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

13212results about How to "Adaptable" patented technology

Construction method and device of knowledge base question-answering system, equipment and storage medium

The invention relates to the technical field of database construction, in particular to a knowledge base question-answering system construction method and device, equipment and a storage medium. The method comprises the following steps: acquiring a user question instruction, and performing part-of-speech tagging and keyword vectorization on a target text to generate a retrieval text keyword vector; performing semantic linear embedding and spatial projection processing on the keyword vectors to obtain keyword semantic vectors; logic mining is conducted on the keywords, a logic relation set among the keywords is obtained, logic recognition is conducted on the target text based on the relations, and retrieval text logic is generated; performing matching retrieval with semantic vectors in a knowledge base to obtain a candidate semantic query data set; and performing coherent logic retrieval on the candidate data set according to the retrieval text logic and the keyword vector to generate a final retrieval target answer. According to the method and the system, more accurate and efficient knowledge base question-answering system construction is realized.
Owner:YINGZHI FUTURE (SHENZHEN) ARTIFICIAL INTELLIGENCE TECH CO LTD

Scheduling automation system application state management method

The invention relates to the technical field of dispatching automation, and discloses a dispatching automation system application state management method which comprises the following steps: dynamic task state management: monitoring dynamic state indexes of various computing tasks in real time; according to different characteristics of task types, making differentiated priority management strategies; the task priority is dynamically adjusted, and it is ensured that key tasks are preferentially and efficiently executed; dynamic resource state management: continuously monitoring dynamic state indexes of various computing resources, wherein the dynamic state indexes comprise utilization rates and load conditions; dynamically adjusting a resource allocation scheme according to the resource state; dynamically optimizing resource allocation to ensure that the overall resource utilization rate of the system is continuously improved; and optimizing a self-adaptive scheduling strategy: introducing a self-adaptive scheduling algorithm based on reinforcement learning. According to the application state management method of the dispatching automation system, dynamic state management is adopted, a traditional static dispatching mode is abandoned, and the method can better adapt to a complex and changeable computing environment.
Owner:STATE GRID XINJIANG ELECTRIC POWER CO LTD CHANGJI POWER SUPPLY CO

Commercial credit evaluation and supervision method based on multi-modal coevolution algorithm

The invention relates to a business credit evaluation and supervision method based on a multi-modal coevolution algorithm, and the method comprises the steps: collecting and cleaning multi-modal data, guaranteeing the data quality, uniformly storing the multi-modal data as a structural database, extracting features through cross-modal comparative learning, and enabling the features to be embedded into a dynamic multi-modal knowledge graph, a modal sharing network is used to extract and fuse modal sharing and specific features, consistency of modal feature distribution is optimized through adversarial learning, a global co-evolution credit scoring model is initialized, a dynamic multi-objective algorithm is used to optimize accuracy, robustness and interpretability of the model, and a credit scoring result is obtained. A causal reasoning model is introduced to analyze driving factors of enterprise credit changes, a causal relationship is established, a closed-loop feedback system is designed, a credit evaluation model is updated, adaptability is enhanced, an interpretable credit evaluation report is generated based on a generative adversarial network, and transparency and credibility are enhanced. According to the method, the accuracy and adaptability of credit assessment are improved, and the robustness and interpretability of an assessment result are ensured.
Owner:SOUTHEAST UNIV

Multi-modal sensing humanoid robot action self-adaptive control method and multi-modal sensing humanoid robot action self-adaptive control system

