594 results about "Hide markov model" patented technology

The invention relates to the technical field of user behavior analysis, and discloses a user behavior intelligent analysis and management system based on a big data technology. The system comprises a user behavior data acquisition module for acquiring behavior data in a multi-dimensional scene; the behavior feature intelligent recognition module is used for extracting features by using a deep neural network and a time sequence analysis algorithm and generating a map; the behavior pattern dynamic analysis module is used for analyzing pattern changes through dynamic clustering and a hidden Markov model; the abnormal behavior autonomous detection module is used for detecting anomalies based on the multi-dimensional anomaly score and an adaptive threshold value; and the behavior management intelligent optimization module is used for optimizing a management strategy by utilizing a reinforcement learning algorithm. In addition, a behavior data archiving module is further arranged to guarantee safe storage of data. The system can comprehensively collect and analyze user behavior data, accurately detect abnormity, intelligently optimize a management strategy, improve user experience, system safety and operation efficiency, and have wide application value in multiple fields.

The invention relates to the technical field of intrusion detection, in particular to a network threat detection method and system, and the method comprises the following steps: building a threat path logic diagram through collecting field dependency items, action trigger timestamp items and action propagation hop count items of an attack behavior chain, and matching field dependency items among nodes based on a graph theory algorithm to obtain a threat path logic diagram; and detecting a mutual exclusion logic field combination, and generating a logic diagram structure with a connecting edge and a mutual exclusion mark. In the method, a threat path logic diagram is constructed by fusing field dependence, action timestamps and propagation hops, graph theory identification field mutual exclusion combination enhances cross-protocol attack chain analysis, and hidden Markov modeling state transition probability verifies time sequence continuity and path length. And performing dynamic time warping alignment on forward and reverse instruction sequences to extract semantic offset, overlapping rate and time sequence entropy, and performing non-linear score classification based on an isolated forest to detect an adversarial sample, topological structure analysis, time sequence verification, instruction alignment and non-linear classification to cooperatively identify a composite attack with field mutual exclusion and time sequence confusion.

The invention discloses a data security dynamic evaluation system and a protection method, belongs to the technical field of information security, and is used for solving the problem of terminal equipment access control and behavior risk dynamic collaborative protection. The method comprises the following steps: generating fingerprints through terminal equipment features, verifying authorization, inputting access feature slices into a time sequence model by authorized terminal equipment, generating a trust score based on cosine similarity of a behavior sequence and a prediction sequence, and constructing a Markov model to dynamically select an authentication mode according to the trust score; calculating a risk index by combining network and geographic information, and distributing the risk index to a real or virtual environment; and the unauthorized terminal equipment distributes the virtual environment after registration. Differentiated monitoring is carried out, a time sequence library is established in the virtual environment, and doubt scores are generated through sequence matching; the state deviation of the real environment is calculated through a hidden Markov model, and the risk score is generated by fusing the multi-dimensional features. And based on the result management authority, the suspicion terminal equipment isolates and shrinks the authority, the compliance terminal equipment authenticates and migrates, and the access is regulated and controlled according to the minimum privilege principle and the time window mechanism.

The invention relates to the technical field of multi-modal data, provides a pilot competency dynamic evaluation method, system and device based on multi-modal data and a storage medium, and solves the problems of low accuracy of pilot competency evaluation and poor pertinence of training guidance. The method comprises the steps of collecting flight control data, physiological signal data, psychological assessment data, subjective scale data and international civil aviation organization core competency information, performing alignment fusion on multi-source data by adopting a time synchronization algorithm, and identifying an attention fixation mode based on a hidden Markov model. And constructing a workload index by fusing a subjective scale and a physiological entropy value, inputting the multi-modal features into a pre-trained competency assessment model, outputting three levels of psychological assessment indexes including a basic ability layer, a dynamic presentation layer and a risk early warning layer, and finally generating a personalized training report. According to the invention, the accuracy of pilot competency evaluation and the pertinence of training guidance are improved.

