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

279 results about "Reverse analysis" patented technology

Precise injection mold accessory production quality traceability management method and system

The invention provides a precision injection mold accessory production quality traceability management method and system, and relates to the technical field of intelligent manufacturing, and the method comprises the steps: collecting material, process, equipment and environment data in real time through a distributed sensor; fusing multi-source data based on dynamic material characteristic parameters and process stability indexes, and quantifying melt flow and process fluctuation characteristics; constructing a mixed kernel function anomaly detection model to identify quality deviation; establishing a cross-process association map to reveal the space-time relationship among the raw materials, the process and the finished product; generating a three-dimensional traceability identifier containing the material hash, the process compression code and the block chain address; a block chain enhanced database is adopted to realize tamper-proof storage; and generating a visual traceability report through reverse analysis. Through dynamic modeling, cross-process association and block chain technologies, the problems of data isolation, detection lag and low traceability credibility in a traditional method are solved, the quality traceability efficiency and precision are remarkably improved, and precise injection molding full life cycle management is supported.
Owner:ZHEJIANG JIEZHONG SCI & TECH CO LTD

Grid-connected point electric energy quality on-line monitoring and automatic diagnosis method

The invention relates to the field of electric energy quality monitoring and diagnosis, in particular to a grid-connected point electric energy quality on-line monitoring and automatic diagnosis method. The method comprises the following steps: calculating effective values and power parameters of voltage and current, extracting the amplitude and phase of each harmonic, and calculating total harmonic distortion; solving a coupling electromagnetic field equation by using an electromagnetic field coupling effect model; based on a time-space evolution model and in combination with an electromagnetic field reflection coefficient, using an anomaly detection function to locate occurrence time and position of a problem; and constructing a multi-scale electromagnetic reverse analysis model, and constructing a fault diagnosis function by combining a dynamic environment compensation model and introducing an electromagnetic field reflection coefficient and frequency deviation. According to the grid-connected point electric energy quality online monitoring and automatic diagnosis method, through integrating a time-space evolution model, a multi-scale electromagnetic reverse analysis model, an anomaly detection function and a dynamic environment compensation model, accurate control and efficient fault management of a power grid operation state are realized.
Owner:BEIJING RUIDA YINENG TECHNOLOGY CO LTD

Unmanned aerial vehicle target detection method based on space-time synchronization association mechanism

The invention relates to an unmanned aerial vehicle target detection method based on a space-time synchronization association mechanism, and relates to the technical field of wireless detection, and the method comprises the following steps: S1, building a unified time reference system, and ensuring that precise timestamp alignment is carried out on IQ data streams collected by two technologies, and the precision reaches a microsecond level; s2, acquiring unmanned aerial vehicle signal data obtained by protocol reverse analysis and a radio frequency fingerprint identification technology; s3, constructing a three-dimensional incidence matrix containing a time window, a frequency domain position and a space arrival angle, and performing space-time matching on the detection events in the synchronous window; and S4, analyzing a matching result to identify a real unmanned aerial vehicle target. According to the method, the unmanned aerial vehicle signal can be effectively and accurately analyzed, the accuracy and reliability of unmanned aerial vehicle target detection are improved, and the possibility of multi-target false alarm is reduced.
Owner:BEIJING ZHONGDIAN LIANDA INFORMATION TECH CO LTD

Mathematical model modeling method based on data analysis operation processing

The invention relates to the technical field of mathematical modeling, in particular to a mathematical model modeling method based on data analysis operation processing. The method comprises the following steps: collecting metal pollution data of a target water area by using a multi-parameter water quality sensor array; performing time sequence alignment on the metal pollution data to generate a standardized pollution data set; constructing a metal migration model based on fluid dynamics and chemical adsorption coupling; inputting the standardized pollution data set into the metal migration model for three-dimensional space interpolation calculation, and generating a metal pollutant diffusion cloud picture; pollution source reverse analysis is carried out on the metal pollutant diffusion cloud picture, and a potential pollution source coordinate set and pollution contribution degree sorting are generated. According to the method, by integrating multi-parameter water quality sensor data, fluid dynamics and chemical models and multispectral analysis, the modeling precision of the water pollution diffusion mathematical model is improved.
Owner:HUNAN JUNENG CERAMIC MATERIALS CO LTD +1

