Abstract

A method of classifying a dataset based on license risk analysis includes: identifying a context including at least one license clause for each of datasets; determining one of predefined license classification classes for each of the datasets based on the identified context using an artificial intelligence model; associating the determined classification class with an identifier of each of the datasets and storing the datasets in memory; receiving an input signal for inputting condition information including at least one target dataset or target classification class that is a target of license risk analysis; loading at least a part of data stored in the memory through the artificial intelligence model, generating at least one dataset or classification class matching the condition information as recommendation information, and storing the generated recommendation information in the memory; and expressing the generated recommendation information through a user interface.

IPC Classes  ?

• G06F 21/10 - Protecting distributed programs or content, e.g. vending or licensing of copyrighted material
• G06F 18/2431 - Multiple classes

Abstract

A system for training an intent classification model using intent descriptions may generate a dataset including intent descriptions of the intent classification model from a language model, perform intent classification by using at least a portion of a dataset as an input prompt for the intent classification model, and determine performance of the intent classification model by using at least a portion of the dataset as an input prompt for the intent classification model. The dataset may include first data including an independent intent description written independently from other intent descriptions and second data including a dependent intent description written dependently on other intent descriptions.

IPC Classes  ?

• G06F 16/903 - Querying
• G06F 16/906 - ClusteringClassification

Abstract

A method executed by a computer includes: obtaining first input information specifying predetermined domain characteristics; obtaining a validity index that quantitatively indicates difficulty in generating output data of the multi-tasking model according to the first input information; generating first guide information specifying the domain characteristics for reducing the generation difficulty based on the obtained validity index; and providing the first guide information. The method further include: obtaining input information specifying predetermined domain characteristics; converting the input information into low-dimensional latent variables represented in a low-dimensional Gaussian space; obtaining sampled latent variables obtained by sampling the converted low-dimensional latent variables; obtaining optimized latent variables obtained by optimizing the obtained sampled latent variables through a genetic algorithm; restoring the optimized latent variables into high-dimensional latent variables represented in a high-dimensional space; and providing the restored high-dimensional latent variables to the multi-tasking model.

IPC Classes  ?

• G06N 3/042 - Knowledge-based neural networksLogical representations of neural networks
• G06N 3/045 - Combinations of networks
• G06N 3/0985 - Hyperparameter optimisationMeta-learningLearning-to-learn

Abstract

A system for training an intent classification model using intent descriptions may generate a dataset including intent descriptions of the intent classification model from a language model, perform intent classification by using at least a portion of the dataset as an input prompt for the intent classification model, and determine performance of the intent classification model by using at least a portion of the dataset as an input prompt for the intent classification model. The dataset may include first data including independent intent descriptions in which intent names and intent descriptions for the intent names are mutually indistinguishable and second data including dependent intent descriptions in which intent names and intent descriptions for the intent names are mutually distinguishable.

IPC Classes  ?

• G06F 16/3329 - Natural language query formulation
• G06F 40/30 - Semantic analysis
• G06N 5/046 - Forward inferencingProduction systems

Abstract

An asset portfolio prediction method performed by a computing system comprise determining a target prediction task which is data specifying an objective task; collecting raw data to perform the determined target prediction task; aligning the collected raw data in a time-series on a specific time axis; training a predetermined time-series prediction model based on the aligned raw data and the determined target prediction task; predicting daily portfolio asset weight data over a predetermined prediction unit period based on the trained time-series prediction model; generating a single set of portfolio asset weight data by processing the predicted daily portfolio asset weight data at each predetermined rebalancing time; and providing the generated single set of portfolio asset weight data.

IPC Classes  ?

• G06Q 40/06 - Asset managementFinancial planning or analysis
• G06N 20/00 - Machine learning

Abstract

A method executed by a computer, the method includes: loading in-distribution inspection data stored in at least one memory; inputting the loaded in-distribution inspection data into at least one artificial intelligence model, and obtaining process-based noisy inspection data by noising the in-distribution inspection data up to a specific time-step; obtaining a semantic mask which is a mask specifying a semantic element for the in-distribution inspection data, and a nuisance mask which is a mask specifying a nuisance element for the in-distribution inspection data, from the noisy inspection data; generating out-of-distribution inspection data by applying selective data processing guidance configured to preserve the nuisance element and modify the semantic element based on the semantic mask and the nuisance mask; and outputting the out-of-distribution inspection data through at least one interface.

IPC Classes  ?

• G06T 7/00 - Image analysis
• G06N 3/0475 - Generative networks
• G06N 3/063 - Physical realisation, i.e. hardware implementation of neural networks, neurons or parts of neurons using electronic means
• G06N 3/08 - Learning methods
• G06T 7/12 - Edge-based segmentation

Abstract

An artificial intelligence system includes: one memory configured to store instructions; and one processor configured to execute the instructions to encode music data to generate input tokens from input digital music protocol data and store the input tokens in the one memory; access a data structure in the one memory to load the input tokens; generate one data representation by concatenating a token embedding result converted from the loaded input tokens and a structural embedding result comprising one of a part embedding, a type embedding, a time embedding, and a pitch class embedding; ingest the data representation into at least one artificial intelligence model executed by the one processor; infer, by the one artificial intelligence model, a next output token based on the data representation to generate symbolic music data; and manifest the generated symbolic music data through a user interface.

IPC Classes  ?

• G10H 1/00 - Details of electrophonic musical instruments
• G06F 40/284 - Lexical analysis, e.g. tokenisation or collocates
• G10G 1/00 - Means for the representation of music

Abstract

A method and system for training a language model train a language model without a language degeneration phenomenon of the language model. The method comprises: specifying a first text sequence to be input into the language model to fine-tune the language model; processing the first text sequence as input to the language model; generating, by the language model, a second text sequence including a plurality of tokens based on the first text sequence; storing the second text sequence generated by the language model in a memory; performing masking on the second text sequence stored in the memory; and fine-tuning the language model using the second text sequence on which the masking is performed.

IPC Classes  ?

• G06F 40/40 - Processing or translation of natural language

Abstract

A method and system for unlearning of a large language model perform operations comprising specifying data to be forgotten and data to be retained for a pre-trained large language model in a training dataset stored in memory; specifying a parameter having a high importance based on a preset reference criterion for the data to be forgotten among a plurality of parameters of the large language model by comparing the data to be forgotten and the data to be retained; initializing a weight of low-rank adaptation based on the parameter having the high importance for the data to be forgotten; and performing unlearning on the large language model based on the weight of the low-rank adaptation.

IPC Classes  ?

• G06F 3/06 - Digital input from, or digital output to, record carriers

Abstract

A system generates prediction data by processing an input sequence segmented along a time axis based on a predetermined period using neural networks. The neural networks comprise a first neural network configured to apply dilated attention to the input sequence segmented along the time axis based on the predetermined period, and a second neural network configured to apply random partition attention to data arranged along a feature axis.

IPC Classes  ?