The invention discloses an exercise and cognition ability assessment method, system and device, and the method comprises the steps: obtaining real-time exercise information, including real-time joint angle information, real-time gait information, real-time attention information and real-time decision speed information, of a user; constructing a physiological-behavior coupling model based on a hidden Markov model, and generating a joint evaluation index by inputting real-time motion information; performing feature extraction on the real-time motion information by using a hierarchical feature extraction model to obtain a motion feature vector and a cognitive feature vector; performing fusion processing on the feature vector and the joint evaluation index, and outputting abnormal state information including motion abnormality and cognitive abnormality; behavior abnormity is detected through the dynamic threshold model, a real-time feedback instruction is generated in combination with a preset feedback rule, and finally user training task parameters are dynamically adjusted according to the instruction. According to the method, through multi-dimensional data fusion and a dynamic evaluation mechanism, cooperative monitoring and self-adaptive training regulation and control of motion and cognitive competence are realized.

The invention discloses an error correction system and method for marine environment observation data. The error correction system comprises a data acquisition module, a compensation modeling module, an error analysis module, a data compensation module, a data fusion module and a feedback optimization module. The data acquisition module acquires ADCP flow measurement, GPS, IMU, temperature, pressure and water quality monitoring data. And the error analysis module detects a drift error by using Kalman filtering and a hidden Markov model, and analyzes an environmental error based on a long short-term memory network. The data compensation module optimizes a compensation model and improves data precision. And the data fusion module fuses multi-sensor data by adopting a particle filter and a Bayesian optimization algorithm. The feedback optimization module dynamically adjusts the weight of the compensation model according to the error correction data, and improves the adaptability of the system. According to the invention, the accuracy of ocean current monitoring data is improved, and more reliable data support is provided for underwater environment research.

The invention discloses a textile fabric tearing strength detection method and system, and relates to the technical field of fabric detection.The method comprises the steps that fabric microstructure, macromechanics and component data are synchronously collected through a multi-mode sensing system, and detection modes are dynamically switched based on a real-time recognition result; inputting the space-time correlated defect data into the physical constraint enhanced prediction model to generate a crack propagation trend and a tear strength prediction value; wherein the prediction model is fused with a Griffith crack propagation theory and a hidden Markov model, and double constraints of a material mechanics law and dynamic defect evolution are realized; a non-contact detection module and a flexible contact detection module work cooperatively, and a process optimization scheme is output in combination with an edge and cloud distributed architecture.

The invention relates to the technical field of early warning decision making, in particular to an agricultural disaster early warning decision making method and system, and the method comprises the following steps: obtaining a structure parameter set through a multispectral sensor, carrying out the smooth processing of a sliding window, marking the direction consistency, inputting a hidden Markov model, calculating the transition probability, recognizing a stage trigger point, and outputting a label. And matching a physiological and meteorological time sequence to generate a response mapping table, extracting a trend overlapping section mark impact window, judging a disaster grade in combination with multi-factor weighted sorting, and outputting an early warning instruction. According to the invention, through continuous observation of growth parameters and smooth processing of time sequence data, analysis of dynamic consistency of structural indexes, identification of growth mutation, alignment of physiological and meteorological factors, extraction of trend overlapping sensitive areas, and superposition of residual errors to lock risk time windows, the sensitivity and pertinence of disaster early warning are improved, and the risk of misinformation and missing report is reduced. Fine data support is provided for management, and risk management and control scientificity and initiative are enhanced.

The invention relates to the technical field of biomedicine, and discloses a female private rehabilitation training system integrating a breathing method and neural motor control, and the system comprises a data collection module which is used for collecting physiological data of a user; the personalized training scheme generation module is used for generating a personalized nerve-muscle-fascia training scheme; the nerve-muscle synchronous resonance training module is used for constructing a time sequence matching model and generating an adaptive training dynamic control instruction; the space-time adaptability training module is used for adjusting training duration, intensity and stimulation frequency; the multi-dimensional nerve-muscle feedback fusion module is used for constructing a feedback response model; and the fascia synchronous activation and relaxation module is used for coordinating the tension relationship between the fascia and the muscle system. According to the method, feature matching is carried out on an electric activation heat map matrix through the convolutional neural network, analysis of a myoelectricity response state transition probability is carried out in combination with a hidden Markov model, and stimulation parameters and respiratory rhythm are optimized in real time according to a training process.

