4687 results about "Computing systems" patented technology

A federated distributed computational system enables secure oncological therapy optimization through robotic integration. The system establishes a distributed graph architecture with secure communication channels connecting computational nodes, implementing encryption protocols for cross-institutional data exchange. Each node contains processing capabilities for fluorescence-guided imaging, uncertainty quantification, and expert knowledge integration while maintaining hierarchical knowledge graphs of oncological biomarkers, interventions, and outcomes. The system coordinates domain-specific knowledge through token-space communication and implements an advanced robotic integration system for surgical interventions using spatiotemporal tumor mapping, multi-modal fluorescence imaging, surgical robot coordination, and space-time stabilized mesh management. Key capabilities include wavelength-specific multi-modal fluorescence detection, combined epistemic and aleatoric uncertainty estimation, tensor-based data integration with adaptive dimensionality control, and light cone search for adaptive treatment optimization—all while maintaining strict privacy controls.

A computing system for adaptive electronic message classification employs a multi-agent architecture comprising a media feature analysis system, a user context refinement system, and a response synthesis system. The media feature analysis system generates pillar scores including message type, intent, and link risk scores with associated confidence values using trained classification models. When pillar scores and confidence values do not satisfy predetermined threshold conditions, the user context refinement system dynamically constructs contextual prompts using the pillar scores and confidence values as input parameters. User responses generate score modification data that refines the pillar scores and contextual response data for recommendation generation. The response synthesis system generates refined classifications and personalized recommendations using the refined pillar scores and contextual response data. An orchestration system coordinates agent interactions using learned uncertainty points and implements asymmetric influence algorithms with variable weighting based on content and URL analysis concordance.

The invention discloses a real-time computing system resource coordination and decision engine system based on a large language model. According to the system, a large language model is innovatively used as a central strategic decision engine, and a'decision-coordination-execution 'three-layer architecture is constructed. According to the system, macroscopic strategy generation and microscopic real-time control are decoupled by introducing a hierarchical decision-making mechanism (a strategic layer, a tactical layer and an execution layer), so that the core contradiction between LLM high reasoning delay and the microsecond / millisecond-level real-time requirement of the system is effectively solved, and the method is suitable for local computing equipment and a cloud data center. The system comprises a predictive strategy preloading system, and transient response can be achieved. Meanwhile, the system adopts an asynchronous event-driven decision-making mechanism for continuous intelligent optimization. According to the method, the top-down, semantic understanding-based and global collaborative intelligent management of the computing resources is realized, and the resource utilization efficiency, the system automation degree and the overall energy efficiency in a complex and dynamic computing environment are remarkably improved.

The invention discloses an energy-efficient task scheduling method for an edge computing system, which comprises the following steps of: acquiring a task state, a computing node resource state, a link state and an energy consumption state according to a unified time slot under a computing power network control domain, and constructing a system state vector; performing priority evaluation on the to-be-scheduled task based on the residual delay budget, the candidate node energy efficiency coefficient and the queue position to obtain a target task set; inputting a system state vector and a target task set into an energy efficiency perception deep reinforcement learning scheduling model, outputting a task-node allocation decision under the constraint of computing node resources and task time delay, and introducing a system-level energy consumption ratio, self-adaptive energy consumption penalty and exploration bias facing high-energy-efficiency nodes into rewards; and scheduling tasks according to the allocation decision, recording state transition and instant rewards, updating a double-commentator and actor network, and performing iterative execution in continuous time slots. According to the method, task success rate, time delay, load balancing and energy-saving performance are considered, and system energy consumption is reduced.

Techniques for determining a presence of an object, especially an object such as animal or debris, in a path of a vehicle, are discussed herein. For example, sensors of various modalities, which may include multispectral sensors, may capture data representing an environment the vehicle is traversing. In examples, one or more trained machine learned (ML) models, operating on a vehicle computing system, may detect and / or classify objects in the environment, based on input data of one or more modalities or spectral bands. The ML models may be pre-trained using training data including real sensor data, synthetic data, and / or augmented data, along with auto-generated annotations. In some examples, hyperspectral data may be used to identify materials associated with detected objects. A confidence score associated with the detection of the object may also be computed. The vehicle may be controlled based on detection of the object and its classification.

