32results about How to "High data efficiency" patented technology

The invention provides a thinking tree guidance-based large model target spatial relationship determination method and apparatus, relates to the technical field of artificial intelligence, and aims to solve the technical problems of low interpretability and low data processing efficiency when an existing large model processes a complex spatial reasoning task. The method comprises the following steps: acquiring a spatial reasoning task to be processed; according to the spatial reasoning task, task description features corresponding to the spatial reasoning task are analyzed, and the task description features comprise story features and problem features representing spatial relations of all objects; the task description features are input into a pre-trained large language model, and the following operations are executed: the problem features are split into a thinking tree structure with a plurality of nodes, and each node represents a thinking step; according to each thinking step, identifying potential spatial relationship features between the source object and the target object in the story features; and determining the spatial relationship between the source object and the target object according to the potential spatial relationship characteristics.

According to the Modbus communication method and communication system based on the DCS controller, after a Modbus master station sends a data reading instruction to the DCS controller through a Modbus slave station gateway, the DCS controller interrupts receiving of Modbus communication data after receiving the data reading instruction and inquires whether Modbus address table data is updated or not at present, and if yes, the Modbus communication data is updated. The Modbus address table is a slave station data area established in a controller memory by the DCS controller through Modbus slave station data configuration; if the DCS controller currently updates the Modbus address table data, the data reading instruction is cached, and the data reading instruction is called until updating is completed; if the DCS controller does not update the Modbus address table data at present, corresponding slave station data are acquired from the Modbus address table data according to the data reading instruction, packaged and fed back to the Modbus slave station gateway, so that a Modbus master station can receive all data in a DCS control process, and the data transmission efficiency and flexibility are improved.

The invention discloses a Petri network-based fault diagnosis method and system and a storage medium, and the method comprises the steps: S1, obtaining a time sequence signal of substation equipment, the time sequence signal comprising alarm information and accident and displacement information; s2, on the basis of the time sequence signal of the substation equipment, constructing a fault judgment rule base and setting a front part weight, a rule starting threshold value and a back part credibility; s3, establishing a fuzzy function based on the preceding component weight, the rule starting threshold and the consequent component credibility; s4, on the basis of the Petri network and the fuzzy function, a network topology model of the substation equipment is established, and the network topology model of the substation equipment comprises a fault intelligent judgment rule base; and S5, based on the network topology model of the substation equipment, obtaining a current time sequence signal of the substation equipment, and judging a fault condition of the substation equipment. By establishing the network topology model of the substation equipment, the fault diagnosis analysis speed is increased, the fault diagnosis efficiency is improved, and the diagnosis effect of the power system is optimized.

The present invention provides a method and device for determining the target spatial relationship of a large model based on a mind tree, which relates to the field of artificial intelligence technology and is used to solve the technical problems that the existing large model is not interpretable when processing complex spatial reasoning tasks and the data processing efficiency is low. The method comprises: obtaining a spatial reasoning task to be processed; parsing the task description features corresponding to the spatial reasoning task according to the spatial reasoning task, wherein the task description features include story features and question features that characterize the spatial relationship of each object; inputting the task description features into a pre-trained large language model, and performing the following operations: splitting the question features into a mind tree structure with multiple nodes, wherein each node represents a mind step; according to each mind step, identifying the potential spatial relationship features between the source object and the target object in the story features; and determining the spatial relationship between the source object and the target object according to the potential spatial relationship features.

The invention discloses a thermodynamic system analysis method and system based on a physical information neural network. The method comprises the following steps: constructing a thermodynamic system mathematical model; converting a solving problem of the mathematical model of the thermodynamic system into an optimization problem taking a minimum control equation set residual error as a target function; constructing a physical information neural network; constructing a composite loss function based on the control equation set residual sum of squares, and performing end-to-end training on the physical information neural network to obtain a trained physical information neural network; taking the trained physical information neural network as an approximate solver, and for any given thermodynamic system input working condition, predicting a group of approximate solutions as initial predicted values through one-time forward propagation; and inputting the initial predicted value into a traditional numerical solver for accurate solving to obtain a to-be-solved state variable. According to the method, a feasible technical path is provided for applications with strict requirements on the analysis and calculation speed of the thermodynamic system, such as real-time simulation, online optimization and digital twinning.