The invention discloses a multi-modal perception humanoid robot action adaptive control method and system, and belongs to the technical field of computers, and the method comprises the steps: obtaining first multi-modal data; the first multi-modal data comprises first image data, first point cloud data and first force sense data; performing data fusion on the first image data and the first point cloud data, and constructing a three-dimensional model of the scene in real time; generating an optimal path according to the real-time environment data of the three-dimensional model, converting the optimal path into a joint instruction of the humanoid robot, and generating an action control strategy; according to the action control strategy, arm movement of the robot is adjusted through visual servo control, and first operation data are obtained; the path and action of the robot are adjusted in a closed-loop control mode, and second operation data are obtained; and reinforcement learning and regular evaluation are carried out through a DDPG algorithm, and an action control strategy is continuously optimized. According to the invention, multi-modal sensing robot motion adaptive control with strong adaptive capability, high operation precision and good robustness can be realized.
Owner:广州里工实业有限公司

Industrial park short-term load prediction method and system based on Diffusion-Transform-AR model

The invention relates to the technical field of electric power short-term load prediction, in particular to an industrial park short-term load prediction method and system based on a Diffusion-Transform-AR model. Acquiring non-stationary historical load data and meteorological data of the industrial park, and performing missing value processing on the data; performing correlation analysis on the data by using the maximum information coefficient, selecting meteorological data with relatively high correlation, and reprocessing time data; performing time sequence decomposition on the load data by using a seasonal trend decomposition method to obtain trend term, seasonal term and residual term features; constructing a diffusion Transform prediction model, and taking the residual term, the meteorological data and the time data as input prediction residual; constructing an autoregression prediction model and taking the trend term as an input prediction trend; according to the method, the advantages of various models are combined, time sequence features are deeply mined, the prediction precision and the model generalization ability are effectively improved, and the method is suitable for complex industrial park load prediction scenes.
Owner:YUNNAN POWER GRID CO LTD

Memory retrieval method for enhancing multi-modal long-context dialogue ability of large language model

The invention discloses a memory retrieval method for enhancing multi-modal long-context dialogue ability of a large language model. The method comprises the following steps: carrying out self-adaptive segmentation based on information density on an original multi-modal dialogue sequence and extracting local features; constructing a three-layer feature pyramid structure to realize multi-scale feature representation; the time sequence expression capability of the features is enhanced through feature compression and time sequence dependency graph modeling; constructing a memory vector sequence based on feature stability evaluation; carrying out structured representation on the query data and carrying out multi-level interaction with the memory vector; efficient retrieval is realized through hierarchical indexing and multi-dimensional similarity calculation; the memory sequence is periodically optimized based on user feedback. According to the method, the multi-modal information understanding and retrieval capability of the model in a long dialogue scene can be effectively improved, and the method has important practical application value.
Owner:NANJING ARTIFICIAL INTELLIGENCE CHIPS RES INST OF AUTOMATION CHINESE ACAD OF SCI +1

Intelligent building full life cycle monitoring management method and system

The invention relates to the technical field of intelligent building management, in particular to an intelligent building full-life-cycle monitoring management method and system, and the system comprises a data collection module, a multi-source data fusion and analysis module, a full-life-cycle management model construction module, an intelligent early warning module, a self-adaptive feedback regulation and control module, a data storage module and a remote visual monitoring module. According to the system, environment parameters and equipment operation state data of a building are acquired in real time through the data acquisition module, key operation indexes are extracted by using the multi-source data fusion and analysis module, and accurate risk assessment and early warning are realized under the support of the full-life-cycle management model. The self-adaptive feedback regulation and control module can dynamically adjust key operation parameters according to real-time data to ensure stable operation of equipment under different environment conditions, the data storage module supports long-term performance analysis, and the remote visual monitoring module realizes remote monitoring and multi-party collaborative management. According to the invention, the operation safety, stability and management efficiency of hydraulic facilities are effectively improved.
Owner:福州市城区水系联排联调中心

Education resource recommendation method and system based on artificial intelligence