The invention discloses a distributed computing task non-perception migration method and system under optical fiber network interruption. The distributed computing task non-perception migration method comprises the following steps: constructing a distributed task migration system and an output system architecture; collecting network state indexes, constructing a network topological graph, and analyzing the state of an optical fiber link for fault prediction; obtaining a calculation task operation state, establishing a sub-task mapping relation, constructing a directed dependency graph, and generating a state snapshot; analyzing resource requirements, reserving standby resources, and deploying a distributed cache system; analyzing a fault influence range, extracting an influenced calculation sub-graph, and selecting a migration target node; in a target node preloading environment, reconstructing an execution context, and redirecting a communication path; and setting a data change capture mechanism, synchronizing incremental data and executing consistency verification. According to the method, non-perception migration of the computing tasks is realized, task continuity and data consistency are guaranteed, and the reliability of the distributed computing system in an optical fiber network fault scene is improved.

A method of question answering using enhanced retrieval-augmented generation according to an embodiment includes receiving, by a computing system, a user query, pre-processing, by the computing system, the user query to determine whether the user query is associated with malicious intent, retrieving, by the computing system, relevant data from a knowledge base by using a keyword index and a semantic index in response to determining that the user query is not associated with malicious intent, prompting, by the computing system, a large language model to generate an answer to the user query based on only the relevant data retrieved from the knowledge base, and receiving, by the computing system, the answer to the user query from the large language model in response to the prompt.

An adaptive modular multimodal communication and computing panel includes a multilayer stack with a protective layer transmissive in selected bands, a reconfigurable communication layer operable in phased array, reflectarray, hybrid phased reflector, free space optical, or quantum modes, and electronics with heterogeneous processors. A multi scale interconnect and input and output fabric couples electrical, radio frequency, guided optical, and free space optical domains through interfaces including electro optic transduction and RF or baseband conversion. The fabric may implement programmable true time delay, resonators, and comb referenced timing. A management system coordinates beamforming, sensing, routing, calibration, workload placement, and security. Panels tessellate and connect by electrical, radio frequency, and fiber optic interfaces, supporting hot swappable modules, blind mate connectors, robotic servicing, and anti tamper features. Power and thermal subsystems harvest, store, regulate, and dissipate energy. The architecture scales from chip level modules to vehicle, airborne, maritime, orbital, and deployable systems.

A computing system is disclosed for generating and optimizing schema-conformant object models. The system obtains input data from multiple sources in structured, semi-structured, or unstructured formats and processes the data using parsing logic to derive a structured rule set defining spatial relationships and constraint conditions. The system generates schema-conformant object representations comprising parametric assemblies, applies the constraint conditions using machine-executed resolution logic, and produces candidate object models through iterative modification of spatial components, dimensional parameters, and adjacency relationships. Performance values are computed for the candidate models using quantitative evaluation of spatial efficiency, material usage, and constraint compliance. An optimized object model is selected based on the computed performance values and may be used to generate construction project plans including technical drawings, material specifications, and scheduling instructions.

A platform for multi-stage simulations in a multi-agent simulator computing system utilizes context sharing across simulation sessions. The platform generates agents based on input traits, executes simulation sessions to produce outputs, and persists outputs and agent configuration data (e.g., metadata associated with simulation sessions). A graphical user interface displays simulation outputs. In response to user interaction with a particular output item (e.g., a user follow-up query or inquiry into simulation traceability), the platform identifies the associated agent using persisted configuration data and performs additional operations, which can include generation and execution of additional queries for follow-up simulations.

The invention discloses a sewage treatment whole-process operation regulation and control calculation system based on deep learning, and relates to the technical field of intelligent control, and the system comprises a strategy optimization module which optimizes a future pollution trend prediction sequence and a regulation and control factor weight table by using a reinforcement learning strategy network in combination with a genetic algorithm optimizer, dynamically generating an aeration, dosing and backflow operation parameter combination aiming at a regulation target to form a dynamic regulation instruction set; the instruction execution module is used for issuing a dynamic regulation and control instruction set to the programmable logic controller by utilizing an industrial control interface, and collecting response information and real-time effluent quality data as execution feedback information; and the model updating module carries out error comparison on execution feedback information and a future pollution trend prediction sequence, constructs a weighted error sequence, and dynamically corrects deep network parameters through an online fine tuning strategy to form a prediction control model. According to the method, the generalization ability and robustness of the predictive control model are remarkably improved.