The invention relates to a sea area management and control early warning evidence obtaining method based on video intelligent analysis, and the method comprises the steps: collecting equipment parameters: collecting internal and external parameters of equipment and environment parameters; equipment screening control is carried out, controllable and controllable equipment with a good detection effect is selected through equipment state analysis and target detection effectiveness analysis, and follow-up monitoring of a target area is realized through pan-tilt control; performing video intelligent analysis, determining a follow-up concerned target through mapping matching of a video intelligent analysis model and different coordinate system positioning information, and performing accurate linkage and video snapshot by fine tuning equipment; according to early warning and evidence obtaining association, structured attribute analysis is performed on a target and an area detected in a video capturing process, and an evidence obtaining result is added to early warning information with an association relationship, so that repeated evidence obtaining is avoided. According to the invention, the accuracy and efficiency of early warning evidence obtaining can be effectively improved, the utilization efficiency of data and resources is improved, and powerful technical support is provided for sea area management and control.

The invention discloses a line loss prediction method and system based on integrated DBN-BP, and belongs to the technical field of power system data analysis. The method comprises the steps that firstly, a plurality of parallel DBN sub-networks are constructed, all the sub-networks adopt different activation functions, unsupervised pre-training is carried out with N antenna loss historical data and corresponding weather data as input, and high-dimensional robust features are automatically extracted; and then, taking the output of each sub-network as a feature, inputting the feature into a BP integrated network for supervised training, and finally fusing to obtain a high-precision line loss prediction value. Through the architecture of "unsupervised feature extraction + supervised integrated decision", the problems of strong dependency on annotated data and weak feature extraction ability in the prior art are effectively overcome; meanwhile, forward prediction can be simplified into efficient matrix operation through the full-connection structure of the model, the requirement for real-time dispatching of the power grid is met, excellent generalization ability is achieved, and reliable data support is provided for economical and safe operation of the power grid.

The present application belongs to the field of logistics information technology and edge computing technology, and discloses a logistics terminal data real-time processing method based on edge computing, which comprises the following steps: initializing a bottom hardware interface, mapping heterogeneous original signals into a unified structured data frame; activating a streaming correlation analysis engine, calculating the joint deviation intensity of multi-modal physical quantities and triggering cross-modal fusion; based on task characteristic fingerprints and system load prediction trajectories, hard binding the task to a specified processor core; realizing business logic atomic switching through double-buffer bytecode hot updating; starting a Markov chain probability state machine to maintain autonomous decision-making and perform incremental differentiated storage when the network is disconnected. The present application improves the real-time performance, reliability and business flexibility of logistics terminal data processing, and is suitable for various logistics terminals that require edge computing for real-time data processing. The present application solves the problems of control response delay and business rule updating difficulty of existing logistics terminals under network fluctuation and high concurrent load working conditions.

The application discloses a general-purpose learning method and system for a physical robot, which comprises a special talent model library, a monitor set, a general talent model and a multi-robot distributed exploration cluster. The special talent model library contains L pre-trained special talent models. The monitor set contains L monitors, each of which is arranged with a special talent model and used for evaluating whether a current input state belongs to the use range of the special talent model. The multi-robot distributed exploration cluster contains multiple physical robots, each of which is arranged in a different task scene. In the application, multiple robots are introduced to perform different tasks in parallel, the monitor is used to dynamically determine when the special talent model needs to be involved, the appropriate special talent model is selected for guidance, the DAGGER type iterative data aggregation mechanism is adopted, the general talent model continuously learns on the state distribution generated by self-exploration in multiple scenes, and finally, the general talent model which can adapt to multiple scenes and surpass a single special talent is obtained.

