If you want to distinguish your goods, services or both from those of another company, you may need a trademark or trade name. Find out what they are, what their registration procedure is and what it involves.
Information on the deadlines for filing applications for transformation of European Union trademarks into Spanish national trademarks. See more
If you have a new device, product or procedure that solves a technical problem or has a practical advantage, there are different ways to protect it in Spain and other countries. Find out how.
Does your innovation lie in the aesthetics, ornamentation or appearance of your product? Protect it through industrial design. Find out what rights registration confers and how to proceed.
Patents published worldwide are a valuable source of scientific, technical and commercial information.
Los Bonos 1, 2 y 3 se encuentran actualmente cerrados. En las próximas semanas se proporcionará más información acerca de su apertura de cara a 2025.
If you are an entrepreneur or a company and you want to boost and improve the profitability of your business by adequately protecting the intangible assets of your organisation, in this space you will find what you need.
81
results.
Updated on
26/12/2024 [07:41:00]
Absstract of: WO2023158713A1
The present disclosure provides systems and methods for classifying lupus disease state of a patient is disclosed. The method can include analyzing a patient data set comprising or derived from gene expression measurements data of at least 2 genes, from a biological sample obtained or derived from the patient, to classify the lupus disease state of the patient. The at least 2 genes can be selected from Tables 17-1 to 17- 30, and/or Tables 24-1 to 24-30.
Absstract of: EP4481632A1
System (SYS.MS) and related method for facilitating an assessment operation in relation to a trained machine learning model. The system comprises an input interface (IN) for receiving i) parameters of the trained machine learning model (M), and ii) output data producible by the trained model (M), in response to input data processable by the trained model (M). An analyzer component (AZ) computes, based on the output data, a contribution value per model parameter. The contribution value per parameter is configured to measure, given the input data, a respective contribution to the output data of the respective parameter. The contribution values form a contribution map for the trained model given the input data. The analyzer provides the contribution map for the assessment operation in relation to the trained model (M).
Absstract of: GB2631185A
An Industrial Virtual Assistant (IVA) platform with Robotic Process Automation that operates like a Digital Knowledge Companion and allows operational staff at industrial facilities to have natural language conversations with the IVA to obtain information about, and to control operations of, industrial facilities, and which automates certain processes based in part on those natural language conversations. In an embodiment, the platform uses a Robotic Process Automater (RPA) to ingest information from documentation, human inputs, and operational data from the facility, organize that information into a knowledge graph containing comprehensive facility information, and apply machine learning algorithms to the knowledge graph to provide natural language responses to human queries and to automate certain processes of the facility.
Absstract of: EP4480558A1
An electronic chip, a chip assembly, a computing device, and a method are described. The electronic chip comprises a plurality of processing cores and at least one hardware interface coupled to at least one of the one or more processing cores. At least one processing core implements a game engine and/or a simulation engine and at least one or more processing cores implements an artificial intelligence engine, whereby implementations are on-chip implementations in hardware by dedicated electronic circuitry. The at least one or more game and/or simulation engines performs tasks on sensory, generating data sets that are processed through machine learning algorithms by the hardwired artificial intelligence engine. The data sets processed by the hardwired artificial intelligence engine include at least contextual data and target data, wherein combining both data and processing by dedicated hardware results in enhanced machine learning processing.
Absstract of: WO2024255997A1
A data processing apparatus (10) for enhancing, in particular optimizing a machine learning, ML, model for parallelized operation on a plurality of processing devices (20) is disclosed, wherein each processing device (20) comprises a plurality of processing elements, PEs, (21a- d) configured to perform one or more of a plurality of ML model tasks. The data processing apparatus (10) is configured to generate based on the ML model a computational graph, CG, representation (30) of the ML model, wherein the CG representation (30) comprises a plurality of nodes (31) and a plurality of edges (32), wherein each of the plurality of nodes (31) is associated with one or more of the plurality of ML model tasks and wherein the plurality of edges (32) define a plurality of dependencies of the plurality of nodes (32) of the CG representation (30). Furthermore, the data processing apparatus (10) is configured to generate an enhanced CG representation of the ML model by adding to the CG representation (30) of the ML model one or more further dependencies of the plurality of nodes (31) of the CG representation (30) of the ML model. The data processing apparatus (10) is further configured to compile the enhanced CG representation of the ML model for generating code for each of the plurality of processing devices (20).