The invention relates to the technical field of air traffic management, and particularly provides an airport scene aircraft taxiing conflict real-time prediction and dynamic scheduling method, which comprises the following steps: collecting the motion state of an aircraft and airport road network data, and generating the original trajectory of the aircraft by adopting a hidden Markov model; predicting a future taxiing trajectory of the aircraft to obtain a predicted trajectory; screening potential conflict aircrafts by adopting a dynamic R-Tree spatial index technology, judging whether tracks between the potential conflict aircrafts are intersected or not, and generating a dynamic risk value; executing a dynamic scheduling decision based on the dynamic risk value, and generating an aircraft bypass path by adopting a path generation algorithm; rolling time domain control is adopted, and a local path is re-planned based on data obtained in real time. According to the method, prediction of the taxiing trajectory of the aircraft is fully considered, the risk value of the taxiing conflict of the aircraft is pre-judged in advance, and dynamic path adjustment is performed, so that the labor cost is reduced, and the efficiency and safety of airport ground operation are improved.

The invention relates to the technical field of image state recognition, in particular to an unhooking and rehooking AI accurate recognition grabbing system and method based on pattern recognition, in the system, node construction is conducted through contour changes, boundary difference values and gray level dynamic states of a hook assembly in an image sequence frame, edge displacement accumulation analysis is combined, meanwhile, through a graph neural network, an image sequence frame is obtained, and the image sequence frame is obtained. Cosine values and coordinate difference values between nodes are subjected to combined comparison, and a path hopping sequence is constructed, so that the response sensitivity to state abrupt change is enhanced, a key path of morphological evolution can still be stably extracted under the condition of complex background interference or local shielding, the anti-interference performance and fault tolerance of space path identification are effectively improved, and the space path identification accuracy is improved. Statistical modeling is further carried out on state rate sudden change points through a hidden Markov model, paragraph merging and invalid fragment removing operation are carried out on abnormal point segments by matching a standard state mode, a state label sequence is constructed, and accurate division of high-confidence and multi-segment continuous states is achieved.

The invention discloses a mining equipment energy consumption prediction method, and relates to the technical field of mining equipment energy consumption prediction.The mining equipment energy consumption prediction method comprises the steps that through multi-dimensional data collection, operation, process and environment parameters are collected through a sensor cluster; noise reduction is carried out through a generative adversarial network in combination with empirical mode decomposition, and data is restored through a space-time interpolation network; identifying working conditions and extracting features by means of a hidden Markov model in combination with an attention mechanism; a cross-device transfer learning framework is constructed, and a cloud training general model is combined with local data fine tuning; the edge end deploys a lightweight model for real-time prediction, and the cloud end generates a global energy-saving strategy; through digital twinborn visualization, a model and a strategy are automatically corrected based on SHAP value analysis. The equipment idling rate is reduced; the unit energy consumption of the crushing link is reduced; the abnormal response time is shortened; and the prediction precision and the system adaptability are remarkably improved.

The invention relates to the technical field of network security management, in particular to a network security management system based on big data, which comprises a data acquisition and integration unit, a dynamic threshold setting unit, a fuzzy comprehensive evaluation unit, a machine learning optimization unit and a control unit. The acquisition process has intelligent characteristics and adopts a block chain to cache data, the dynamic threshold setting unit constructs a model to adjust a threshold by combining a hidden Markov model, kernel density estimation and a reinforcement learning algorithm for different network crime types, and the fuzzy comprehensive evaluation unit determines a membership function and distributes weights by applying a fuzzy mathematical algorithm. And the machine learning optimization unit uses historical data to train and update the model, assists in case-related account determination, effectively solves the problems of missed determination and misjudgment caused by a fixed threshold value in traditional account risk assessment, and improves the accuracy of network criminal account risk assessment.

