96 results about "Information domain" patented technology

The invention provides a method and a system for detecting and defending cross-domain threats of a power system. The method comprises the following steps: after carrying out anomaly identification on operation monitoring data of a physical domain node in a target power grid region to obtain an anomaly identification result and carrying out denial of service attack identification according to network flow data of an information domain node to obtain an attack identification result, carrying out abnormal event association analysis on the anomaly identification result and the attack identification result to obtain an attack cross-domain anomaly identification result; according to key nodes and key risk propagation paths in a cross-domain attack chain generated based on a graph theory algorithm, generating an attack tracing atlas, and according to vulnerability information of the key nodes in the atlas, obtaining a corresponding power system topological graph and a corresponding communication network topological graph; and iteratively generating an active defense rule based on a game theory algorithm and a reinforcement learning algorithm, and issuing the active defense rule to the node. According to the method, the cross-domain attack risk is accurately perceived in real time and adaptive security defense is executed through cross-domain abnormal event association analysis, so that the comprehensiveness and reliability of security protection of the power system are improved.

The invention discloses a fault analysis method and device, electronic equipment and a storage medium, and the method comprises the steps: obtaining first burying point information corresponding to an abnormal event if the vehicle detects that the abnormal event of a burying point is triggered, the first burying point information comprises at least one of a subsystem type corresponding to the abnormal event, an application module corresponding to the abnormal event, an abnormal type corresponding to the abnormal event, an information domain corresponding to the abnormal event, a fault identifier corresponding to the abnormal event, an abnormal name corresponding to the abnormal event and an abnormal position corresponding to the abnormal event; and sending the first burying point information to a server, so that the server determines the fault information corresponding to the abnormal event according to the first burying point information, thereby improving the vehicle fault problem determination rate.

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 invention discloses an anti-phishing webpage detection system and method. The anti-phishing webpage detection system comprises a webpage data capture module, a risk analysis module, a malicious webpage judgment module and a response decision module, relates to the technical field of anti-phishing webpage detection. According to the method, multi-dimensional data, including URL information, domain name information and webpage content information, of a webpage are extracted through the webpage data capturing module, a comprehensive original data basis is provided, and accurate support is provided for follow-up risk analysis; according to the method, comprehensive risk analysis is carried out by utilizing various webpage features including URL features, domain name features and content features, and potential phishing webpages can be effectively identified by calculating risk scores of the URL, the domain name and the webpage content; according to the method, the web pages are classified according to the comprehensive risk scores, the high-risk web pages are intercepted, the emergency response logs are generated, the low-risk web pages are continuously monitored, and safe browsing of a user is ensured.

The invention relates to a multi-energy information physical system scheduling method, system and device with bidirectional aging perception, and belongs to the technical field of telecommunication. The method comprises the following steps: firstly, constructing a physical domain multi-energy system model and an information domain multi-energy bidirectional timeliness model based on an information physical fusion multi-energy system; secondly, constructing an information physical fusion multi-energy system scheduling model considering the multi-energy bidirectional timeliness to minimize the global scheduling cost of the system; bidirectional timeliness constraint is converted through a virtual queue, and decoupling of short-term decision and long-term constraint is achieved. On the basis, model learning at an offline stage and extrinsic matching optimization at an online stage are combined, an information interaction sequence and a consistency variable weight are dynamically adjusted, information domain interaction and physical domain regulation and control are coordinated, and through distributed iterative optimization, the calculation complexity is effectively reduced, and the calculation efficiency is improved. The convergence speed of the consistency variable and the system regulation and control efficiency and stability are improved, and the system scheduling cost is reduced.