Unmanned aerial vehicle communication link cracking method and system based on chaotic modulation waveform

The invention provides an unmanned aerial vehicle communication link cracking method and system based on a chaotic modulation waveform. The method comprises the following steps: generating a receiving signal matrix by using a mixed index multi-carrier chaotic signal, carrying out separation operation on an index bit characteristic and a modulation bit characteristic which are mixed and superposed in the matrix, generating an independently modulated carrier component set, and then adjusting a beam forming direction of a multi-channel antenna array according to a frequency band distribution range of the set. The method comprises the following steps: generating a carrier component signal, then performing matrix reconstruction on the carrier component signal, removing environmental noise components, extracting a corresponding chaotic waveform base vector, and finally generating a spreading code sequence according to a modulation symbol mapping relation between the chaotic waveform base vector and a target unmanned aerial vehicle; according to the technical scheme provided by the invention, the problems that a traditional method is poor in adaptability to aperiodic chaotic signals and insufficient in hybrid feature decoupling precision are solved, the anti-interference capability of target signals is improved, and efficient reverse analysis and spreading code accurate reconstruction of an unmanned aerial vehicle communication protocol in a complex electromagnetic environment are realized.
Owner:ZHONGLIAN GOLDEN CROWN INFORMATION TECH (BEIJING) CO LTD

BOM (Bill of Material) data structured construction method in whole process of product manufacturing and related equipment

The invention relates to the field of information technology application, and discloses a product manufacturing whole process BOM data structured construction method and related equipment, and the method comprises the steps: obtaining defect BOM data of an order output result of an ERP system; according to the defect BOM data, data features of ABOM, MBOM and EBOM are reversely analyzed and traced, and an analysis result is obtained; according to the analysis result, the ABOM, the MBOM and the EBOM are reconstructed to obtain a BOM data structure; the BOM data structure transmits the obtained data features to an ERP system, and BOM data structured construction work in the whole product manufacturing process is completed. According to the method, result defect BOM data is output through an enterprise resource planning system, BOM data characteristics in various BOM data driving business operation are reversely analyzed, difference removal, same storage and combination are carried out, a product design source EBOM model is reconstructed, and finally a'three-in-one 'simplified new BOM reconstruction model for driving enterprise business operation based on the source EBOM as a product digital main line is realized.
Owner:XIAN AERO ENGINE CONTROLS

Distributed household photovoltaic production data access method

The invention discloses a distributed household photovoltaic production data access method comprising the following steps: obtaining a unique identifier of a distributed household photovoltaic device, the unique identifier comprising a communication protocol association feature; judging whether a communication rule corresponding to the unique identifier is included in a preset communication protocol feature library of the cloud server or not; if the preset communication protocol feature library comprises a communication rule corresponding to the unique identifier, performing data communication with the distributed household photovoltaic equipment based on the communication rule; if the preset communication protocol feature library does not include the communication rule corresponding to the unique identifier, performing reverse analysis on original communication data of the distributed household photovoltaic equipment, constructing a structured communication protocol template, and performing data communication with the distributed household photovoltaic equipment based on the structured communication protocol template; and the cloud server is in data communication with a plurality of distributed household photovoltaic devices.
Owner:HUANENG ANHUI MENGCHENG WIND POWER CO LTD +1

Soft tissue constitutive parameter calibration method in soft tissue-skeleton bird body model for bird strike simulation

