49 results about "Heuristic" patented technology

A data platform monitors a compute environment by performing multi-stage heuristic analysis of event data representing a plurality of events occurring within the environment. The platform utilizes multiple event analyzers, each configured according to a distinct analysis heuristic, to evaluate different subsets of the event data and generate corresponding output signals. A higher-level event analyzer applies a further heuristic to the multiple output signals to generate a composite alert signal, indicating whether the combination of analyzed events collectively represents a security intrusion or other anomalous condition of sufficient severity to warrant alerting. Based on the composite alert signal, the platform performs an alert-based operation, such as generating a user-facing alert, initiating an automated mitigation, or updating a contextual model of system behavior. By combining the analytical outputs of heterogeneous heuristics, the disclosed architecture enhances the accuracy and contextual relevance of automated intrusion detection within complex computing environments.

This disclosure describes techniques and architecture provide automated contribution analysis for “why question” style NLQ answering, e.g., “why is revenue down in North America Q1 2022.” In particular, the techniques described herein combine multiple signals together including, for example, frequency of use of combinations of dimensions in previous NLQs (warm-start), statistical information about columns (e.g., entropy), correlation / co-occurrence between pairs of dimension columns, and correlation between dimensions and dates. This information is used with a set of heuristics and rules to pick the best set of dimensions as contributing factors for a particular metric over a particular time period and present an automatic contribution analysis to the users to give them insights into their data.

There is provided a system and methods to determine an improved solution to a Mixed Integer Problem (MIP) using a quantum-assisted MIP solver. The methods are performed by a digital processor in communication with a quantum processor. Methods include: selecting at least one feasible solution determined by an MIP solver, determining a first sub-problem of the MIP based on the at least one feasible solution; casting the first sub-problem as Binary Quadratic Models (BQMs); solving the BQMs using the quantum processor to generate sample solutions; determining a second sub-problem based on at least the sample solutions, and obtaining a current solution to the MIP by evaluating the second sub-problem; and updating an incumbent solution if the current solution improves over the current incumbent solution. The quantum-assisted MIP solver uses hybrid crossover and mutation heuristics to improve the convergence time and accuracy of solutions obtained using Branch-and-Cut solvers.

Aspects of this technical solution can generate, according to one or more first environment metrics, a three-dimensional (3D) model including a first surface corresponding to one or more physical ways through a physical environment, the one or more first environment metrics indicative of boundaries of the one or more physical ways, generate, according to one or more second environment metrics, one or more geometric two-dimensional (2D) objects on the first surface, the second environment metrics indicative of the one or more physical ways, identify, according to one or more viewpoint metrics indicative of cameras of a physical object configured to move along the one or more physical ways, one or more viewpoints oriented to capture corresponding portions of the 3D model, and render, from the one or more corresponding portions of the 3D model, one or more 2D images each corresponding to respective ones of the viewpoints.

The invention discloses a two-stage reinforcement learning SAT solving method for structure perception and a related device, and belongs to the field of chip design. Chip signal polarity and logic consistency information is introduced in a variable initialization stage, an initial feature vector for structure perception is constructed, and the limitation that traditional graph modeling can only represent a local logic relation is broken through; a two-stage reinforcement learning framework composed of a main path and a sampling path is designed, the sampling path is used for exploring a chip logic solution space, the main path is used for stably utilizing an optimal verification strategy, and the problems of unstable training convergence, single strategy and the like are effectively relieved. Based on a reward-guided feature updating mechanism, dynamic evolution of chip signal features and enhanced feedback are explicitly bound, the interpretability of a solver is improved, and the difference between neural reasoning and chip logic symbol reasoning is reduced. A signal assignment decision is executed based on GNN multi-round message passing results, and a verification track is continuously optimized, so that efficient chip design verification capability can be obtained without depending on an artificial heuristic mode.

The invention discloses a heuristic-based iterative legalization method and system for an analog circuit layout, and the method comprises the steps: dividing layout groups according to a special structure and an array module in a layout based on the initial layout of the layout containing overlapped devices or modules; constructing a constraint graph for describing the relative position relationship between the layout groups, and solving symmetric constraint conflicts in the layout so as to ensure that all symmetric constraints are met; performing simulation processing on a non-overlapping constraint, a minimum area constraint and a minimum spacing constraint through a code simulation solver to generate an initial legal layout; and iteratively adjusting the constraint graph based on a heuristic method, identifying a suspicious group and adjusting the constraint edge of the suspicious group, and re-verifying and repairing the symmetric constraint after each adjustment until the layout area converges. According to the method, the symmetric constraint is synchronously verified and repaired in each iterative optimization, so that the layout area is minimized on the premise of ensuring the layout legality, and the solving efficiency is greatly improved at the same time.