The invention relates to a pre-sleep hypoglycemia risk probability assessment method based on local-global features, and belongs to the technical field of medical risk assessment. According to the method, a feature set is constructed through the multi-source information domain time sequence data and the target domain time sequence data of the patient to reflect the blood glucose level of the patient; searching a common subspace with the minimum distribution difference through the heterogeneous domain adaptive model to obtain a target function, and calculating the target function to obtain a shared representation space; mapping the feature set into a shared representation space, and obtaining a representation sample set of projection from the shared representation space; and evaluating the pre-sleep hypoglycemia risk probability of the characterization sample set through a transfer learning method based on local-global features. According to the method, the performance of an early warning system can be effectively improved, and better guarantee is provided for early warning of hypoglycemia at night before sleep of diabetic patients.

The invention discloses an image generation and understanding unification method and system based on joint diffusion modeling, and relates to the technical field of image generation and understanding. According to the method, image generation and understanding tasks are unified through joint diffusion modeling, models do not need to be designed for the generation and understanding tasks respectively, and the efficiency is improved. Through improved DINOv2, Segmenter and DETR models, classification feature class cluster polymerizability, boundary detail segmentation and small target feature expression detection are enhanced. A random role allocation mechanism and a mask full attention mechanism flexibly process multi-domain information, domain invariant position coding assists cross-domain alignment, and the modeling precision is improved. Through optimization training, the model supports joint generation, controllable generation and image perception tasks at the same time, the performance is superior to that of an existing unified model, and even exceeds that of a proprietary model in tasks such as edge detection.

The invention discloses an electromechanical system heterogeneous domain generalization fault diagnosis method and device based on digital twinning, and belongs to the technical field of electric data processing. The method comprises the following steps: constructing a digital twin model to simulate entity characteristics of an electromechanical system, generating virtual fault data and structured interconnection knowledge distributed across working conditions through the digital twin model, and reconstructing a K-class information domain according to the virtual fault data and entity data of the electromechanical system; the information source is divided into a source domain and a target domain, the source domain represents visible operation conditions, and the target domain represents invisible operation conditions; performing structured interconnection knowledge embedding on the source domains to obtain a knowledge embedding data set of the K-class source domains; and constructing a heterogeneous domain generalization network, and training the heterogeneous domain generalization network by utilizing the knowledge embedding data set of the K-type source domain and the K-type target domain data set to obtain a fault diagnosis model so as to perform fault diagnosis on invisible operation condition information to be diagnosed. According to the invention, fault diagnosis can be carried out on the electromechanical system under the limitation of invisible operation conditions.

The invention discloses a configuration determination method, a capability reporting method and a period configuration method, and relates to the field of communication. The method comprises: receiving a first DCI, the first DCI comprising a first information domain and a second information domain, the first information domain and the second information domain being used for determining a first period configuration; wherein the UE is configured with N sets of period configurations, the N sets of period configurations comprise the first period configuration, and N is an integer greater than 1. And the first period configuration is determined through the first information domain and the second information domain of the first DCI. Compared with a method that only one information domain is used for determining the first period configuration, the method has the advantages that due to the fact that the two information domains comprise more bits, determination of more sets of period configuration can be accurately and efficiently achieved, and higher flexibility is achieved when the period configuration is determined.

Existing multi-agent system are employed collaboratively, where each agent specialized in extracting entities, relations, or events from documents which is a more generalized collaborative framework without specific customizations. The disclosed method presents a collaborative multi-agent knowledge graph Retrieval-Augmented Generation (RAG) framework using a plurality of collaborative multi-agent LLMs for extracting information from a plurality of multimodal documents and constructing the unified knowledge graph to facilitate accurate and efficient query-based retrieval. A query generator agent generates a plurality of queries that aim to uncover all possible information present in the plurality of multimodal documents. A domain model is generated by a domain model generator agent based on the plurality of queries. The domain model populator agent populates the domain model with data extracted from the plurality of multimodal documents. A unified knowledge graph is constructed from ta plurality of populated domain models and organizes the extracted information for accurate retrieval.

The invention discloses a PPDU receiving method and device, a PPDU sending method and device, equipment and a storage medium, and belongs to the field of wireless communication. The method is executed by an electronic device, and the method comprises: receiving all or part of information domains of a first PPDU, the all or part of information domains comprising a first information domain, and the first information domain being used for indicating the type of a target device receiving the first PPDU. Optionally, the target device type comprises a WUR device and an AMP device.