• G06N 5/022 - Knowledge engineeringKnowledge acquisition
• G06N 3/04 - Architecture, e.g. interconnection topology

Abstract

A method and system for unlearning of a large language model perform operations comprising specifying data to be forgotten and data to be retained for a large language model trained with a training dataset; specifying at least one parameter having a high importance based on a preset criterion for the data to be forgotten among a plurality of parameters of the trained large language model by using the data to be forgotten and the data to be retained; initializing a weight of a preset adapter based on an importance of the specified parameter; and performing unlearning on the trained large language model to which the initialized weight of the preset adapter is applied.

IPC Classes  ?

• G06N 3/045 - Combinations of networks
• G06N 3/08 - Learning methods

Abstract

A method and system perform operations comprising: setting a first instruction tuning dataset comprising tasks in a first language; setting a second instruction tuning dataset comprising tasks in a second language; generating a first instruction, written in a same language as the first language, for the first instruction tuning dataset, and storing the first instruction for the first instruction tuning dataset; generating a second instruction, written in a same language as the second language, for the second instruction tuning dataset, and storing the first instruction for the first instruction tuning dataset; generating a cross-language instruction based on the first instruction tuning dataset, the first instruction for the first instruction tuning dataset, the second instruction tuning dataset, and the second instruction for the second instruction tuning dataset; and performing instruction tuning for an artificial intelligence model using the cross-language instruction.

IPC Classes  ?

• G06F 40/58 - Use of machine translation, e.g. for multi-lingual retrieval, for server-side translation for client devices or for real-time translation
• G06N 20/00 - Machine learning

Abstract

An embodiment of the invention is directed to providing a system including at least one processor, an artificial intelligence prediction model, and at least one memory storing one or more instructions that, when executed by the at least one processor, cause the at least one processor to perform operations. The operations may include generating a plurality of observation data by sampling past data with an arbitrary time distribution, generating a propagation signal associated with each of the plurality of observation data based on mean-field theory, determining a predicted value by aggregating calculation results of the propagation signals associated with the plurality of observation data, determining a loss value based on a difference between the predicted value and a true value, and training the artificial intelligence prediction model until the loss value becomes less than or equal to a predetermined value.

IPC Classes  ?

• G06N 20/00 - Machine learning

Abstract

A method and system for large language model alignment may search for high-quality responses among various responses of a language model using a self-reflection mechanism and improve the performance of the language model based on the high-quality responses.

IPC Classes  ?

• G06F 40/279 - Recognition of textual entities

Abstract

A prediction system may predict valid customer companies or valid customers in business-to-business (B2B) and/or business-to-consumer (B2C) sales situations. A computerized learning method of a prediction system may comprise specifying a train dataset including a plurality of records having values for a plurality of different categories; classifying the plurality of records included in the train dataset based on at least one value corresponding to a target category among the plurality of different categories; configuring a plurality of different sub-datasets based on indexes corresponding to the plurality of the classified records; and training at least one target prediction model using each of the plurality of different sub-datasets.

IPC Classes  ?

• G06N 20/00 - Machine learning
• G06Q 30/02 - MarketingPrice estimation or determinationFundraising

Abstract

A combinatorial optimization system, its control method, and a learning method of a combinatorial optimization system. The learning method includes specifying a training dataset including at least one combinatorial optimization problem instance and at least one reference solution corresponding to the instance; performing supervised learning on a combinatorial optimization model using the training dataset; acquiring a supervised-learned combinatorial optimization model based on the training data; and performing reinforcement learning on the supervised-learned combinatorial optimization model.

IPC Classes  ?

• G06N 20/00 - Machine learning

Abstract

A prediction system predict valid customer companies or valid customers in business-to-business (B2B) and/or business-to-consumer (B2C) sales situations. A computerized method comprise: specifying a train dataset including values for a plurality of different categories; configuring a plurality of different sub-datasets based on a specific value of a specific category using the train dataset such that a ratio of different values corresponding to the specific category among the plurality of different categories satisfy a preset ratio criterion; training a plurality of target prediction models on each of the plurality of different sub-datasets; inputting input data to be predicted to each of the plurality of the trained target prediction models; acquiring a plurality of prediction values for the input data from the plurality of trained target prediction models; and specifying a final prediction value for the input data using the plurality of prediction values.

IPC Classes  ?

• G06Q 30/0202 - Market predictions or forecasting for commercial activities
• G06N 5/01 - Dynamic search techniquesHeuristicsDynamic treesBranch-and-bound

Abstract

An answer generation method is performed by cooperation of a memory and at least one processor. The answer generation method and system perform operations including specifying an analysis target document, extracting a plurality of content from the document, storing the plurality of content extracted from the document in the memory, receiving a user query from a user terminal, specifying specific content related to the user query among the plurality of content stored in the memory, processing the specific content as input to a pre-trained chemical reaction prediction model, and generating an answer to the user query using output data of the chemical reaction prediction model.

IPC Classes  ?

• G06N 5/04 - Inference or reasoning models

Abstract

A printed circuit board (PCB) wiring automatic design method in a PCB wiring automatic design system, the system including at least one processor and at least one memory including an instruction, and the PCB wiring automatic design method performed in cooperation with the instruction, the memory, and the processor, includes: receiving PCB data including a net list and information on a plurality of terminals; updating a cost of a wiring exploration region so that a cost of at least some of the wiring exploration region is increased based on a preset constraint condition; exploring a shortest path for wiring the plurality of terminals according to the net list in a cost-updated wiring exploration region; and performing wiring of the plurality of terminals based on wiring probability according to the shortest path.

IPC Classes  ?

• G06F 30/398 - Design verification or optimisation, e.g. using design rule check [DRC], layout versus schematics [LVS] or finite element methods [FEM]
• G06F 30/392 - Floor-planning or layout, e.g. partitioning or placement
• G06F 30/394 - Routing
• G06F 111/04 - Constraint-based CAD
• G06F 111/08 - Probabilistic or stochastic CAD
• G06F 111/10 - Numerical modelling
• G06F 115/12 - Printed circuit boards [PCB] or multi-chip modules [MCM]

Abstract

A system for reinforcement learning includes at least one processor, and at least one memory storing at least one instruction that, when executed by the at least one processor, is configured to: perform offline reinforcement learning; and perform online reinforcement learning. The performing of the offline reinforcement learning includes identifying a data-retained region and a data-unretained region, and reducing a Q-value estimated in the data-unretained region.

IPC Classes  ?

• G06N 3/092 - Reinforcement learning

Abstract

A system for predicting a property of a material of the present invention may extract a graph embedding by inputting material information into a first artificial intelligence (AI) model, and extract a text embedding by inputting a text description of a crystal structure of the material into a second AI model, classify the text embedding into a plurality of structure information embeddings, and concatenate the graph embedding with at least one of the plurality of structure information embeddings, wherein the structure information embeddings may be classified to include global information, semi-global information, and local information of the crystal structure. The provided system and method may be employed to predict aspects of a crystal structure, a molecular structure, a protein structure, a catalyst structure, or a metal-organic framework of a target material, or to predict physical properties of a target material.