Absstract of: WO2024258645A1
A computer-implemented method comprising detecting, by an application in a focussed operating mode, a trigger event; determining, using machine learning (ML) content classification applied to content associated with the trigger event, that content associated with the trigger event does not match a permitted topic associated with the focussed operating mode; and based on determining that the second content does not match the permitted topic applicable to the focussed operating mode, suppressing, by the application in the focussed operating mode, notification of the second trigger event.
Absstract of: US2024420840A1
A method, computer program product, and computer system for converting controller data uploaded to the cloud to digital report stored on the cloud and accessible via an online portal. One or more data packets from a controller of a compressor are received over a network, the one or more data packets including data associated with technical parameters of the compressor at a given state of the compressor. The data contained in the data packets are converted to a digital report of the given state of the compressor in a human readable format. The digital reports are stored in one or more databases accessible through an online portal associated with the computer system. One or more artificial intelligence models and machine learning techniques are leveraged to improve failure event predicting and corrective action response time for technical system, using the digital reports as input datasets.
Absstract of: US2024419994A1
A system for predicting performance of building equipment is configured to determine whether a machine learning model is capable of generating a predicted performance of the building equipment based on sensor data obtained while operating the building equipment. The machine learning model is used to generate the predicted performance if the machine learning model is determined to be capable, whereas additional data related to the predicted performance of the building equipment are obtained if the machine learning model is determined to be not capable. The system determines whether the building equipment is in need of maintenance based on the predicted performance generated using the machine learning model and/or the additional data and automatically initiates a maintenance activity for the building equipment in response to determining that the building equipment is in need of maintenance.
Absstract of: US2024420229A1
A system may identify, using a machine learning model, a series of recurring events associated with an account and may generate, using the machine learning model, a prediction of a future date on which a predicted event, associated with the series of recurring events, is to occur. The system may determine that a condition associated with the account is satisfied and may determine that a current date is within a threshold number of days of the future date based on the prediction of the future date. The system may transmit, to a user device, a notification based on determining that the current date is within the threshold number of days of the future date and that the condition associated with the account is satisfied, wherein the notification includes information for presentation of an input element that enables an action to be performed in connection with the account.
Absstract of: US2024419713A1
Systems and methods managing, by an orchestrator, a plurality of agents to generate a response to an input. The orchestrator employs one or more multimodal models such as a large language models to process or deconstruct the prompt into a series of instructions for different agents. Each agent employs one or more machine-learning models to process disparate inputs or different portions of an input associated with the prompt. The system generates, by the orchestrator, a natural language summary of the structured and unstructured data records. The system formulates output and transmits the natural language summary of the data records.
Absstract of: US2024422194A1
Aspects of the disclosure relate to detecting impersonation in email body content using machine learning. Based on email data received from user accounts, a computing platform may generate user identification models that are each specific to one of the user accounts. The computing platform may intercept a message from a first user account to a second user account and may apply a user identification model, specific to the first user account, to the message, so as to calculate feature vectors for the message. The computing platform then may apply impersonation algorithms to the feature vectors and may determine that the message is impersonated. Based on results of the impersonation algorithms, the computing platform may modify delivery of the message.
Absstract of: US2024419984A1
A computer-implemented method comprising detecting, by an application in a focussed operating mode, a trigger event; determining, using machine learning (ML) content classification applied to content associated with the trigger event, that content associated with the trigger event does not match a permitted topic associated with the focussed operating mode; and based on determining that the second content does not match the permitted topic applicable to the focussed operating mode, suppressing, by the application in the focussed operating mode, notification of the second trigger event.
