Patents
Literature
Patsnap Eureka AI that helps you search prior art, draft patents, and assess FTO risks, powered by patent and scientific literature data.

13results about How to "Prevent error propagation" patented technology

Server memory fault detection method and device, equipment and medium

The invention relates to the technical field of computers, and discloses a server memory fault detection method and device, equipment and a medium, which are used for periodically inspecting a target memory unit with a hard fault and carrying out offline processing on a memory page where the target memory unit is located. And when a hard fault exists in the memory unit adjacent to the target memory unit, performing offline processing on the memory page where the hard fault unit is located. When the number of the hard fault units occurring in the row and column areas where the target memory unit and the hard fault units are located is larger than or equal to a set threshold value, off-line processing is conducted on the memory pages corresponding to the row and column areas. By detecting the memory units around the target memory unit, the memory unit with the hard fault can be recognized earlier, and the delay from fault occurrence to detection is remarkably reduced. Off-line processing is carried out on the memory pages corresponding to the row and column areas with high risks, error diffusion can be prevented, the risk of data damage is reduced, and the stability and reliability of the whole system are improved.
Owner:INSPUR SUZHOU INTELLIGENT TECH CO LTD

Redundancy-based hardware failure time division multiplexing detection circuit and detection method

The invention discloses a redundancy-based hardware failure time division multiplexing detection circuit and method, and the method comprises the steps: enabling the counting of an input selection counter to be connected with a first input completion mark outputted by an upstream circuit, and enabling the counting of an output selection counter to be connected with a second input completion mark outputted by a downstream circuit; the output end of the input selection counter is connected with the enabling end of the input selector muxin, and the output end of the output selection counter is connected with the enabling end of the output selector muxout; the input end of the input selector muxin is connected with the output of the upstream circuit, the output end of the input selector muxin is connected with the input end of the redundant circuit, the input end of the output selector muxout is connected with the output of the hardware circuit, and the output end of the output selector muxout is connected with one input end of the comparator; the input end of the redundant circuit is connected with the output end of the input selector muxin, the output end of the redundant circuit is connected with the other input end of the comparator, and the output end of the comparator is connected with the control register.
Owner:北极雄芯智驾科技(无锡)有限公司

Telemetry data elastic transmission method, device, electronic equipment and storage medium

The present application relates to the field of communication technology, and in particular to a method, device, electronic device and computer-readable storage medium for elastic transmission of telemetry data, wherein the method comprises: obtaining telemetry data to be transmitted; compressing repeated bytes of at least one data frame in the telemetry data, and generating a new data frame according to the remaining uncompressed bytes and corresponding positions in at least one data frame; generating compressed telemetry data according to the new data frame and the uncompressed data frame, and sending the compressed telemetry data to a receiving end, so that the receiving end decompresses the compressed telemetry data to obtain the telemetry data. Thus, the problems in the related art such as the slow change of telemetry parameters and the high redundancy of satellite telemetry data caused by the newly added information amount each time are solved.
Owner:TSINGHUA UNIVERSITY

Human-computer collaborative multi-modal data intelligent labeling and quality checking method

The application discloses a kind of man-machine collaborative multi-modal data intelligent labeling and quality checking method, it is related to man-machine collaborative technical field.The method first obtains at least containing two modalities of original data of image, text, audio, generates multi-modal joint data sample after pre-processing and modal alignment;Input pre-trained multi-modal AI pre-labeling model generates pre-labeling result with confidence;Through cross-modal consistency check calculation consistency score, sample is divided into high, medium, low confidence three categories;High confidence sample is directly adopted and enters the sampling pool, and medium and low confidence sample is based on labeling personnel ability portrait and AI model dynamic capability evaluation and carries out intelligent task distribution.The application effectively solves the problem that efficiency and quality are difficult to balance in multi-modal data labeling, significantly improves labeling accuracy and automation rate, reduces labeling cost, and can meet the construction demand of large-scale high-quality multi-modal data set.
Owner:LIAONING HONGTU CHUANGZHAN SURVEYING & MAPPING CO