IPC Classes  ?

• G06N 3/045 - Combinations of networks
• G06N 3/096 - Transfer learning

Abstract

A visual inspection method, computing system and computing device are provided. An exemplary method includes providing a uniform group of manufactured products, performing a first process for detecting noisy label data within a training data set, acquiring a noisy data set and a clean data set according to the noisy label data detected based on the first process, performing a second process for training a vision inspection model based on the acquired noisy data set and clean data set, visually inspecting the products using the vision inspection model to identify defective products within the group, and removing the defective products from the group. The two stage vision inspection model training method and system prevents performance degradation due to mislabeled training data, maintains maximum recall on defective data, and improves precision for good product data.

IPC Classes  ?

• G06T 7/00 - Image analysis
• G06N 20/00 - Machine learning
• G06V 10/764 - Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects

Abstract

A computerized method and system for providing and implementing an artificial intelligence (AI) model that includes a plurality of models are provided. The method employs, for example, a computer having at least one processor and at least one memory and comprises receiving a query, identifying a user's context based on the query, and receiving the identified context through at least one artificial intelligence model and generating a response to the query, wherein the generating of a response may comprise controlling at least one router to determine at least one of a plurality of artificial intelligence models as a task execution model for the query, ingesting input data based on the context into the at least one determined task execution model, and sequentially or concurrently operating the at least one task execution model into which the input data has been ingested to generate a response to the query.

IPC Classes  ?

• G06F 16/3329 - Natural language query formulation
• G06F 9/50 - Allocation of resources, e.g. of the central processing unit [CPU]
• G06N 20/00 - Machine learning

Abstract

A method for a computing system including at least one memory and at least one processor configured to predict characteristics regarding a plurality of material properties includes: obtaining experimental data including characteristics data on the plurality of material properties regarding materials; pre-training an integrated prediction model for a plurality of tasks of predicting characteristics regarding the plurality of material properties from the obtained experimental data; inputting, to the pre-trained integrated prediction model, material information to be predicted; outputting, by the integrated prediction model, a characteristic value for each of the plurality of material properties in regard to the material information; and providing the output characteristic value for each of the plurality of material properties.

IPC Classes  ?

• G16C 20/30 - Prediction of properties of chemical compounds, compositions or mixtures
• G16C 20/70 - Machine learning, data mining or chemometrics

Abstract

A method of performing action-based automation tasks includes: receiving an input signal representing a target task; identifying a context from the input signal; determining the target task and an application or web for performing the target task through the context; acquiring user interface information of a user interface of the application or web; identifying interaction elements included in the user interface information using an artificial intelligence model, and determining and storing attribute information of each of the interaction elements; generating and storing an execution plan including an action for at least one of the interaction elements based on the target task and the attribute information; and performing the target task according to the execution plan through at least one artificial intelligence model, wherein the performing of the target task comprises controlling the action to be executed through the interaction elements.

IPC Classes  ?

• G06N 20/00 - Machine learning
• G06F 9/48 - Program initiatingProgram switching, e.g. by interrupt

Abstract

A multi-tasking model training method and a multi-tasking performing method using a machine learning model trained on the basis thereof, which mutually transfer and learn knowledge data of a latent space for each task through geometric alignment in one integrated latent space in order to process a multi-task for output according to a plurality of domains.

IPC Classes  ?

• G06N 3/096 - Transfer learning

Abstract

A method for providing an artificial intelligence (AI) agent based on a large language model (LLM) applying an artificial intelligence model including a plurality of models includes: executing an on-device AI agent service; acquiring predetermined input data based on the executed on-device AI agent service; determining a domain according to the acquired input data; deciding an application model, which is an AI model that will process a task according to the determined domain; generating output data for the input data based on the decided application model; and providing the generated output data based on the on-device AI agent service.

IPC Classes  ?

• G06N 5/043 - Distributed expert systemsBlackboards

Abstract

A system and method for generating protein amino acid sequences having a user-desired property are provided. Using a noise-based diffusion model, the system and method can generate amino acid sequences of proteins that have excellent disease treatment effects and are safe for use as therapeutic agents in a human body. The system can function by obtaining reference protein sequence information, generating noise-added protein sequence information, iteratively generating noise-removed protein sequence information and partially noise-added protein sequence information, and generating noise-removed output protein sequence information. Noise may be added to protein sequence information using a Gaussian or other known noise model. Noise may be removed from protein sequence information using an artificial neural network model trained by a method of minimizing a loss function. By incorporating sequence guidance and structure guidance derived from known proteins, users can generate improved candidate protein drugs for testing.

IPC Classes  ?

• G16B 15/00 - ICT specially adapted for analysing two-dimensional or three-dimensional molecular structures, e.g. structural or functional relations or structure alignment
• G16B 40/00 - ICT specially adapted for biostatisticsICT specially adapted for bioinformatics-related machine learning or data mining, e.g. knowledge discovery or pattern finding

Abstract

A system for predicting physical properties of a material which: extracts a “graph embedding” by inputting material information into a first artificial intelligence (AI) model; extracts a “text embedding” by inputting a textual description of a crystal structure of the material into a second AI model; divides the “text embedding” into a plurality of “structural information embeddings”; and combines the “graph embedding” with at least one of the plurality of “structural information embeddings”. The “structural information embeddings” may be categorized into global information, semi-global information, and local information of the crystal structure.

IPC Classes  ?

• G16C 20/30 - Prediction of properties of chemical compounds, compositions or mixtures
• G06N 3/042 - Knowledge-based neural networksLogical representations of neural networks
• G06N 3/045 - Combinations of networks
• G16C 20/70 - Machine learning, data mining or chemometrics

Abstract

A method of enhancing language model performance through structured knowledge injection performed by a computing system including a memory and a processor including obtaining knowledge base data including a predetermined knowledge graph, generating linearly structured data by structuring the obtained knowledge base data into a text format, training a first language model based on the generated linearly structured data, and providing a predetermined application service based on the trained first language model. The generating linearly structured data includes generating the first linearly structured data by structuring the knowledge graph in the text format based on multi-hop linearization.

IPC Classes  ?

• G06N 3/042 - Knowledge-based neural networksLogical representations of neural networks
• G06N 3/096 - Transfer learning

Abstract

A method for learning a 3D geometric structure of a molecule and a target property prediction method including the same concern a target property prediction method in which a computing system including a memory and a processor learns a 3D geometric structure of a molecule and predicts a target property. The method includes: performing denoising-based, first pre-training based on a 3D conformer encoder which takes, as input, 3D molecular data specifying a 3D-level molecular structure; performing distillation-based, second pre-training based on the first pre-trained 3D conformer encoder and a 2D graph encoder which takes, as input, 2D molecular data specifying a 2D-level molecular structure; performing fine-tuning-based third pre-training based on the second pre-trained 2D graph encoder; and providing the third pre-trained 2D graph encoder.