The invention relates to the technical field of educational resource recommendation, in particular to an educational resource recommendation method and system based on artificial intelligence. The method comprises the steps of firstly constructing an educational resource engine, then generating a preliminary user portrait by collecting basic information of a user, dynamically updating the user portrait in combination with personalized demands of the user, then performing data interaction with the educational resource engine based on a data reliability transmission method, and calling educational resource data. The method comprises the following steps of: selecting a user, performing weighted fusion on recommended contents by adopting a collaborative filtering and content-based recommendation mode, providing personalized learning resources for the user, generating a learning path plan for the user, monitoring a learning behavior of the user in a user learning process by the system, and optimizing a recommendation model in combination with user feedback. Through personalized recommendation, intelligent learning path planning, resource matching optimization, data reliability transmission and adaptive optimization, an accurate, efficient, adaptive and reliable educational resource recommendation effect is realized.
Owner:JIANGXI HANFENG CULTURAL DEVELOPMENT CO LTD

Three-dimensional point cloud data segmentation method and system based on multi-scale point features

The invention provides a three-dimensional point cloud data segmentation method and system based on multi-scale point features, and relates to the technical field of point cloud processing, and the method comprises the steps: obtaining original point cloud data, constructing a three-dimensional Hash index table, carrying out the self-adaptive hierarchical division through a local maximum value of a density distribution curve, and obtaining a local maximum value of a density distribution curve; noise point elimination is carried out based on a region density count value and a geometric distribution coefficient, an enhanced feature vector containing a main feature direction, a main curvature value and the like is constructed for non-eliminated points, a local geometric descriptor is constructed by adopting four spherical search regions with increasing radiuses, a three-branch space attention network is input to extract spatial features, and the spatial features are extracted; and fused feature data are obtained through a multi-level geometric feature extraction network and a bidirectional feature propagation network. And obtaining a final segmentation result through segmentation energy function optimization and a region merging strategy.
Owner:YUNTURING ARTIFICIAL INTELLIGENCE TECHNOLOGY (SUZHOU) CO LTD

Bridge support static displacement over-limit early warning correction method based on prediction model

The invention relates to the technical field of bridge structure health monitoring and early warning, and discloses a bridge support static displacement overrun early warning correction method based on a prediction model, and the method comprises the following steps: S1, simulating the dynamic response of a support and an overall structure under various working conditions through building a coupling finite element model of the bridge support and the overall bridge structure; s2, displacement, vibration and temperature data of the support are collected in real time through a multi-source sensor, and data fusion and noise reduction processing are carried out; s3, establishing a multi-level prediction model based on a physical model and a data driving model, and predicting a future displacement trend of the support; and S4, monitoring a prediction error in real time through an error feedback mechanism. Prediction errors are corrected in real time through recursive Kalman filtering and an error feedback mechanism, an early warning threshold value is dynamically adjusted through Bayesian updating, the precision and reliability of early warning are improved in combination with a double triggering mechanism, the method adapts to changes under complex working conditions, and false alarms and missing alarms are reduced.
Owner:HEBEI BAOLI ENG EQUIP GRP CO LTD

Fire rescue unmanned aerial vehicle route automatic planning system based on AI identification

The invention relates to the technical field of unmanned aerial vehicle autonomous navigation, and discloses a fire rescue unmanned aerial vehicle route automatic planning system based on AI identification. Comprising a multi-sensor fusion and environment perception module, a deep learning environment identification module, a self-adaptive route planning module, an intelligent task distribution and scheduling module, a self-organizing communication and data transmission module, an intelligent obstacle avoidance and dynamic adjustment module, an AI control and task execution module and a fault prediction and emergency processing module. And the multi-sensor fusion and environment perception module integrates multi-mode environment perception of a plurality of sensors on a fire scene. Through a deep learning technology of a convolutional neural network and principal component analysis, high-precision identification of key features in a complex scene of a fire scene is realized, and in a complex illumination condition and a smoke shielding environment, a deep learning model can automatically extract effective features, and the identification accuracy is improved.
Owner:NANJING BANGFEI TECHNOLOGY DEVELOPMENT CO LTD