A method, computer program product, and computing system for processing a query provided to a generative AI model. A content portion retrieved by a Retrieval Augmented Generation system for the query is processed. User context information associated with a user providing the query is determined. Hyperparameters are generated for processing the prompt with the generative AI model by processing the query, the content portion, and the user context information using run-time surrogate model inversion optimization.

The invention relates to the technical field of transformer substation intelligent inspection, in particular to a meta-learning-based small-sample transformer substation equipment state adaptive inspection system, which comprises a state acquisition module for acquiring the current feature vector and environmental parameter data of a target node; the drift detection module is used for comparing environment parameters to judge data drift and dynamically adjusting a confidence coefficient threshold value; the risk assessment module inputs the feature data into a meta-learning model to output an initial risk probability, and generates an effective risk probability based on threshold filtering; the blind area measurement module is used for acquiring unobserved nodes and calculating system state blind area entropy; the scheduling decision-making module is used for comparing the blind area entropy with a threshold value and generating an entropy reduction bottom instruction or a self-adaptive routing inspection distribution instruction; the strategy updating module is used for extracting an actual inspection result and feeding back to the model for parameter updating; according to the invention, the scheduling difficulty when the resources are limited is solved, and the self-adaptive capability of the system under different environment interferences is improved.

The invention relates to the technical field of power dispatching management and control, and discloses a power distribution network power dispatching method based on a virtual power plant AI large model and demand response, and the method comprises the steps: collecting the operation data of a power distribution network, and constructing a feature vector; an AI large model is adopted to calculate and predict load output, and joint uncertainty information is output; calculating a system power unbalance amount, and generating a scheduling strategy; issuing a scheduling instruction corresponding to the scheduling strategy and executing the scheduling instruction; comprehensive performance evaluation indexes are calculated, and whether a performance reduction reason diagnosis mechanism is started or not is judged; according to the method, the AI large model is adopted, the load power, the photovoltaic output and the wind power output are predicted at the same time through a multi-task learning strategy, and the correlation among multiple variables is fully utilized; by constructing a multi-objective optimization model, comprehensively considering economy, safety and reliability and adopting an improved particle swarm optimization algorithm for solving, coordinated optimization configuration of demand response resources is realized, power grid fluctuation is effectively reduced, and power supply reliability is improved.

Certain aspects provide techniques and apparatus for executing queries in a computing system using machine learning models. An example method generally includes receiving a plan to satisfy a request in the computing system and event log data associated with execution of the plan. The plan generally specifies a first plurality of function calls at a first level of granularity. Using a plan refinement machine learning model, a refined plan is generated when the event log data indicates that execution of the generated plan results in one or more execution errors and the one or more execution errors are solvable. Generally, the refined plan specifies a second plurality of function calls at a second level of granularity, the second level of granularity being finer than the first level of granularity.

The invention discloses an air pressure-boiling point self-adaptive regulation and control system and method of an energy storage immersed phase change liquid cooling system, and relates to the technical field of energy storage systems. The method comprises the following steps: calculating a thermal load of a system in real time, performing multi-objective optimization grading, and dynamically determining an optimal boiling point set value under a current working condition; resolving and obtaining a target air pressure set value by using the air pressure-boiling point relation mapping library; an improved composite control algorithm integrating feedforward control, fuzzy adaptive PID, integral saturation resistance and change rate limitation is adopted to drive an air pressure regulation execution mechanism, and regulation and control of the air pressure in the system are achieved. The system and the method have the advantages of high control precision, high response speed, good stability, high adaptability and the like.

A computer-implemented method, computer program product and computing system for defining a formatting script for use with a Generative AI Model; receiving a plurality of notifications of a security event, wherein each of the plurality of notifications includes a computer-readable language portion that defines one or more specifics of the security event, thus defining a plurality of computer-readable language portions; processing at least a portion of each of the plurality of computer-readable language portions using the Generative AI Model and the formatting script to summarize each of the computer-readable language portions and generate a plurality of event summaries; and′ processing at least a portion of each of the plurality of event summaries using the Generative AI Model and the formatting script to summarize the plurality of event summaries and generate a summarized human-readable report.