Absstract of: US2024419714A1
A system and method for data management is provided. The method includes obtaining a dataset from a data source by a processing unit. The dataset includes a plurality of datapoints, and each of the datapoints belongs to a column among a plurality of columns. Further, an ontology label for at least one column in the dataset is predicted using a machine learning model. The predicted ontology label is associated with an ontology comprising a plurality of ontology labels. Further, a mapping between the dataset and the ontology is generated based on the relation between the predicted ontology label and the column. Furthermore, the datapoints are classified with respect to the ontology labels based on the mapping generated. The classified datasets are outputted on a user interface.
Absstract of: WO2024258464A1
Techniques for generating synthetic data for machine learning (ML) models are described. A system includes a language model that processes a task and a corresponding set of example inputs to generate another input, referred to herein as a machine-generated data. The machine-generated data is processed using a ML model (that data is being generated for) to determine a model output, and the model output is analyzed to determine whether it corresponds to a target output. If the model output corresponds to the target output, then the machine-generated data is added to the set of example inputs and one of the original example inputs is removed to generate an updated set of example inputs. The updated set can be used for various training techniques.
Absstract of: US2024416971A1
A method for implementing a machine learning model to predict risk exposure can include acquiring, via a sleep detecting device associated with a user, a set of user data. The method for implementing the machine learning model can also include predicting, by at least a trained ML model, a level of risk exposure for an other activity for the user. The trained ML model can be trained utilizing data indicative of one or more sleep patterns and data indicative of the other activity to identify one or more relationships between the one or more sleep patterns and the level of risk exposure for the other activity. The method can further include generating a notification to alert the user of the level of risk exposure, as predicted, for the other activity. Other embodiments are disclosed.
Absstract of: US2024420032A1
Aspects relate to a machine learning system implementing an evolutionary boosting machine. The system may initially select randomized feature sets for an initial generation of candidate models. Evolutionary algorithms may be applied to the system to create later generations of the cycle, combining and mutating the feature selections of the candidate models. The system may determine optimal number of boosting iterations for each candidate model in a generation by building boosting iterations from an initial value up to a predetermined maximum number of boosting iterations. When a final generation is achieved, the system may evaluate the optimal model of the generation. If the optimal boosting iterations of the optimal model does not meet solution constraints on the optimal boosting iterations, the system may adjust a learning rate parameter and then proceed to the next cycle. Based on termination criteria, the system may determine a resulting/final optimal mode.
Absstract of: US2024419985A1
Certain aspects of the disclosure pertain to predicting a candidate entity match for a transaction with a machine learning model. A description of a transaction comprising encoded transaction data associated with an organization is received as input. In response, at least one machine learning model can be invoked to infer a transaction embedding based on the description, a first score that captures similarity between the transaction embedding entity embeddings associated with a global list of entities and organizations, a second score that captures a probability of interaction between the first organization and the entities based on organization and entity embeddings that capture profile data associated with the organization and the entities, and at least one candidate entity based on the first score and the second score. Finally, the inferred candidate entity can be output for use by an automated data entry or other process or system.
Absstract of: EP4478251A1
The present invention relates to a computer-implemented method for building a layered regressor chains model for performing a multi-target prediction in a machine learning system, using an input dataset of (N) samples, a predefined number (L) of target variables in said input dataset, a predefined number (K) of re-prediction layers, and a predefined number of connections (p) between every two consequent re-prediction layers, the method comprising at least the steps of:- replicating said target variables as many times as the number K of re-prediction layers, creating a copy of each target variable for each next re-prediction layer,- for each re-prediction layer, generating a random linear order on target vertices, andadding p connections from random vertices of the k-th re-prediction layer to random vertices of the (k + 1)-th re-prediction layer, in order to build said layered regressor chains model and obtain a prediction result.