The invention discloses a soft tissue constitutive parameter calibration method in a soft tissue-skeleton bird body model for bird strike simulation, and the method comprises the construction of a soft tissue-skeleton bird body finite element model and finite element reverse analysis based on flat bird strike. Dividing wing bones, leg bones and head and neck parts in the bones of the bird body into hexahedral unit grids, dividing wishbones, pecking bones, fossil protrusions and ribs into shell units, and dividing soft tissues into SPH particles; further obtaining bone elastic-plastic constitutive parameters through a static compression test, and endowing the bone units with the bone elastic-plastic constitutive parameters; an objective function is set as a mean square error between a flat plate center point pressure-time curve obtained by a real bird body impact flat plate test and corresponding curve data calculated by soft tissue-skeleton bird body impact flat plate finite element simulation, and soft tissue constitutive model parameters are inversely calibrated by adopting a genetic algorithm; and model and material parameter support is provided for bird strike simulation of a high-fidelity aircraft structure.
Owner:ZHENGZHOU UNIVERSITY OF AERONAUTICS

Instant conference evidence obtaining method and device based on memory reverse analysis

The invention provides an instant conference evidence obtaining method and device based on memory reverse analysis. The method comprises the following steps: acquiring a target memory image; analyzing the target memory image by using a preset conference metadata reverse extraction algorithm to obtain conference metadata; the conference metadata reverse extraction algorithm comprises the following steps: identifying process information of an instant conference in a memory image, extracting and dumping files related to the process information in a memory, and analyzing the dumped memory files to extract conference metadata; scanning and matching the memory image by using a preset conference data stream engraving algorithm to obtain conference data stream information; the conference data flow library adjusting algorithm comprises the steps of reconstructing a data structure of a text message and / or a file message transmitted in an instant conference, identifying and positioning a key data structure needing evidence obtaining in the memory mapping according to the reconstructed data structure, and extracting conference data flow information from the positioned key data structure.
Owner:Chinese People's Liberation Army Cyberspace Force Information Engineering University

Humanoid robot navigation method, device and equipment based on defect complementation

The invention discloses a humanoid robot navigation method, device and equipment based on defect complementation, and the method comprises the steps: extracting, recognizing and measuring defect points and data cavity regions through multi-sensor defect features, and generating a defect feature map; establishing a confidence decreasing verification mechanism based on defect mutual exclusion analysis, determining sensor weight distribution, and generating a navigation gain parameter from a negative error feature set; performing reverse analysis on the navigation data to extract data back information, reconstructing environment implicit features and constructing a reverse navigation field; analyzing the spatial distribution density of the data void region to generate a void density map, dividing a path phase change region and generating a phase change rule set; and fusing the curve path parameters, the three-dimensional path parameters and the navigation gain parameters to generate a self-adaptive navigation sequence, and driving the humanoid robot to realize intelligent navigation control. According to the method, the sensor defects are converted into navigation resources, and the navigation performance in a complex environment is improved.
Owner:JIANGSU SMART WORKSHOP TECHNOLOGY RESEARCH INSTITUTE CO LTD

Static analysis-based Pascal-like binary program structured information extraction method

The invention relates to a static analysis-based Pascal-like binary program structured information extraction method, which specifically comprises the following steps of: (1) preliminarily reading basic attributes in a binary file compiled by a Pascal-like by a script and other tools, (2) finding all functions for creating class objects through an obtained construction characteristic function and a control flow analysis technology, and (3) extracting the structured information of the Pascal-like binary program. (3) recursively identifying a member object definition relationship in a binary file and an inheritance relationship between classes by taking a basic object address as a base address and combining a data analysis technology, (4) confirming a corresponding construction function name and a corresponding parameter type and name by combining a result of script automatic generation, and (5) searching a corresponding class interface according to an analysis result, and performing classification and classification on the corresponding construction function. And the code restoration logic is consistent with the original binary file behavior. Accurate restoration of class structures, interfaces and functions is achieved, and therefore the efficiency and accuracy of reverse analysis are improved.
Owner:SOUTHEAST UNIV