The embodiments of the present disclosure relate to the technical field of communications, and provide a communication method and apparatus, and a device and a storage medium, which can be applied to an AP MLD. The method comprises: determining a first message frame, wherein the first message frame comprises a first information domain, and the first information domain is used for respectively indicating that an operation parameter update request corresponding to each first communication connection is approved or rejected, and is used for indicating the number of first communication connections, or, the first message frame comprises a second information domain and a third information domain, the second information domain is used for respectively indicating that an operation parameter update request corresponding to each first communication connection is approved or rejected, and the third information domain is used for indicating the number of first communication connections, each first communication connection being a communication connection for a non-access point multi-link device (Non-AP MLD) to request that a multi-link operation parameter update is performed; and sending the first message frame. The embodiments of the present disclosure can provide a method for an AP MLD to respectively respond to an operation parameter update request corresponding to one or more communication connections.

This invention relates to the field of smart city lighting facility operation and maintenance, and discloses a method and system for assessing the health status and predicting faults in street light networks. The method includes the following steps: First, energy domain and information domain data of street light nodes are collected. A dynamic topology map with isomorphic information and energy domains is constructed based on electrical waveform correlation and channel characteristic similarity. Node features are reconstructed using a graph attention network, and passive monitoring residuals are calculated. Based on the dual-threshold judgment results of the residuals, when a node falls into a suspected grayscale range, an active micro-perturbation excitation mechanism is automatically triggered, breaking the steady state by issuing a fine-tuning light command. Subsequently, the degree of anomaly in the circuit physical layer is quantified by comparing the integral deviation between the actual physical response and the ideal response based on the transfer function. Finally, the passive residuals and active deviations are dynamically fused to output a full lifecycle health index. This invention solves the problem of difficulty in identifying early, weak faults under complex noise conditions, improving the accuracy of predictive maintenance of street light networks.

This invention provides a self-inspection control method, device, and server for vehicle production and maintenance, relating to the technical field of the automotive industry. The method includes: when the power supply to an ordered vehicle is detected to be on, connecting an information domain controller to the vehicle's manufacturing execution system (MES) based on a key sent by a vehicle networking service platform; sending vehicle information provided by the MES to the information domain controller, enabling the information domain controller to perform a self-inspection process to prevent errors in the vehicle's electronic control system; after the self-inspection of the vehicle's electronic control system passes, switching the information domain controller to production mode and using an electronic inspection program and a set of external cameras to perform a production self-inspection process on the vehicle's electronic control components and external equipment, so that the ordered vehicle can be delivered after the vehicle's production self-inspection passes. This invention can significantly improve the accuracy and efficiency of fault detection during vehicle production and maintenance.

The invention discloses a remote sensing image unsupervised domain adaptive semantic segmentation method and system fusing frequency domain and spatial domain features, and aims to solve the problems of insufficient cross-domain feature alignment and limited segmentation precision caused by video domain information negligence and single domain discriminator scale in the prior art. According to the method, firstly, a source domain data set and a target domain data set are obtained, and then an unsupervised domain self-adaptive framework is built. A generator of the framework extracts multi-scale features through a visual backbone network, frequency domain and spatial domain information is compensated through a bidirectional recursion fusion module, then the features are processed by a content perception decoder containing four decoding stages, and each decoding stage is configured with a weight fusion module and an efficient content perception module to optimize feature representation; the discriminator distinguishes the attribution of the feature domain through four cascade stages, and each cascade stage is matched with a down-sampling unit and an efficient content awareness module to strengthen domain attribute feature extraction. Inputting a source domain training set and a target domain training set into a framework for training, back-propagating optimization parameters by using a multi-joint loss function, and storing an optimal model with the highest average intersection-union ratio in the training process; and finally, processing a target domain remote sensing image by using the model to realize semantic segmentation. According to the method, the feature distribution difference between the source domain and the target domain is reduced through deep fusion of the frequency domain and spatial domain features, and the problem of low segmentation precision caused by inter-domain difference of an existing unsupervised domain adaptive semantic segmentation method is effectively solved.