Absstract of: GB2631068A
A machine learning system 600 for processing transaction data. The machine learning system 600 has a first processing stage 603 with: an interface 622 to receive a vector representation of a previous state for the first processing stage; a time difference encoding 628 to generate a vector representation of a time difference between the current and previous iterations/transactions. Combinatory logic (632, fig 6b) modifies the vector representation of the previous state based on the time difference encoding. Logic (634, fig 6b) combines the modified vector representation and a representation of the current transaction data to generate a vector representation of the current state. The machine learning system 600 also has a second processing stage 604 with a neural network architecture 660, 690 to receive data from the first processing stage and to map said data to a scalar value 602 representative of a likelihood that the proposed transaction presents an anomaly within a sequence of actions. The scalar value is used to determine whether to approve or decline the proposed transaction. The first stage may comprise a recurrent neural network and the second stage may comprise multiple attention heads.
Absstract of: GB2631032A
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.
Absstract of: EP4478145A1
A method, computer program product, and computer system for converting controller data uploaded to the cloud to digital report stored on the cloud and accessible via an online portal. One or more data packets from a controller of a compressor are received over a network, the one or more data packets including data associated with technical parameters of the compressor at a given state of the compressor. The data contained in the data packets are converted to a digital report of the given state of the compressor in a human readable format. The digital reports are stored in one or more databases accessible through an online portal associated with the computer system. One or more artificial intelligence models and machine learning techniques are leveraged to improve failure event predicting and corrective action response time for technical system, using the digital reports as input datasets.
Absstract of: WO2024251381A1
Embodiments relate to providing self-learning automated information technology change risk prediction. A processor inputs a change request to a first machine learning model, the first machine learning model determining at least one word pair in the change request, the change request being a modification in an IT environment. The processor classifies the at least one word pair into a change category for the IT environment using a second machine learning model, the change category identifying a type of the modification to be executed in the IT environment. The processor determines a likelihood of causing a problem in the IT environment as a result of executing the modification. The processor automatically performs an action to prevent the modification of the change request in the IT environment.
Absstract of: WO2024251703A1
The invention relates to an injection molding machine and to a method for operating same. The injection molding machine has a plasticizing screw with a nonreturn valve for preventing a backflow of plasticized material during an injection process. At least one injection process is carried out, wherein at least one curve of at least one variable (IP, TM, RM, SP, SV, RV) which characterizes the injection process is detected. The detected curve is evaluated using an evaluation algorithm which is trained using a machine learning process in order to determine the closing behavior of the nonreturn valve, in particular the most probable closing time (S) and/or the backflow blocking efficiency.
Absstract of: US2024414064A1
Embodiments relate to providing self-learning automated information technology change risk prediction. A processor inputs a change request to a first machine learning model, the first machine learning model determining at least one word pair in the change request, the change request being a modification in an IT environment. The processor classifies the at least one word pair into a change category for the IT environment using a second machine learning model, the change category identifying a type of the modification to be executed in the IT environment. The processor determines a likelihood of causing a problem in the IT environment as a result of executing the modification. The processor automatically performs an action to prevent the modification of the change request in the IT environment.
Nº publicación: US2024411802A1 12/12/2024
Applicant:
GOOGLE LLC [US]
Google LLC
Absstract of: US2024411802A1
Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for determining breakpoints in a media item. Methods can include determining a candidate set of breakpoints within a media item. A machine learning model is used to generate a score for each particular candidate breakpoint in the set of candidate breakpoints based on presentation features of the media item. A subset of candidate breakpoints is selected from the set of candidate breakpoints based on the score. A final set of breakpoints is selected from the subset of candidate breakpoints based on a combination of the score for each particular candidate breakpoint and a location of the particular candidate breakpoint relative to a different candidate breakpoint. The final set of breakpoints is stored in a database and during playback of the media item, a digital component is presented when the media item reaches a stored breakpoint.
BOPI
Electronic site