IPC Classes  ?

• G16C 20/70 - Machine learning, data mining or chemometrics
• G06N 3/045 - Combinations of networks
• G06N 3/096 - Transfer learning
• G16C 20/30 - Prediction of properties of chemical compounds, compositions or mixtures

Abstract

An artificial intelligence system performing operations including: an operation of calculating an importance score for data points of a dataset, an operation of calculating an oversampling rate for each of the data points, an operation of calculating a sample weight based on the oversampling rate for each of the data points, and an operation of oversampling the data points in correspondence to the calculated sample weight.

IPC Classes  ?

• G06F 18/214 - Generating training patternsBootstrap methods, e.g. bagging or boosting
• G06N 20/00 - Machine learning

Abstract

A target prediction method for predicting a future outlook of a target performed by a computing device or a processor may collect related structured and unstructured data when a user requests target prediction, analyze the relationship between the target and a variable affecting the target at a semantic level, and compute a target outlook of a future.

IPC Classes  ?

• G06N 5/048 - Fuzzy inferencing

Abstract

A target prediction method for predicting a future outlook of a target performed by a computing device or a processor may collect related structured and unstructured data when a user requests predictive generation, analyze the relationship between the target and a variable affecting the target at a semantic level, and compute a target outlook of a future.

IPC Classes  ?

• G06F 40/30 - Semantic analysis
• G06F 16/3329 - Natural language query formulation
• G06F 16/3332 - Query translation
• G06F 16/338 - Presentation of query results
• G06F 40/295 - Named entity recognition
• G06N 5/022 - Knowledge engineeringKnowledge acquisition

Abstract

A predictive generation method for predicting a future outlook of a target performed by a computing device or a processor may collect related structured and unstructured data when a user requests predictive generation, analyze the relationship between the target and a variable affecting the target at a semantic level, and compute a target outlook of a future.

IPC Classes  ?

• G06F 16/25 - Integrating or interfacing systems involving database management systems
• G06F 16/242 - Query formulation
• G06F 16/28 - Databases characterised by their database models, e.g. relational or object models

Abstract

A method and system for providing an intelligent response agent based on a sophisticated reasoning and speculation function can generate and provide response data for queries related to specialized documents using a deep-learning neural network that implements a stepwise process for a sophisticated reasoning and speculation function.

IPC Classes  ?

• G06F 16/28 - Databases characterised by their database models, e.g. relational or object models
• G06F 16/2452 - Query translation

Abstract

Provided is a computer-implemented method for training a block transformer architecture model including: generating a plurality of input token embeddings by processing input data in a form of a sequence, generating a plurality of block embeddings by sequentially merging the plurality of input token embeddings into a predetermined unit number, generating a plurality of context embeddings by performing a self-attention operation on the plurality of block embeddings, wherein each of the plurality of context embeddings corresponds to each of the block embeddings, and generating a subsequent predicted token embedding for the plurality of input token embeddings, based on the plurality of context embeddings.

IPC Classes  ?

• G06N 3/08 - Learning methods
• G06N 3/045 - Combinations of networks

Abstract

A system, a computer program, a device, and a method for measuring confidence of a molecular structure prediction model. The method includes obtaining a first molecular structure image, obtaining a first molecular structure graph using the molecular structure prediction model, performing image rendering on the first molecular structure image based on the first molecular structure graph, and determining confidence of the first molecular structure graph based on the image rendering result and the first molecular structure graph.

IPC Classes  ?

• G16C 20/80 - Data visualisation
• G16C 20/20 - Identification of molecular entities, parts thereof or of chemical compositions
• G16C 20/70 - Machine learning, data mining or chemometrics

Abstract

A method and system for providing an intelligent response agent based on a sophisticated reasoning and speculation function can generate and provide response data for queries related to specialized documents using a deep-learning neural network that implements a stepwise process for a sophisticated reasoning and speculation function.

IPC Classes  ?

• G06F 16/332 - Query formulation
• G06F 16/338 - Presentation of query results

Abstract

A system, method, and program for constructing a data set that improves zero-shot learning performance of an AI model through instruction tuning extract instructions from each of a training task used for training an AI model, and a target task that is a task to be trained through the training task, evaluate similarity by comparing the extracted instruction of the training task with the extracted instruction of the target task, select, from among the extracted instructions of the training task, instructions having a similarities equal to or greater than a predetermined value, and output the selected instructions of the training task as a data set.

IPC Classes  ?

• G06N 20/00 - Machine learning

Abstract

A system, method, and program for constructing a data set that improves zero-shot learning performance of an AI model through instruction tuning extract instructions from each of a training task used for training an AI model, and a target task that is a task to be trained through the training task, evaluate similarity by comparing the extracted instruction of the training task with the extracted instruction of the target task, select, from among the extracted instructions of the training task, instructions having a similarities equal to or greater than a predetermined value, and output the selected instructions of the training task as a data set.

IPC Classes  ?

• G06N 20/00 - Machine learning

Abstract

A re-ranking system for extracting passages having higher relevance to a query. Re-ranking is accomplished by performing a plurality of tournament sortings, which may include arranging first passages included in the passages into units of a specific number to divide the first passages into a plurality of groups, evaluating relevance between the first passages included in a group and a query for each group, and extracting passages having higher relevance up to a predetermined rank among the first passages to output the extracted first passages as second passages, and arranging the second passages into units of a specific number to divide the second passages into a plurality of groups, evaluating relevance between the second passages included in a group and the query for each group, and extracting passages having higher relevance up to a predetermined rank among the second passages to output the extracted second passages as third passages.

IPC Classes  ?

• G06F 16/334 - Query execution
• G06F 16/35 - ClusteringClassification

Abstract

A method for performing pre-training for a multi-tasking model includes: acquiring experimental data including material-specific characteristic information, which is information specifying unique characteristics of a predetermined material, and material-physical property specific information, which is information specifying characteristic values for a plurality of physical properties of the material; simultaneously training a plurality of tasks for predicting the characteristic values for the plurality of physical properties based on the acquired experimental data in the multi-tasking model; and providing the trained multi-tasking model. The simultaneous training of the plurality of tasks includes simultaneously training the plurality of tasks based on a plurality of task processing units, each including a task processing unit configured to process a plurality of sub-tasks for predicting a characteristic value for each physical property.

IPC Classes  ?

• G06N 20/00 - Machine learning

Abstract

A patch feature learning method and a patch feature learning system for anomaly detection perform patch feature-based learning on a predetermined pretrained model based on an image data set for an anomaly detection target. The method and the system may acquire a feature map according to a first image data set; acquire a plurality of patch features based on local data in a predetermined image, based on the acquired feature map; perform feature representation learning based on the plurality of acquired patch features; acquire a reconstructing patch feature based on the performed feature representation learning; and perform anomaly detection based on the acquired reconstructing patch feature.