The present application relates to the technical field of GPU computing optimization, and in particular to a sparse attention computing method, device and medium for GPU, wherein the method realizes the high efficiency of long context reasoning through the geometric perception sparse attention framework of ball hashing, and combines a large-scale parallel hashing optimization algorithm and a load adaptive computing kernel. Compared with the existing sparse attention methods based on heuristics or gradient learning, the present application realizes higher retrieval recall rate, lower preprocessing overhead and efficient hardware adaptation to irregular sparse patterns.

Methods, systems, and storage media for providing a heuristic multilanguage tokenizer in a web browser environment are disclosed. Exemplary implementations can receive a query; generate a query set comprising at least one query token; generate a result set from a searchable phrase, wherein the result set comprises at least one phrase token; generating at least one supplemental set. Determining that any of the sets comprise at least one of: a first character-type, a second character-type, or an emoji. In response to determining the first character-type: determining a word boundary and extracting a diacritic. In response to determining that the query, result set and the supplemental set comprise the second-type or the emoji, adding a space around each second character-type or emoji in the set; and segmenting the set into a plurality of tokens.

Systems and methods for implementation of a multi-agent reinforcement learning based decision system for a materials handling system, including initializing a simulation environment comprising decision points for dispatching materials and attributes of the materials handling system, the simulation environment configured to request a decision for materials dispatch at the decision points to the multi-agent reinforcement learning based decision system; initializing the reinforcement learning agents representative of the decision points for the multi-agent reinforcement learning based decision system; initializing domain expert heuristics for the decision points for the multi-agent reinforcement learning based decision system; and iteratively training the reinforcement learning based decision system with the initialized domain expert heuristics on the simulation environment.

The application relates to the technical field of binary program analysis and rewriting, and discloses an immediate number symbolization judgment method and system of a binary rewriting program, which comprises a preprocessing step, a basic evidence analysis step, an intermediate evidence analysis step, a high-level evidence analysis step and a fusion decision step. The preprocessing layer carries out structural analysis and semantic modeling on a binary file, extracts candidate immediate numbers and meta information, the basic evidence layer carries out preliminary weighting based on explicit rules, the intermediate evidence layer carries out quantitative evaluation through heuristics and statistical patterns, the high-level evidence layer carries out high-precision analysis on the immediate numbers with semantic ambiguity, the fusion decision layer summarizes the evidences at all levels, forms a comprehensive tendency value through weighted calculation, classifies the immediate numbers, and generates a final symbolization strategy. The application significantly improves the accuracy and interpretability of symbolization judgment, balances the analysis precision and processing efficiency, and is suitable for binary files of different compilers, platforms and file stripping states.

Implementations generally relate to text clustering with heuristic and multi-metric control. In some implementations, a method includes receiving an electronic source document containing text. The method further includes dividing the text into text units, encoding the text units, and transforming the text units into numerical values. The method further includes generating a graph of the text units based on the numeric values, where the graph includes nodes corresponding to the text units and edges corresponding to pairs of the text units. The method further includes ordering the text units into text clusters based on the graph of the text units. The method further includes generating an electronic target document that presents the text clusters based on one or more preference heuristics.

The present application relates to a kind of heuristic Q-learning-based multi-robot full coverage path planning method, including constructing global gridding map and dividing mutually non-overlapping connected sub-region by DARP algorithm;Each robot independent sub-environment is constructed and Q-learning agent is initialized;Agent uses the enhanced state definition of "absolute coordinate+local environment topological feature", and the optimal action is selected by heuristic strategy of unvisited priority and backtrack distance guidance;The Q value table is updated based on the comprehensive function of coverage reward, dynamic repeated access penalty and completion reward;Path is generated after iteration training to full coverage or reaching preset number.The present application reduces 23.8% of total moving steps under the premise of ensuring 100% coverage, reduces path repetition rate from 26.35% to 3.36%, reduces 44.1% of turning number, significantly improves work efficiency, and can be widely applied to collaborative work scenarios such as cleaning robot cluster and agricultural automatic harvester group.