The invention provides a BLAS3 structured operator accelerated computing system based on a Hopper architecture GPU, and relates to the technical field of computers. The system comprises: a calculation unit discrimination module for determining a calculation unit used by a current operator during operation, and estimating the maximum row dimension upper bound of the current operator in a tensor core execution path; an instruction sensing block parameter determination module dynamically determines the optimal block size and number of the input matrix in real time; the block matrix loading and aligning module divides an input matrix and a matrix to be updated into sub-matrixes by taking the block size as a basic block and completes loading of the corresponding sub-matrixes; the operator kernel function execution module completes shared memory structured parallel loading and storage of a double-precision floating-point number array of a sub-matrix corresponding to the input matrix, and calls a tensor core to carry out multiply-add accumulation calculation; and the assembly line and concurrent scheduling module adds the block calculation tasks into corresponding task sets and performs multi-stream concurrent scheduling on the task sets.

A method, computer program product, and computing system for processing a dataset of query-answer pairs. Synthetic variations of queries are generated and each of the synthetic variations of queries are mapped to a corresponding answer from the dataset. An embedding dataset is generated by transforming the synthetic variations into synthetic query embeddings and the queries into query embeddings. A first set of embeddings is defined for storage in a semantic cache and a second set of embeddings are defined and are not stored in the semantic cache. A separate distance threshold is assigned to each embedding of the first set of embeddings and a pairwise distance between each query and the synthetic variations is determined. Distance thresholds for respective pairwise distances between a query and synthetic variations of the query are generated. Subsequent queries are processed using the semantic cache and the distance thresholds.

Techniques and apparatuses for enhanced text suggestions are described. An example method includes detecting a user gesture performed by a user of the computing system based on data from one or more neuromuscular sensors and identifying a set of text characters corresponding to the user gesture. The method further includes causing display of the set of text terms in a user interface and determining whether a cognitive load of the user meets one or more criteria. The method also includes providing a text suggestion to the user based on the set of text characters in accordance with a determination that the cognitive load of the user meets the one or more criteria, and forgoing providing the text suggestion to the user based on the set of text characters, in accordance with a determination that the cognitive load of the user does not meet the one or more criteria.

The invention relates to the technical field of data processing, and discloses a mine production-oriented multi-source data acquisition and edge calculation fusion device, which comprises a clock synchronization access module, a data governance control module, a flow pipeline backpressure module, an AI reasoning optimization module, a rule closed-loop control module, a message safety uplink module and a center training iteration module, according to the method, the problem of difficulty in data fusion of multi-source equipment is solved, and the consistency of heterogeneous data in time and semantic dimensions is ensured; the stability of an edge computing system under a complex working condition is improved, and data loss and processing delay are avoided; collaborative decision-making of the AI model and the rule engine is realized, and the risk of false report and missing report is reduced; the security and reliability of the data transmission process are ensured, and local autonomy when the network is abnormal is supported; a model automatic iteration mechanism is established, and the ability of the system to adapt to different working conditions is improved.

In some aspects, a cloud-based computer system includes: a quantum computing system comprising a quantum processing unit; a container management and execution system configured to receive a container and execute a program within the container; and a communication channel between the container management and execution system and the quantum computing system for providing program instructions to the quantum computing system. The container management and execution system and the quantum computer system may be co-located in a data center or located in different data centers. The latency of the communication channel may be selected to optimize cost for a required computer performance.

A method, computer program product, and computing system for processing a plurality of query-answer pairs associated with a generative artificial intelligence (AI) model. A first set of query variations are generated from the plurality of query-answer pairs using a genetic algorithm. A plurality of content portions associated with the first set of query variations are identified using a Retrieval Augmentation Generation (RAG) system. A fitness score associated with each of the query variations of the first set of query variations is determined using the plurality of content portions. A plurality of query variation-answer pairs are generated by generating a second set of query variations from the first set of query variations using the genetic algorithm and the fitness scores associated with each of the first set of query variations.

The invention relates to the technical field of streaming computing, and provides a real-time service computing system based on a dynamic rule engine, which comprises a rule management module and a streaming computing engine, the rule management module is used for providing visual configuration and release functions of service rules and performing versioning storage on the released service rules; the streaming computation engine comprises a rule synchronization unit and a plurality of parallel processing units; the rule synchronization unit is used for acquiring service rules from the rule management module and distributing the acquired service rules to each parallel processing unit based on a broadcast mechanism; and each parallel processing unit is used for receiving the business event flow and performing real-time rule matching on the business event flow according to the received business rule so as to output a decision result. According to the system, complete decoupling of business rule configuration and execution is realized, and the problem that rule updating in a traditional business system needs shutdown deployment is effectively solved.