The invention relates to the technical field of network security, and discloses a response processing method and system for a network security event, and the method comprises the steps: carrying out the feature extraction and time sequence behavior clustering of network flow data, and obtaining a behavior segment and a corresponding time sequence feature; according to the behavior segments and the time sequence features, a hidden Markov model is adopted, and the causal relationship confidence degree between the adjacent behavior segments is calculated; according to the behavior fragment and the causal relationship confidence coefficient, attack chain reconstruction and key path analysis are carried out to obtain an attack key path; inputting the attack key path into a pre-threat mode library for threat matching to obtain an attack intention prediction result; and generating a dynamic response strategy according to the attack intention prediction result, and executing the dynamic response strategy by adopting a streaming processing engine. According to the method, the attack detection precision and the defense response efficiency in a complex attack scene can be remarkably improved, and a self-adaptive and reliable technical scheme is provided for network security protection, so that the security and the stability of network operation are ensured.

The invention provides a method for identifying a power grid frequency signal assessment standard, and the method comprises the steps: constructing a system architecture composed of a master station, a substation and a communication network, and achieving the initialization of equipment through a finite-state machine; the method comprises the following steps: collecting power grid frequency, power generation side frequency difference and communication state multi-dimensional data, processing signals by applying median filtering, a sliding window and an EWMA algorithm, introducing fuzzy logic to evaluate a system state, and dynamically adjusting a response strategy; an improved PID algorithm is adopted to track frequency change, feed-forward compensation and PSO parameter optimization are combined, a hidden Markov model is utilized to predict a communication fault, and local mode switching is triggered in advance; main station, mixing and local three-state switching is carried out according to communication states and load changes, and a frequency modulation dead zone is automatically adjusted according to power grid loads through a dynamic threshold value self-adaptive algorithm; the control effect is verified by using a digital twinning technology; and the safety and reliability of the system are guaranteed by optional quantum encryption and active-active redundancy design. The whole scheme effectively reduces the power loss of power generation enterprises, and maintains the safe and stable operation of a power grid.

A sequence of polymer units in a polymer (3), eg. DNA, is estimated from at least one series of measurements related to the polymer, eg. ion current as a function of translocation through a nanopore (1), wherein the value of each measurement is dependent on a k-mer being a group of k polymer units (4). A probabilistic model, especially a hidden Markov model (HMM), is provided, comprising, for a set of possible k-mers: transition weightings representing the chances of transitions from origin k-mers to destination k-mers; and emission weightings in respect of each k-mer that represent the chances of observing given values of measurements for that k-mer. The series of measurements is analysed using an analytical technique, eg. Viterbi decoding, that refers to the model and estimates at least one estimated sequence of polymer units in the polymer based on the likelihood predicted by the model of the series of measurements being produced by sequences of polymer units. In a further embodiment, different voltages are applied across the nanopore during translocation in order to improve the resolution of polymer units.

The invention relates to the technical field of sealing performance testing, in particular to a breather valve performance online testing method for oil and gas storage and transportation, which comprises the following steps: acquiring a vibration signal of a breather valve body, a multi-band acoustic signal of a valve port and a total pressure signal in a storage tank; performing multi-scale complex wavelet decomposition, and constructing a time frequency-energy correlation feature tensor; the total pressure signal and the time frequency-energy correlation characteristic tensor serve as a combined observation value and are input into a preset continuous Gaussian mixture hidden Markov model containing four hidden states of sealing, transient micro-leakage, continuous leakage and full-amount opening, and the posterior probability is calculated; and calculating to obtain a real-time leakage rate. According to the method, the opening pressure can be accurately determined, the real-time leakage rate can be quantitatively calculated after the leakage state is recognized, comprehensive and accurate quantitative online evaluation of core performance parameters of the breather valve is achieved, and the multi-source information fusion degree and the anti-interference capacity are improved.