NOMA-oriented bit-level communication probability shaping method and system

The invention relates to the technical field of optical fiber communication, and discloses an NOMA-oriented bit-level communication probability shaping method and system, and the shaping method comprises the following steps: modulating the transmission data of two different users into QPSK-OFDM (Quadrature Particle Swarm Keying-Orthogonal Frequency Division Multiplexing) signals; for one of the QPSK-OFDM signals, symbol probability transformation is realized through improved BWDM (Binary Wavelength Division Multiplexing); performing power distribution and superposition on the two QPSK-OFDM signals to form a NOMA-OFDM signal; after receiving a signal, carrying out channel estimation and equalization on the signal; carrying out region judgment on the balanced signals, and respectively recovering the signals through a region judgment method of high-power and low-power signals; and the recovered low-power QPSK-OFDM signal is obtained through the solution of the BWDM. In combination with the improved bit-level probabilistic shaping method, the problems of tedious calculation and error propagation of the SIC technology are avoided, more accurate signal recovery can be obtained, the signal judgment process is further simplified, and the coding complexity of the system is reduced.
Owner:CHINA JILIANG UNIV

A method for extracting parameters from deep neural networks with constrained architectural knowledge conditions

PendingCN122734945ASignificant technological progressprevent error propagation
This invention discloses a method for extracting parameters from deep neural networks under constrained architectural knowledge conditions. Its key feature is that before extracting parameters from the current hidden layer, it analyzes the algebraic consistency between the perturbation basis matrix and the output difference vector in the input space to accurately identify whether there are any missing neurons in the previous layer. When a missing neuron is detected, a re-extraction mechanism is triggered, increasing the sampling density of key points and re-performing parameter recovery of the missing layer. Compared with existing technologies, this invention achieves efficient and accurate extraction of DNN parameters under constrained architectural knowledge conditions through an adaptive extraction workflow and neuron omission detection. Its error detection recall rate reaches 100%, and its error detection specificity remains stable between 1.91% and 2.03%. This provides a robust and efficient technical solution for model vulnerability assessment, black-box model parameter extraction attack prevention, and neural network intellectual property protection in the field of artificial intelligence security, and has broad application prospects and commercial value.
Owner:EAST CHINA NORMAL UNIV

Database real-time backup and recovery method and related equipment

The invention belongs to the technical field of databases, and discloses a database real-time backup and recovery method and related equipment, a main database and a backup database are respectively created and stored in different partitions of a nonvolatile memory, and access is performed in a memory mapping mode, so that rapid read-write and synchronization of data are realized. When the main database is modified, the backup process of the backup database is synchronously triggered to ensure that the backup database can accurately reflect the latest state of the main database in real time; the problems of data inconsistency and data loss caused by abnormal reasons are avoided by adopting a real-time backup and self-check recovery mechanism, and the method is suitable for application scenes with high requirements on data sensitivity and real-time performance; by setting the size of the database file and naming the database file name with the first record value of the index, the access speed of the single database is improved, the damage probability of the database is reduced, and stable operation of the system and integrity and safety of data are ensured by combining a real-time backup and recovery method.
Owner:XIDIAN POWER RECTIFIER XIAN +1

Design and construction method of human-in-the-loop multi-agent microservice system AgentInn

PendingCN122653773Aprevent error propagationimprove securityLoop controlControl engineering
The application discloses a kind of human in loop multi-agent microservice system AgentInn design and construction method, including human in loop control module, multi-agent cooperation module, dynamic capability expansion module and task arrangement module.Human in loop control module realizes the control, participation and observation of human to agent by starting confirmation, running intervention, abnormal recovery, human agent registration, cooperation routing and experience feedback;Multi-agent cooperation module realizes cooperation arrangement and load balancing by cooperation space, role load balancing and agent discovery;Dynamic capability expansion module supports on-demand creation and hierarchical exposure of tool service and intelligent service;Task arrangement module manages progress using Cycle-Sprint-Phase three-layer time abstraction, and realizes task flow by combining flow decision and context transmission.The application solves the problems of lack of human participation in multi-agent cooperation, high complexity of cooperation arrangement and limited capability expansion, and realizes multi-agent microservice cooperation.
Owner:BEIJING INST OF TECH

A deep learning-based method for biomedical entity recognition and relationship prediction

