Resumen de: US2023162289A1

Provided is a process of modeling methods organized in racks of a machine learning pipeline to facilitate optimization of performance using modelling methods for implementation of machine learning design in an object-oriented modeling (OOM) framework, the process including: writing classes using object-oriented modelling of optimization methods, modelling methods, and modelling racks; writing parameters and hyper-parameters of the modeling methods as attributes as the modeling methods; scanning modelling racks classes to determine first class definition information; selecting a collection of rack and selecting modeling method objects; scanning modelling method classes to determine second class definition information; assigning racks and locations within the racks to modeling method objects; and invoking the class definition information to produce object manipulation functions that allow access the methods and attributes of at least some of the modeling method objects, the manipulation functions being configured to effectuate writing locations within racks and attributes of racks.

Resumen de: US2023162082A1

A method for integrating a machine learning (ML) model that impacts different factor groups for generating a dynamic recommendation to collectively optimize a parameter is provided. The method includes (i) processing a specification information and operational data associated with a demand management service obtained from client devices (116A-N), (ii) training the ML models with processed specification information and the operational data to obtain a trained ML model that includes an anticipation ML model that optimizes demand parameter or recommendation ML model that generates recommendation for optimizing a factor group, (iii) integrating the trained ML model with the ML models by setting an output of a first ML model as a feature of a second ML model and (iv) determining a demand of a product using the trained ML models and quantifying probabilistic values that signify prediction of the demand.

Resumen de: US2023162063A1

Apparatuses, systems, program products, and methods are disclosed for interpretability-based machine learning adjustment during production. An apparatus includes a first results module that is configured to receive a first set of inference results of a first machine learning algorithm during inference of a production data set. An apparatus includes a second results module that is configured to receive a second set of inference results of a second machine learning algorithm during inference of a production data set. An apparatus includes an action module that is configured to trigger one or more actions that are related to a first machine learning algorithm in response to a comparison of first and second sets of inference results not satisfying explainability criteria.

Resumen de: US2023161843A1

Apparatuses, systems, program products, and method are disclosed for detecting suitability of machine learning models for datasets. An apparatus includes a training evaluation module configured to calculate a first statistical data signature for a training data set of a machine learning system using one or more predefined statistical algorithms. An apparatus includes an inference evaluation module configured to calculate a second statistical data signature for an inference data set of a machine learning system using one or more predefined statistical algorithms. An apparatus includes a score module configured to calculate a suitability score describing the suitability of a training data set to an inference data set as a function of a first and a second statistical data signature. An apparatus includes an action module configured to perform an action related to a machine learning system in response to a suitability score satisfying an unsuitability threshold.

Resumen de: WO2023091507A1

The present invention is directed to image/video retrieval methods and techniques. According to a specific embodiment, a text query is received from a user. The most relevant images and/or video segments are identified and retrieved using a hashing model, which is trained using a machine learning process. A cross-modal affinity matrix may be used for training purposes. There are other embodiments as well.

Resumen de: US2023161946A1

Systems and methods are disclosed for manually and programmatically remediating websites to thereby facilitate website navigation by people with diverse abilities. For example, an administrator portal is provided for simplified, form-based creation and deployment of remediation code, and a machine learning system is utilized to create and suggest remediations based on past remediation history. Voice command systems and portable document format (PDF) remediation techniques are also provided for improving the accessibility of such websites.

Resumen de: US2023157790A1

Embodiments relate to an aligner breakage solution that tests damage to an aligner using machine learning. A method includes of training a machine learning model to predict damage to an orthodontic aligner includes gathering a training dataset comprising digital designs for a plurality of orthodontic aligners, wherein each digital design is associated with a respective orthodontic aligner of the plurality of orthodontic aligners, and wherein each digital design comprises metadata indicating whether the associated respective orthodontic aligner was damaged during manufacturing of the associated respective orthodontic aligner. The method further includes training the machine learning model using the training dataset, wherein the machine learning model is trained to process data from a digital design for an orthodontic aligner and to output a probability that the orthodontic aligner associated with the digital design will be damaged during manufacturing of the orthodontic aligner.