The invention discloses an online monitoring alarm network system based on a lightning protection environment, and relates to the technical field of lightning protection monitoring, and the system comprises a data collection module which is disposed at an offshore wind power plant and is used for collecting multi-dimensional data including salt mist concentration, wind speed, lightning parameters and lightning protection equipment state parameters; the data processing module is in communication connection with the data acquisition module and is used for receiving, fusing and analyzing the multi-dimensional data, performing scoring calculation by constructing a quantitative scoring model and endowing each dimensional parameter with a weight, and outputting a quantitative risk level according to a total score interval judgment mode; the early warning and linkage module is in communication connection with the data processing module and is used for executing graded early warning and linkage control based on the risk grades; the data processing module is further used for calculating the health state index of the SPD and dynamically predicting the remaining effective life of the SPD based on the health state index and the real-time environment parameters. The system has the functions of self-adaption to environment change and lightning protection monitoring and early warning.

The application provides a ship-vehicle-person virtual image establishment method and system, which comprises the following steps: obtaining ship, personnel and vehicle data as source data for preprocessing, calculating and mining labels according to the preprocessed source data, and producing ship, personnel and vehicle labels; defining hierarchical labels; defining group labels; extracting basic attributes of the ship, personnel and vehicle; defining personalized labels, adding personalized labels to the ship, personnel and vehicle according to their basic attributes and respective source data; defining correlation relationship labels among the ship, personnel and vehicle; creating a label table in a database, adding the calculated labels into the label table, and then performing correlation analysis on the respective source data of the ship, personnel and vehicle and the label table according to business requirements to obtain index data; and providing the index data to a ship-vehicle-person virtual image system for drawing charts. The application can improve traffic operation efficiency, safety and risk prediction.

The utility model belongs to the field of torque measurement, and particularly relates to a ball screw friction torque measuring device which comprises a base assembly, a fixing plate and a measuring assembly. A sliding groove is formed in the top of a base of the base assembly, and four mounting blocks distributed in a rectangular shape are arranged on the outer surface. A motor and an electric push rod are installed on the fixing plate. The motor transmits power through a coupler. The measuring assembly comprises a connecting block, a first clamping plate, a second clamping plate and a long bolt, the first clamping plate and the second clamping plate are embedded into the first torque sensor and the second torque sensor respectively, the bottom of the connecting block is in sliding fit with the sliding groove, and the output end of the electric push rod is fixedly connected with the connecting block. The electric push rod drives the measuring assembly to move on the sliding groove, clamping and position adjusting of the ball screws of different specifications are achieved, the double torque sensors are used for synchronously collecting friction torque data, and the measuring efficiency and reliability of the friction torque of the ball screws can be effectively improved.

The invention discloses a pathological image segmentation method and system based on coevolution generation type difficult sample mining, and the method comprises the steps: constructing a mask synthesis engine guided by biological information, and generating a cell nucleus mask through introducing a cell affinity matrix and structure prior based on a graph theory; establishing a segmentation-oriented adversarial renderer, and aligning the generated image with a real image in a feature space by using a multi-layer feature discriminator; implementing a closed-loop co-evolution strategy, dynamically identifying vulnerability categories by using performance feedback of the segmentation model, and guiding a generator to carry out adaptive difficult sample mining; and obtaining a cell nucleus segmentation result through alternate mutual promotion of the generator and the segmentation model and regression fine tuning of real data. According to the method, the problems that in existing small sample learning, generated data lacks biological rationality and visual fidelity cannot be converted into segmentation performance are solved, and the segmentation precision and generalization ability of the model are remarkably improved under the condition of extremely few labeled data.

The invention discloses an unstructured data report filling method and system based on a large language model, and belongs to the technical field of artificial intelligence, and the method comprises the steps: preprocessing unstructured data, and generating preprocessed unstructured text data; based on the preprocessed unstructured text data, constructing and executing a semantic structured extraction chain; field mapping and report template binding are carried out based on the constructed semantic structured extraction chain, and a field mapping rule is established; based on a field mapping rule, automatically generating and filling a report, and automatically generating the report according to the extracted structured data; and interpretable proofreading and manual auditing are carried out on the automatically generated report. According to the method, implicit information can be accurately extracted, and semantic inference and association are supported; automatic report filling is achieved, and the manual arrangement workload is remarkably reduced; and the output is explainable, and each field can be positioned to the original text, so that the auditing credibility is improved.