The embodiment of the invention provides a method and device for opening UE domain information of an application function. A method performed by a first network node in a communication network includes receiving a first request from a second network node, where the first request includes a user equipment identifier (UE ID) indicating a user equipment (UE), determining UE domain information according to the received UE ID, and sending a first response to the second network node. The first response includes the determined UE domain information. The UE domain information includes a core network type and a subscription domain.

The embodiment of the invention discloses a model simulation method and device, electronic equipment and a storage medium, and the method comprises the steps: obtaining a target script file corresponding to a target block diagram assembly when the target block diagram assembly in a system simulation model meets a preset simulation condition; wherein the system simulation model comprises a first block diagram component and a target block diagram component, and the first block diagram component and the target block diagram component respectively correspond to different program languages; performing initialization processing on the target block diagram component based on the component attribute parameters and the initialization function; and determining interface output data of the target block diagram component based on the preposed first block diagram component and the single-step calculation function of the target block diagram component, and completing a component simulation processing process, so that a program language suitable for an information domain is embedded into a system simulation model constructed based on a physical domain program language for simulation calculation, and the simulation calculation efficiency is improved. The research and development cost of the block diagram model of information domain and physical domain fusion simulation is reduced, and the simulation effect and applicability of the block diagram model are improved.

The present disclosure relates to the field of communications. Provided are a non-codebook-based PUSCH transmission configuration method and apparatus. The technical solution of the present application mainly involves: a network device sending, to a UE, single DCI that carries TCI beam indication information and transmission configuration information, and the UE performing PUSCH transmission according to the single DCI, wherein the TCI beam indication information is used for indicating beam information used by the UE to perform transmission; when the TCI beam indication information indicates one beam, the transmission configuration information comprises a group of information indicator domains for single-panel single-TRP transmission, and when the TCI beam indicator information indicates two or more beams, the transmission configuration information comprises two or more groups of information indicator domains for multi-panel multi-TRP transmission; and each group of information indicator domains comprises at least one of an SRI domain and a TPMI domain. In the precoding indication method and apparatus in the embodiments of the present disclosure, single DCI carries TCI beam indication information and transmission configuration information, and an information indicator domain comprised in the transmission configuration information in the single DCI can be dynamically applied to single-panel single-TRP transmission and multi-panel multi-TRP transmission, such that switching between a single-TRP mode and a multi-TRP mode can be achieved, thereby making coordinated multi-point transmission more effective, and thus effectively improving the reliability of data transmission and increasing the throughput rate thereof.

The invention discloses a cross-domain system reliability modeling and evaluation method based on an OODA ring theory, which is oriented to a cross-domain equipment system formed by information domain and physical domain collaboration, constructs an information domain-physical domain collaboration network model, and establishes a mapping relation model among different types of nodes. On the basis, the number of OODA rings capable of being formed in the system is counted, and the operation capacity of the cross-domain system is quantitatively represented. Furthermore, the mapping relation model is dynamically updated under the conditions of node faults, random strike and the combined action of the node faults and the random strike, and the change characteristics of the system reliability under different failure conditions are evaluated. And meanwhile, under the condition that a failure is caused by a node fault or random strike, a dynamic reconstruction mechanism of an information domain and a physical domain is introduced, the system structure is dynamically reconstructed, and the system reliability under the dynamic reconstruction mechanism is evaluated based on the change of the number of OODA rings before and after reconstruction.

This application provides a method and apparatus, a device, and a storage medium for data processing and LLM training. The method includes: extracting raw data representing world knowledge from an information domain comprising websites, the raw data comprising a set of data elements, and each data element in the set of data elements comprising at least one of: a text portion; an image portion; an audio portion; or a video portion; using the each data element in the set of data elements as input, instructing a first LLM to infer a seed persona corresponding to the each data element; and storing the seed persona into a persona set comprising at least one persona.