Fault diagnosis method and device in PLC system, PLC system and storage medium

The invention relates to a fault diagnosis method and device in a PLC system, the PLC system and a storage medium, and belongs to the technical field of industrial automation control. The method comprises the following steps: acquiring a starting signal and a plurality of shutdown fault signals of equipment in real time; when it is detected that the starting signal jumps from starting to stopping, a reverse analysis process is triggered, and multiple shutdown fault signals are polled according to a preset priority sequence; if a certain shutdown fault signal is in a fault triggering state, generating a corresponding fault code, and keeping the duration of the fault code to be not less than a preset duration through a timer; and transmitting the fault code to the HMI for display, and recording the fault code to a PLC internal fault log database. According to the invention, through embedded real-time diagnosis and a reverse trigger mechanism, the real-time performance of fault capture and the automation of diagnosis are realized, and the efficiency of fault diagnosis is improved. And meanwhile, the diagnosis function block is only activated when the equipment is shut down, so that the CPU occupancy rate is greatly reduced.
Owner:SHANGHAI ARITIME INFORMATION TECH CO LTD

Reverse de-signed binary code analysis method based on library function matching

The invention discloses a de-signed binary code reverse analysis method based on library function matching. The method comprises the following steps of: obtaining de-signed binary codes and a candidate library file list thereof in the embedded equipment, and extracting a library function and information of each object file of each candidate library file; performing matching operation on each object file in sequence to establish a library function matching table; and acquiring addresses for calling other library functions in each library function, performing consistency comparison with the addresses of the successfully matched library functions, and confirming the calling relationship of the library functions, thereby determining the function of the de-signed binary code in the embedded equipment. According to the method, the library function in the de-signed binary code can be accurately identified, the calling relation is checked, and the method is suitable for component analysis and traceability of scenes such as computer programs, embedded firmware and DSP programs so as to accurately identify the function of the de-signed binary code in embedded equipment.
Owner:ZHEJIANG UNIV

Dosing method and system based on timing constraint and priori knowledge enhancement, and storage medium

The invention discloses a dosing method and system based on time sequence constraint and priori knowledge enhancement and a storage medium, and belongs to the technical field of water quality regulation and control, the method comprises the following steps: firstly, deriving features based on a lag operator, a future operator, an interaction operator and a rolling statistical operator in a pre-stage and an intervention stage through correlation analysis under the constraint of a time sequence; and finally, keeping the features which are highly related to the target variables in the result stage. A prediction model is constructed based on an XGBoost model, and feature weights of key variables are dynamically adjusted based on priori knowledge of chemical reactions and physical dynamics. In a reverse analysis stage of the prediction model, solving a unique group of dosing suggestion values, and integrating the dosing suggestion values to form a future dosing sequence; and outputting a corresponding dosing strategy based on the future dosing sequence. According to the method, the time sequence characteristics and the chemical and physical priori knowledge are combined, the prediction model with high interpretability and high prediction precision is constructed, and the accuracy and foresight of the dosing strategy are effectively improved.
Owner:AOTU TECHNOLOGY CO LTD

Cascade operation state real-time monitoring and anti-collision risk intelligent early warning method and system

The invention discloses a cascade operation state real-time monitoring and anti-collision risk intelligent early warning method and system, and the method comprises the steps: obtaining multi-sensor data, determining a key monitoring node, and extracting parameter changes to form an operation state trend sample; carrying out edge calculation processing on the trend sample, reversely analyzing and reconstructing component state parameters from the vibration spectrum signal, generating a step gap change curve, matching with a standard model to obtain a risk characteristic probability value, and generating a state traction chain according to the risk characteristic probability value; obtaining a displacement distribution coefficient and a vibration speed index from the state drag chain, predicting the collision probability distribution of the displacement distribution coefficient through cloud deep learning, determining an early warning level in combination with the vibration speed index, and generating early warning optimization configuration; emergency distribution is determined through linkage control analysis, differentiated response areas are identified, and linkage optimization factors are extracted from the differentiated response areas; finally, differential control parameters are generated and matched with the state traction chain to generate an early warning signal, and intelligent abnormal recognition and self-adaptive early warning of the step equipment are achieved.
Owner:JIANGYIN PURUITE CONTROL ENG CO LTD +1