The invention discloses a computer system based on a BIRA-5 algorithm and multiple BIOS modules and a starting method, the system comprises a CPU with the BIRA-5 algorithm deployed inside and three BIOS modules with the same firmware and different hardware, the computer system is powered on, the BIRA-5 algorithm is operated for initialization, and the first BIOS module executes hardware initialization and I / O setting; the three BIOS modules respectively generate corresponding check blocks by using own algorithm modules; the third BIOS module performs data verification on the three verification blocks, and if the data of the three verification blocks are consistent, the second BIOS module loads the operating system; otherwise, the abnormal BIOS module corresponding to the abnormal check block is repaired through the BIRA-5 algorithm. Three BIOS modules are introduced into the system, and a BIRA-5 algorithm is deployed in a processor, so that a brand new BIOS repair strategy is realized, and the data consistency and fault recovery efficiency of the system are improved.

The application relates to the technical field of electric power inspection, and discloses a method and system for power grid inspection and identification of an unmanned aerial vehicle, which comprises the following steps: acquiring channel path data, tower position data and inspection task configuration data; generating a channel inspection main flight path and a tower fine inspection sub-flight path; establishing a channel inspection mode parameter set and a tower fine inspection mode parameter set, and setting a mode switching trigger area; controlling the unmanned aerial vehicle to execute the channel inspection mode along the channel inspection main flight path; after completing tower inspection, executing key component collection integrity judgment, and executing supplementary shooting control when there are uncovered key components or unqualified images; then switching back to the channel inspection mode to continue flying; and identifying and analyzing the channel inspection data and the tower fine inspection data, and performing unified spatial marking and task association output. The application realizes integrated execution of channel inspection and tower fine inspection, reduces repeated flight, and improves inspection data integrity.

The application discloses a solid electrolyte damage prediction method based on a physical enhanced time sequence network, comprising: obtaining an electrolyte characteristic parameter to be measured; inputting the electrolyte characteristic parameter to be measured into a trained physical enhanced Transform-LSTM network model to obtain a future elastic energy density historical maximum value of each time; and calculating a damage sequence parameter according to the predicted future elastic energy density historical maximum value of each time to complete the prediction. The solid electrolyte damage prediction system based on the physical enhanced time sequence network comprises a data acquisition module, a data preprocessing module, a physical enhanced network inference module, a damage evaluation module and a result output and early warning module connected in series. The solid electrolyte damage prediction method and system based on the physical enhanced time sequence network can greatly reduce the data acquisition cost by introducing irreversible physical constraints and damage evolution residuals, and only about 30% of the working conditions required by the pure phase field simulation method is needed as training data to achieve the same prediction accuracy.

The invention discloses a lithium ion battery health state estimation method based on physical information Transform. The method comprises the following steps: acquiring voltage and current time sequence data of a lithium ion battery under a pulse charging condition; feature parameters are extracted from the time series data, and a training data set containing the feature parameters and corresponding health state labels is constructed; and constructing a physical information neural network model based on a Transform architecture, inputting the training data set into the physical information neural network model for training, processing pulse charging data of the lithium ion battery to be tested by using the trained physical information neural network model, and outputting a battery health state estimation result. According to the method, a framework which is high in principle and can be popularized is established, and an important contribution is made for constructing a battery health prediction model which is higher in interpretability, better in data efficiency and higher in physical credibility.

The application discloses a six-degree-of-freedom object pose estimation system, method and medium in an industrial scene, and the system comprises a multi-modal data preprocessing module, a shared encoder feature extraction module, a contrast learning and attention fusion module, a pose regression and rotation decoupling module and a simulation-driven data enhancement module, the multi-modal data preprocessing module is used for receiving and processing original RGB images and depth maps, and through filtering denoising and coordinate projection transformation based on camera parameters, an RGB-D data pair of pixel-level spatial alignment is output; the shared encoder feature extraction module is used for extracting features from the aligned RGB-D data pair, and adaptively fusing through a channel attention mechanism to output a shared feature fused with appearance and geometric information. The application can improve the estimation accuracy, the ADD index is improved by 12.8% and the rotation error is reduced by 21.4% under a 70% occlusion or reflection scene, and the application has strong robustness to depth noise, occlusion and reflection and strong practicability.

