69 results about "Algorithmics" patented technology

The present invention relates to the field of pipeline leakage monitoring. Disclosed is an oil and gas pipeline leakage wave identification and monitoring system. In the present invention, an mCNN is combined with LFLBs for performing feature extraction on an acoustic wave signal collected by a DFB, and the collected data improves information completeness; a three-way parallel one-dimensional CNN used in the present invention exhibits good temporal resolution and sensitivity to high-frequency feature transformations in signals; and the present invention integrates advantages of different scales, enabling the algorithm to learn more features, and incorporating the LFLBs to further extract high-level local features. An mCNN-LFLBs network model of the present invention exhibits significant innovation and advancement on the technical level, and also demonstrates extremely high value in actual application. The network model not only provides a novel and efficient technical means for critical fields such as natural gas pipeline inspection, but also introduces new ideas and methods to research fields related to deep learning and signal processing.

The invention discloses a power transmission line engineering quality defect acceptance method based on generative adversarial and reinforcement learning, and relates to the technical field of power engineering quality detection and intelligent image recognition, and the method comprises the steps: carrying out the sample amplification of original image data of a power transmission line tower through a generative adversarial network module, and obtaining an amplified training data set; constructing a PaFPN feature extraction network according to the amplification training data set, extracting multi-scale defect feature vectors and generating a coding feature matrix; establishing a reinforcement learning agent module, taking the coding feature matrix as state input, learning an optimal defect detection strategy through a Q-learning algorithm, and outputting a defect detection parameter combination; and performing feature fusion on the coding feature matrix to generate a fusion feature vector, inputting the fusion feature vector into a classifier network, and outputting a defect category label and a confidence score of the power transmission line project quality. According to the invention, the automation level and the detection precision of power transmission line project quality defect acceptance are improved.

The invention provides an industrial graph construction method and system based on scene type marketing, and relates to the technical field of industrial graph construction, and the method comprises the steps: processing a media text through a BERT pre-training model to generate a text data set, processing scene data through a space-time calibration algorithm to generate a behavior data set, and summarizing to generate an unstructured marketing data set. Generating a multi-modal marketing scene data set in combination with the structured marketing data set; processing the multi-modal data set by adopting a stream-batch integrated framework and an entity disambiguation technology, and constructing a four-dimensional data lake; constructing a three-dimensional feature library and training a marketing scene weight model; a data lake is mapped to a graph database, an industrial chain topological structure is formed, node relation strength is adjusted based on a weight model, node implicit features are learned through a GraphSAGE algorithm, and a scene-sensitive industrial graph topological structure is generated, so that industrial entity relations in different marketing scenes can be reflected in real time, and the marketing efficiency is improved. And the accuracy of the industrial map in marketing decision making is improved.

The invention belongs to the technical field of data processing, and discloses an active intelligent operation and maintenance monitoring method for a data center, which comprises the following steps: step 1, component modeling and topology configuration; 2, carrying out distributed health detection and data acquisition; 3, performing real-time health assessment and anomaly detection; 4, performing intelligent alarm and root cause analysis; 5, unified operation and maintenance and closed-loop control are carried out; and step 6, dynamically optimizing the intelligent operation and maintenance strategy. According to the method, a monitoring object and a dependency relationship are clarified through component modeling and topological configuration, and specific scenes, such as multi-mode acquisition, active detection, index pulling, log analysis, coverage message queue theme accumulation and database connection pool exhaustion, of distributed health detection are combined. The quantitative health score is calculated based on the preset scoring model, and by combining with the dynamic baseline learned by the ARIMA or LSTM algorithm, the module abnormity can be actively detected in different periods and weekly updating, and the problems of fault discovery lagging and incomplete monitoring coverage are solved.