Method and device for intelligent adaptation of intelligent terminal equipment

According to the intelligent terminal equipment intelligent adaptation method and device, intelligent terminal automatic discovery is carried out based on scene-based adaptive ARP scanning and multi-fingerprint UPnP filtering, access equipment is obtained, automatic and precise discovery of intelligent terminal equipment is achieved, and the intelligent terminal equipment can be automatically and accurately found by standardizing the scanning frequency and the filtering rule. The equipment discovery efficiency and accuracy are improved, the access equipment is subjected to prefabricated API library matching and AI reverse analysis to obtain interface information of the access equipment, automatic analysis of a standard interface and a private interface is realized based on a multi-dimensional analysis technology of an AI large language model, and the equipment discovery efficiency and accuracy are improved by utilizing the AI large language model and combining a built-in multi-language programming template. According to the method, the adaptive code matched with the interface information is automatically compiled, the adaptive code is automatically generated based on the AI technology, the compatibility of multi-protocol and multi-interface type equipment is supported, and finally the core problems of low efficiency, poor compatibility, difficult maintenance and high threshold in the existing intelligent terminal adaptation process are solved.
Owner:REDSTONE SUN BEIJING TECH

Natural language query method and system for multi-dimensional database

The invention discloses a natural language query method and system for a multi-dimensional database. The method comprises the following steps: collecting a natural language problem of a user and extracting data required by a multi-dimensional expression; constructing a cue word template; performing similarity calculation on vectors of the external knowledge documents required by the multi-dimensional expression by using a retrieval enhancement technology to obtain the external knowledge documents corresponding to the vectors; constructing a multi-dimensional database of a tree structure according to the dimensionality and the measurement, and then performing dimensionality filtering on the multi-dimensional database to obtain a filtered dimensionality tree structure character string; calculating the similarity between the vector data of the vector database and the natural language problem of the user by using a retrieval enhancement technology to obtain a problem-multi-dimensional expression pattern sample corresponding to the vector; inputting the content as a cue word into a large model to generate a multi-dimensional expression; performing grammar and illusion inspection on the multi-dimensional expression to obtain an executable multi-dimensional expression; and performing reverse analysis to obtain queried rows, columns, pages and conditions in the multi-dimensional expression, and completing natural language query.
Owner:BEIJING UNION UNIVERSITY

Multi-protocol file one-way import method

The invention relates to the technical field of file one-way import, and discloses a multi-protocol file one-way import method, which comprises the following steps: S1, protocol dynamic analysis: based on protocol fingerprint features and a machine learning model, identifying a protocol type of a source end input data stream, and generating a protocol adaptation rule; s2, intelligent fragmentation of the file: dynamically calculating a fragmentation strategy according to a protocol type and a network state, splitting the file into a plurality of fragments and distributing the fragments to different protocol transmission channels; s3, multi-protocol parallel transmission is carried out; s4, performing adaptive fault-tolerant recovery; and S5, recombining and checking the target end. According to the invention, through the protocol fingerprint feature extraction and the hybrid neural network model, and through capturing the message header flag bit, the encryption algorithm identifier and the time sequence interaction behavior in the protocol handshake stage, accurate identification of multiple protocol types and reverse analysis of the private protocol are realized, and the anti-interference capability and the dynamic adaptation efficiency of protocol identification are improved.
Owner:ZHENGZHOU UNIV

Web reverse analysis method based on large model and dynamic feedback

The invention relates to the technical field of Web security and artificial intelligence, and discloses a Web reverse analysis method based on a large model and dynamic feedback, which comprises the following steps: constructing an AST-LLM joint analysis engine, defining an AST node importance evaluation formula, carrying out weight quantification on AST nodes, and screening out key functions or code snippets in reverse analysis; semantic analysis is carried out through LLM in combination with context, and candidate names of confusion variables are generated; semantic similarity calculation is carried out on the key nodes screened out through weight quantification and candidate variable names generated by LLM, and semantic grouping is carried out on confusion variables associated with AST nodes through a spectral clustering algorithm; a code structure is optimized through AST node remapping, and codes are corrected through real-time interaction; a closed-loop optimization system of LLM and log instrumentation is constructed, and an optimization engine is dynamically fed back; the method has the advantages that multi-state confusion is resisted, the semantic consistency of reverse output and original logic is ensured, the problem of reverse analysis distortion in a dynamic confusion scene is solved, and the readability, the performability and the maintainability of codes are kept.
Owner:中科天玑数据科技股份有限公司