The present invention discloses a method for biomedical entity recognition and relationship prediction based on deep learning, and the steps include: 1. Obtaining neural network training data, i.e. biomedical literature, performing sentence segmentation and word segmentation operations on it, and processing unstructured text into structured text; 2. Annotating structured text, manually annotating entities in sentences and relationships between entities; 3. Building a deep neural network model; 4. Training the constructed model with annotated data to obtain a deep learning model with optimal experimental results; 5. Inputting unannotated data into the optimal model to predict entity relationships in the literature. The present invention can simultaneously identify entities in biomedical literature and the relationships between entities, thereby effectively improving the accuracy of recognition and reducing the demand for computing resources.
Owner:ANHUI UNIV

Methods for handling encrypted write anomalies in enterprise storage systems

This invention discloses a method for managing encrypted write anomalies in enterprise-level storage systems. During the data write process, based on the security requirements of the data and the operational status of the storage unit, a corresponding encryption strategy is dynamically selected. During the encrypted write process, reversible encryption markers or failure markers are established for data blocks. When a data block is written but has not reached stable write conditions, its encryption and write phase states are recorded using reversible encryption markers. In subsequent management operations, the process is rolled back to the previous stable point, reconfirming the correspondence between the encryption strategy and the key version without changing the original encrypted content. When a data block write fails, re-encryption and cross-storage unit compensation write processing are triggered using failure markers. By performing distinct management operations based on different markers, this invention can effectively reduce the impact of write anomalies on system stability and performance while ensuring data security.
Owner:JINDA SEMICONDUCTOR CO LTD

A continuous action control method and system based on fork picking and placing

The present application relates to the technical field of action control, in particular to a continuous action control method and system based on fork loading and unloading, the present application realizes adaptive identification of cargo unloading event by collecting torque feedback of lifting driving mechanism and performing differential analysis, and latches actual unloading fork position; based on the position, middle position and target loading position, a complete motion path is constructed, and two-stage stroke compatibility determination of fork retraction and extension is performed to determine whether continuous action is enabled; during continuous action, fork extension and walking shaft motion are scheduled in parallel, and subsequent fork extension action is triggered through state flag synchronization mechanism; at the same time, motion parameter is used to predict loading completion time and send pre-notification message; in abnormal conditions, a cancellation message is sent and a safety rollback is performed. The present application can effectively improve the continuity, efficiency and safety of fork operation in automatic warehouse system.
Owner:STARK INTELLIGENT AUTOMATION EQUIP (SUZHOU) CO LTD

Multi-agent task cooperative processing system and processing method for voice interaction

The application discloses a multi-agent task cooperative processing system and method for voice interaction. The system comprises: a voice input module for receiving and preprocessing original audio signals from a user; a voice processing module for generating a structured task representation based on the audio signals using a deep neural network model; a task coordination module for assigning tasks to agents in a task processing module based on the structured task representation; the task processing module contains multiple agents, all connected to the task coordination module, each configured to process tasks in a specific field; a response generation module for integrating the processing results from the agents into a coherent response and converting it into a voice signal for output. The application integrates voice understanding, task scheduling and cooperative execution to provide a robust, efficient and intelligent voice-driven solution that can complete complex voice interaction tasks.
Owner:NANJING TIANSU AUTOMATION CONTROL SYST CO LTD

An online and offline dual-track classification-based delivery fee management method and device, and electronic equipment

This application provides a method, device, and electronic device for managing advertising campaign costs based on a dual-track online and offline classification system. By integrating a dynamic knowledge graph with a prompting learning model that efficiently fine-tunes parameters, it achieves high-precision automatic classification of advertising campaign cost categories. The method acquires the user-inputted cost description text and specified category, utilizes the dynamic knowledge graph for key entity extraction and multi-hop reasoning, and generates a first classification result and confidence score. Simultaneously, the text is input into the prompting learning model, which guides fill-in-the-blank prediction through soft prompts, outputting a second classification result and confidence score. Combining the confidence scores of both, a decision fusion rule is used to determine whether to trigger user correction prompts, and the knowledge graph and model parameters are dynamically updated based on user feedback. The system supports new entity recognition and incremental learning, forming a closed-loop optimization mechanism. This solution effectively solves the problems of inaccurate budget allocation, low execution efficiency, and difficulty in cost control caused by the fragmentation of data from online and offline channels, improving the accuracy, interpretability, and adaptability of cost classification, and achieving intelligent and refined advertising campaign cost management.
Owner:ZHEJIANG BOGUAN RUISI TECH CO LTD