The invention relates to the technical field of path planning, in particular to an automatic path planning method for a mechanical arm. According to the technical scheme, the method comprises the steps of environment perception and modeling, global rough planning, learning parameter initialization based on a deep reinforcement algorithm, local fine planning and learning optimization, and path execution and real-time feedback adjustment. The rapid exploration random tree algorithm is adopted for global rough planning, a basic framework is provided for subsequent local fine planning, the global optimal path can be effectively searched through the deep reinforcement learning algorithm, the path is further optimized through local fine planning, the problem that a traditional intelligent path planning algorithm is prone to falling into a local optimal solution is solved, and the path planning efficiency is improved. The multi-sensor fusion technology is used for sensing environment information in real time, the environment model and the state space are updated in time, the robustness and reliability of the system are improved, the mechanical arm can adapt to diversified working environments and task requirements, and more intelligent decision making and path planning are achieved.

The invention discloses a novel power distribution network real-time topology tracing method and system, and the method comprises the steps: carrying out the comprehensive collection of the voltage, current and power of a key node based on a power distribution network SCADA system, and constructing a historical measurement data set containing a topological structure label; designing and training a Transform deep learning model suitable for the characteristics of the power distribution network; the feature space of the Transform model is optimized on the basis of the maximum margin principle; constructing a topological graph model of the power distribution network, carrying out weight assignment, and rapidly tracing and positioning a problem region when a fault or an abnormal condition occurs by using an improved depth-first search algorithm; and constructing a multi-scene topology traceability collaborative decision-making system, and generating a visual traceability report including a fault area topology structure, an influence range and a key equipment state. According to the method, the problems of incomplete data collection, limited learning ability of an identification algorithm, lack of an efficient local tracing mechanism and the like in novel power distribution network topology tracing are solved, and the fault processing efficiency and the operation reliability of the power distribution network are improved.

The invention discloses a memory enhancement action recognition method and system on a Riemannian manifold and a storage medium, and the method comprises the steps: 1, collecting human body action data, and representing the human body action data as a third-order tensor; 2, expanding along three modes to obtain three corresponding matrixes; 3, calculating by adopting a human short-term memory mechanism to obtain a memory enhanced weight matrix; 4, decomposing the weight matrix through a principal component analysis method to obtain a base vector with a weight; 5, recombining, normalizing and mapping to a unit hyper-sphere, and reserving an angle relation; 6, learning modal weight parameters through a Monte Carlo Markov algorithm, and calculating geometric differences between points on the hypersphere; and 7, carrying out human body action classification by adopting a K-nearest neighbor classifier. The method effectively solves the problem of time information loss in a complex scene, and is suitable for various application scenes such as medical health, virtual reality, physical training and the like.

The invention relates to the field of in-vehicle infotainment testing, in particular to a stability testing method, system and device for an in-vehicle infotainment system and a medium, and the method comprises the steps: learning a first weight corresponding to each display area, support operation and a second weight corresponding to each support operation by using a Q-learning algorithm according to a priori knowledge rule set; executing a test step for a predetermined number of times, the test step comprising: determining a target area based on the first weight according to a predetermined rule; determining a target operation corresponding to a target area according to the second weight; and executing the target operation on the target area, judging the execution validity, and generating a stability test report according to an execution result. According to the characteristics of the vehicle machine system interface, the test event is intelligently generated, and the exploration probability is dynamically adjusted, so that the test coverage rate is improved, the test efficiency is also improved, and invalid and repeated tests are reduced.

The invention discloses a wafer defect detection method and a computer program product, and relates to the technical field of semiconductor measurement. The wafer defect detection method comprises the following steps: acquiring a defect image sample with a real defect label or a false positive defect label; the method comprises the following steps: firstly, respectively performing morphological structure analysis on areas to be detected in a defect image sample to determine defect morphological characteristics, performing frequency domain transformation and energy analysis to determine defect texture characteristics and performing boundary line gray gradient analysis to determine defect boundary characteristics, and then integrating the characteristics of the three types of areas to be detected into multi-dimensional characteristics; and learning a mapping relationship between the multi-dimensional features and the defect tags through a decision tree generation algorithm in combination with the defect tags so as to construct a target decision tree model. By means of the mode that the multi-dimensional features cooperatively describe the physical and structural essence of the defects and the decision tree model is combined for classified learning, the real defects and the false positive defects can be effectively distinguished, and the accuracy of wafer defect detection is improved.

