificial intelligence or machine learning model explainability as said trustworthiness factor, and said first artificial intelligence or machine learning trustworthiness related message comprises a first information element inc

traducir

Página1 de 3 nextPage por página

punteroimgVolver