The present application relates to biological signal processing technology, and is a non-invasive continuous blood pressure estimation system based on a subject adaptive feature modulation mechanism, an individual prior embedding vector is generated by an individual prior embedding vector generation module; a subject adaptive feature extraction module performs real-time multi-level dynamic modulation on the preprocessed time series physiological signal according to the individual prior embedding vector, and outputs a high-dimensional time series feature map; a sequence processing module performs time series dependence modeling and context refining on the high-dimensional time series feature map, and outputs a time series feature; a cross-modal attention fusion module splices the individual prior embedding vector and the time series feature; the spliced feature vector is input into a multi-head attention fusion module to realize dynamic cross-modal feature weighted fusion and obtain a high-dimensional feature vector; and a blood pressure regression output module maps the high-dimensional feature vector through a full connection layer to regress to obtain an estimated value of systolic pressure and diastolic pressure. The present application solves the problem that the existing static mapping paradigm cannot cope with individual heterogeneity.

The invention discloses a block chain-based multi-node fusion supervision method, which comprises a node management module, a data recording module, a block chain data verification module and a supply chain supervision optimization module, and is characterized in that the node management module is used for managing supervision nodes in a supply chain; the data recording module is used for recording supervision data and supply chain historical processing data, the block chain data verification module is used for writing the supervision data into a block chain and then verifying and tracing the supervision data, and the supply chain supervision optimization module is used for analyzing and optimizing a supply chain. The node management module, the data recording module, the block chain data verification module and the supply chain supervision optimization module are in network connection with one another; according to the method, the operation of the supply chain is optimized, the risk and uncertainty in the supply chain are reduced, the overall efficiency and quality of the supply chain are improved, and the method has the characteristics of high supervision safety and capability of optimizing the supply chain.

The invention discloses a test data generation method and device, equipment, a storage medium and a product, and relates to the technical field of test.The method comprises the steps that a corresponding source data source is accessed in response to a data generation requirement and / or a strategy configuration instruction of a front-end user, and technical metadata, service metadata and sample data are collected from the source data source; according to the technical metadata, the business metadata and the sample data in the source data source, matching a pre-generated standard data creation rule, and screening out a target data creation rule; generating a corresponding data creation task based on the target data creation rule; and executing the data creation task to perform data creation, and writing data obtained by data creation into a corresponding target data source. According to the technical scheme, full-process automatic processing can be achieved, the data quality and the data creation efficiency are improved in multiple links, and the manual technical requirements and the investment time are greatly reduced.

Methods, systems and apparatus for determining a neural network architecture, including a computer program encoded on a computer storage medium. One method includes obtaining training data for a dense image prediction task; and determining an architecture of a neural network configured to perform the dense image prediction task, including: searching a space of candidate architectures using the training data to identify one or more best performing architectures, wherein each candidate architecture in the space of candidate architectures includes: (i) a same first neural network backbone configured to receive an input image and process the input image to generate a plurality of feature maps, and (ii) different dense prediction units configured to process the plurality of feature maps and generate outputs for the dense image prediction task; and determining the architecture of the neural network based on the best performing candidate architecture.

The invention relates to the technical field of data filling and reporting, in particular to a data filling and reporting method and a data filling and reporting system applying the same, and the data filling and reporting method comprises the following steps: S1, initializing the data filling and reporting system; s2, creating a report by calling a database table, a model and a data set according to the business condition, making a perspective table through source data in the report, pulling corresponding dimensions according to the business condition to perform screening, and generating a template and a corresponding search condition through combination of columns, rows and values; s3, performing batch filling and reporting of multi-dimensional data for corresponding role personnel according to the divided templates and the corresponding search conditions; s4, after the role personnel complete filling and reporting, the filled and reported data is transmitted back to the database table; and S5, splitting and analyzing the returned data by the data filling and reporting system. The method is high in self-definition degree and compatibility, high in real-time performance, convenient to improve filling efficiency and cooperation efficiency, high in safety coefficient and capable of reducing labor intensity of operators.