Systems and methods are provided for learning normal behavior for user roles of an application running within a cluster of container orchestration platform and based thereon proactively taking action responsive to suspicious events. According to one embodiment, an event data stream is created by an API server of the cluster. The data for each event includes information regarding a request made to an API exposed by the API server with which the event is associated and a user of the application by which the event was initiated. The data is augmented with a role associated with the user and an anomaly threshold for the role. Normal behavior is learned by an ML algorithm of respective user roles by processing the augmented data. When an anomaly score associated with a particular event is output by the ML algorithm that exceeds the anomaly threshold, a predefined or configurable action may be triggered.

The invention discloses an e-commerce platform private domain content intelligent generation and distribution method based on data analysis, and the method comprises the following steps: collecting behavior data, including browsing, clicking, collecting, purchasing and interactive recording, of a user in a private domain scene, and combining the behavior frequency and time information to generate a user behavior representation vector; a user multi-interest representation structure is constructed by using an improved Rocchio algorithm and a clustering mechanism, a heterogeneous graph model is further constructed by combining users, contents and behaviors, random walk is performed based on a graph structure, and node representation is learned by using a DeepWalk algorithm. And carrying out weighted fusion on the user interest vector and the graph embedding result to generate joint user representation, carrying out matching scoring and sorting on candidate contents, and finally realizing accurate pushing and dynamic updating of personalized contents.

The present application discloses a method and device for constructing a digital power system based on multifunctional intelligent agents. The method comprises: respectively extracting feature production element data and control production element data from power data of a power plant side and power data of a power grid side; constructing a target data vector on the basis of a power function requirement, and determining key control production element data associated with the power function requirement; using an artificial intelligence algorithm to learn a mapping function between the target data vector and the key control production element data, constructing a functional operator using the mapping function as a core, and constructing an intelligent agent on the basis of the functional operator; and adding intelligent agents corresponding to a plurality of different power function requirements into a digital power system as power function implementation units. The system can realize data-driven diversified and digital power functions, and implement more accurate capturing of the relationship between data, thereby forming high-value data assets in the power system.

The present invention proposes an AI-driven intelligent modeling method for self-distributing 3D printing parameters of complex geological structures, including the following steps: acquiring multi-source characteristic data of complex geological bodies and performing preprocessing; extracting geological geometric parameters and mapping them into a 3D printing voxel model, and converting them into geometric parameters that can be used for 3D printing; using intelligent algorithms to learn the non-linear mapping relationship between the physical parameters and material parameters of historical complex geological bodies, constructing and training an AI model to predict material distribution parameters; converting the geometric parameters and material distribution parameters into a three-dimensional model of complex geological structures and verifying; exporting parameterized full-model slice data; verifying the performance of the 3D printed complex geological structure model. Compared with the prior art, the present invention realizes the intelligent conversion from data to model, can accurately describe the complex spatial heterogeneity in geological disaster models, improves the adaptability and accuracy of the models, and provides a basis for subsequent prediction and prevention of complex geological body disasters.

1. The name of the design product: artificial intelligence comprehensive experiment box. 2. The use of the design product: for teaching simulation test algorithm learning and practice, visual detection, etc. Teaching product. 3. The design points of the design product: in shape. 4. The picture or photo that best indicates the design points: perspective view.

The application discloses an intelligent pushing method and system based on intention recognition, relates to the technical field of data processing, and implements the following contents: S10, language information, text information and historical information of a user are collected, and the collected information is mapped to a high-dimensional space; S20, a LightGBM algorithm is used to learn high-dimensional features of the information, and then according to feature importance, unimportant features are removed, and the data dimension is reduced; S30, based on a BiGRU-Attention model, output data of step S20 is processed, and key information reflecting a user intention is output; S40, a demand scheme similar to the key information is found from a database, and the demand scheme with the highest similarity is intelligently pushed to the user. The application can effectively improve pushing efficiency and pushing accuracy.