Resumen de: US2023161070A1

The present disclosure describes various embodiments of systems, apparatuses, and methods for large-scale processing of weather-related data. For one such system, the system comprises a database of weather-related data providing from at least one weather monitoring station and at least one processor for coordinating a data processing job for processing a set of input weather-related data from the database. Accordingly, the input data comprises sensor data from the at least one weather monitoring station positioned on an open shoreline during a hydrodynamic event, weather model data for the hydrodynamic event, and at least one of air-craft reconnaissance data or satellite reconnaissance data regarding the hydrodynamic event, wherein the at least one processor is configured to assimilate the input data and generate, using machine learning, an improved weather prediction model for the hydrodynamic event. Other systems, apparatuses, and methods are also provided.

Resumen de: US2023162096A1

The present disclosure relates to systems, methods, and computer readable media that evaluate performance of a machine learning system in connection with a test dataset. For example, systems disclosed herein may receive a test dataset and identify label information for the test dataset including feature information and ground truth data. The systems disclosed herein can compare the ground truth data and outputs generated by a machine learning system to evaluate performance of the machine learning system with respect to the test dataset. The systems disclosed herein may further generate feature clusters based on failed outputs and corresponding features and generate a number of performance views that illustrate performance of the machine learning system with respect to clustered groupings of the test dataset.

Resumen de: WO2023091275A1

Techniques to generate a digitally optimized schedule for a construction activity to meet a construction objective(s) of a construction project are disclosed. An artificial intelligence system receives a plurality of input data sets that impact the construction project. Each of the plurality of input data sets is processed to achieve the construction objective(s). The artificial intelligence system processes the plurality of input data sets using a respective ensemble of machine learning models. The artificial intelligence system generates machine learning validated intermediate output data sets corresponding to each of the plurality of input data sets. The artificial intelligence system implements a supervisory machine learning model to generate an optimized schedule for the construction activity based on the machine learning validated intermediate output data sets and the construction objective(s).

Resumen de: US2023162061A1

A method and system for using a trained machine learning model with respect to information pertaining to a job title of multiple job titles to determine a job family of multiple job families that corresponds to the job title is disclosed. First input comprising information identifying the job title associated with an organization of a plurality of organizations is provided to the trained machine learning model. One or more outputs identifying (i) an indication of the job family that identifies a category of personnel positions that are categorized based on one or more characteristics that are shared between the personnel positions of the category, and (ii) a level of confidence that the job family corresponds to the job title is obtained from the trained machine learning model.

Resumen de: US2023162083A1

In example embodiments, machine learning techniques are provided for ensuring quality and consistency of the data in a digital representation of infrastructure (e.g., a BIM or digital twin). A machine learning model learns the structure of the digital representation of infrastructure, and then detects and suggests fixes for data errors. The machine learning model may include an embedding generator, an autoencoder, and decoding logic, employing embeddings and metamorphic truth to enable the handling of heterogenous data, with missing and erroneous property values. The machine learning model may be trained in an unsupervised manner from the digital representation of infrastructure itself (e.g., by assuming that a significant portion is correct). An SME review workflow may be provided to correct predictions and inject ground truth to improve performance.

Resumen de: US2023162095A1

Churn-aware training of a classifier which reduces the difference between predictions of two different models, such as a prior generation of a classification model and a subsequent generation. A second dataset of labelled data is scored on a prior generation of a classification model, wherein the prior generation was trained on a first dataset of labelled data. A subsequent generation of a classification model is trained with the second dataset of labelled data, wherein in training of the subsequent generation, weighting of at least some of the labelled data in the second dataset, such as labelled data threat yielded an incorrect classification, is adjusted based on the score of such labelled data in the prior generation.

Resumen de: US2023162050A1

A method and device for predicting and controlling time series data based on automatic learning are disclosed. According to an example embodiment, the method of predicting and controlling the time series data based on automatic learning includes training a plurality of time series data prediction models according to conditions respective for the models, determining, among the trained time series data prediction models, one or more optimal models that meet a predetermined condition, and generating a final model by combining the one or more optimal models, wherein the plurality of time series data prediction models includes at least one of statistical-based prediction models and deep learning-based prediction models.