IPC Classes  ?

• G06V 10/771 - Feature selection, e.g. selecting representative features from a multi-dimensional feature space
• G06T 7/00 - Image analysis
• G06V 10/44 - Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersectionsConnectivity analysis, e.g. of connected components
• G06V 10/74 - Image or video pattern matchingProximity measures in feature spaces
• G06V 10/82 - Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks

Abstract

A method and system for providing a spatio-temporal preservation transformer for 3D human pose and shape estimation may provide a transformer that considers both spatial and temporal dimensions and minimizes computational complexity when estimating a 3D human pose and shape based on an image sequence such as a video, thereby improving the data processing efficiency and performance required for the 3D human pose and shape estimation based on the image sequence, enhancing the quality of the resulting data and improving various application services and related industrial environments.

IPC Classes  ?

• G06T 7/73 - Determining position or orientation of objects or cameras using feature-based methods
• G06T 3/02 - Affine transformations
• G06T 3/14 - Transformations for image registration, e.g. adjusting or mapping for alignment of images
• G06T 7/33 - Determination of transform parameters for the alignment of images, i.e. image registration using feature-based methods
• G06T 7/55 - Depth or shape recovery from multiple images
• G06T 13/40 - 3D [Three Dimensional] animation of characters, e.g. humans, animals or virtual beings
• G06T 17/00 - 3D modelling for computer graphics
• G06T 19/00 - Manipulating 3D models or images for computer graphics

Abstract

A method for monitoring judgment records for an outlier judgment guide according to an embodiment of the inventive concepts is configured to detect at least one similarity image having a similarity greater than or equal to a predetermined reference with a predetermined inspection image, provide judgment detailed information, which is information specifying a judgement content on the presence or absence of an outlier, acquire first judgment result information, which is information specifying a judgement result on the presence or absence of an outlier for the inspection image, and then generates the inspection image and a first judgment result depending on a similarity between each of the inspection image and the similarity image.

IPC Classes  ?

• G06T 7/00 - Image analysis
• G06V 10/74 - Image or video pattern matchingProximity measures in feature spaces

Abstract

A method for providing a domain-adaptive chatbot service based on a large language model (LLM) is performed by a computing device including a memory and a processor, and includes generating a plurality of domain-specific structured training prompts, each of which corresponds to a respective one of a plurality of different domains and includes a plurality of labeled intent sample sentences corresponding to the respective one domain, training the LLM based on the plurality of training prompts, receiving a user input query, generating a structured inference prompt including a plurality of labeled intent sample sentences corresponding to a domain of the user input query and the user input query, inputting the inference prompt into the trained LLM, and providing a response to the user input query according to the intent of the user input query determined by the trained LLM based on the inference prompt.

IPC Classes  ?

• G06N 3/0895 - Weakly supervised learning, e.g. semi-supervised or self-supervised learning
• G06N 5/04 - Inference or reasoning models

Abstract

A method and a computing system including a memory and a processor learn a content generation model. The method may include preparing a training data set including a plurality of pairs of contents and captions, learning a first machine learning model to restore the contents from a low-dimensional latent code, learning a second machine learning model to output a latent code for a text embedding by learning relationship between text embeddings and latent codes of the pairs of the contents and the captions, and combining the first machine learning model and the second machine learning model. The content is implicit data which is function-based 3D shape data.

IPC Classes  ?

• G06N 20/00 - Machine learning
• G06T 17/20 - Wire-frame description, e.g. polygonalisation or tessellation

Abstract

The present disclosure relates to a method and a system for promptly training a simplified vision-language transformer, in which large uncurated datasets are augmented (e.g., through image enlargement and/or masking, etc.) and vision-language transformers are pre-trained by reflecting, through a knowledge distillation framework, misaligned information between an augmented image and text upon the augmentation, thereby reducing both the necessary size of the utilized data set and data processing overhead.

IPC Classes  ?

• G06N 3/096 - Transfer learning
• G06N 3/045 - Combinations of networks
• G06T 11/60 - Editing figures and textCombining figures or text

Abstract

Provided is a system for implementing model for evaluating accuracy of a chart de-rendering model. The system includes one processor, and one memory storing instructions for the processor. The processor inputs a chart stored in test set into artificial intelligence (AI) model to output data format in which information of the chart is predicted, and inputs the data format into performance evaluation model to output performance evaluation result for the AI model by comparing information of the data format with ground truth (GT), which is stored in the test set. The performance evaluation result includes line accuracy indicating degree of proximity between the chart of the data format and the chart of the GT, and axis accuracy indicating degree of overlap between range in which the chart of the data format is distributed and range in which the chart of the GT is distributed on one axis of the chart.

IPC Classes  ?

• G06F 16/23 - Updating

Abstract

A system, method, and program for recognizing a polymer molecular structure formula using artificial intelligence are disclosed. The system includes at least one processor, and at least one memory storing a command or information that causes the at least one processor to perform an operation, wherein the operation includes detecting a polymer molecular structure formula image to generate detection data, the detection data including information about atomic regions including atoms, bonding between the atoms, and a bracket pair with an associated subscript, the system further including inputting the detection data to each of a first model and a second model to output first cluster data from the first model and to output from the second model second cluster data including group information about the bracket pair and the associated subscript and including information different from the first cluster data.

IPC Classes  ?

• G16C 20/20 - Identification of molecular entities, parts thereof or of chemical compositions
• G16C 20/70 - Machine learning, data mining or chemometrics
• G16C 20/80 - Data visualisation

Abstract

A system, method, and program evaluate the performance of an artificial intelligence (AI) model that de-renders a chart or for training the AI model by constructing a data set including chart information. The system includes memory storing a data set generation model and an AI model, and a processor configured to execute or train the AI model and execute a performance evaluation model. The data set generation model stores line information, which is information about a line of a chart, and meta information, which is information about meta data, as ground truth (GT), stores an image formed using the GT as a chart image, and outputs the GT and the chart image as a data set, and the AI model receives the chart image stored in the data set as input and outputs a data format in which information of the chart is predicted.

IPC Classes  ?

• G06N 20/00 - Machine learning

Abstract

Provided is a system for implementing an artificial intelligence (AI) model for extracting meta information and data information included in a chart. The system includes at least one processor; and at least one memory storing instructions for the processor. The processor is configured to input the chart into an image encoder to convert the chart into a first embedding processable by the AI model, input the first embedding to the AI model to output a second embedding including the meta information from the first embedding, and to output a fourth embedding including the data information from a third embedding including information about an entity included in the second embedding, and output each of a first data format in which the meta information included in the second embedding is recorded, and a second data format in which the data information included in the fourth embedding is recorded.

IPC Classes  ?