Early warning and cooling system for thermal runaway of battery

The invention relates to the technical field of batteries, and discloses a battery thermal runaway early warning and cooling system which comprises a multi-parameter monitoring module, a data processing and early warning model and a cooling system control module. Wherein the multi-parameter monitoring module is used for acquiring the internal resistance value of each battery monomer in real time in a battery charging process, calculating the internal resistance range, the internal resistance standard deviation and the variable coefficient according to the internal resistance value at a sampling time point, monitoring the working environment gas of the battery through a mass spectrometer, and acquiring the real-time mass spectrum monitoring data of the gas in real time; release characteristics, including hydrogen, hydrocarbon compounds and the like, of escaped gas are quantitatively analyzed on the basis of an equivalent characteristic spectrum method. According to the battery thermal runaway early warning and cooling system, various key parameters in the battery charging process are comprehensively monitored, early warning of the battery thermal runaway risk is achieved, timely intervention is conducted in combination with the cooling system, the thermal runaway risk is reduced, and vehicle and personal safety is guaranteed.
Owner:杨之星

Prediction model construction method and system for personalized equipment operation and maintenance

The invention provides a prediction model construction method and system for personalized equipment operation and maintenance, and relates to the technical field of data processing, and the method comprises the steps: collecting equipment operation data and environment data, extracting the change characteristics of the equipment operation state, carrying out the correlation analysis of the environment data based on historical equipment fault records, and obtaining a prediction model. Performing normalization processing, performing time sequence analysis, generating a joint feature matrix, segmenting the joint feature matrix into time slices of a fixed window according to a time sequence, classifying the time slices into a normal state and an abnormal state, performing feature contribution degree analysis, generating a feature weight matrix, and performing feature extraction; re-combining the equipment features in the time slice feature data set with the environment factors according to feature weights, generating fusion feature data layer by layer, performing supervised learning training on the fusion feature data, constructing an equipment prediction model, and outputting the equipment prediction model as a prediction model of personalized equipment operation and maintenance; according to the invention, the operation and maintenance effect of personalized equipment is improved.
Owner:FUJIAN WENDASEN INFORMATION TECHNOLOGY CO LTD

Unmanned aerial vehicle return detection method and system based on AI identification

The invention provides an unmanned aerial vehicle return detection method and system based on AI recognition, and relates to the technical field of image recognition, and the method comprises the steps: extracting multi-scale features through an improved moving window hierarchical converter model, obtaining target attitude information through the combination of cross-modal comparative learning and a dynamic routing capsule network, and obtaining target attitude information; an alignment feature representation is obtained by using a feature enhancement module and an adversarial feature alignment method, the alignment feature representation is input into a graph attention diffusion model to obtain an accurate state representation, and a state evolution trajectory is obtained in combination with an adaptive causal convolutional network and an ordinary differential equation network; posterior distribution is determined through a variational inference network and an autoregression flow model, a state sequence is predicted by using a neural process network and a dynamic point process model, an expert strategy is learned by using a hierarchical generative adversarial imitation learning network and a distributed trust domain evolutionary strategy algorithm, and optimal parameter configuration is obtained; and accurate prediction of the return state of the unmanned aerial vehicle is realized.
Owner:ZHONGDIAN GUOKE TECH CO LTD +1

Data access method and system of intelligent Internet of Things gateway

The invention relates to a data access method and system of an intelligent Internet of Things gateway. The method comprises the following steps: performing feature matching and protocol identification on a plurality of sensors and terminal equipment connected to the intelligent Internet of Things gateway by using an equipment feature library to obtain an equipment protocol type; analyzing the original data to obtain standardized data; performing encryption processing to obtain an encrypted security data packet and an encrypted session key; performing multi-factor transmission channel selection to obtain an optimal transmission channel combination; and based on the optimal transmission channel combination, sending the encrypted security data packet to the Internet of Things platform, verifying the received data confirmation information based on a consensus algorithm, and outputting a data access state report through a data visual interface and an AI voice assistant. The processing strategy can be dynamically adjusted according to the equipment characteristics, the data characteristics and the network environment, and the flexibility and adaptability of the system are improved.
Owner:BEIJING GANWEI DIGITAL TECHNOLOGY CO LTD