Bronchoscope cleaning and tracing intelligent management system and method based on Internet of Things technology

The invention discloses a bronchoscope cleaning and tracing intelligent management system and method based on the Internet of Things technology, and relates to the technical field of medical equipment. The invention discloses a bronchoscope cleaning and tracing intelligent management system based on the Internet of Things technology. The bronchoscope cleaning and tracing intelligent management system comprises a cleaning data collection module, a cleaning data reverse analysis module and a cleaning data backtracking module. By setting the cleaning equipment set and the cleaning operation model, comprehensive monitoring and data collection of the bronchoscope cleaning process are realized, the accuracy and efficiency of cleaning work are improved, and cleaning judgment is performed through dense connection of the model and a twin network; the analysis capability of the cleaned sample is enhanced, and a cleaning feedback result is obtained through multi-scale feature extraction; the traceability of the cleaning data is realized, the cleaning data and the feedback result are stored in the database, management and query are facilitated, and continuous monitoring and improvement of the cleaning quality are ensured.
Owner:JILIN UNIV FIRST HOSPITAL

Intelligent office space management method based on digital twinborn technology

The invention relates to the technical field of digital twinning and environment control, and discloses an intelligent office space management method based on a digital twinning technology, which comprises the following steps: constructing a lumped parameter network model to calculate theoretical state data, calculating state residual vectors of actually measured data and theoretical data, and calculating the state residual vectors of the actually measured data and the theoretical data; the residual error is decoupled into a transient load disturbance component and a structure parameter drift component through a dual-band filter, the transient component is reversely projected into an equivalent disturbance parameter injection model by using a model inverse dynamics principle for advanced deduction, and a model structure parameter matrix is identified and corrected by using a gradual state component; according to the method, through frequency domain decoupling and reverse analysis of the state residual error, software-defined perception of an unmeasurable hidden load and internal adaptive correction of model aging drift are realized, response lag of a large thermal inertia system is avoided, and the self-evolution ability of the system in the whole life cycle is improved without extra hardware investment.
Owner:SHENZHEN TIANPEI SPACE TECHNOLOGY SERVICE CO LTD

Advanced network threat intelligent detection and defense system

The invention discloses an advanced network threat intelligent detection and defense system and method in the technical field of network defense. The system comprises a data acquisition module which analyzes encrypted traffic through a deep packet inspection technology and marks space-time metadata; the feature extraction module is used for constructing a node behavior association graph by adopting a multi-scale sliding window and a graph neural network; the detection engine module integrates multi-model parallel analysis of LSTM, random forest and the like, and dynamically fuses detection results through an entropy weight method; and the defense execution module is used for realizing flow cleaning and virtual trapping node deployment based on an SDN (Software Defined Network) technology. The method comprises the steps of protocol extension field reverse analysis, covert channel time sequence correlation analysis and dynamic network topology adjustment. According to the method, the encryption APT attack detection accuracy reaches 98.7%, the false alarm rate is reduced to 0.15%, the defense strategy effective time is shorter than 1 second, and the method is suitable for complex network environments such as cloud computing and industrial Internet of Things.
Owner:GUOANYUN (XIAN) TECH GRP CO LTD

Comprehensive energy supply system reliability detection method considering state reverse analysis