The present invention discloses a jitter measurement method combining time domain, frequency domain and statistical domain in a digital oscilloscope. First, the digital oscilloscope collects a long series of continuous signals and forwards the sampled data to a host computer. Then, each jump moment of the signal to be measured is found. Then, a software phase-locked loop is used to recover the reference edge moment according to the jump moment of the signal to be measured. Then, the jump moment of the signal to be measured is subtracted from the reference jump moment to obtain a set of time interval error sequences. Finally, based on this sequence, the jitter is analyzed and processed from multiple information domains to obtain the magnitude of the overall jitter, deterministic jitter, random jitter, periodic jitter, data correlation jitter, intersymbol interference and duty cycle distortion.

The invention provides an automatic relay configuration method based on a scoring mechanism and capable of being customized in multiple dimensions. The method comprises the following steps: classifying all nodes under a gateway according to information domains; the node is reset, the gateway resets the node role, and the reset role is a common node; searching nodes in a node gateway search area, collecting the nodes into an upper computer list, and simultaneously collecting the signal-to-noise ratio and the received signal strength indication of the nodes by an instruction; configuring a node role; a pre-relay scoring mechanism is established; and calculating scores. The problem of network coverage blind area or resource redundancy caused by the fact that a traditional PLC depends on fixed distance / experience to deploy a repeater is solved, a fixed routing binding mode is broken through, real-time path updating in dynamic environments such as electromagnetic interference and impedance mismatch is achieved, a flexible framework capable of configuring scoring weights and the number of relays is provided, and the real-time route updating is achieved. And different transformer area scales and time delay requirements are adapted, and the manual maintenance cost is reduced.

The invention provides a power monitoring system network attack real-time detection method and system, and belongs to the technical field of power system information physical security. The method comprises the following steps: acquiring an attack path of a power monitoring system and information equipment related to the attack path, and constructing a security event set by using predictable security alarms; calculating the average attack time of a single security vulnerability in an attack path by establishing a security vulnerability attack time model; the implementation probability of the attack path is calculated according to information equipment related to the attack path, and then the average implementation time of intrusion of the SCADA system is calculated; and based on the security event set and the average implementation time, judging the occurrence stage of the network attack, tracing initial equipment where the attack occurs, and predicting possible attack behaviors. According to the method, the problems that an existing method only considers information domain intrusion behavior characteristics and space-time correlation is insufficient are solved, and the safety degree of operation of the power system in a large-scale information equipment access scene can be improved.

The invention discloses a multi-domain parameter adaptive adjustment method for a digital oscilloscope matched with signal frequency characteristics, and the method comprises the steps: firstly sampling an unknown input signal through a high-speed data collection system, obtaining a digital parallel sampling signal, and transmitting the digital parallel sampling signal to a multi-information-domain data processing module in an FPGA (Field Programmable Gate Array); in the multi-information-domain data processing module, time-frequency graph data acquisition of unknown signals is completed based on accurate control, fast Fourier transform and data delay feedback of time-domain data required by each frame of frequency spectrum, and the time-frequency graph data is transmitted to an industrial personal computer through a high-speed interface after being acquired. The method comprises the following steps: performing data analysis, obtaining a maximum value of spectrum energy and calculating an effective frequency index value to obtain a maximum effective frequency index value and a minimum effective frequency index value, then obtaining a multi-domain analysis parameter center frequency and an analysis bandwidth through calculation, and setting, feeding back and adjusting a multi-domain analysis processing module on a user interface of a digital oscilloscope.

The present invention discloses a train control defense method and system based on an infectious disease model. The method includes: S1. Establish an APT attack propagation model to describe the node state transition and propagation process of the attack in the train control system; S2. Based on the APT attack propagation model, obtain the performance of the information domain network of the train control system and the train operation performance in the physical domain; S3. Collect the physical state data of train operation and the communication state data of the information domain to construct a multi-dimensional feature vector; S4. Use the random forest algorithm and the long short-term memory network to dynamically detect the train operation data and identify the false data injection attack; S5. After the APT attack occurs, optimize the train operation path and speed control strategy, and reduce the impact of the attack on the system by adjusting the mobile authorization information flow path. Through the dynamic interaction between the information domain and the physical domain, the present invention makes up for the neglect of the impact on the physical domain in the traditional defense method.

