39 results about "Error reduction" patented technology

The invention discloses a power grid frequency balance intelligent control system based on a distributed architecture, relates to the technical field of power grid control, and is used for solving the problems that the existing WLS / UKF and other methods are generally assumed to be good in synchronization, are insensitive to heteroscedasticity time delay and missing measurement, and are difficult to ensure robustness under real communication and equipment conditions. Through a through link, under the real clock misalignment, time delay jitter and packet loss conditions, measurement of a unified time axis and quality quantification are realized, and frequency estimation bias and uncertain transmission are significantly reduced. Reconstruction, filtering and triggering are penetrated with the same confidence degree, and abnormal measurement suppression and effective information utilization are improved; the fusion efficiency and timeliness of asynchronous arrival data are improved by utilizing graph prior and information domain incremental updating; and regional measurement abnormity and real power imbalance are discriminated through double-model causality, and error event reporting is reduced.

The present invention provides a computer system and a computer-implemented method for adaptive quality management in artificial intelligence (AI) processing. The system comprises a memory unit storing machine-readable instructions and a processor configured to execute the instructions to store, in a persistent correction memory, records of prior corrections to AI outputs; retrieve a correction for a current input based on similarity between the input and stored records; generate, by an audit-trail module, a tamper-evident record of the correction and its application; schedule, by a predictive resource manager, AI workloads in dependence on service-level constraints, carbon-intensity data, and quality metrics; and update, by a feedback controller, retrieval and scheduling parameters based on effectiveness information. The processor thereby enables the persistent correction memory, audit-trail module, predictive resource manager, and feedback controller to operate as a closed-loop adaptive system that reduces recurrence of AI errors, ensures verifiable auditability, and optimizes computational efficiency.

The invention discloses a target data selection method based on an approximate Shapley value, electronic equipment and a medium. The target data selection method comprises the steps of obtaining a ratio of a source data set to a target utility, and calculating a total utility value and a target utility value. And screening to obtain an extended sample and a feature set. And sample optimization: carrying out Monte Carlo sampling on the expanded sample set to generate random arrangement, forming a plurality of third subsets and calculating utility values of the third subsets. And after a sample Shapley value is calculated, selecting a subset with the minimum error to carry out iterative sample replacement. And if the error reduction degree is smaller than a second threshold value, re-sampling, otherwise, taking a subset of which the error is smaller than a third threshold value as an initial candidate. And if the final error still exceeds the tolerance threshold, turning to feature optimization. And feature optimization: the process is similar to sample optimization, and feature iteration and replacement are guided through a Shapley value. And alternately optimizing the sample subsets and the feature subsets until the utility value error of the combined candidate set (the candidate sample subsets + the candidate feature subsets) is smaller than an error tolerance threshold.

The application provides a work order processing method and device, the method comprising: obtaining work order data; extracting fault information from the work order data to obtain the fault information; matching the fault information with work order instances in a previously established fault feature database to obtain matched work order instances; wherein the fault feature database is established based on work order instances and corresponding processing strategies; and calling the corresponding processing strategies and executing according to the matched work order instances. The application extracts fault information from the obtained work order data to clearly define the core content of the fault, remove irrelevant information interference, improve the accuracy and efficiency of subsequent processing, matches the extracted fault information with work order instances in the fault feature database to quickly locate the verified processing strategy corresponding to the matched work order instances, improves the accuracy of work order processing, reduces the possibility of incorrect processing, reduces the time and cost of starting from scratch to analyze and solve problems, and improves the speed and success rate of fault processing.

The invention relates to the technical field of community management, in particular to a community management method and system based on artificial intelligence. The method comprises the following steps: obtaining an owner question content; analyzing the question content of the owner, and determining a question item; based on the question item, utilizing artificial intelligence to obtain item data; summarizing project bills according to the project data; and checking the project bill to obtain and display a final project bill. The problems of delay and fragmentation of manual association of data sources are eliminated, the integrity and consistency of project data are ensured, data missing or conflicts are reduced, and traceability is enhanced. The problems of error proneness and static account division depending on manual summarization are avoided, the accuracy and dynamic adaptability of bills are improved, and the error rate is reduced. The project bill is checked, and the final project bill is obtained and displayed, so that the problems of omission and low efficiency of manual checking are avoided, the accuracy and the displayability of the final project bill are ensured, real-time and safe publicity is realized, the transparency is improved, and the owner trust is enhanced.