Multi-scene terminal signal-to-noise ratio estimation implementation method and device

The invention discloses a multi-scene terminal signal-to-noise ratio estimation implementation method and device, and the method comprises the steps: obtaining a received signal sample sequence, platform attitude data, antenna pointing data and environment parameter data, and obtaining a feature vector through feature extraction and adaptive window processing; generating a compensation feature vector based on the feature vector and environment compensation data; performing feature fusion in combination with platform state data to obtain a scene feature vector; performing parameter optimization on the scene feature vector, establishing a dynamic memory mechanism, and generating memory state data; performing dynamic correction and robustness processing on a signal-to-noise ratio by using the memory state data to obtain a corrected signal-to-noise ratio; and performing quality evaluation based on the performance evaluation vector and the dynamic threshold vector, and outputting a final signal-to-noise ratio and a control parameter set. Through adaptive feature extraction, multi-dimensional compensation and a dynamic memory mechanism, the precision and reliability of signal-to-noise ratio estimation are improved.
Owner:COWAVE SATELLITE COMM TECH CO LTD

Data analysis method and system based on three-dimensional map display

The invention belongs to the technical field of data processing, and discloses a data analysis method and system based on three-dimensional map display, and the method comprises the steps: collecting real-time data from a plurality of data sources, adding geographic position information to each piece of data after preprocessing, marking the spatial position of the data in a three-dimensional map through geographic coordinates, and obtaining a data analysis result; a standardized three-dimensional map basic model is loaded and constructed, a three-dimensional space environment is constructed through a GIS standard, different marks are visually marked on a map according to attributes and features of data, and a convolutional neural network is used for automatically performing anomaly detection and classification on a time sequence of the data. And generating and displaying a dynamic animation according to the time dimension of the data. According to the invention, the three-dimensional map technology is utilized to enhance the intuition, interactivity and flexibility of data analysis, and meanwhile, the efficiency of data monitoring and exception handling is improved through intelligent data early warning and dispatching command functions.
Owner:江西省通信产业服务有限公司

Intelligent path optimization method and system based on link state perception enhancement

The invention discloses an intelligent path optimization method and system based on link state perception enhancement, and the method comprises the steps: building an intelligent path decision model based on a PPO algorithm of an AC architecture, introducing a GRU network and a GAT network to respectively capture the time-space correlation characteristics of a network state sequence composed of a plurality of link states, and meanwhile, carrying out the optimization of the link state perception enhancement. An attention mechanism is used to perceive important features of a network state sequence, and an optimal path selection strategy is generated through a training mechanism based on deep reinforcement learning; generating a flow table according to the optimal path selection strategy, issuing the flow table to switch equipment of a target network, and performing path installation and service data forwarding; compared with the existing routing algorithm, the algorithm provided by the invention can accurately realize the routing decision when the network topology structure dynamically changes, and has superiority in the aspects of improving the network service performance and adapting to the change of the dynamic topology structure.
Owner:NANJING UNIV OF INFORMATION SCI & TECH

Source code detection method

The invention relates to the technical field of software engineering, in particular to a source code detection method, which comprises the steps of source code preprocessing, code dependency analysis, semantic understanding and analysis, code quality evaluation, dynamic behavior simulation, intelligent vulnerability detection and the like to realize comprehensive detection of potential vulnerabilities and quality problems in source codes. A support vector machine and a K-means clustering algorithm are combined, known and unknown vulnerabilities can be effectively recognized, in addition, a continuous optimization feedback mechanism is introduced, a mixed vulnerability detection model can be continuously optimized according to repair operation and feedback information of a developer, the detection accuracy is improved, and the coverage range is expanded. The generated comprehensive detection report covers code structures, vulnerability positioning, quality problems and optimization suggestions, supports integration of various output formats and development tool chains, helps developers to efficiently repair problems, and improves code quality and project progress; according to the method, the comprehensiveness, the self-adaptability and the user experience of code detection are effectively improved.
Owner:HLJ E LINK NETWORK CORP LTD