This invention discloses a single-arm combined device scheduling method based on hierarchical attention graph deep reinforcement learning. This method aims to address the problems of existing rule-based methods relying on artificial heuristics, and the complexity of Petri net models while neglecting topological properties. This invention proposes a State Extraction Graph (SEG) to simplify the modeling process for multi-variety wafer manufacturing, and its graph structure is simpler than Petri nets. Based on SEG, a graph deep reinforcement learning framework is developed, integrating a graph neural network based on a hierarchical attention mechanism (called A-GIN) as a feature extractor to better extract the topological properties of the graph. The single-arm robot agent interacts with the environment, autonomously learns and optimizes wafer release and task sequences, achieving end-to-end policy optimization.

Method and arrangement for determining current location speed limit in a road vehicle. Described herein is a method of determining a current location speed limit in a road vehicle speed limit information system. One or more signals corresponding to respective candidate speed limits for a current location are received. A parameterized heuristics algorithm with an associated cost function is applied to decide which candidate speed limit is applicable, if any. If available for the current location, an estimated true speed limit supplied by a cloud service and an associated confidence in the estimate are received. An online learning or reinforcement learning method is used to continuously fit the parameterization of the heuristics to reproduce the estimated true speed limit supplied by the cloud service with high confidence based on the estimated true speed limit supplied by the cloud service and the associated confidence in the estimate. A speed limit information signal corresponding to the decision of the parameterized heuristics algorithm is output.

Aspects of this technical solution can generate, according to one or more first environment metrics, a three-dimensional (3D) model including a first surface corresponding to one or more physical ways through a physical environment, the one or more first environment metrics indicative of boundaries of the one or more physical ways, generate, according to one or more second environment metrics, one or more geometric two-dimensional (2D) objects on the first surface, the second environment metrics indicative of the one or more physical ways, identify, according to one or more viewpoint metrics indicative of cameras of a physical object configured to move along the one or more physical ways, one or more viewpoints oriented to capture corresponding portions of the 3D model, and render, from the one or more corresponding portions of the 3D model, one or more 2D images each corresponding to respective ones of the viewpoints.

Systems and methods for enterprise production scheduling using a self-learning, resilient Reinforcement Learning (RL) agent. The RL agent interacts with a simulated production environment modeled as a dynamic graph, enabling efficient handling of complex multi-stage scheduling dependencies. Through iterative training, inference, and continuous learning modes, the agent autonomously learns optimal scheduling policies, adapts to evolving production conditions, and incorporates user preferences. The system includes components such as a data profiler for historical analysis, a synthesizer for training data generation, and an initializer for environment setup. The RL agent generates multiple feasible schedules, refines its policy based on feedback, and significantly reduces computational overhead compared to traditional heuristics and genetic algorithms.

A joint segmenting and ASR model includes an encoder and decoder. The encoder configured to: receive a sequence of acoustic frames characterizing one or more utterances; and generate, at each output step, a higher order feature representation for a corresponding acoustic frame. The decoder configured to: receive the higher order feature representation and generate, at each output step: a probability distribution over possible speech recognition hypotheses, and an indication of whether the corresponding output step corresponds to an end of speech segment. The joint segmenting and ASR model trained on a set of training samples, each training sample including: audio data characterizing a spoken utterance; and a corresponding transcription of the spoken utterance, the corresponding transcription having an end of speech segment ground truth token inserted into the corresponding transcription automatically based on a set of heuristic-based rules and exceptions applied to the training sample.

Methods, systems, and computer-readable storage media for providing a set of heuristics representative of training data that is to be used to process a ML model through a training pipeline, the training pipeline including multiple phases, determining a set of time estimates by providing the set of heuristics as input to a training heuristics model that provides the set of time estimates as output, each time estimate in the set of time estimates indicating an estimated duration of a respective phase of the training pipeline, receiving, during processing of the ML model through the training pipeline, progress data representative of a progress of processing of the ML model, determining a set of status estimates including a status estimate for each phase of the training pipeline based on the progress data, and transmitting the set of time estimates and the set of status estimates for display.

A training optimization system implements algorithmic solutions to solve the conjoined problem of accelerator architecture search and model partitioning for distributed training. The system makes the multi-dimensional optimization space of architecture search and device placement tractable by reducing the number of accelerator architectures explored through area-based heuristics and employing a novel integer linear program (ILP), the size of which is dependent only on the number of operators. The ILP scheduling optimization also explores the partitioning of operators across cores, known as intra-operator parallelism. Despite the vast space, the ILP described herein requires significantly less time to perform the optimizations across all explored accelerator configurations. Based on the optimal backward and forward pass latencies, the system leverages a novel dynamic programming (DP) approach to determine the device placement and model partitioning scheme.

