Alerta

CYBERSECURITY EVENT DETECTION, ANALYSIS, AND INTEGRATION FROM MULTIPLE SOURCES

Resumen de: US2025294033A1

The present disclosure presents methods and systems for determining cybersecurity risk exposure for entities. In one aspect, a method is provided that includes providing first text data to a trained LLM to identify data associated with a first candidate cybersecurity event for an entity, comparing the entity's identifier to domain information to verify the entity's identifier, determining if the first candidate cybersecurity event represents a new cybersecurity event based on com with previous data, and updating a cybersecurity risk score for the entity based on this determination. Further enhancements include training the LLM with cybersecurity event data, outputting documentation of the event source, and various methods for evaluating the novelty and severity of the cybersecurity event, including similarity measures and manual review triggers. The techniques leverage LLMs, machine learning models, and automated actions to provide a comprehensive approach to cybersecurity risk assessment and response. Other aspects are also provided.

Improved machine learning systems

Resumen de: AU2025202625A1

Systems and methods for training a machine learning (ML) model to predict outcomes is disclosed. The ML model includes a plurality of ML sub-models and an ensemble model. The method includes: receiving a plurality of data records; creating the ML sub-models based on the data records; assigning at least a subset of the data records to each of the ML sub-models; training each ML sub-model using the assigned subset of data records, each sub-model trained to determine a predicted outcome based on a given user data record; providing the predicted outcomes generated by each of the sub-models to the ensemble model, the ensemble model trained to combine the predicted outcomes from the sub-models to obtain a combined predicted outcome; using the trained ML model to determine a predicted outcome for an individual data record; and reusing the determined predicted outcome for the individual data record to retrain the ML model. Systems and methods for training a machine learning (ML) model to predict outcomes is disclosed. The ML model includes a plurality of ML sub-models and an ensemble model. The method includes: receiving a plurality of data records; creating the ML sub-models based on the data records; assigning at least a subset of the data records to each of the ML sub-models; training each ML sub-model using the assigned subset of data records, each sub-model trained to determine a predicted outcome based on a given user data record; providing the predicted outcomes generated by e

SEARCH REQUEST PROCESSING

Resumen de: EP4617903A1

Method, systems and computer programs for handling search requests at a search platform are provided. The search platform determines, using a cache with a number of incomplete search results, one or more of the incomplete search results with first data fields that correspond to the least one search parameter. For each determined incomplete search result, the search platform generates at least one second data field using a machine learning model. The at least one second data field corresponds to at least one search parameter and the at least one first data field of each determined incomplete search result. The search platform assembles a number of completed search results on the basis of the determined incomplete search results and the generated at least one second data field and returns at least one of the completed search results.

DIGITAL LIFESTYLE INTERVENTION SYSTEM USING MACHINE LEARNING AND REMOTE MONITORING DEVICES

Resumen de: WO2024102668A1

Systems and methods for a digital lifestyle intervention system using machine learning and remote monitoring devices is described herein. The disclosed systems can include a processor configured to train, based on historical user data, a personal machine learning model to generate an output indicative of a blood pressure prediction and lifestyle feature impact on blood pressure prediction. The trained personal machine learning model can be further configured to receive user data including blood pressure data for the user and generate output including lifestyle feature impact and a blood pressure prediction by applying the trained personal machine learning model to the received user data. At least one lifestyle recommendation can be generated based on the output of the trained personal machine learning model and/or output from a population model applied to the received user data. The at least one lifestyle recommendation can be provided to a user via a user interface.

MACHINE LEARNING TRAINING DURATION CONTROL

Resumen de: US2024152798A1

Some embodiments select a machine learning model training duration based at least in part on a fractal dimension calculated for a training data dataset. Model training durations are based on one or more characteristics of the data, such as a fractal dimension, a data distribution, or a spike count. Default long training durations are sometimes replaced by shorter durations without any loss of model accuracy. For instance, the time-to-detect for a model-based intrusion detection system is shortened by days in some circumstances. Model training is performed per a profile which specifies particular resources or particular entities, or both. Realistic test data is generated on demand. Test data generation allows the trained model to be exercised for demonstrations, or for scheduled confirmations of effective monitoring by a model-based security tool, without thereby altering the model's training.