Unmanned aerial vehicle inspection control system and method based on data analysis

The invention relates to the technical field of unmanned aerial vehicle control, and discloses an unmanned aerial vehicle inspection control system and method based on data analysis, and the method comprises the steps: receiving environment feature data of a target region, and constructing a static environment model; obtaining kinetic parameters of the unmanned aerial vehicle, and calculating a feasible flight envelope in combination with the static environment model; after taking off, the unmanned aerial vehicle collects environment data in real time, and a multi-level environment topology model is constructed; acquiring state data in real time, and judging an obstacle avoidance level; if yes, local path planning is carried out, and an optimal flight path is generated; acquiring trajectory deviation and energy consumption data, dynamically calibrating the flight envelope, and optimizing the flight envelope; according to the method, environment perception, trajectory optimization and online learning are combined, the method is adaptive to a complex environment, and the intelligent level of unmanned aerial vehicle inspection is improved.
Owner:JIANGSU SUQI INTELLIGENT TECH CO LTD

Speculation decoding method and device for large language model and medium

The embodiment of the invention discloses a speculation decoding method and device for a large language model and a medium, and relates to the technical field of large language models, and the method comprises the steps: obtaining the current task information of a target large language model; the method comprises the steps of inputting original text prompt information into a target large language model, determining initial token information, constructing a plurality of patch data of a specified patch level according to the initial token information and the original text prompt information, generating a plurality of candidate patch sequences in parallel according to each patch data and a draft model, mapping each candidate patch sequence, determining initial draft information, and outputting the initial draft information. The preliminary draft information comprises a token sequence corresponding to each candidate patch sequence; and performing parallel verification on the token sequence corresponding to each candidate patch sequence through the target large language model, screening the token sequences corresponding to the candidate patch sequences, determining the next round of input of the draft model, and performing speculative decoding.
Owner:SHANDONG INSPUR SCI RES INST CO LTD

Large container crane intelligent early warning system based on personnel behavior analysis

The invention discloses a large container crane intelligent early warning system based on personnel behavior analysis, and the system comprises the following steps: collecting operator behaviors, equipment operation states and environment parameters in real time through a multi-mode sensor network, constructing a dynamic data set, extracting behavior characteristics through a time difference embedding algorithm, and carrying out the early warning of the operator behaviors, the equipment operation states and the environment parameters; a multi-level spatial-temporal characteristic matrix is generated in combination with dynamic scene influence factors, regional risk factors are dynamically calculated by using a Bayesian inference model, comprehensive risk values are generated through an adaptive multi-objective optimization algorithm, risk levels are divided into low, medium and high classes, and a system triggers graded early warning responses according to the risk levels. And an optimized behavior adjustment suggestion is generated in combination with a quantum probability behavior prediction algorithm, and a feature extraction rule and risk assessment logic are dynamically optimized through a progressive learning algorithm to form a closed-loop optimization process. According to the invention, intelligent analysis and real-time early warning of personnel behaviors are realized, and the safety and adaptability of the crane in an operation environment are improved.
Owner:BEIJING GUOXINZHIKE TECH DEV CO LTD

Temperature prediction method and system for multi-mode AIGC cold-chain logistics monitoring platform