Resumen de: US2023162062A1

Techniques are described herein for reducing the computing cost of decision-making when simulating a real-world system. A machine learning model is trained using data generated by a simulator of the real-world system. Knowledge about how the simulator is implemented is used to improve the efficiency of the machine learning model and to improve the relevance of data selected to train the machine learning model. For example, structural knowledge—the flow of input variables through components of the simulator—is used to determine a causal relationship between input variables. Having identified the causal relationship, the number of simulator iterations used to generate training data may be reduced. Furthermore, large complex machine learning models may be replaced with smaller, more efficient models. Additionally, or alternatively, causal relationships between input variables are identified during training, enabling further refinement of input selection and model design.

Resumen de: US2023162060A1

Various examples are provided related to identification of protected information elements associated with unique entities in data files present in data file collections associated with enterprise IT networks. The unique entities can be associated with one or more entity identifications in one or more data files. Computer-generated identification of entity identifications and protected information elements can be conducted, in part, by at least some human review. Information generated accordingly to the disclosed methodology can be used to generate plans for a time and number of human reviewers needed to review data files. Information generated from the processes herein can be configured as user notifications, reports, dashboards, machine learning for subsequent data file analyses, and notifications of unique entities having protected information elements present in one or more data files.

Resumen de: EP4184395A1

In an embodiment, each of a set of subgraphs associating an entity from an entity graph with an item is extracted from a graph database. A label score, which is an importance of an item to a respective entity is computed for each subgraph. A training dataset including the set of subgraphs and the label score for each subgraph is generated. A set of ML regression models is trained on respective entity-specific subsets of the training dataset. An ML regression model associated with a second entity generates a prediction score for an unseen graph. From the set of subgraphs, one or more subgraphs associated with the second entity are determined based on the prediction score. A recommendation for one or more items is determined, based on the one or more subgraphs. The recommendation is displayed on a user device of the first entity.

Resumen de: GB2613117A

A method comprises analyzing, by a machine-learning model, a first network communication with a first set of inputs. The method also comprises inferring, by the machine-learning model and based on the analyzing, that a first device that is a party to the first network communication exhibits a device property. The method also comprises extracting, from the machine-learning model, a first set of significant inputs that had a significant impact on the determining. The method also comprises creating, using the first set of inputs, a rule for identifying the device property. The rule establishes a condition that, when present in a network communication, implies that a party to the network communication exhibits the device property.

Resumen de: EP4184347A1

The invention regards a computer-implemented method of collecting, organizing and storing data relating to the memories of a user. Automatically collected data are separated into digital raw files and processed by: inputting (203) the raw files into at least one machine learning identification module, ML ID module, and receiving as semantic output of the ML ID module a first cognitive block of information, providing (204) a first factual block of information that comprises at least one attribute relating to the first cognitive block of information, the first factual block of information being automatically provided through interaction with a first database (5), pairing (205) the first cognitive block of information and the first factual block of information into a meta pair of information, and logging (206) the meta pair of information and a reference to the respective processed raw file in a second database (6). The invention further regards a data processing system (10) of collecting, organizing and storing data relating to the memories of a user.

Resumen de: EP3958271A1

A computer-implemented method (100) for predicting hydrocarbon fluid properties using machine-learning-based models is provided. The method comprises the step of receiving (101) a minimal set of pressure-volume-temperature (PVT) data for hydrocarbon fluid samples from a PVT data base; reading (102) the minimal set of PVT data by a reader module; transforming (103) the minimal set of PVT data into a unified data structure by the reader module; selecting (104) items of the PVT data from the minimal set of PVT data by the reader module; processing (105) the selected items of the PVT data by a correlating module to identify a plurality of correlations in the selected items of the PVT data based on one or more of the fluid properties of the hydrocarbon fluid samples; clustering (106), using of at least one of a plurality of clustering algorithms, the selected items of the PVT data into a plurality of clusters by a clustering module; and performing (107) machine learning by a machine learning module on ones of the plurality of clusters to predict missing fluid properties in the minimal set of PVT data and thus to obtain a complete set of PVT data. Further a computer-implemented method (200) for generating equations of state (EoS) for a plurality of hydrocarbon fluids is provided. The method comprises the step of delumping (201) pressure-volume-temperature (PVT) data for hydrocarbon fluid samples from a complete set of PVT data to one of a set of detailed fluid components, or to a c