The application provides an airborne wind measurement laser radar dynamic adaptive attitude-position collaborative compensation system and method which can dynamically adapt to flight states and accurately couple attitude and position interference. The system comprises a GNSS positioning module (1), a MEMS-IMU attitude sensing module (2), a two-stage coordinate conversion module (3), a dynamic speed solving module (4), an adaptive collaborative compensation module (5) and a laser radar wind measurement module (6). The method comprises the following steps: S1, multi-source data synchronous acquisition, S2, ECEF coordinate system conversion, S3, ENU coordinate system conversion, S4, dynamic speed solving, S5, dynamic weight adaptive compensation, S6, data output and feedback storage. The application is applied to the technical field of wind measurement laser radar.

The application discloses a physical information multi-fidelity neural network three-dimensional cascade flow field reconstruction method based on Fourier characteristics, and relates to the field of aero-engine turbine machinery aerodynamic design. The method comprises the following steps: generating high / low fidelity data sets with boundary consistent and gradient perception sampling; constructing a multi-fidelity neural network containing Fourier characteristic embedding, multi-fidelity collaborative network and RANS equation residual constraint; adopting a two-stage training strategy, first optimizing data fitting loss to learn the flow field mapping relationship, and then jointly improving the conservation with physical loss; finally, realizing fast, high-precision and physically consistent reconstruction of three-dimensional cascade space coordinates to key physical quantities such as velocity, static pressure and temperature. The method significantly reduces the dependence on high-fidelity data, improves the prediction accuracy in high gradient areas, and is suitable for rapid iterative design of aero-engine cascades.

A reinforcement learning system, method, and computer program code for controlling an agent to perform multiple tasks while interacting with an environment. The system learns options, where an option comprises a sequence of primitive actions performed by the agent under the control of an option policy neural network. In implementations, while the agent interacts with the environment, the system discovers options useful for multiple different tasks by a meta-learning reward for training the option policy neural network.

This invention relates to the field of digital psychology and provides an AI-based method and system for crawling dynamic multi-modal psychological test questions. The method includes the following steps: obtaining the URL of the target psychological test page and selecting a set of device configuration parameters that includes at least desktop and mobile versions according to a preset device type library; loading and rendering the target psychological test page according to each configuration parameter in the device configuration parameter set, and crawling the complete document object model tree presented in each simulation environment; using AI to compare multiple document object model trees to obtain unique content nodes between versions, and selecting effective nodes to merge into a unified content tree structure; generating standardized test question data based on the unified content tree structure. This invention achieves efficient, accurate, and automated crawling of dynamic multi-modal psychological test questions by simulating multiple client access environments and introducing an AI-driven intelligent comparison, filtering, and fusion mechanism.

The invention discloses an improved imitation learning control method based on a Markov chain, and relates to the technical field of autonomous control, and the method comprises the following steps: 1, collecting and marking automatic driving videos in a plurality of scenes, and constructing an automatic driving data set; wherein the annotation of the automatic driving data comprises a given strategy, a state and an action; 2, calculating a state transition probability according to the automatic driving data; 3, constructing a reward function according to the state transition probability; 4, calculating value estimation according to the state transition probability and a given strategy; 5, collecting real-time automatic driving data, updating a given strategy in combination with value estimation, a state transition probability and a reward function, if the value estimation meets a termination condition, taking the current given strategy as an optimal strategy, and otherwise, returning to the step 2; and step 6, generating a decision action according to the optimal strategy. The learning efficiency and the autonomous control performance are improved by introducing a strategy iteration method of sudden obstacles and a reward function design.

This invention discloses a knowledge-guided method and system for predicting metal-ion-organic interactions, belonging to the fields of environmental separation and computational chemistry. The method constructs a training set through DFT calculations, extracts organic molecule descriptors, and quantifies their prior relationship with binding free energy. It employs a graph attention network to extract molecular features and fuses metal ion features using a cross-attention mechanism. A loss function incorporating prior knowledge is designed, and high-precision prediction is achieved through two-stage training. This invention solves the problem of traditional machine learning's dependence on large amounts of labeled data, maintaining excellent performance even in sparse data scenarios. It is suitable for high-throughput screening of separation agents such as extractants and adsorbents, significantly reducing R&D costs.