The invention relates to the technical field of cold-chain logistics monitoring, and discloses a temperature prediction method and system for a multi-modal AIGC cold-chain logistics monitoring platform, and the method comprises the steps: carrying out the multi-modal data collection and data fusion of a cold-chain logistics transportation process based on a cold-chain logistics monitoring platform, and obtaining a multi-modal fusion data matrix; inputting an AIGC model to carry out feature extraction and inter-modal feature weight calculation to obtain a multi-modal feature importance vector; performing cross-modal weighted fusion calculation and associated feature map construction to obtain a temperature state feature sequence; inputting a multi-modal deep belief network to carry out probability distribution modeling to obtain a temperature prediction probability distribution sequence; performing time sequence characteristic analysis to obtain a temperature prediction interval sequence; and performing dynamic threshold judgment to obtain a multi-stage temperature early warning trigger signal. According to the invention, the temperature prediction accuracy of the cold-chain logistics monitoring platform is improved.
Owner:SHENZHEN QIANHAI YUESHI INFORMATION TECH CO LTD

Intelligent fault diagnosis method based on multi-input neural network

PendingCN119557763AAdapt to real-time processing needsImprove real-time performanceNeural learning methodsMulti inputTime domain
The invention discloses an intelligent fault diagnosis method based on a multi-input neural network. The method comprises the steps of data acquisition, preprocessing, feature extraction, model training and fault judgment. A variety of sensor signals are collected from the device, de-noised and normalized to generate high quality features. Time domain and frequency domain features are extracted in combination with methods such as wavelet transform, deep learning is performed on feature data by using a neural network, and a potential fault mode is identified. Through the trained model, the system can detect and classify faults in real time, output fault levels and diagnosis reports, and provide support for equipment maintenance. The method is suitable for a large-scale complex environment, has high diagnosis precision and quick response capability, effectively improves the management efficiency, and reduces the non-planned downtime.
Owner:SOUTHEAST UNIV +1

Internet data security protection method and system based on intelligent algorithm

The invention discloses an internet data security protection method and system based on an intelligent algorithm, and relates to the technical field of security protection. During system operation, user behavior data are collected in real time through log recording, a sensor and an API interface, the real-time operation behavior of a user is monitored, the interaction mode and transaction behavior of the user on a platform are analyzed, and the security of the user is improved. Calculating and acquiring a user behavior safety coefficient Yhxw, a data transmission safety coefficient Sjcs and a risk protection response coefficient Fxfh, identifying potential fraudulent behaviors, performing dynamic risk assessment by combining user historical behaviors, a transaction amount, a geographic position and data of payment equipment, performing threshold comparison to obtain an assessment scheme, and during login and transaction, combining multiple identity verification means to obtain a risk protection result; according to the method, user identity verification is carried out, security of login behaviors is dynamically monitored, network traffic and platform logs are analyzed, abnormal access and malicious requests or DDOS attacks are detected in real time, and abnormal behaviors or attacks are automatically identified and prevented.
Owner:上海笑聘网络科技有限公司

Segmentation method for rail defect detection based on improved YOLOv10 and SETR

The invention discloses a segmentation method for rail defect detection based on improved YOLOv10 and SETR, and the method comprises the steps: S1, collecting image data, carrying out the enhancement processing of the image data, carrying out the segmentation processing, and making a data set; s2, an improved YOLOV10 algorithm model is built and trained; s3, using the improved YOLOV10 model weight to detect image data to be detected, judging whether defects exist or not, if the defects are detected, storing detection frame information of the defects, and outputting a target detection frame and confidence; and S4, transmitting the detection frame information as prompt information into the SETR model, segmenting the target by adopting the SETR model to obtain a segmentation result, and outputting a mask pattern. The improved YOLOv10 algorithm and the SETR algorithm are adopted to detect the rail defects, the calculation complexity and the efficient detection speed are kept, the detection precision is improved, and the robustness of the model is improved.
Owner:NANJING HOWSO TECH +1