The invention relates to the technical field of on-machine measurement, and discloses a heuristic and TS-based OMI path optimization method, system, medium and equipment, and the method comprises the steps: obtaining on-machine measurement points to obtain an initial measurement point set, and constructing an initial flag bit set; combining the two initial sets to construct an initial measurement path, and updating a measurement point set according to the initial measurement path; iteratively optimizing the measurement path and the measurement point set, in each iteration optimization, selecting points from the measurement point set according to the distance between the measurement path and the points in the measurement point set, adding the points into the measurement path, and updating the flag bit set; obtaining a candidate path until the measurement point set is empty; repeatedly generating candidate paths by using the same method until the flag bit set contains all the measurement points, and selecting the shortest path from all the candidate paths as an initial path; and optimizing the initial path by using a tabu search algorithm to obtain a final measurement path. According to the method, the optimal measurement path can be ensured under different measured characteristics, and the solving efficiency is improved.

Exemplary embodiments provide methods, mediums, and systems for facilitating the review of chromatography data. An interface may be presented displaying multiple chromatograms or other types of chromatography data. The interface is configured to receive input that selects a subset of the displayed chromatography data, which is designated as known- good data. The remaining chromatography data is compared to the known-good data using machine learning or heuristics. Based on (e.g.) the peak shapes in the chromatograms, the system determines whether the remaining chromatograms are within an acceptable tolerance of the known-good data or represents a deviation. Using this technique, a user is empowered to train the system based on site-specific or user-specific known-good data, thus allowing the user to quickly determine which of the results may require further investigation.

A system and method of source and type-independent organization, presentation, and management of security detection artifacts, with heuristic and ML-based (machine learning) prioritization algorithms, providing for unified threat detection management and accurate prioritization without requiring an expert user. This is accomplished using an alternative presentation paradigm underpinned by a combination of heuristics and machine learning. The benefits include greater information gain; improved speed of decisioning cybersecurity detection data; elimination of the split-brain problem where different classes of detection artifacts are stored and managed in different systems; and reduced need for expert users. In cases where machine learning and / or anomaly detections are not available for clustering.

The invention relates to the technical field of machine learning, in particular to a heuristic mechanical arm path planning method and device, a mechanical arm and a storage medium. Inputting the path planning data into a semantic segmentation model, and performing feature extraction through a sequential residual module of the semantic segmentation model to obtain a first feature; balancing local details and global backgrounds in the first features through a cavity space pyramid pooling module of the semantic segmentation model to obtain second features; removing redundant features of the second features through a self-attention mechanism module of the semantic segmentation model to obtain third features; obtaining path region features through the semantic segmentation model; and processing the path region features through a path planning algorithm to obtain a planned path. Wherein the accuracy of path region feature generation is increased through a sequence residual module and a cavity space pyramid pooling module of the semantic segmentation model.

Prior methods of state estimation rely on penalty-based heuristics to enforce inequality constraints, which can produce very large weight values, resulting in ill-conditioning of the gain matrix. Disclosed embodiments of state estimation convert the inequality-constrained optimization problem into an unconstrained optimization problem in which violated inequality constraints are represented as parameterized potential functions, each comprising a center-of-attraction parameter. This unconstrained convex optimization problem can be iteratively prepared, using successively updated values for the center-of-attraction parameters, and solved, until no inequality constraints are violated, to produce a final estimated state. This final estimated state may then be used to control the system being monitored, such as a power system.

The application discloses a heuristic online log parsing method and system based on an adaptive deep parsing tree, wherein the method comprises the following steps: constructing a parsing tree, inputting the field number of each log message into different log length matching nodes, and matching the preprocessed log message to the related sub-tree according to the matching result; determining the depth of the current sub-tree according to the length of the preprocessed log message and the preset fitness; matching the several fields of the preprocessed log message to the nodes of the current sub-tree in a head-to-tail alternating manner; after the multi-layer node traversal, reaching the leaf node of the current sub-tree; finding the most matched log group of the preprocessed log message in the leaf node of the current sub-tree; updating the log template and the log ID list of the most matched log group; and obtaining the structured data of the log message set to be parsed after all the log messages are processed.