The invention discloses a comprehensive energy supply system reliability detection method considering state reverse analysis. The method comprises the following steps: firstly, constructing an energy conversion model of a multi-energy coupling element in a comprehensive energy supply system; thirdly, constructing an output power model of the multi-energy coupling element based on the energy conversion model of the multi-energy coupling element and initial input energy of the comprehensive energy supply system; and finally, the reliability of the comprehensive energy supply system is rapidly detected by using the output power model of the multi-energy coupling element. The method provided by the invention focuses on the component combination of which the output power is smaller than the energy demand to realize the rapid evaluation of the reliability of the comprehensive energy supply system.
Owner:ZHEJIANG UNIV CITY COLLEGE

Correlation analysis method and system for rotation flexibility test data and assembly parameters of self-aligning roller bearing

The invention discloses a self-aligning roller bearing rotation flexibility test data and assembly parameter correlation analysis method and a self-aligning roller bearing rotation flexibility test data and assembly parameter correlation analysis system. According to the method, bearing assembly parameters and multi-dimensional time sequence data of a rotation test are acquired through a system, and a quantitative correlation model between the bearing assembly parameters and the multi-dimensional time sequence data is constructed by using a machine learning algorithm. On the basis of the model, reverse analysis can be carried out on abnormal test data, and an assembly deviation source which causes poor flexibility is accurately positioned; target parameters can be input in the process design stage, and the expected performance of the bearing can be predicted in the forward direction. The corresponding system integrates a data acquisition module, a model analysis module, an application output module and a process feedback control module, and is integrated with a production line control system. According to the method, traditional qualitative judgment depending on experience is converted into quantitative analysis driven by data and models, intelligent closed loop from quality detection and root diagnosis to process optimization is achieved, and the consistency of bearing assembly quality and the intelligent level of process control are remarkably improved.
Owner:LINQING FANGTE BEARING CO LTD

Assembly code-oriented malicious software intelligent classification detection method and system

The invention discloses an assembly code-oriented malicious software intelligent classification detection method and system. A malicious code sample is obtained from the malicious code data set, an assembly code is obtained through reverse analysis, an API calling sequence is extracted from the assembly code of the assembly file through a regular expression, and a type label is added and stored in a CSV file; carrying out feature vectorization on the API calling sequence by using a Doc2vec algorithm; constructing a GRU attention classification model based on the vectorized API calling sequence, verifying the model by using a verification set, and compiling the GRU attention classification model; and training the training data by using the compiled GRU attention classification model to realize the classification of malicious software behaviors, and evaluating the model performance by using the test set. According to the scheme, the accuracy and robustness of malicious code analysis are enhanced.
Owner:STATE GRID LIAONING ELECTRIC POWER CO LTD +1

Defect detection device for basket-type rotor using AI

The purpose of the present invention is to provide a defect detection device for a basket-type rotor, said defect detection device being capable of easily and reliably estimating and reporting the presence or absence of a broken bar or an air hole (defect), which is likely to be present in a conductor rod formed in a locking slot, using an AI without requiring a skilled person. The scale of the defect and the position of the defect can be estimated and reported. This defect detection device for a basket-type rotor is provided with: a fluctuating magnetic field generation means (1) and a detection means (2) that are disposed so as to be able to straddle one conductor rod of a basket-type rotor (R); a rotor model data output means (3) for creating rotor models (M1-Mn) and outputting configuration data (K1-Kn) of the rotor models (M1-Mn); a rotor model analysis means (4) for receiving the structure data (K1-Kn) and AC power source data (AC), performing numerical analysis on the current value induced in the second coil, and generating a large amount of learning data (L1-Ln); and a neural network (5) and a defect information reporting means (6) that are optimized by the learning data (L1-Ln) provided in advance, receive the time-series current value data (C) detected by the detection means (2), perform inverse analysis, and output defect state estimation information indicating the presence or absence of a defect, the scale, and the position of the conductor bar existing in the basket-type rotor (R).
Owner:YAMANAKA SANGYO KK +2

Intelligent evaluation system for tensile property of down jacket fabric based on big data analysis