The invention provides an intelligent control method and system for a refrigeration house, and relates to the field of control. A refrigeration house space thermodynamic diagram model is constructed based on temperature measuring points, and a historical temperature sequence, a house door opening and closing state sequence, cargo warehouse-in and warehouse-out records and external environment parameters are obtained; predicting a temperature change track of each node in a future control time domain by using a space-time diagram convolutional network; establishing an equipment health state evaluation model based on a hidden Markov model, evaluating the health state of each refrigeration compressor unit and quantifying the health state into an equipment health index; and solving the rolling optimization objective function in the control time domain to obtain an optimal start-stop time sequence and operation power combination instruction of each refrigeration compressor unit and auxiliary equipment, and issuing the combination instruction to a corresponding field controller for execution. The temperature change of each area in the refrigeration house can be accurately predicted, the operation load can be reasonably distributed according to the health condition of the unit, the service life of equipment is effectively prolonged, and the sudden failure risk and the maintenance cost of the whole life cycle are reduced.

The invention discloses a distribution line early-stage fault time sequence hidden Markov modeling and identification method and system based on multistage evolution characteristics, and belongs to the field of distribution line early-stage fault identification. Comprising the steps of obtaining a current waveform sample sequence of an early fault in a distribution line; for each current waveform sample in the sequence, extracting a multi-dimensional time-frequency feature, and constructing a feature vector of each sample; performing fault stage identification on each sample by using the first-level hidden Markov model group, and outputting a fault stage tag sequence corresponding to each sample; combining the fault stage label sequences of the current sample and a plurality of previous historical samples to form a stage label sequence window; and respectively inputting the stage label sequence window into a second-level tree line fault hidden Markov model and a second-level non-tree line fault hidden Markov model, calculating a corresponding first average log-likelihood value and a corresponding second average log-likelihood value, comparing the two average log-likelihood values, and judging whether a current sample belongs to a tree line early fault or not.

The invention discloses a digital archive multi-protection-based data security transmission method, and relates to the field of data security transmission, and the method comprises the steps: generating a random seed in real time based on a quantum state, carrying out the iterative blocking of the quantum seed through combining with Logistic chaotic mapping, outputting variable-length secret key fragmentation, carrying out the symmetric encryption of archive data through employing a lightweight SM4 algorithm, and carrying out the encryption of the archive data. Obtaining encrypted data of the fragments; a behavior anomaly probability is calculated through a hidden Markov model, a risk score is calculated through a safety interval, and when a score value exceeds a safety threshold value, a grading response is triggered; key fragments are generated by adopting n nodes, at least k fragments can reconstruct signatures to monitor the node state of the block chain, and when the node anomaly rate exceeds a node threshold value, a three-layer architecture is automatically switched. The method has the advantages that an active multi-protection system is constructed through a quantum dynamic key, risk-driven hierarchical response and block chain disaster recovery switching, and quantum attack resistance and dynamic adaptation to transmission of network risks are realized.

The invention provides an examination room multi-source data fusion abnormal behavior intelligent analysis method and system, and relates to the technical field of artificial intelligence, and the method comprises the steps: collecting examination room video and audio data, and carrying out the multi-view skeleton point fusion and sound source positioning to extract features; constructing a hidden Markov model and kernel density estimation to carry out abnormal behavior identification; calculating a seat correlation degree based on a spatial weight coefficient and wavelet decomposition to identify multi-person cooperative cheating; and early warning information is pushed in real time. According to the invention, the cheating behavior identification accuracy is improved, and effective detection of multi-person cooperative cheating behaviors is realized.