The invention relates to the technical field of binary program analysis and rewriting, and discloses an immediate operand symbolization judgment method and system for a binary rewriting program, and the method comprises a preprocessing step, a basic evidence analysis step, an intermediate evidence analysis step, an advanced evidence analysis step and a fusion decision-making step. The preprocessing layer is used for carrying out structure analysis and semantic modeling on the binary file and extracting candidate immediate operands and meta-information; performing preliminary weighting on the basic evidence layer based on an explicit rule; the intermediate evidence layer carries out quantitative evaluation through a heuristic mode and a statistical mode; the advanced evidence layer performs high-precision analysis on the immediate data of semantic ambiguity; and the fusion decision-making layer summarizes the evidences of all levels, forms a comprehensive tendency value through weighted calculation, classifies immediate operands, and generates a final symbolization strategy. According to the method, the accuracy and interpretability of symbolization judgment are remarkably improved, the analysis precision and the processing efficiency are both considered, and the method is suitable for binary files in different compilers, platforms and file stripping states.

The present application relates to the technical field of unmanned aerial vehicles, in particular to a heuristic-driven unmanned aerial vehicle multi-target task planning and path planning system. The present application decouples tasks into unmanned aerial vehicle, task and battlefield environment models through a model module, and is connected with an optimization algorithm module. The optimization algorithm module receives the decoupled model data, determines the planning target and generates the optimization result, and feeds back to the model module. The path planning module generates the unmanned aerial vehicle flight path according to the optimization result. The target identification module receives real-time image data, and detects and identifies the target by using a pre-trained model. The target tracking module receives the identified target information, and calculates the predicted trajectory. The algorithm optimization module iterates and mutates the algorithm based on historical data and dynamic weight optimization. The system effectively improves the task completion efficiency, path optimization, safety and adaptability, and opens up new possibilities for the intelligent application of unmanned aerial vehicles in complex dynamic environments.

This invention relates to a heuristic-based method for generating fault patterns in the aviation field, comprising: S1, extracting features from aviation fault text data using a bag-of-words model and the term frequency-inverse text frequency index method; S2, performing clustering category analysis of aviation fault text data based on k-means heuristics; S3, detecting outliers, extracting faults, and concatenating faults in the aviation fault text data to obtain fault pattern names; and S4, processing the obtained fault description text in real time to generate aviation fault patterns. This invention completes text data clustering category analysis using a bag-of-words model, the term frequency-inverse text frequency index method, and the k-means heuristic method. Furthermore, it obtains fault pattern names through outlier detection, fault extraction, and concatenation, enabling real-time detection of fault text data. By periodically re-clustering, it can discover new fault patterns by utilizing existing prior knowledge, thereby improving the accuracy and effectiveness of fault pattern detection.

The invention relates to a multi-robot full-coverage path planning method based on heuristic Q-Learning. The multi-robot full-coverage path planning method comprises the following steps: constructing a global rasterized map and dividing non-overlapped connected sub-regions through a DARP algorithm; an independent sub-environment of each robot is constructed, and a Q-Learning agent is initialized; the intelligent agent adopts an enhanced state definition of absolute coordinates and local environment topological characteristics, and an optimal action is selected through a heuristic strategy of non-access degree priority and backtracking distance guidance; updating a Q value table based on a comprehensive function of coverage rewards, dynamic repeated access punishment and completion rewards; and iteratively training to full coverage or generating a path after a preset number of times is reached. On the premise of ensuring 100% coverage rate, the total moving step number of the system is reduced by 23.8%, the path repetition rate is reduced from 26.35% to 3.36%, the turning frequency is reduced by 44.1%, the operation efficiency is remarkably improved, and the method can be widely applied to collaborative operation scenes such as cleaning robot clusters and agricultural automatic harvester groups.

Mechanisms are provided for automated rule set generation for identifying relations in knowledge graph data structures. An input knowledge graph is processed to extract tuples representing relations between entities present in the input knowledge graph. A set of rules is generated based on one or more heuristics applied to tuples, and candidate rule(s) are identified that are candidates for adding to the set of rules. A linear programming computer model is evaluated for a modified set of rules comprising the set of rules and the candidate rule(s) to determine whether or not adding the candidate rule(s) improves an objective function of the linear programming model. The set of rules is expanded to include the candidate rule(s) in response to the evaluation of the linear programming computer model indicating that the addition of the candidate rule(s) improves the objective function of the linear programming computer model.