• G06V 30/416 - Extracting the logical structure, e.g. chapters, sections or page numbersIdentifying elements of the document, e.g. authors
• G06T 11/00 - 2D [Two Dimensional] image generation
• G06V 10/40 - Extraction of image or video features
• G06V 10/70 - Arrangements for image or video recognition or understanding using pattern recognition or machine learning
• G06V 30/18 - Extraction of features or characteristics of the image
• G06V 30/19 - Recognition using electronic means
• G06V 30/30 - Character recognition based on the type of data

Abstract

A chemical reaction prediction system and a control method thereof, and a learning method of the chemical reaction prediction system are provided. More specifically, the chemical reaction prediction system may perform forward reaction prediction based on an electron flow and a control method thereof.

IPC Classes  ?

• G16C 20/30 - Prediction of properties of chemical compounds, compositions or mixtures
• G06N 3/0499 - Feedforward networks
• G06N 3/082 - Learning methods modifying the architecture, e.g. adding, deleting or silencing nodes or connections
• G16C 20/50 - Molecular design, e.g. of drugs
• G16C 20/70 - Machine learning, data mining or chemometrics

Abstract

A system, method, and program for constructing a dataset to evaluate user information personalization functionality of retrievers. The method includes extracting a plurality of queries and a target corresponding to each of the plurality of queries from sample data, inputting a first prompt into an Artificial Intelligence (AI) model to output an instruction set composed of a plurality of instructions including virtual user scenarios, additionally associating the instruction set with each of the corresponding plurality of queries and target to output as element data, inputting the element data together with a second prompt into the AI model to tune the target included in the element data to fit the virtual user scenario included in the plurality of instructions, and storing the plurality of tuned element data as a dataset.

IPC Classes  ?

• G06F 40/40 - Processing or translation of natural language
• G06F 16/334 - Query execution

Abstract

An answer generation method is performed by cooperation of a memory and at least one processor. The answer generation method and system perform operations including specifying an analysis target document, extracting a plurality of content from the document, storing the plurality of content extracted from the document in the memory, receiving a user query from a user terminal, specifying specific content related to the user query among the plurality of content stored in the memory, processing the specific content as input to a pre-trained chemical reaction prediction model, and generating an answer to the user query using output data of the chemical reaction prediction model.

IPC Classes  ?

• G06N 5/04 - Inference or reasoning models

Abstract

An answer generation method and system may relate to an answer generation method and system using an ultra-large foundation model, and an answer generation platform based on an ultra-large foundation model. In addition, an answer generation method and system may relates to a chemical reaction prediction system, a control method thereof, and a learning method of a chemical reaction prediction system. More specifically, the chemical reaction prediction system may perform forward reaction prediction based on an electron flow.

IPC Classes  ?

• G16C 20/10 - Analysis or design of chemical reactions, syntheses or processes
• G16C 20/30 - Prediction of properties of chemical compounds, compositions or mixtures
• G16C 20/80 - Data visualisation

Abstract

Provided are an example product and text input-based product recommendation method and system, which are configured to provide a recommendation product that matches a current intention of a user based on an example product and needs-related text entered by the user.

IPC Classes  ?

• G06Q 30/0601 - Electronic shopping [e-shopping]
• G06F 40/30 - Semantic analysis

Abstract

Data augmentation methods, devices, and programs for an MHC class II binding and immunogenicity predictive models may select a plurality of augmentation target data including first-type data and second-type data from original data according to a predetermined selection condition, to generate a plurality of augmentation data by augmenting the plurality of selected augmentation target data according to a predetermined augmentation condition, wherein the plurality of selected augmentation target data is augmented according to each of an augmentation condition of the first-type data and an augmentation condition of the second-type data, and to modify labeling of the plurality of augmentation data, wherein labels are modified according to different labeling conditions for each of the first-type data and the second-type data.

IPC Classes  ?

• G16B 40/20 - Supervised data analysis
• G16B 15/30 - Drug targeting using structural dataDocking or binding prediction
• G16B 30/20 - Sequence assembly

Abstract

A device and method for training data generation through object diversification of a chemical structure are disclosed. The device comprises a processor and at least one memory electrically connected to the processor. The at least one memory stores one or more feature variables determining the features of objects expressing structural formulas; and a first setpoint set determined in advance for each of the one or more feature variables. The method comprises loading first chemical formula data; setting setpoint(s) of the one or more feature variables as the first setpoint set; generating a first structural formula on the basis of the first chemical formula by applying an object set to the first setpoint set; acquiring, in response to an input changing the setpoint(s) of one or more feature variables, a second setpoint set; generating a second structural formula by applying an object set to the second setpoint set; and generating the training data including the generated second structural formula.

IPC Classes  ?

• G16C 20/30 - Prediction of properties of chemical compounds, compositions or mixtures
• G06N 20/00 - Machine learning
• G16C 20/70 - Machine learning, data mining or chemometrics

Abstract

A computing device for performing anomaly detection according to the present disclosure includes a memory including at least one memory bank that is a logical area, and a processor which: is configured to train a neural network by using at least one function module; generating a reduced feature extraction module; generating the memory bank on the basis of reduced feature data generated from the reduced feature extraction module; and determining whether inspection data is normal by using the generated reduced feature extraction module and the memory bank.

IPC Classes  ?

• G06T 7/00 - Image analysis
• G06V 10/774 - Generating sets of training patternsBootstrap methods, e.g. bagging or boosting
• G06V 10/82 - Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks

Abstract

A line connection-type object prediction device and method using artificial intelligence in which objects are detected using atoms and bonds, which make up a molecular structural formula, as nodes and edges, respectively, when recognizing a molecular structural formula image representing the molecular structure of a compound, and the detection information about nodes is used when detecting edges for bonds.

IPC Classes  ?

• G06V 30/422 - Technical drawingsGeographical maps
• G06V 10/25 - Determination of region of interest [ROI] or a volume of interest [VOI]
• G06V 10/26 - Segmentation of patterns in the image fieldCutting or merging of image elements to establish the pattern region, e.g. clustering-based techniquesDetection of occlusion
• G06V 10/764 - Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects
• G06V 10/77 - Processing image or video features in feature spacesArrangements for image or video recognition or understanding using pattern recognition or machine learning using data integration or data reduction, e.g. principal component analysis [PCA] or independent component analysis [ICA] or self-organising maps [SOM]Blind source separation
• G06V 10/774 - Generating sets of training patternsBootstrap methods, e.g. bagging or boosting
• G06V 10/82 - Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks
• G06V 30/413 - Classification of content, e.g. text, photographs or tables

Abstract

A system for multi-agent reinforcement learning includes a multi-agent including a first agent and a second agent, a history encoder including a first history encoder corresponding to the first agent and a second history encoder corresponding to the second agent, a memory configured to store one or more commands, and at least one processor configured to execute the one or more commands stored in the memory, wherein, the at least one processor, by executing the one or more commands, is configured to i) generate first history information of the first agent by inputting observation data of the first agent into the first history encoder and ii) generate second history information of the second agent by inputting observation data of the second agent into the second history encoder.

IPC Classes  ?