The invention discloses an intelligent fault diagnosis and early warning method for an electrical automatic composting process system, and relates to the technical field of intelligent monitoring. Sensor data in a composting process is collected, high-frequency noise is removed by adopting sliding window filtering, and a timestamp is synchronized to align multi-dimensional signals; based on a hidden Markov model, dividing composting stages of temperature rise / high temperature / decomposition period, and extracting time domain and frequency domain features for different working conditions; and an online K-means + + algorithm is adopted to initialize a clustering center. According to the method, multi-dimensional sensor data such as temperature, humidity and oxygen content in the composting process are collected in real time, the online K-means + + algorithm and the density peak value clustering technology are utilized to dynamically adapt to the time-varying characteristics of composting parameters, outliers caused by sensor drift or dust interference are effectively filtered, the sensitivity of a model to noise data is remarkably reduced, and the method has the advantages of being high in reliability and high in reliability. It is ensured that the composting system can still operate stably under complex working conditions, and the risk of fermentation interruption or material decay caused by parameter abnormity is reduced.

The invention discloses an electric pump control method and system based on instruction perception, and relates to the technical field of electric pump control, comprising: starting a voice recognition module, a wireless communication module and a sensor acquisition module, and establishing a bidirectional communication link with a remote controller; an AI-driven noise reduction algorithm is adopted to pre-process the environment audio collected by the microphone array, and an improved hidden Markov model is utilized to perform keyword recognition on the pre-processed audio to obtain a voice instruction signal; the remote controller sends a control instruction to a receiving end, analyzes the instruction content, records the current communication channel quality, dynamically adjusts the transmitting power, the frequency hopping strategy or the coding mode according to the channel quality, and ensures stable communication between the remote controller and the electric pump; and the main control unit simultaneously receives a voice command signal and a remote controller command signal, sets a command priority rule in combination with data acquired by the sensor, and executes corresponding operation according to the priority.

The invention provides a scanning method and system for hidden asset identification in an electric power industrial control network, and aims to solve the problem that silent, non-registered or illegal access equipment is difficult to discover by the existing asset surveying and mapping means. According to the method, multiple protocol induced detection messages are injected into a target network, equipment response data are collected, feature vectors are extracted, and abnormal equipment behaviors are identified by using an unsupervised clustering and anomaly detection algorithm; and meanwhile, in combination with a graph neural network and a hidden Markov model, modeling is performed on a network communication chain structure and a historical behavior sequence, and potential hidden asset nodes are deduced. According to the method, active discovery and risk reasoning of hidden assets can be realized on the premise of not influencing industrial control services, and the method is suitable for industrial control scenes such as transformer substations and dispatching centers in the power industry and has high safety, intelligence and feasibility.

The invention provides a highway pavement intelligent maintenance scientific decision-making system and a decision-making method thereof. A data collection and preprocessing module collects multi-source data in a public network and a highway management intranet, and performs cleaning, integration and dimensionality reduction by using a specific algorithm. And building an automatic road detection system based on a Python Django framework, determining an index weight by using a rough set theory, calculating PQI and MQI values, and generating a road technical condition evaluation report. And the pavement performance prediction module integrates multi-source data and predicts pavement performance by adopting a composite kernel function and a Gaussian process regression model. And the maintenance decision module determines the maintenance priority through ANP, generates a maintenance demand list in combination with a hidden Markov model, and generates a fund distribution scheme by using a cuckoo search algorithm. And the maintenance benefit evaluation module evaluates the maintenance benefit by adopting a gray ideal solution and a super-efficiency DEA model. And finally, utilizing a WebGL-based 3D visualization technology and an Echarts-based interactive query analysis function to realize road condition information display and auxiliary decision making.

The invention belongs to the crossing field of artificial intelligence and mechanical engineering, particularly relates to a micro-motor fault prediction and health management system, and aims to solve the problems that early faults of a micro-motor are difficult to recognize, degradation modeling is inaccurate and maintenance lags. The system collects multi-source data through high-density sensing, combines denoising reconstruction, composite feature extraction and time-varying weighted fusion to generate health indexes, identifies health stages by using a segmented hidden Markov model, iteratively updates residual life prediction based on a Wiener process, outputs an estimation result with a confidence interval, and links a hierarchical maintenance strategy. And continuous optimization of the model is realized through federal learning. The system improves the fault early warning accuracy and prediction reliability, and reduces the operation and maintenance cost.