SOFTWARE ASSESSMENT TOOL FOR MIGRATING COMPUTING APPLICATIONS USING MACHINE LEARNING

Resumen de: US2024152869A1

A computing system includes a processor; and a memory having stored thereon instructions that, when executed by the one or more processors, cause the system to: receive content migration project parameters, resource migration project parameters and one or more services parameters of a user; scan a tenant computing environment; process the parameters by applying a multiplier display the costs, profits and pricing information. A method includes receiving content migration project parameters, resource migration projecting parameters and one or more services parameters of a user; scanning a tenant computing environment; processing the parameters by applying a multiplier displaying the costs, profits and pricing information. A non-transitory computer readable medium includes program instructions that when executed, cause a computer to: receive content migration project parameters, resource migration project parameters and one or more services parameters of a user; scan a tenant computing environment; process the parameters by applying a multiplier display the costs, profits and pricing information.

HYBRID MACHINE LEARNING METHODS OF TRAINING AND USING MODELS TO PREDICT FORMULATION PROPERTIES

Resumen de: AU2023407504A1

Methods include training a machine learning module to predict one or more target product properties for a prospective chemical formulation, including (a) constructing or updating a training data set from one or more variable parameters; (b) performing feature selection on the training data set; (c) building one or more machine learning models using one or more model architectures; (d) validating the one or more machine learning models; (e) selecting at least one of the one or more machine learning models and generating prediction intervals; (g) interpreting the one or more machine learning models; and (h) determining if the one or more target product properties calculated are acceptable and deploying one or more trained machine learning models, or optimizing the one or more machine learning models by repeating steps (b) to (g). Methods also include application of trained machine learning modules to predict formulation properties from prospective data.

DETECTING COMPATIBILITY MISMATCH BY GENERATIVE ARTIFICIAL INTELLIGENCE

Resumen de: EP4617989A1

Detecting compatibility mismatch by generative artificial intelligence is described. Compatibility data is obtained (e.g., by accessing a database). The compatibility data is associated with a compatibility between items (e.g., items and categories of vehicles or an item and another item) and includes a list of recommended compatibilities between the items and a user reported compatibility for at least one item. A machine learning model is generated for detecting a compatibility mismatch between a first item and a second item and/or between an item and a category of vehicle. At least a portion of the compatibility data is provided as input to generative artificial intelligence to generate the machine learning model. An update to the list of recommended compatibilities is determined based on the detected compatibility mismatch.

SYSTEM AND METHOD FOR RECOGNIZING USER GESTURES OR OTHER MOVEMENT OR STATES

Resumen de: WO2025186543A1

A system comprising: at least one sensor configured to obtain sensor data representing at least one of muscle, nerve and/or brain activity of a user; a processing resource configured to: obtain unlabelled sample data from said sensor data for the user for a plurality of samples; apply a classifier to the sample data and/or data derived from said sample data to obtain a pseudo-label for each sample, wherein the pseudo-label represents similarity of the sample to a selected one of a plurality of gestures, movements or states or to each of the plurality of gestures, movements or states; wherein the system further comprises storage for storing sample data for a set of samples together with the obtained pseudo-label, wherein the processing resource is further configured to: update the sample data stored in the storage based on the obtained pseudo-labels of the samples; calibrate a trained or partially trained gesture recognition model or other machine learning derived model for the user using at least the sample data of the updated sample data stored in the storage.

SYSTEMS AND METHODS FOR REAL-TIME BIDDING

Resumen de: WO2025189094A1

A real-time bidding method includes receiving user input data, generating a first machine learning model that generates a predicted expected performance based on the user input data, and adjusting at least one bid on at least one of at least one keyword and at least one product associated with at least one marketplace, based on the predicted expected performance.