Certain aspects provide techniques and apparatus for executing queries in a computing system using machine learning models. An example method generally includes receiving a plan to satisfy a request in the computing system and event log data associated with execution of the plan. The plan generally specifies a first plurality of actions to be performed by the computing system at a first level of granularity. Using a plan refinement machine learning model, a refined plan is generated when the event log data indicates that execution of the generated plan results in one or more execution errors and the one or more execution errors are solvable. Generally, the refined plan specifies a second plurality of actions to be performed by the computing system at a second level of granularity, the second level of granularity being finer than the first level of granularity.

The invention provides a rotating mechanical system performance evaluation and optimization method and system based on system negentropy conversion rate, and the method comprises the following steps: carrying out the numerical simulation of a flow field of a rotating mechanical system through a computational fluid mechanics method, and obtaining the parameters of the flow field; calculating a viscous dissipation entropy yield, a turbulent dissipation entropy yield and a wall entropy yield in the fluid domain based on the flow field parameters; the total entropy yield of the system is obtained through the volume fraction and the wall area fraction of the whole fluid domain; converting the input power of the rotating machinery into an equivalent negentropy flow, and calculating the negentropy conversion rate of the system for evaluating the effective utilization degree of the input power; and evaluating the performance of the rotating machinery system based on the negentropy conversion rate, and identifying a key area of energy loss. According to the method, the negentropy conversion rate result is applied to structural design optimization, running state diagnosis and energy efficiency adjustment of the rotating machinery, and online calculation and dynamic visualization can be realized in combination with real-time monitoring data.

Provided are computer-implemented methods and quantum computing systems for preparing computational states representing quantum states of a physical system, including performing a computational evolution of the state and then determining physical properties of the system using the time-evolved computational state. Hamiltonian dynamics of observables are computed on a quantum computer to provide information about the physical system represented by the Hamiltonian. Low energy electronic structure states of a physical system are prepared using adiabatic evolution. The energy of an equilibrium quantum state of a physical system is determined using a time-evolution operator. The energy of an eigenstate of a physical system is indirectly determined by evaluating expectation values of a time-evolution operator averaged across multiple shots for randomly-generated quantum circuits. Example methods enable calculation of the energy of an evolved computational state with chemical accuracy, due to avoiding discretization errors, with a smaller circuit depth than known alternatives.

Exemplary system and methods for processing a natural language query in an edge computing system are disclosed. A processor of the computing system receives a natural language textual input as a query from a user interface and receives one or more containers of documentation over a communication channel. The processor generates a query embedding vector from the textual input. The processor extracts text from the received container and generates text chunks of specified length from the extracted data. Text embeddings are generated from the text chunks and stored in memory for a specified period. The query embeddings are compared with the text embeddings to determine relevant context information. The processor passes the relevant context information and the query through a trained neural network to generate a response. The response generated by the trained neural network is formatted and output to a user interface.

Various examples, systems, and methods are disclosed relating to frame selection via activity-based ranking and optimization. A first computing system can receive a plurality of frames and metadata from a capture device capturing a video stream. The first computing system can generate, using a ranking model, a plurality of rankings for the plurality of frames based on a plurality of video parameters of the plurality of frames and the metadata, wherein the plurality of rankings correspond to a summarization of the video stream. The first computing system can determine at least one of the plurality of frames to provide to at least one buffer based on the plurality of rankings, wherein the at least one buffer stores a subset of frames of the plurality of frames. The first computing system can provide, from the at least one buffer, the subset of frames as input to a machine-learning model.

The invention discloses an automatic fault repairing method for an operating system based on artificial intelligence, and relates to the technical field of automatic fault repairing, and the method comprises the steps: carrying out the feature analysis of system operation data through a pre-trained fault feature extraction model, generating a fault feature vector, inputting the fault feature vector into a fault classifier, and obtaining a fault feature vector; a current fault type is identified through a multi-classification algorithm, fault cause primary tracing is performed according to the fault type to obtain a fault generation factor, secondary tracing is performed on the fault generation factor to obtain a fault influence factor, positioning is performed based on the fault generation factor, and a corresponding repair strategy is matched from a knowledge base. The method comprises the following steps: acquiring historical system operation data with relevance on the basis of a fault influence factor, acquiring updated real-time system operation data after executing a repair operation to calculate a system optimization coefficient, judging a forward trend of a repair strategy according to a preset optimization threshold value, and updating the forward trend into a knowledge base to realize rapid and efficient automatic repair.