The invention discloses a spine tactile sensing system and method based on a multi-modal sensor, and the method comprises the steps: obtaining an original tactile signal, carrying out the preprocessing of the original tactile signal, carrying out the feature extraction based on the preprocessed original tactile signal, and obtaining a spatial distribution feature and a time dynamic feature; on the basis of tail end coordinates collected by forward kinematics of the tail end of the mechanical arm, space mapping of the tactile signals and the spine anatomical structure is constructed, and anatomical position features are obtained on the basis of the preprocessed original tactile signals and the space mapping; constructing task-oriented feature vectors based on the spatial distribution features, the anatomical position features and the time dynamic features, wherein the task-oriented feature vectors comprise a sliding state recognition feature vector and a spine ordinal number positioning feature vector; and constructing a multi-stage adaptive evolution hidden Markov model, and realizing spine ordinal number positioning in combination with the task-oriented feature vector. According to the method, through multi-dimensional feature fusion and dynamic model adjustment, anatomical prior knowledge and real-time tactile signals are combined, and spine segments are accurately recognized.

The invention discloses an operation index determination method and device for an endoscopic surgery, equipment and a storage medium, and can be applied to the technical field of surgical operation data processing. The method comprises the following steps: firstly, acquiring a surgical operation data set of a target operation object for an endoscopic surgery; the surgical operation data set comprises a plurality of pieces of surgical operation data sorted according to a time sequence. Each piece of surgical operation data comprises five-dimensional data, namely endoscope action data, endoscope type data, instrument action data, instrument type data and surgical object data. And constructing a hidden Markov model by using the surgical operation data set. In the hidden Markov model, the surgical operation described by the surgical operation data is the observed quantity, and the surgical state is the state quantity, and based on the hidden Markov model, the statistical principle is utilized to carry out quantitative evaluation on the surgical operation indexes, so that the accurate evaluation of the surgical operation when a doctor carries out the endoscopic surgery is realized, and the reference effectiveness of the operation indexes is improved.

The invention discloses a real-time early warning system for analyzing abnormal behaviors of prison prisoners based on a behavior sequence, and relates to the field of real-time early warning, and the system comprises a data collection module which is used for collecting and obtaining structured data and unstructured data in a prison area; the behavior sequence extraction module generates a feature vector of a behavior atomic unit through three-dimensional convolution spatial-temporal feature extraction, and obtains a behavior vector through feature fusion; the behavior sequence modeling module constructs a behavior sequence through a double-flow LSTM architecture; the anomaly detection module calculates the KL divergence of the behavior codes and a hidden Markov model baseline by constructing the hidden Markov model baseline, and outputs anomaly probability distribution; and the grading early warning module performs grading early warning based on the output abnormal probability distribution. The method has the advantages that by fusing multi-source data and a deep learning technology, the behavior sequence of the prisoner is analyzed in real time, intelligent early warning is performed, the supervision efficiency and safety are remarkably improved, and conversion from passive monitoring to active intervention is realized.

The invention relates to the technical field of building energy saving, and discloses a building energy-saving control system and method.The method comprises the steps that firstly, multi-source environment data inside and outside a building is collected, and a time-space fusion data set is generated through timestamp synchronization and data alignment; dynamic energy consumption characteristics are extracted, and the future energy consumption state of each region is predicted by using a hidden Markov model; decomposing a historical energy consumption mode according to a prediction result and a non-negative matrix factorization algorithm to generate a multi-objective optimization control strategy; and finally, adjusting an equipment operation sequence through a dynamic priority scheduling algorithm and outputting an instruction. The system comprises a multi-source data acquisition module, a feature extraction module, a state prediction module, a strategy generation module, an equipment scheduling module and a feedback correction module. According to the method, energy consumption can be accurately predicted, multi-target optimization control, dynamic equipment scheduling and online strategy correction are realized, the building energy utilization efficiency is effectively improved, energy consumption is reduced, the comfort level is guaranteed, and equipment loss is reduced.