The present application relates to the technical field of data processing, and especially relates to a box-type transformer substation intelligent integrated design method based on cloud data, which comprises: integrated storage of historical system graph data, component data, cabinet type data and heat dissipation scheme data; through a machine learning algorithm, the correlation between each data after classification and arrangement is learned, and the machine learning algorithm is applied to a prediction model; the prediction model is trained, and according to new input system graph data, corresponding component data, cabinet type data and heat dissipation scheme are output; in the data transmission process, encryption processing is carried out, and the encryption processing adopts a transmission layer security protocol. The present application simplifies the design process, improves the accuracy and speed of the design, optimizes the matching of each component and the heat dissipation scheme, solves the parameter complex correlation problem through systematic data analysis, and can ensure the safety of data in the transmission and storage process, so as to comprehensively improve the design efficiency and quality of the box-type transformer substation.

The invention relates to the technical field of data processing, in particular to a box-type substation intelligent integrated design method based on cloud data, and the method comprises the steps: carrying out the integrated storage of historical system diagram data, component data, cabinet type data and heat dissipation scheme data; through a machine learning algorithm, the relevance between the classified and sorted data is learned, and the machine learning algorithm is applied to the prediction model; training the prediction model, and outputting corresponding component data, cabinet type data and a heat dissipation scheme according to newly input system diagram data; in the data transmission process, encryption processing is carried out, and a transport layer security protocol is adopted for encryption processing. According to the method, the design process is simplified, the design accuracy and speed are improved, the matching and heat dissipation scheme of each component is optimized, the problem of parameter complex relevance is solved through systematic data analysis, meanwhile, the safety of data in the transmission and storage process can be ensured, and the reliability of the system is improved. Therefore, the design efficiency and quality of the box-type substation are comprehensively improved.

The invention discloses a navigation method, device and equipment based on a GRPO algorithm and a medium, and relates to the technical field of reinforcement learning, and the method comprises the steps: calculating the average similarity between a current strategy and a plurality of previous iteration strategies based on KL divergence; updating a step length factor through an average reward change rate and an average similarity determined based on a plurality of iterated rewards; determining a gradient estimation correction item based on the gradient estimation of the sampling trajectory, determining target gradient estimation according to the gradient estimation correction item and the original gradient estimation, and updating the current strategy through the target gradient estimation and the updated step length factor; when the current strategy is updated, the importance weight is cut, the target function of the GRPO algorithm is corrected according to the cut weight, the GRPO algorithm is trained based on the corrected function and the updated strategy, so that the intelligent agent learns the optimal strategy based on the trained GRPO algorithm, and the outlet of the labyrinth is determined according to the optimal strategy. Therefore, the stability of the algorithm is improved.

This invention discloses a device type identification method, terminal device, and storage medium based on traffic sampling. It eliminates the need to collect complete device traffic data; device identification is achieved simply by sampling traffic at the gateway. To address the issue of missing traffic features, traditional tensor imputation algorithms learn the embeddings corresponding to tensor rows, columns, and depths, but cannot generalize to unknown rows, columns, or depths. This results in repeated retraining, time-consuming and costly feature imputation. This invention proposes an inductive tensor imputation method that utilizes historical information to learn and generate embedding functions, enabling fast and effective device traffic feature imputation.

The invention discloses an abnormal login detection method and device based on a time ring coordinate system, and relates to the technical field of network security. The method comprises the steps of collecting historical login events of a target host, and extracting login time of each historical login event to form a historical login time sequence; marking the historical login time sequence as a plurality of coordinate points on a time annular coordinate system; dividing the coordinate points on the circumference into a plurality of adjacent point clusters, and calculating the weight of each adjacent point cluster according to the weight of each coordinate point in the adjacent point clusters; and judging whether the current login event is abnormal login or not by comparing the weight of the adjacent point cluster where the coordinate point of the current login event on the time annular coordinate system is located with a preset weight threshold value. According to the method, the abnormal login can be automatically found by learning the time rule of the login event through an algorithm without depending on a manually configured detection rule.