The invention provides a zero sample cross-domain data generation method and system based on data inversion, and aims to solve the problem of lack of target domain data. The method comprises the following steps: converting a domain text of a target domain into a domain text feature vector through a domain information retrieval step; retrieving in a source domain information base according to the domain text feature vector, calculating the similarity between the domain text feature vector and the existing domain information in the source domain information base, and screening out the closest domain information; in the domain information inversion step, DDPM inversion is carried out on the retrieved domain information to obtain initial noise of a target domain; in the data generation step, initial noise obtained through inversion serves as initial denoising data, conditional denoising is carried out on the initial denoising data in combination with conditional information, and finally cross-domain data meeting the target domain requirement is generated. According to the method, data generation in a new scene becomes possible and only depends on the target domain text description information, so that the quality of the generated data is improved.

The invention discloses an Internet of Things terminal network security early warning platform based on artificial intelligence, which performs cross-domain feature alignment on information domain and physical domain data analyzed at a bottom layer, and innovatively converts the information domain and physical domain data into a time sequence texture grey-scale map, thereby utilizing the characteristics of a convolutional neural network on a spatial receptive field, and improving the security of the Internet of Things terminal network security early warning platform. And deeply extracting potential semantic association and time sequence evolution laws among the heterogeneous data streams. Finally, through full-connection classification and real-time estimation of threat probability, a full-link early warning closed loop from multi-dimensional feature fusion, deep feature mining to defense instruction automatic generation is realized, and the security defense efficiency and response speed of the industrial-grade Internet of Things in the face of advanced persistent threats are greatly improved.

The invention provides a self-inspection control method and device for vehicle production and maintenance and a server, and relates to the technical field of the automobile industry, and the method comprises the steps: enabling an information domain controller to be connected with a production and manufacturing execution system of a vehicle based on a secret key transmitted by a vehicle networking service platform when monitoring that an order vehicle is powered on; vehicle information provided by a production and manufacturing execution system is sent to an information domain controller, so that the information domain controller carries out error-proofing self-checking processing on a whole vehicle electronic control system according to the vehicle information; and after the error-proofing self-inspection of the whole vehicle electronic control system is passed, switching the information domain controller to a production mode, and carrying out production self-inspection processing on vehicle electronic control parts and vehicle external equipment actions by utilizing an electric inspection program and an external camera set, so as to carry out order vehicle delivery after the vehicle production self-inspection is passed. According to the method, the fault detection accuracy and detection efficiency in the vehicle production and maintenance process can be remarkably improved.

This application discloses an unsupervised multi-source information domain adaptation method, device, medium, and product for rotating machinery migration diagnosis, relating to the field of mechanical fault diagnosis. The method comprises: acquiring multi-source information; fusing and compressing the multi-source information into a single fused sample; constructing a domain-adaptive self-attention network transfer learning model enhanced by information fusion; and inputting the single fused sample into the domain-adaptive self-attention network transfer learning model to obtain a migration diagnosis result for the rotating machinery. This application can address the problems of negative transfer, information loss, and high computational burden that exist in existing multi-source information domain adaptation methods.

A communication method, a first device and a second device are provided. The method includes that a first device transmits first information to a second device. The first information includes value field information or information field information corresponding to collected data information. The first information is associated with second information including at least one of: data type identifier, format / length indication information corresponding to the value field information or the information field information; first indication information for indicating whether current type of data is last single-type data in a data sample in the collected data information; second indication information for indicating whether current single-type data contained in the data sample in the collected data information appears; quantity indication information of data samples in the collected data information; indication information of whether a current data sample is a last data sample in the collected data information; or data collection task identifier.