Emotion analysis method and system based on multi-modal fusion

The invention discloses an emotion analysis method and system based on multi-modal fusion. The method comprises the following steps: S1, acquiring multi-modal data and initial feature representation of each modal; s2, inputting the initial feature representation of each mode into a multi-head attention mechanism for preliminary fusion, and generating a primary fusion feature; s3, in combination with the bidirectional long-short-term memory network and the multi-scale causal convolutional network, generating time sequence features; s4, constructing a hierarchical dependency relationship network among modals by using a multilayer graph neural network, and forming global context sensing feature representation; s5, dynamically generating and adjusting the fusion weight of each mode; s6, combining classification and regression output by using a multi-layer full-connection network and a multi-task learning framework, and generating multi-dimensional expression of an emotional state; and S7, migrating the group sentiment model to specific sentiment analysis of individual users through transfer learning and personalized modeling technologies. According to the method, high-precision and multi-dimensional sentiment analysis is realized by utilizing multi-modal fusion and self-adaptive weight adjustment.
Owner:无锡慧仁创欣智能科技有限公司

Photovoltaic grid-connected inverter and alternating current side starting method of photovoltaic grid-connected inverter

The invention relates to a photovoltaic grid-connected inverter and an alternating current side starting method of the photovoltaic grid-connected inverter, and the inverter comprises a bus capacitor, a DC / AC inverter circuit, a control unit and a pre-charging circuit. The input end of the DC / AC inverter circuit is connected with the bus capacitor, and the output end of the DC / AC inverter circuit is connected with a power grid; the input end of the pre-charging circuit is connected with a power grid, the output end of the pre-charging circuit is connected with the bus capacitor, and the pre-charging circuit is used for taking electricity from the midpoint of the grid-connected relay to charge the bus capacitor; the bus capacitor is used for starting the DC / AC inverter circuit after charging is completed; the control unit is used for controlling work of the pre-charging circuit. According to the invention, the AC side starting of the inverter can be realized, the starting process is safer, and the work is stable and reliable.
Owner:SHANGHAI SIGEYUAN INTELLIGENT TECH CO LTD

Magnet surface defect detection equipment control method for AI optimization and controller

The invention discloses a magnet surface defect detection equipment control method for AI optimization and a controller, and relates to the field of control adjusting systems.The method comprises the steps that according to a conveying monitoring image, surface brightness information of a to-be-detected magnet on a conveying platform is determined; determining detection light source parameters according to the surface brightness information, and adjusting an irradiation light source of the detection station according to the detection light source parameters; when the to-be-detected magnet arrives at the detection station, collecting a surface image of the to-be-detected magnet, and calculating a gray feature value of the surface image in real time; when the numerical deviation between the gray feature value and a preset gray target exceeds a preset deviation threshold value, finely adjusting the detection light source parameter according to the numerical deviation, and determining a target light source parameter; controlling the irradiation light source of the detection station to irradiate according to the target light source parameter, and obtaining the surface image of the to-be-detected magnet again as a target image; and inputting the target image into the AI detection model to obtain a defect detection result. By implementing the method, the detection effect on different magnets can be improved.
Owner:BEIJING HONGHAOXINDA TECH

Site detection and dispensing control method and system based on image information

The invention provides a site detection and dispensing control method and system based on image information, and relates to the technical field of control, and the method comprises the steps: obtaining the image information of a to-be-dispensed workpiece, building a dispensing process model on the basis of initial dispensing parameters according to the characteristics of a to-be-dispensed material and the area and height information of a to-be-dispensed region, and calculating the dispensing process model according to the initial dispensing parameters. Obtaining target dispensing parameters by solving the dispensing process model; dispensing equipment is controlled to carry out dispensing according to the target dispensing parameters, a dispensing result is obtained, a dispensing area image of the workpiece after dispensing is obtained, quality detection is carried out, and a quality detection result is obtained; the quality detection result is compared with a preset quality standard, and when the quality requirement is met, dispensing is completed; when the quality requirement is not met, parameters in the dispensing process model are corrected according to the quality detection result, target dispensing parameters are obtained again, and dispensing is conducted till the quality requirement is met.
Owner:RUIFENG TIANJIN ELECTRONIC CO LTD