Disclosed are artificial intelligence (AI)-based security risk prediction system and method for targets to be protected in a cloud environment. The method includes: collecting cloud logs and system logs for the targets to be protected in real time; learning all activity logs included in the cloud logs and the system logs for the targets to be protected of a corresponding member company through an AI algorithm; identifying a new activity among activities for the targets to be protected based on a learning process through the AI algorithm, and in response to the identified new activity being a new activity related to security, identifying a first activity pattern comprising the corresponding new activity; identifying an order of an preparatory activity for the new activity in the first activity pattern; identifying a risk score corresponding to the order of the preparatory activity for the new activity; and calculating a risk score of each target to be protected by summing identified risk scores of all new activities.

The invention provides a multi-unmanned aerial vehicle communication topology network optimization method based on improved Q-Learning, and the method comprises the steps: firstly analyzing an unmanned aerial vehicle formation communication network influence factor, and constructing a multi-unmanned aerial vehicle communication topology network routing evaluation model; secondly, on the basis of the Q-Learning algorithm, designing a greedy factor adaptive adjustment mechanism, and improving the learning and exploration capability of the Q-Learning algorithm; and finally, according to the requirement of minimum communication required by formation control, considering the requirement of multi-unmanned aerial vehicle formation control for a communication network, and optimally designing the communication connection condition between the formation unmanned aerial vehicles. According to the method, the problem that the calculation complexity of an algorithm is increased due to a rule-based routing design method under large-scale formation constraint can be solved, the minimum routing requirement on the basis of optimal balance formation control is met, and the unmanned aerial vehicle formation communication network optimization problem of the attack and defense game confrontation and the minimum information flow requirement is solved.

The invention discloses a teenager AI data scientific practical training system and training method. The system comprises a data acquisition and preprocessing module, an algorithm learning and practice module, a model construction and training module, a visual display module, a personalized learning module, an interaction and cooperation module and an intelligent evaluation and feedback module. The teenager AI data scientific practical training system provided by the invention has abundant functions, covers a plurality of core modules such as data acquisition and preprocessing, algorithm learning and practice, model construction and training and the like, can provide a complete AI data scientific practical training process for teenagers, and helps the teenagers to comprehensively master AI data scientific knowledge and skills.

The invention discloses an energy management method and system based on big data, and belongs to the technical field of energy management, and the method comprises the steps: building a digital twin model of an enterprise energy system through a digital twin modeling module, and building a physical and virtual real-time mapping relation; the method comprises the following steps: integrating multi-dimensional data such as energy consumption, business operation, environmental parameters and real-time electricity price through a multi-source data fusion module, and generating a unified energy state feature vector based on an adaptive fusion weight; learning an optimal energy configuration strategy by adopting a deep Q network algorithm through a reinforcement learning optimization module; the energy configuration effect is evaluated in real time through the closed-loop feedback adjustment module, feedback adjustment parameters are generated and transmitted to the front module, the four modules form a deep coupling closed-loop cooperative system, and real-time modeling, self-adaptive optimization and closed-loop feedback of an energy system can be achieved.

The invention belongs to the technical field of recommendation algorithms, and particularly relates to a reinforcement learning reward function improvement method for introducing feature words. The method comprises the following steps: S1, extracting users, items and interactive comment texts thereof, and performing sentiment analysis on the comment texts thereof; s2, designing a reinforcement learning model, defining an MDP environment and formulating an action strategy network of an intelligent agent; s3, performing word segmentation and stop word removal preprocessing operation on the text to obtain a standardized vocabulary set, and converting the standardized vocabulary set into a word-document matrix; s4, inputting the constructed word-document matrix into a PLSA model, learning potential topic distribution through an EM algorithm, and generating comment feature words; and S5, comment feature words are introduced to adjust a reward function in the reinforcement learning strategy. According to the method, the feature words in the user comments are introduced to adjust the reward function in the strategy network, so that useful information in the user comments is fully utilized.