Methods and systems are provided for performance optimization of object grouping patterns in storage devices. The methods include receiving object IOs for a target device; grouping the object IOs using a first plurality of input parameters; associating tracking parameters with the first plurality of input parameters and performance parameters corresponding to the first plurality of input parameters; storing first data entries comprising the tracking parameters, the first plurality of input parameters, and the performance parameters in a database; extracting a plurality of data entries from the database, the plurality of data entries including the first data entries; training a training model using one or more of the plurality of data entries; cross-validating the training model to determine a degree of error reduction of the training model; performing a model check to compare the training model to an inference model; and updating the inference model based on the model check.

The embodiment of the invention provides a small sample anti-fraud classification method and device, a medium and a product, and relates to the technical field of artificial intelligence. The method comprises the steps of constructing intra-class semantic features and inter-class difference features based on a preset task framework of small sample learning; determining an anti-fraud classification network model according to the intra-class semantic features and the inter-class difference features; and according to the network model, performing anti-fraud classification identification on a to-be-classified text. According to the scheme, the preset task framework based on small sample learning does not need large-scale labeling, when a category is newly added, only a small number of samples need to be supplemented according to the framework to be fused into an existing model, an overall data system does not need to be reconstructed, the expansibility is greatly improved, through intra-class and inter-class feature learning, the distinction degree of similar fraud classes is enhanced, wrong classification is reduced, and the classification efficiency is improved. The classification accuracy is improved, general fraud features can be migrated to a new scene, and the generalization ability of the new fraud scene is improved.

The invention provides a tool bar strain measurement device and a machining error reduction method thereof, and relates to the technical field of numerical control lathe machining. The tool bar strain measuring device comprises a tool bar, a sensor mounting groove is formed in the tool bar, a strain sensor is fixed in the sensor mounting groove, a signal transmission channel is arranged at the tail of the tool bar and used for being connected with the strain sensor and a data acquisition device, and the data acquisition device is used for collecting and processing strain signals in real time. Tool bar strain data of the strain sensor are acquired in real time through the data acquisition device, whether machining errors exist or not is quickly judged, and cutting parameters are dynamically adjusted. Machining errors caused by cutting force can be remarkably reduced, universality is high, installation is easy and convenient, the method is suitable for various working conditions, and the machining precision of the numerical control lathe can be effectively improved.

The invention discloses a field expert-based machine question and answer large model illusion question mitigation method, which comprises the following steps: S1, expert field identification: generating a declaration basis for initial reasoning and judgment through a large language model, and identifying experts involved in declaration through a field expert large language model; s2, obtaining a final evidence, identifying a key entity in the statement through a domain expert big language model, taking the key entity as an external evidence for query and retrieval, and selecting an external evidence useful for analysis of the statement as the final evidence; and S3, verifying correctness, comparing the declaration with the final evidence through a domain expert big language model, analyzing the correctness of the declaration, and giving a declaration modification suggestion, so that generation of wrong reasoning is reduced, and the reasoning accuracy is improved.

The invention discloses a large model context error management method and system based on regression testing, belongs to the technical field of artificial intelligence, and aims to solve the technical problems of repeated errors, lack of error learning ability and imperfect error prevention mechanism existing in a large model at present. Comprising the following steps: constructing an error history library based on a triple data structure corresponding to historical error data; performing similarity analysis on the current user input and historical user input in an error historical library; generating a test case based on a historical user input similar to the current user input; optimizing the current user input to obtain optimized user input; and establishing an error reduction rate evaluation index, comparing error occurrence rates before and after user input optimization through an A / B test framework, and adaptively optimizing a similarity judgment standard, a weight parameter and an error avoidance instruction template based on a feedback result.