Resumen de: KR20230069428A

본 발명의 일 실시 예에 따른 머신러닝(Machine Learning)/딥러닝(Deep Learning) 모델을 이용한 메타데이터(Metadata) 생성 장치가 데이터의 타입 - 상기 데이터의 타입은 숫자형, 문자형, 범주형 및 날짜형을 포함함 - 을 자동으로 판별하여 메타데이터를 생성하는 방법은 (a) 수신한 데이터의 필드값이 날짜형 타입인지 1차적으로 판단하는 단계, (b) 상기 (a) 단계의 판단 결과, 날짜형 타입이 아니라고 1차적으로 판단되었다면, 상기 수신한 데이터의 필드값에 메타데이터 생성 규칙이 포함하는 데이터 타입 결정 조건을 적용하여 범주형 및 날짜형 중 어느 하나의 타입인지 2차적으로 판단하는 단계, (c) 상기 (b) 단계의 판단 결과, 범주형 및 날짜형 중 어느 하나의 타입이 아니라고 2차적으로 판단되었다면, 상기 수신한 데이터의 필드명을 상기 메타데이터 생성 규칙이 포함하는 데이터 타입의 판별에 관한 필드 매핑 테이블(Field Mapping Table)에 적용하여 숫자형, 문자형, 범주형 및 날짜형 중 어느 하나의 타입인지 최종적으로 판단하고 메타데이터를 생성하는 단계 및 (d) 상기 생성한 메타데이터를 머신러닝/딥러닝 모델로 학습하여 상기 메타데이터 생성 규칙을 업데이트하는 단계를 포함한다.

Resumen de: WO2023085649A1

The present invention proposes a device and a method for predicting behavior recognition or the physical property of an object by using a channel state information (CSI) pattern change and standard deviation. The prediction device according to the present invention comprises: a transmission/reception unit provided in a specific space so as to process a WiFi signal obtained by sensing a person or an object; a first data pre-processing unit for obtaining a standard deviation value corresponding to a pattern change in CSI data transmitted through the WiFi signal; a second data pre-processing unit for obtaining time-series data of the standard deviation value; a learning unit for learning the time-series data through machine learning; and a prediction unit for predicting a behavior of the person or a lattice density of the object by analyzing the machine learning result. According to the present invention, a behavior of a person or a characteristic of an object can be predicted without separate equipment by using a pre-constructed WiFi communication infrastructure.

Resumen de: WO2023085984A1

A method for use in protecting a first machine learning model that is queryable over an application programming interface, API, against an adversary querying the first machine learning model through the API in order to build up a database of query-response pairs. The method comprises: identifying (202) a user of the API as a potential adversary. In response to a query from the potential adversary, through the API, then method comprises providing (204) a response from a second machine learning model instead of the first machine learning model, wherein the first machine learning model has been trained on a first dataset and wherein the second machine learning model has been trained on a second dataset that is different to the first dataset.

Resumen de: US2023156075A1

A machine learning engine identifies training data that includes historical user data and historical content data. A machine learning classifier is trained on the training data to generate a relevancy value for each of a plurality of given content items associated with a given user. The relevancy value for each given content item is indicative of a likelihood that the given user will perform a first user device input action and of a likelihood that the given user will perform a second user device input action, in response to being presented with the given content item. The machine learning classifier receives a plurality of candidate content items associated with a first user. The machine learning classifier generates a relevancy value for each candidate content item. At least one of the candidate content items is identified for inclusion in a first content collection based on the generated relevancy values.

Resumen de: US2023153342A1

A computer-implemented method includes obtaining a plurality of textual records divided into clusters and a residual set of the textual records, where a machine learning (ML) clustering model has divided the plurality of textual records into the clusters based on a similarity metric. The method also includes receiving, from a client device, a particular textual record representing a query and determining, by way of the ML clustering model and based on the similarity metric, that the particular textual record does not fit into any of the clusters. The method additionally includes, in response to determining that the particular textual record does not fit into any of the clusters, adding the particular textual record to the residual set of the textual records. The method can additionally include identifying, by way of the ML clustering model, that the residual set of the textual records contains a further cluster.