The invention discloses an intelligent evaluation system for the tensile property of a down jacket fabric based on big data analysis, relates to the technical field of down jacket fabric tensile testing, and solves the problems that an original detection mode is too high in subjectivity and low in precision. According to the invention, deep detection is carried out on an abnormal area from different angles through the front analysis end and the back analysis end; the front analysis end accurately analyzes the spacing parameters of the hole sites between the two groups of circles by constructing an abnormal center circle and an outer circle, and can accurately judge whether the front test of an abnormal area is normal or not; and the reverse analysis end generates a diffusion interval and performs scale error confirmation by confirming the diffusion degree of the silk threads wound in the hole sites in the reverse area, so that the reverse test condition of the abnormal area is comprehensively evaluated, and the comprehensive and three-dimensional evaluation of the tensile property of the down jacket fabric is realized.
Owner:HANGZHOU MANSON SUPPLY CHAIN MANAGEMENT CO LTD

Specific information studying and judging method and system based on large language model

The invention provides a specific information research and judgment method and system based on a large language model, and the method comprises the steps: obtaining information data through the combination of API access, a reverse analysis APP and a web crawler, carrying out the cleaning and standardization processing of the information data, and storing the information data into a distributed database for unified management; the method comprises the following steps: preprocessing information data based on a large language model, extracting basic attribute information of a to-be-analyzed object in the information data by adopting a mode of combining pre-training and fine tuning, and constructing a relationship knowledge base based on the basic attribute information; obtaining online features of the to-be-analyzed object through the online dimension, obtaining offline features of the to-be-analyzed object through the offline dimension, and carrying out feature fusion on the online features and the offline features to obtain three-dimensional attribute description; and based on a sliding window technology, carrying out information research and judgment analysis on the text determined by the relation knowledge base and the three-dimensional attribute description, and carrying out real-time prompting on abnormal information according to a research and judgment analysis result.
Owner:NAT COMP NETWORK & INFORMATION SECURITY MANAGEMENT CENT

Unknown protocol reverse analysis and feature extraction method

The invention discloses an unknown protocol reverse analysis and feature extraction method, which comprises the following steps of: extracting a message mixed with an unknown protocol data packet, and dividing the extracted message into tokens with additional attributes according to bytes by adopting an ABNF grammar core rule mapping table; carrying out similarity calculation on tokens in different messages to obtain token format distances of the tokens among the different messages; based on the token format distance, a text similarity measurement algorithm is adopted, and the message format distance between different messages is obtained; clustering different messages by adopting a DBSCAN (Density Based Spatial Clustering of Applications with Noise) algorithm based on the message format distance; and for each message type formed by clustering, extracting area content with area similarity value jump in the message, and marking the area content as a feature character of an unknown protocol. According to the method, a protocol reverse technology is utilized, and reverse analysis and feature extraction of an unknown protocol can be effectively realized.
Owner:JIANGSU ELECTRIC POWER INFORMATION TECH

Industrial network protocol data packet capturing and analyzing method and system

The invention relates to a method and a system for capturing and analyzing industrial network protocol data packets, which solve the technical problem that the existing industrial protocol analysis technology is poor in adaptability to unknown, private or non-standard protocols, and the method comprises the following steps: capturing and screening network data packets for protocol identification. If the protocol is the known protocol, calling a preset analyzer for analysis; if the protocol is an unknown protocol, extracting a protocol feature vector of the protocol, obtaining a candidate protocol and confidence through reasoning of a neural mapping model, and dynamically judging whether to start interactive reasoning to obtain user feedback, calibrating a parameterized protocol template and instantiating to generate an executable analysis rule according to the structural matching degree of an existing analyzer; and finally, registering and using the new analyzer to realize adaptive learning and analysis. The method has the following effects: intelligent identification of an unknown protocol, dynamic construction of an analyzer and system self-expansion are autonomously realized through an adaptive learning mechanism, and normal form upgrading from manual reverse analysis to system autonomous evolution is completed.
Owner:NINGBO WANDE HI TECH INTELLIGENT TECH CO LTD