Provide a system. 【Solution means】 Means for collecting information from a past contract database and learning the characteristics of fraudulent contracts using a machine learning algorithm; Means for analyzing real-time information transmitted from an information processing device during the contract procedure and interpreting this information using natural language processing technology; Means for obtaining image data of personal identification materials and evaluating their authenticity using image recognition technology; Means for comparing the analyzed data with learned abnormal patterns to detect abnormalities; Means for performing a risk assessment on the detected abnormalities and calculating a risk score; Means for sending a warning to the person in charge based on the risk score and proposing additional confirmation procedures; Means for continuously improving the machine learning model upon receiving feedback; Means for analyzing personal information and identification information in real time when opening an e-commerce transaction, and collating with past patterns of unauthorized use to detect abnormalities; Means for instructing additional personal verification when an abnormality is detected; A system including the above.

This invention discloses an autonomous driving reward learning and control method based on ensemble maximum entropy deep inverse reinforcement learning, comprising the following steps: Step 1: Learning the reward function and control operation in a highway autonomous vehicle driving environment and constructing it into a Markov decision process model; Step 2: Constructing a soft Q-learning model based on value pruning to obtain expert demonstrations, and dividing the inverse reinforcement learning task into sub-tasks according to expert preferences; Step 3: Establishing a strong learner ensemble model and recovering the reward function through maximum entropy deep inverse reinforcement learning; Step 4: Achieving the fusion of reward functions of each sub-task through linear combination, thereby improving the learning accuracy of the reward function. This invention considers the problems of gradient explosion, gradient vanishing, and data overflow in soft Q-learning. It learns expert demonstrations through an improved soft Q-learning algorithm and proposes an ensemble maximum entropy deep inverse reinforcement learning algorithm based on the learned expert demonstrations, which can better achieve decision control.

The application provides a manufacturing network maintenance-detection joint optimization method based on deep reinforcement learning, and the steps are as follows: firstly, for the machine level, a machine reliability model considering the influence of feed quality and a processing quality model considering the influence of machine reliability are constructed under the condition that the dynamic production speed caused by machine failure shutdown is considered; secondly, the system evaluation of the manufacturing network state and performance is carried out based on the reliability model and the quality model; and a manufacturing network maintenance and quality detection joint optimization model is built; finally, at the system level, the economic operation of the manufacturing network is taken as the standard of strategy evaluation, and a deep deterministic policy gradient algorithm is designed to learn the optimal strategy of quality detection and maintenance under the given manufacturing network state. The application can well balance the contradiction between the economic benefits and the operation risks of the manufacturing network, and has better adaptability to dynamic and diversified manufacturing scenes.

The present invention relates to a reverse design method and system for a backward multi-pumped Raman fiber amplifier, belonging to the field of Raman fiber amplifiers. An improved particle swarm optimization algorithm is first used to optimize the pump light parameter configuration. A neural network algorithm is then used to learn the nonlinear mapping relationship between output gain and pump light parameters to reversely design the Raman fiber amplifier. By determining the target output gain and generating matching pump light parameters, this method replaces the traditional method of numerically solving the Raman coupled wave differential equation. By combining the improved particle swarm optimization algorithm with the neural network, the accuracy of the neural network model is improved, resulting in a Raman fiber amplifier designed for C+L band signal light amplification. This improves computational efficiency and enhances the output gain and output gain flatness of the Raman amplifier.

The present invention provides a method for nonlinear flow reduction modeling and prediction based on meta-learning. The method proposed in the present invention first establishes a flow prediction model with an autoencoder configuration suitable for the current flow problem; secondly, the relationship between flow fields with different parameters is learned through the MAML algorithm, and a meta-model is established; then, the established meta-model is used as the initialization model under new physical parameters, and fine-tuned with a small number of training data points; finally, the flow prediction model after small sample training is used to perform reduction analysis and prediction research on the flow field under the new parameters. By introducing a meta-learning strategy, this method proposes a new solution to the problems of poor generalization ability and long training time of the current model. In addition, the method is simple to implement, has high accuracy, and strong versatility. It can be widely used in the reduction modeling and prediction of complex parameterized flow systems.