The invention discloses a pulmonary nodule sub-voxel volume VDT method based on deep learning, and aims to solve the problem of adjustable mapping of depth model probability output to physical volume and the problem of deviation introduced by anisotropic voxels and reconstruction kernels. According to the method, direction-conditioned spatial variable point spread function distribution self-supervised estimation, edge spread function and modulation transfer function consistency constraint, global mapping and local residual error calibration of two-segment conditional flow under monotonous bounded constraint, and occupancy rate quantile output are carried out; and in combination with subvoxel integration and quality control closed-loop trigger conservative expansion and artificial recheck, the technical effects of cross-device and acquisition protocol robust volume and VDT point estimation and interval, uncertainty quantization and error reduction are realized.

This application relates to a method, electronic device, and storage medium for locating errors in a logic system design. The method includes: testing the logic system design using multiple test cases; dividing the multiple test cases into a pass case group and a fail case group based on the test results, the test results including coverage data of the multiple test cases; determining multiple key features based at least on the coverage data of the test cases in the fail case group; and locating the error in the logic system design based on the multiple key features. This method can reduce error location time and accurately pinpoint the source of errors in the logic system design.

The application relates to a knowledge graph multi-hop question answering method and system based on a contrast learning relationship representation, which comprises the following steps: for a KG subgraph corresponding to a question, a corresponding relationship representation is trained based on a contrast learning and a negative sampling mechanism, that is, an encoder is obtained; the relationship is encoded through the encoder, integrated processing is conducted by using a KG context processor, a correlation score for multi-hop reasoning is determined, and a weighted subgraph is obtained; a text classification model is used to predict the number of hops of the question, and an adaptive beam search method is used to search for an optimal weighted chain on the weighted subgraph, and then the answer corresponding to the question is returned. Compared with the prior art, the application can conduct fine multi-hop reasoning on a knowledge graph containing various relationships, effectively find an optimal reasoning chain, reduce error propagation and provide interpretability.

The application belongs to the technical field of neural network model training, and discloses a neural network model training method and system based on an improved random configuration algorithm, which comprises the following steps: under the condition of reducing the root mean square error of the neural network model output, screening suitable neurons as candidate hidden layer nodes through the inequality constraint condition of the random configuration algorithm; screening K neurons with the fastest training error reduction from the candidate hidden layer nodes, and selecting the neuron least related to the previous L-1 hidden layer nodes from the selected K neurons as the optimal hidden layer node; calculating the output weight through the least square method, and updating the structure of the random configuration network; and judging whether the network structure is completed by using the maximum allowable number of hidden layer nodes and the maximum allowable output error. The application can reduce the overall calculation amount of the algorithm while ensuring the prediction accuracy, and is suitable for application scenarios with high real-time requirements.

The invention relates to a point cloud thermal prediction method for a large-scale unstructured 2.5 D integrated circuit. The network comprises three core modules: an adaptive multi-path coupling diffusion module (AMD), a wavelet-based fine-grained recovery module (WFR) and a thermal sensing material expert hybrid adapter (TA-MoME). The AMD module adaptively learns interaction of a thermal diffusion path through an attention mechanism based on serialized gating; the WFR module recovers fine-grained thermal gradient features by using a high-frequency wavelet domain enhancement technology; and the TA-MoME adapter dynamically routes the material specific expert to adapt to the heat distribution difference between the heterogeneous materials. Particularly, the framework also introduces a continuous learning mechanism with efficient parameters to ensure that when the model adapts to a new geometric scale, catastrophic forgetting can be prevented, and cross-scale adaptation and mobility can be realized. Experimental results show that in 80K-scale point cloud prediction, compared with an existing FSA-Heat method, the average precision index is remarkably improved (errors are reduced by about 78% or above), compared with commercial COMSOL, acceleration of 147 times is achieved, and the generalization ability for larger-scale nodes (0.4 M) and zero samples without geometrical shapes is shown.

It is already known that quantum computers can be used to simulate materials and molecules. However, quantum computers are error-prone and exhibit intrinsic noise, which has so far made the real technical application of quantum computers impossible. Approaches are already known from the prior art which, despite the error susceptibility, allow meaningful simulations of quantum mechanical systems to be created, but the errors still exist. Building on this, the invention now makes it possible to reduce the errors and to include the errors as part of the simulation. In addition, the invention makes it possible to inhibit the effect of intrinsic noise. This further improves the technical applicability of quantum computers for simulating materials and molecules.

A branch predictor predicts a first outcome for a first branch in a first block of instructions. Fetch logic fetches instructions for speculative execution along a first path indicated by the first outcome. In response to taking the first predicted outcome, information representing a remainder of the first block is stored. In response to not taking the first branch instruction, the branch predictor is restarted based on the remainder block. In some cases, an address of the first block is used as an index into a branch prediction structure to access an entry corresponding to a second block along a speculative path from the first block. A corresponding set of instances of branch condition logic are used to simultaneously predict outcomes for branch instructions in the second block, and in response to a misprediction, the predicted outcomes are used in combination with the remainder block to restart the branch predictor.

This invention discloses a method, apparatus, device, and computer-readable medium for automated testing, relating to the field of big data intelligent analysis technology. One specific embodiment of the method includes: modifying an error code enumeration class file according to updated error codes, and pushing the modified error code enumeration class file, wherein the error code enumeration class file is obtained from a data warehouse; compiling and packaging the modified error code enumeration class file, and sending the compiled error code enumeration class file package to a code server; the code server pushing the compiled error code enumeration class file package to perform automated testing using the updated error codes. This embodiment can reduce error code referencing errors and achieve automated testing.

Systems, methods, and other embodiments described herein relate to an automated vehicle (AV) navigating on roads with a control model trained using residual policies for reducing error. In one embodiment, a method includes generating a generic policy for a control model used to navigate a road having multiple agents with traffic data acquired, the generic policy applying to general traffic scenarios associated with the road. The method also includes training a task policy with reinforcement learning a plurality of residual functions for error reduction of the generic policy, the residual functions factoring parameters about the multiple agents and specific traffic scenarios. The method also includes communicating the generic policy, the task policy for error reduction, and a domain distribution learned by comparing simulated data with the traffic data to a vehicle.

The invention discloses a self-adaptive production scheduling method and system based on multi-modal perception, and relates to the technical field of production scheduling, and the method comprises the steps: building a modal historical behavior track through collecting the state information of each type of sensor data participating in a plurality of historical scheduling cycles; calculating the semantic inertia intensity value of each mode according to the historical behavior track of the mode, and measuring the degree of dependence of the scheduling model on each mode when the scheduling instruction is generated; redistributing each modal data weight in the current scheduling model according to the semantic inertia intensity value; and outputting a production scheduling instruction according to the scheduling model after weight redistribution of the modal data. According to the method, whether the scheduling model generates'solidification trust for one or some modal data or not can be judged, the scheduling model is corrected in time, it is ensured that the production scheduling instruction output by the scheduling model is accurate and reliable, the problems of wrong shutdown, excessive scheduling correction or disordered production rhythm and the like are reduced, and the stability and reliability of adaptive scheduling are ensured.

The invention relates to the technical field of data processing, in particular to a health monitoring method and system for an intelligent wearable device, and the method comprises the steps: carrying out the anomaly detection according to sample data adopted for modeling, obtaining the anomaly possibility of the data, according to the method and the device provided by the invention, the residual error trend of each piece of data is detected according to the variation trend of the residual error of the data along with the iteration process of the GBDT algorithm, so that the residual error reduction index of each piece of data is obtained, and the residual error of the data which is possibly abnormal is reduced, thereby reducing the influence of the abnormal data on the GBDT algorithm, and realizing more accurate GBDT modeling.

A pre-processor (PP) component and related method for a machine learning system (MLS) for processing medical data. The preprocessor comprises an input interface (IN) for receiving a human generated initial finding for a patient and a medical image to which the said finding pertains. An encoder (ENC) DPS of preprocessor encodes the finding and the medical image into encoded data, including encoded image data and encoded finding data. A combiner (COM) component of preprocessor combines the encoded finding and the encoded image data into combined encoded data. An output interface (OUT) provides the combined encoded data to the machine learning system. More robust machine learning performance may be achieved with the proposed pre-processor (PP).

The invention discloses a dynamic error prediction and real-time compensation method suitable for an angular displacement sensor. The method comprises the following steps: firstly, establishing a dynamic error mathematical model of the angular displacement sensor, and extracting main harmonic components by using Fourier expansion to obtain a relational expression between errors and space signal parameters; then performing real-time prediction on the dynamic error based on an unscented Kalman filter (UKF) algorithm to obtain an error value at the next moment; and finally, the prediction error is used as the compensation amount to calibrate the real-time measurement value of the sensor, so that the real-time compensation of the dynamic error is realized. According to the method, the dynamic error can be remarkably reduced in various motion states such as constant rotating speed, uniform acceleration and variable acceleration, experimental results show that the error reduction amplitude is remarkable, and the higher the rotating speed is, the better the compensation effect is. Compared with a traditional harmonic compensation method, the harmonic compensation method has better real-time performance and robustness, and is suitable for high-precision numerical control machine tools, servo motor control, precision measurement equipment and the like.

The invention relates to a method, a device and equipment for automatically adding a test point silk screen to a PCB (Printed Circuit Board), and a medium. The method comprises the following steps: acquiring a bit number and a network name of at least one test point in the PCB to be processed; pre-adding the network names of all the test points into the to-be-processed PCB to obtain a first result indicating whether each test point is successfully pre-added; if the first results corresponding to all the test points are successful, adding the network names of all the test points to the to-be-processed PCB according to the positions corresponding to pre-addition; and if the first results corresponding to all the test points fail, reducing the network names corresponding to the first results which are failure to obtain abbreviated names, and adding all the network names and the abbreviated names to the PCB to be processed. According to the method provided by the invention, the automatic screening of the test point silk-screen and the adding of the silk-screen are realized through an automatic program, the time of designers is saved, and errors are reduced.

The invention discloses a Smart 3D (Three Dimensional)-based drawing audit management method, which comprises the following steps of: S1, adding a module of which the name is' Review Management 'in a Smart 3D platform as a configurable Task for a user to switch in a menu; s2, the designer and the check and verification personnel enter corresponding interfaces through permission recognition; s3, the checking and auditing personnel enter an auditing mode, obtain complete authority, check all auditing suggestions and modify the drawing or the three-dimensional model; s4, enabling the designer to enter a modification mode, obtaining a complete authority, modifying the drawing or the three-dimensional model according to a modification opinion fed back by the school auditor, and filling the feedback opinion to the school auditor; and S5, the designer feeds back the modified drawing or three-dimensional model to the checking and auditing personnel, and reauditing is carried out until the drawing or the three-dimensional model is modified correctly. According to the method, process informatization, task closed-loop tracking and authority isolation management are realized, the design efficiency is improved, the operation process is standardized, and errors and omissions are reduced.

Techniques are presented for reducing readout error of quantum expectation. A calibration component applies a first random Pauli gate to a qubit at a first output of a first circuit prior to a first readout measurement of the qubit. An estimation component applies a second random Pauli gate to the qubit at a second output of a second circuit prior to a second readout measurement of the qubit, and generates an error-reduced readout determination based on the first random Pauli gate applied to the qubit at the first circuit output and the second random Pauli gate applied to the qubit at the second circuit output. The calibration component determines calibration data based on the first readout measurement. The estimation component determines estimation data based on the second readout measurement. The estimation component determines a normalization scalar value based on the calibration data, determines an estimation scalar value based on the estimation data, and determines an error-reduced readout determination associated with a circuit of interest based on the normalization scalar value and the estimation scalar value.

The invention relates to the technical field of text processing, in particular to a method and a system for correcting an OCR (Optical Character Recognition) result. According to the correction method for the OCR recognition result, a large language model serves as an inference engine, a plurality of search agents and a circulation verification mechanism are dynamically configured for the large language model, and by introducing dynamic and accurate domain knowledge and contexts, the knowledge shortages of the large model are fundamentally made up, so that correction decisions of the large model are based on data, and the correction accuracy of the OCR recognition result is improved. And error correction can be greatly reduced. And a cyclic verification mechanism ensures that each correction is subjected to cross verification, so that the output result is more reliable. Moreover, the correction method does not depend on fixed rules or model parameters, can be quickly adapted to a new professional field only by replacing or expanding a data source connected with the search agent, and is high in universality and flexible in deployment.