• G06N 3/092 - Reinforcement learning
• G06N 3/045 - Combinations of networks

Abstract

A method whereby a computing system including a memory and a processor trains an image classification model, according to an embodiment of the present invention, comprises the steps of: augmenting text data in sample data of a plurality of image-text pairs; training the image classification model by fine-tuning a pretrained vision-language model on the basis of the data-augmented texts and images; and providing the trained image classification model.

IPC Classes  ?

• G16H 30/40 - ICT specially adapted for the handling or processing of medical images for processing medical images, e.g. editing
• G06V 10/74 - Image or video pattern matchingProximity measures in feature spaces
• G06V 10/774 - Generating sets of training patternsBootstrap methods, e.g. bagging or boosting
• G06V 10/82 - Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks
• G06V 30/416 - Extracting the logical structure, e.g. chapters, sections or page numbersIdentifying elements of the document, e.g. authors
• G16H 15/00 - ICT specially adapted for medical reports, e.g. generation or transmission thereof

Abstract

Disclosed is a method and system for pretraining vision transformers using large uncurated datasets in a self-supervised learning manner according to a knowledge distillation framework, thereby reducing data processing overhead and rapidly training simplified vision transformers.

IPC Classes  ?

• G06V 10/778 - Active pattern-learning, e.g. online learning of image or video features
• G06V 10/774 - Generating sets of training patternsBootstrap methods, e.g. bagging or boosting
• G06V 10/82 - Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks

Abstract

The present disclosure relates to an electrolyte for a lithium-sulfur secondary battery that can improve output power characteristics of lithium-sulfur secondary batteries, and a lithium-sulfur secondary battery including the same. The electrolyte for the lithium-sulfur secondary battery includes a lithium salt, a non-aqueous solvent and an additive, wherein a first mixing energy (Gmix1) of the electrolyte and dilithio pertetrasulfide (Li2S8) and a second mixing energy (Gmix2) of the electrolyte and lithium sulfide (Li2S) are each within a certain range.

IPC Classes  ?

• H01M 10/0569 - Liquid materials characterised by the solvents
• H01M 4/58 - Selection of substances as active materials, active masses, active liquids of inorganic compounds other than oxides or hydroxides, e.g. sulfides, selenides, tellurides, halogenides or LiCoFySelection of substances as active materials, active masses, active liquids of polyanionic structures, e.g. phosphates, silicates or borates
• H01M 10/0525 - Rocking-chair batteries, i.e. batteries with lithium insertion or intercalation in both electrodesLithium-ion batteries
• H01M 10/0567 - Liquid materials characterised by the additives

Abstract

A method for learning tabular data analyzing model in a computing system including a memory and a processor, the method includes the steps of: acquiring tabular data; performing binning on the tabular data to acquire binned data; and training an autoencoder to output the binned data from the input tabular data.

IPC Classes  ?

• G06N 3/09 - Supervised learning
• G06N 3/0455 - Auto-encoder networksEncoder-decoder networks

Abstract

A method for improving a performance for an instruction-following language model including the steps of determining a degree of bias of neurons with respect to an instruction label, selecting one or more biased neuron based on the degree of bias, and removing an influence of the biased neuron.

IPC Classes  ?

• G06N 3/082 - Learning methods modifying the architecture, e.g. adding, deleting or silencing nodes or connections

Abstract

A device for predicting the physical properties of a mixture including a plurality of component materials is disclosed. The device may comprise a memory in which a first AI model trained to output first feature data of material information, and a second AI model trained to output physical property prediction information of the first feature data are stored, and a processor for executing the first AI model and the second AI model, wherein the processor may input, into the first AI model, material information of each of the plurality of materials to acquire first feature data of each of the plurality of materials, and input the first feature data into the second AI model to acquire physical property prediction information of the mixture.

IPC Classes  ?

• G06F 30/27 - Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
• G16C 20/30 - Prediction of properties of chemical compounds, compositions or mixtures
• G16C 20/70 - Machine learning, data mining or chemometrics

Abstract

A method for scheduling a naphtha cracking center by at least one processor, includes the steps of: obtaining input information; determining, by the at least one processor, incoming tank information using a first agent based on the input information, wherein the first agent is a first artificial intelligence device configured to be learned by reinforcement learning; determining, by the at least one processor, mixing tank combination information using a second agent, wherein the second agent is a second artificial intelligence device configured to be learned by reinforcement learning; and determining, by the at least one processor, cracking furnace operation information using a third agent, wherein the third agent is a third artificial intelligence device configured to be learned by reinforcement learning.

IPC Classes  ?

• G06Q 10/0631 - Resource planning, allocation, distributing or scheduling for enterprises or organisations
• G06Q 50/04 - Manufacturing

Abstract

A platform server for generating content based on user experience includes: a memory including a first learning model trained to generate a reconstructed content, based on a text, and a processor to communicate with the memory and to control the first learning model to output at least one reconstructed content corresponding to the text when the text is input from a user terminal. The processor is configured to receive an input content and a first text matching the input content from the user terminal, generate a bag of words, based on the first text, determine caption data using a second text derived from the first text included in the bag of words and a predetermined sentence structure, input a sentence indicated by the caption data to the first learning model, generate at least one reconstructed content corresponding to the sentence, connect the at least one reconstructed content with the input content, and output the at least one reconstructed content and the input content to the user terminal.

IPC Classes  ?

• G06F 40/40 - Processing or translation of natural language
• G06F 40/268 - Morphological analysis
• G06F 40/284 - Lexical analysis, e.g. tokenisation or collocates

Abstract

A neural network implementation device may comprise at least one memory and at least one processor. The at least one processor is configured to: receive first input data; receive second input data corresponding to the first input data; train a sequence transduction neural network by performing an attention operation using the first input data and the second input data labeled with predetermined label information; and determine output data output by the sequence transduction neural network trained using the first input data, the second input data, and the label information.

IPC Classes  ?

• G06N 3/09 - Supervised learning
• G16B 40/20 - Supervised data analysis

Abstract

A method for automatically performing a task may perform a task based on a user dialogue input by a computing system including a memory and a processor. The method may include: receiving a user dialogue input; determining a type of a task requested by a user by analyzing the user dialogue input; obtaining task context data required to perform the task based on the user dialogue input; and performing the task of which type is determined based on the task context data.

IPC Classes  ?

• G06F 8/35 - Creation or generation of source code model driven

Abstract

A task-oriented dialogue method may be performed by a computing system including a memory and a processor using a dialogue model. The task-oriented dialogue method includes: generating a dialogue graph which models at least one conditional relationship for a dialogue dataset; receiving a user dialogue input; sampling a plurality of dialogue act groups for responding to the user dialogue input by using a pre-trained dialogue model; adjusting the plurality of dialogue act groups based on the dialogue graph; and selecting any one dialogue act group which satisfies a predetermined condition among the plurality of dialogue act groups.

IPC Classes  ?