WIRELESS DEVICE POWER OPTIMIZATION UTILIZING ARTIFICIAL INTELLIGENCE AND/OR MACHINE LEARNING

Resumen de: AU2025220808A1

A method of reducing a power consumption of wireless communication circuitry of an edge device, the method comprising: learning, by an edge device, a delivery traffic indication map (DTIM) interval of a wireless access point communicatively coupled to the edge device via the wireless communication circuitry of the edge device using machine learning based on a machine learning model that includes an input associated with the DTIM interval; learning, by the edge device, at least one of (i) a number of Broadcasting/Multicasting Traffic messages received from the wireless access point that can be ignored without loss of a communication between the edge device and the wireless access point using machine learning, or (ii) a number of Address Resolution Protocol (ARP) packets received from the wireless access point that can be ignored without loss of a communication between the edge device and the wireless access point using machine learning; and adjusting, by the edge device, a wake-up interval of the wireless communication circuitry of the edge device based on the DTIM interval to reduce the power consumption of the wireless communication circuitry of the edge device. A method of reducing a power consumption of wireless communication circuitry of an edge device, the method comprising: learning, by an edge device, a delivery traffic indication map (DTIM) interval of a wireless access point communicatively coupled to the edge device via the wireless communication circuitry of the ed

CREATING AND DISTRIBUTING CUSTOMIZED ARTIFICIAL INTELLIGENCE CHATBOTS

Resumen de: US2025284963A1

Methods, systems, and apparatus, including computer programs encoded on computer-storage media, for creating and distributing customized artificial intelligence chatbots. In some implementations, a system provides an interface for creating or editing an interactive application configured to provide responses generated using one or more artificial intelligence (AI) or machine learning models. The system receives customization data through the interface, where the customization data indicates customizations specified by a user to customize the interactive application. The system stores one or more records specifying configuration settings representing the customizations for the interactive application. The system provides one or more users access to the interactive application with the customizations.

Data Pre-Processing for Search Indexes and Machine Learning Pipelines With a Common Specification

Resumen de: US2025284978A1

Methods, systems, and apparatus, including computer-readable storage media relating to a database management system (DBMS) configured to perform data searching and machine learning (ML) pre-processing using a common user specification. Two common functions associated with large databases are searching for data in the database and using data stored in databases for data-intensive processing, such as training or executing a machine learning model. While a single DBMS may implement separate sub-systems for searching and machine learning model processing that rely on similar operations, e.g., text processing, the respective interfaces for each sub-system are different and have different requirements for properly formed user input. A specification, when parsed by either a search sub-system or ML pre-processing system, can allow for correctly pre-processing data in accordance with the specification, without the user having to provide separate specifications for either sub-system.

MACHINE LEARNING BASED APPROACH FOR TARGETED ITEM RECOMMENDATIONS BASED ON LATENT RELATIONSHIPS AMONG USER FEATURES AND ITEMS OF DIFFERENT TYPES

Resumen de: US2025285010A1

A method for automatically recommending items in a software application. Embodiments include retrieving attributes of a user of the software application and retrieving a machine learning model that has been trained through a supervised learning process based on labeled training data indicating whether users represented by user features historically selected, within the software application, first items of a first item type and second items of a second item type. In certain embodiments, the machine learning model is configured, as a result of the supervised learning process, to recognize latent relationships between the first items of the first item type and the second items of the second item type based on distances between embeddings. Embodiments include providing inputs to the machine learning model based on the attributes of the user and receiving, in response, indications of one or more recommended items of the first item type or the second item type.

EXTRACTING WEAKLY CORRELATED RULES FROM SINGLE-TREE MACHINE LEARNING MODELS

Resumen de: US2025285008A1

Data associated with a plurality of transactions is accessed. Based on the data, a first tree-based machine learning model (e.g., a gradient boosted tree-based model) is generated that contains a plurality of first nodes and a plurality of first branches interconnecting the plurality of first nodes. A first rule is extracted from the first tree-based machine learning model. The data is adjusted after the first rule has been extracted. Based on the adjusted data, a second tree-based machine learning model (e.g., a gradient boosted tree-based model) is generated that contains a plurality of second nodes and a plurality of second branches interconnecting the plurality of second nodes. A second rule is extracted from the second tree-based machine learning model. The second rule and the first rule have a correlation below a specified threshold, for example, at or close to zero.

STREAMING ENGINE FOR MACHINE LEARNING ARCHITECTURE

Resumen de: US2025284499A1

A programmable hardware system for machine learning (ML) includes a core and a streaming engine. The core receives a plurality of commands and a plurality of data from a host to be analyzed and inferred via machine learning. The core transmits a first subset of commands of the plurality of commands that is performance-critical operations and associated data thereof of the plurality of data for efficient processing thereof. The first subset of commands and the associated data are passed through via a function call. The streaming engine is coupled to the core and receives the first subset of commands and the associated data from the core. The streaming engine streams a second subset of commands of the first subset of commands and its associated data to an inference engine by executing a single instruction.

MACHINE LEARNED FEATURE RECOMMENDATION ENGINE IN A DIGITAL TRANSACTION MANAGEMENT PLATFORM

Resumen de: US2025284774A1

An online document system provides a recommendation for one or more features within the online document system to an entity. The online document system accesses a set of feature training data to train a machine learning model. The set of feature training data may describe characteristics of entities associated with the online document system and historical activity associated with the entities' usage of the online document system's features. The machine learning model may be configured to identify a feature to recommend to an entity based on the entity's characteristics and history of using other features within the online document system. For example, data representing the entity's user accounts and use of an electronic signature feature is used by the machine learning model to identify a document authentication feature to recommend to the entity. The online document system may then provide the identified feature in a recommendation to the entity.

SYSTEM AND METHOD FOR CONSTRUCTING DIGITAL DOCUMENTS

Resumen de: US2025284730A1

In some aspects described herein, a computer-based system that is capable of constructing digital documents is provided. In some implementations, a machine learning system is provided that learns certain terms within a document. The terms may be, for example, part of a document that forms a legally-binding contract between two entities. In one implementation of the machine learning system, the machine learning system interoperates within a user interface to show predictions of certain terms within the document to the user. Further, the machine learning system may capture user answers relating to certain terms and provide feedback into the system that learns during operation of the system, improving user interactions, accuracy and reducing the number of user interactions.

ARTIFICIAL INTELLIGENCE CHATBOTS USING EXTERNAL KNOWLEDGE ASSETS

Resumen de: US2025284967A1

Methods, systems, and apparatus, including computer-readable media, for artificial intelligence chatbots using external knowledge assets. In some implementations, a system stores a knowledge base that comprises one or more knowledge items for an organization. The system receives a user prompt for a chatbot, and generates a chatbot response to the user prompt using one or more artificial intelligence and/or machine learning (AI/ML) chatbots. The chatbot response to the user prompt is generated at least in part based on the one or more AI/ML models processing the one or more knowledge items from the knowledge base. The system provides the chatbot response for presentation.

Automatic Generation of Floor Layouts

Resumen de: US2025285375A1

Aspects described herein relate to the automatic generation of floorplan layouts based on a floorplan image. Image data comprising an image of an area may be accessed. Based on the image data, a floorplan of the area may be determined. A determination of whether constraints associated with occupancy are met may be made. Based on the constraints being met, and based on the floorplan, a light zones map may be generated. Based on the light zones map, spatial zones corresponding to the light zones may be determined. Based on the spatial zones, candidate floorplan layouts may be generated. Based on application of metaheuristic algorithms or machine-learning models to the candidate floorplan layouts, a subset of candidate floorplan layouts may be selected from the plurality of candidate floorplan layouts. Furthermore, floorplan layout data comprising a subset of floorplan layouts for use by a design application may be generated.

Iterative machine learning interatomic potential (MLIP) training methods

Resumen de: GB2639070A

An iterative machine learning interatomic potential (MLIP) training method which includes training a first multiplicity of first MLIP models in a first iteration of a training loop; training a second multiplicity of second MLIP models in a second iteration of the training loop in parallel with the first training step; then combining the first MLIP models and the second MLIP models to create an iteratively trained MLIP configured to predict one or more values of a material. The values may be total energy, atomic forces, atomic stresses, atomic charges, and/or polarization. The MLIP may be a Gaussian Process (GP) based MLIP (e.g. FLARE). The MLIP may be a graph neural network (GNN) based MLIP (e.g. NequIP or Allegro). A third MLIP model may be used when predicted confidence or predicted uncertainty pass a threshold. The MLIP models may use different sets of hyperparameters. The first and second MLIP models may use different starting atomic structures or different chemical compositions. Iteration can involve selection of the model with the lowest error rate. Combination can be to account for atomic environment overlap or atomic changes in energies. Training may be terminated when a model is not near a Pareto front.

USER INTERFACE FOR MATERIALS AND MATERIAL PROPERTIES PREDICTION USING A MACHINE LEARNING MODEL

Resumen de: AU2023409235A1

Machine learning can be used to predict formulations for an output formulation. The machine learning can be implemented by a machine learning model, which employs a forward model and an inverse model. A user interface can be used to gather raw materials selections and output formulation property selections. The selections can be used to generate formulations that comply with selections using the ML model.

EXTENSIBLE MACHINE LEARNING POWERED BEHAVIORAL FRAMEWORK FOR RISK COVERAGE

Resumen de: US2025272617A1

Some aspects of the present disclosure relate to systems, methods and computer readable media for outputting alerts based on potential violations of predetermined standards of behavior. In one example implementation, a computer implemented method includes: training a natural language-based machine learning model to detect at least one risk of a violation condition in an electronic communication between persons, wherein the violation condition is a potential violation of a first predetermined standard of behavior; receiving a lexicon, wherein the lexicon comprises topic data; receiving connection data representing a relationship between the trained machine learning model and the lexicon; detecting, using the trained machine learning model, the lexicon, and the connection data, a potential violation of a second predetermined standard of behavior; and outputting for display an alert indicating the potential violation of the second predetermined standard of behavior.

Computer-based systems, computing components and computing objects configured to implement dynamic outlier bias reduction in machine learning models

Resumen de: GB2639108A

Receiving training data for a user activity, well drilling; receiving bias criteria; determining a set of model parameters for a machine learning model including: (1) applying the machine learning model to the training data; (2) generating model prediction errors; (3) generating a data selection vector to identify non-outlier target variables based on the model prediction errors; (4) utilizing the data selection vector to generate a non outlier data set; (5) determining updated model parameters based on the non-outlier data set; and (6) repeating steps (1)-(5) until a censoring performance termination criterion is satisfied; training classifier model parameters for an outlier classifier machine learning model; applying the outlier classifier machine learning model to activity-related data to determine non-outlier activity-related data; and applying the machine learning model to the non-outlier activity related data to predict future activity-related attributes for the user activity.

AUTONOMOUS RECOMMENDATION SYSTEMS USING MACHINE LEARNING

Nº publicación: US2025278645A1 04/09/2025

Solicitante:

TORONTO DOMINION BANK [CA]
THE TORONTO-DOMINION BANK

Resumen de: US2025278645A1

An AI-driven recommendation system utilizes a machine learning model and a dynamically updated knowledge graph to generate personalized product recommendations. The system constructs a knowledge graph with nodes and edges representing relationships between users, prior product selections, and historical interactions. A supervised learning framework trains the machine learning model using labeled data from the knowledge graph to predict relevant products based on multi-dimensional constraints. A graphical user interface (GUI) presents dynamically adjusted interactive elements to capture user preferences. User responses are processed using natural language processing (NLP) to refine predictions and generate recommendations. The system continuously updates the knowledge graph with real-time user feedback and external data, retraining the machine learning model to enhance future recommendations. This adaptive approach enables personalized, context-aware recommendations that evolve based on user interactions and external influences.