• G06F 40/35 - Discourse or dialogue representation
• G06F 16/3329 - Natural language query formulation

Abstract

A task performing method may perform a task based on a context of a task-oriented dialogue through a dialogue model by a computing system including a memory and a processor. The task performing method may include: receiving a user dialogue input; determining and providing a response dialogue act to the user dialogue input based on a dialogue graph; determining the context of the task-oriented dialogue by analyzing data of a series of task-oriented dialogues including the user dialogue input and the response dialogue act; determining the type of task requested by a user based on the context of the task-oriented dialogue; and performing the task of which type is determined.

IPC Classes  ?

• G06F 8/35 - Creation or generation of source code model driven
• G06F 40/279 - Recognition of textual entities
• G06F 40/30 - Semantic analysis

Abstract

A system, method, and program predict the properties of a material having a multi-phase. The system for implementing an AI model of predicting the properties of a material having a multi-phase includes memory configured to store instructions that are executable; and one or more processors configured to execute the instructions to perform operations comprising: inputting first material information, which includes information regarding the material, into a first AI model to output first feature data; inputting first phase information, which includes information regarding a first phase of the material, into a second AI model to output first phase feature data; and inputting second phase information, which includes information regarding a second phase of the material, into the second AI model to output second phase feature data; and wherein the first feature data includes information regarding the properties of the material according to the multi-phase of the material.

IPC Classes  ?

• G16C 20/30 - Prediction of properties of chemical compounds, compositions or mixtures
• G16C 20/70 - Machine learning, data mining or chemometrics

Abstract

A method of providing a specialized document sharing platform by a platform application executed by at least one processor of a terminal includes obtaining a first specialized document, generating question and answer content for the first specialized document using a question and answer language model, generating promotional content, which comprises an online promotional material for the first specialized document, based on the question and answer content, providing a promotional material production workspace based on the promotional content, determining promotional start content, which comprises the promotional content to be registered on the specialized document sharing platform, using the promotional material production workspace, and providing the promotional start content using the specialized document sharing platform.

IPC Classes  ?

• G06Q 30/0241 - Advertisements
• G06F 40/40 - Processing or translation of natural language

Abstract

A system, device, method, and program for acquiring feature data for material composition information based on artificial intelligence are disclosed. The system may include a memory configured to store a first artificial intelligence (AI) model configured to output first feature data for composition information of a material and a second AI model configured to output second feature data for structure information of the material; and a processor configured to learn the first AI model and the second AI model. The processor may be configured to learn the first AI model based on the second feature data for the structure information of the material output by the second AI model, and/or to learn the second AI model based on the first feature data for the composition information of the material output by the first AI model.

IPC Classes  ?

• G06N 20/20 - Ensemble learning
• G01N 33/20 - Metals

Abstract

A prediction device for predicting protein-protein interactions using protein complex surface information based on artificial intelligence includes: memory; a communicator; and a processor operably connected to the memory and the communicator, wherein the processor may be configured to: predict a structure of a protein complex based on an artificial intelligence model, extract information related to a surface of a protein complex, and provide interaction prediction data for the protein complex and an external protein based on the extracted information related to the surface of the protein complex surface.

IPC Classes  ?

• G16B 15/30 - Drug targeting using structural dataDocking or binding prediction
• G16B 15/20 - Protein or domain folding
• G16B 40/20 - Supervised data analysis

Abstract

An electronic device including a pretraining module, a loss application module, a score application module, the electronic device includes a memory, and a processor configured to provide a pretraining unified framework based on contrastive text image stored in the memory by controlling operations of the pretraining module, the loss application module, and the score application module, wherein the processor is configured to perform pretraining on a data set including at least one of text and images corresponding to a data set domain input through the pretraining module, apply a loss to a plurality of positive samples in the pretrained data set through the loss application module, and apply a score for embedding pretrained data sets from a plurality of domains in the same space based on a similarity through the score application module.

IPC Classes  ?

• G06T 7/00 - Image analysis
• G06T 3/40 - Scaling of whole images or parts thereof, e.g. expanding or contracting
• G06T 3/60 - Rotation of whole images or parts thereof

Abstract

A learning processing device and method for pooling graph data of a hierarchical structure based on a grouping matrix, and a method for learning an artificial intelligence model. The learning processing device includes a memory and a processor in communication with the memory. The processor generates a grouping matrix of a secondary form, grouped based on a similarity of a pairwise nodes by inputting graph data into a pre-learned first artificial intelligence model; and decomposes the grouping matrix to generate a pooling matrix. The grouping matrix is decomposed in a square-root form to obtain a pooling operator.

IPC Classes  ?

• G06F 18/2323 - Non-hierarchical techniques based on graph theory, e.g. minimum spanning trees [MST] or graph cuts

Abstract

An autoencoding device for a synthesizable molecule generative model may include a memory configured to store chemical reaction data, chemical reaction learning information, and molecular structure information; and a processor configured to learn a neural network for a molecular generative model based on the chemical reaction data, the chemical reaction learning information, and the molecular structural information. The molecular generative model may include: a reaction sequence encoder configured to generate a latent space based on the chemical reaction learning information; a seed molecule encoder configured to generate an embedding space based on seed structural information for a seed molecule that is a final product of chemical reaction; and a decoder configured to output a reconstruction reaction sequence by decoding a reaction molecule predictive neural network and a reaction template prediction model generated from the latent space and the embedding space.

IPC Classes  ?

• G06N 3/08 - Learning methods

Abstract

An artificial intelligence device includes: a memory to store a first normal product image; a learning processor to train an image restoration model through inputting the first normal product image into the image restoration model as learning data to output a normal restored image similar to the first normal product image; and a processor configured to: modify the first normal product image to generate a first normal modified image belonging to a normal classification, and increase a number of a second normal product image belonging to the normal classification, modify at least one of the second normal product image to generate an abnormal modified image belonging to an abnormal classification, and input the abnormal modified image into the image restoration model to acquire an abnormal restored image output from the image restoration model.

IPC Classes  ?

• G06V 10/774 - Generating sets of training patternsBootstrap methods, e.g. bagging or boosting
• G06T 7/00 - Image analysis
• G06V 10/764 - Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects
• G06V 10/82 - Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks

Abstract

A vision inspection device includes: a memory including a buffer; and a processor configured to: acquire a plurality of divided images by dividing a captured product image into a plurality of pieces and a new data set including new normal product type data and new defective type data corresponding to the plurality of divided images; sample at least one buffer data set among a plurality of buffer data sets stored in the buffer; generate a mini batch by combining the sampled buffer data set with the new data set; and determine whether to store the new data set in the buffer by using a soft nearest neighbor loss (SNNL) value of the new data set constituting the mini batch, and a cumulative average SNNL value of each of the buffer data sets constituting the mini batch.

IPC Classes  ?

• G06T 7/00 - Image analysis
• G06T 7/11 - Region-based segmentation
• G06V 10/764 - Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects