263 results about "Analysis of algorithms" patented technology

The invention discloses an intelligent detection method for product defects on an automatic production line and a detection system based on machine vision, and relates to the technical field of industrial product quality detection. According to the method, a multi-waveband imaging technology is combined with temperature and chemical component information to generate a multi-dimensional feature data set, and an unsupervised learning algorithm is utilized to perform clustering analysis, so that the limitation of traditional single-waveband imaging is broken through, product features are comprehensively captured, the defect detection range and accuracy are remarkably improved, and a foundation is laid for subsequent analysis and classification; further utilizing an attention mechanism and a deep learning technology to accurately position and classify defects, and triggering deep scanning through a priority index to improve the detection precision and the system adaptability; and finally, combining with a random forest algorithm to analyze defect influence, and feeding back and optimizing production parameters through a dynamic adjustment mechanism, thereby realizing production optimization closed-loop management, and improving production efficiency and product quality detection.

The invention provides an expectoration auxiliary control method and device. The method comprises the steps that audio signals of breathing sounds and cough sounds at multiple positions of the chest of a patient are collected through an audio sensor array, and a standardized audio feature data set is obtained through noise reduction, segmentation and feature extraction; a dynamic weighted graph model is constructed, and a random edge sampling algorithm and a parallel batch processing dynamic algorithm are combined to analyze and obtain a sputum viscosity index and a sputum distribution position map; based on the result, mapping the vibration parameter space into an unweighted disk diagram, and obtaining a personalized vibration treatment scheme by using a shortest path algorithm; in combination with the real-time breathing cycle of the patient, working parameters of the sound wave vibrator and the negative pressure suction device are synchronously controlled, and a coordinated and consistent multi-mode treatment execution instruction is obtained; and collecting real-time feedback data in treatment, and dynamically adjusting working parameters through reinforcement learning to obtain an optimized expectoration adjuvant therapy scheme. Intelligent adjustment can be achieved based on the real-time breathing state and sputum characteristics of the patient, the expectoration efficiency is improved, and discomfort of the patient is reduced.

The invention provides a prefabricated pipe pile construction total factor intelligent management method and system based on the digital twinborn technology, and relates to the technical field of construction management, a three-dimensional model is established through the BIM technology, pipe pile attributes are bound, construction data are collected in real time through the Internet of Things, and a dynamic digital twinborn body is formed. Through integration of an API interface and a project management platform, an AI algorithm is used for analyzing data, resource allocation and construction plans are dynamically adjusted, instructions are optimized and pushed to the site, construction efficiency and installation precision are improved, and the problems that traditional management is low in efficiency and large in error are solved.

The invention relates to the technical field of rehabilitation training detection, in particular to a rehabilitation training detection method and system based on artificial intelligence, a standard action library is constructed through standard action videos shot at multiple angles, and track and angle features of key joints are extracted for user training comparison; the skeleton key points of the user are extracted in real time through a MoveNet network, and efficient posture recognition in a home scene is achieved; analyzing position difference, angle change and acceleration characteristics by combining a space-time sequence matching algorithm, generating a dynamic matching degree index, and positioning a deviation joint to generate a correction prompt; introducing an attention mechanism model, learning the contribution degree of each joint to cycle recognition, dynamically selecting a dominant joint for action counting, recognizing starting and ending points of an action cycle through an acceleration curve, and finishing effective action statistics in combination with a dynamic threshold value, so that the counting accuracy and the self-adaptive capability are improved; therefore, the training cost is reduced, the evaluation credibility is enhanced, and accurate statistics and analysis of rehabilitation training data are realized.

The invention discloses a security monitoring video intelligent analysis method based on multi-algorithm cooperation and unified architecture, and relates to the technical field of intelligent video monitoring, and the method comprises the steps: collecting a security monitoring video, carrying out the preprocessing, carrying out the spatial-temporal feature extraction and fusion through a CNN-LSTM spatial-temporal fusion engine, and outputting a fusion feature map; performing target detection, behavior recognition and anomaly detection on the fused feature map to obtain a multi-algorithm analysis result; a cross-module fusion mechanism based on an attention mechanism is utilized to perform weighted integration processing on the multi-algorithm analysis result to obtain a fusion event representation vector; performing event type identification and risk level evaluation on the fusion event representation vector to obtain an event classification result and an event risk level; according to the invention, through the CNN-LSTM space-time fusion engine, the front-end perception capability of abnormal behaviors in a complex scene is improved, and the event detection accuracy and the anti-interference capability are improved.

The invention relates to the technical field of machine tool cutter wear monitoring, and particularly provides an integrated multi-dimensional data monitoring system and a monitoring method.The integrated multi-dimensional data monitoring system comprises a multi-dimensional data acquisition module which can acquire multi-dimensional data of the working state of a cutter in real time; the feature information layer and the intelligent analysis layer comprise a multi-source data fusion module, an abnormal state recognition module, a residual life prediction module and a self-adaptive learning module; the decision execution layer comprises an early warning feedback module, a parameter optimization suggestion module and an intervention control module; the knowledge base system comprises a case base module, a rule base module and a model base module, different physical quantities are collected through the multi-dimensional data collection module, full-dimensional sensing of the state of the cutter is achieved in combination with machining features, material information and environment data, multi-sensor collection, physical model construction, feature information integration and intelligent algorithm analysis are combined, and the machining accuracy of the cutter is improved. And comprehensive, real-time and accurate monitoring of various abnormal states of the machine tool cutter is realized.

The invention, which relates to the technical field of traffic management, discloses an intelligent detection system for a vehicle parking space in a passenger and goods mail fusion station, and the system comprises a multi-mode sensing module which is configured to collect vehicle data information, the collection mode comprises the steps that vehicle data information is collected through an enhanced geomagnetic array, an adjustable video monitoring set, a lateral laser radar and a piezoelectric sensor; and the edge computing node module is configured to integrate an AI chip, the AI chip comprises a vehicle classification model, an abnormal parking detection algorithm and a data fusion engine, and the collected data is computed and analyzed. The edge computing node is integrated with an AI chip, and data are analyzed and processed through a built-in algorithm; the hybrid communication network transmits data through an optical fiber backbone network and a specific redundant link, self-adaptive visual adjustment and intelligent algorithm optimization are performed, the problem of complex vehicle type detection in a passenger and goods mail fusion station is solved, and the parking space utilization rate and the operation efficiency are remarkably improved.

The invention discloses a collision identification method and system for a window cleaning robot, and relates to the technical field of robot environment perception, and the method comprises the steps: carrying out the time difference compensation and space synchronization based on a glass material type and collision detection parameters through a distributed perception collaborative analysis method, and generating a three-dimensional space vibration information matrix; enhancing the three-dimensional space vibration information matrix through a dynamic wavelet packet decomposition algorithm and a sliding window analysis method according to the type of a glass material; according to the enhanced three-dimensional space vibration information matrix, collision coordinates are calculated through a time difference positioning algorithm, the characteristic frequency of the vibration waveform is analyzed, and collision characteristic information is obtained; based on the collision feature information, combining safety parameters of glass material types, adopting a hybrid decision algorithm to analyze the collision feature information, and generating and executing a robot obstacle avoidance instruction; according to the method, the high-resolution three-dimensional vibration field is constructed through space-time collaborative modeling, and the collision coordinate calculation precision and the anti-interference capability are improved.

The invention discloses an electric heating deicing system and method based on machine learning prediction and adaptive adjustment, and belongs to the technical field of wind power generation. The system comprises a multi-physical sensor array and a dynamic heating execution module which are arranged on a blade. The multi-physical sensor array and the dynamic heating execution module are both connected with a CAN bus; the CAN bus is connected with an intelligent control module, a cloud collaboration platform and an edge computing node. The method comprises the following steps: acquiring historical operation data of an original unit, and preprocessing the historical operation data to obtain preprocessed data; the original unit historical operation data comprises environmental parameters and blade state monitoring data; analyzing the preprocessed data based on a machine learning algorithm, and establishing a blade icing prediction model; real-time environment parameters and blade state monitoring data are obtained, and the blade surface icing condition is predicted based on the blade icing prediction model; and determining the heating requirement of the blade based on the surface icing condition of the blade, and carrying out deicing.

The invention provides a match alliance platform management system and method, and the system comprises a match authentication module constructed by a block chain, an AI-driven qualification auditing module, a process management module, a convolutional neural network, a big data analysis module, and an RBAC authority management module. Wherein the match authentication module dynamically analyzes and stores authenticated match rule data through an intelligent contract, and realizes rule version tracing by using an encrypted hash chain; the AI-driven qualification auditing module integrates a natural language processing engine to analyze the selection standard and construct a multi-dimensional evaluation model, and adopts a machine learning algorithm to analyze historical data of athletes to generate a visual qualification report; the process management module supported by cloud computing automatically generates an application process based on a rule engine, adopts a Monte Carlo algorithm to execute multi-constraint drawing, and constructs a directed graph model to dynamically generate a schedule topological structure containing a three-person rotation time sequence.

The invention provides a dynamic risk prediction and optimization decision-making method and system for a deep foundation pit construction process. A deep foundation pit numerical simulation model is established, and the model is used for simulating soil mechanical behaviors and supporting system response parameters in the construction process; acquiring multi-dimensional real-time monitoring data of the foundation pit, comparing the monitoring data with a numerical simulation result, and calibrating parameters of the deep foundation pit numerical simulation model according to a comparison result; performing time series data modeling analysis on the real-time monitoring data by using a Transform algorithm, capturing possible risk modes in the construction process, and identifying potential risk signals in the data; on the basis of Transform algorithm analysis and numerical simulation feedback results, the foundation pit construction risk state is predicted in real time, and a real-time risk prediction result is obtained; and according to the prediction result, dynamically adjusting the construction scheme to complete decision optimization. According to the method, the risk management and control capability of the deep foundation pit construction process is remarkably improved, and the construction safety and efficiency are greatly improved.

Computerized methods and systems analyze, using one or more natural language processing algorithms, at least one source of data that is representative of an interaction between a first party and a second party to extract from the at least one source of data, information that is descriptive of at least part of the interaction. The computerized methods and systems upload information derived from the extracted information to a data management system that manages data associated with the first party.

The invention relates to the technical field of railway operation and maintenance communication, and discloses a railway operation and maintenance communication network optimization system fusing power grid information. The system comprises a multi-source data fusion module for collecting power, railway and environment data to generate a space-time multi-dimensional data cube; the communication quality evaluation module is used for analyzing data by using a fuzzy logic fusion algorithm to obtain a communication link quality degradation index sequence; the network topology optimization module is used for constructing a dynamic Bayesian network model to calculate an optimal communication routing table; the dynamic resource scheduling module is used for designing a bilevel programming algorithm to realize frequency spectrum and power joint scheduling; and the exception collaborative processing module is used for establishing a federated learning framework to generate a cross-domain collaborative repair instruction set. The system can accurately evaluate communication quality, optimize network topology, reasonably dispatch resources and cooperatively process exceptions by fusing power grid information, and effectively improves the performance and reliability of a railway operation and maintenance communication network.

The invention provides a cross-system fault diagnosis method and system combined with multi-dimensional anomaly detection, and the method comprises the steps: firstly obtaining an original data set which is generated by cross-system call and comprises fragmented call data, peripheral business transaction data and log data, and carrying out the breakpoint supplement processing to generate a complete data set; then, transverse anomaly diagnosis is carried out on the complete data set, a decision tree algorithm is used for positioning a fault propagation path and an abnormal object, then longitudinal anomaly detection is carried out on the abnormal object, operation logs, error stacks and infrastructure indexes are analyzed based on a multi-dimensional anomaly detection algorithm, and an anomaly reason analysis result is generated; and finally, determining a fault source, a fault object and an influence range according to an analysis result, and outputting a cross-system fault diagnosis report, thereby comprehensively utilizing multi-source data, realizing accurate positioning and deep analysis of cross-system faults, improving fault diagnosis efficiency and accuracy, and ensuring stable operation of the system.

The invention discloses a radix astragali seu hedysari origin traceability system and algorithm. The system comprises a data acquisition module, a quality evaluation module, a risk early warning module, an algorithm analysis module and a block chain evidence storage module. According to the method, geographical indication data, biodiversity characteristic analysis and the Internet of Things technology are integrated, data collection of the whole life cycle of astragalus mongholicus is achieved, and the problems that a traditional method depends on manual recording, tampering is prone to occurring, and the cost is high are solved; a weighted random data model is adopted to perform multi-source data fusion, and the weight is dynamically adjusted through a machine learning algorithm, so that the production area discrimination accuracy is remarkably improved, and the production area discrimination accuracy can reach more than 95%.

The invention discloses a low-carbon asphalt road periodic maintenance method based on an edge computing gateway, and the method comprises the steps: accessing a multi-source sensing device through the edge computing gateway, collecting road surface images, structural stress, environment and maintenance material carbon emission associated data, and carrying out the shunting conversion; calling a multi-modal feature fusion crack recognition algorithm to extract fusion crack features, and synchronously obtaining historical maintenance carbon footprint data; performing association mapping on the multi-dimensional data and then transmitting the data to a carbon-effect double-target maintenance period prediction model; a period prediction result is output through model feature weighting and dimension recombination, and dynamic correction is carried out in combination with material consumption rate data; calling a performance attenuation early warning algorithm driven by time sequence data to analyze the time sequence relevance, and generating early warning information; the edge cloud end cooperates with the carbon footprint monitoring platform to synchronize information to the terminal, and a maintenance execution scheme is generated in combination with different parameters. According to the method, the dynamic adjustment of the maintenance decision is realized, the road performance requirement is ensured, and the carbon emission minimization is realized.

A method comprises receiving a large language model request, analyzing the large language model request using one or more machine learning algorithms, and predicting, based at least in part on the analyzing: (i) a large language model of a plurality of large language models to process and to respond to the large language model request; and (ii) at least one database from which data is to be used to generate a prompt for the large language model. The method further comprises interfacing with the large language model and the at least one database to enable the large language model to process and to respond to the large language model request.

The invention discloses an intelligent interaction system applied to AI glasses, relates to the technical field of man-machine interaction, and is used for solving the problems that resource utilization redundancy is increased and equipment power consumption efficiency is reduced. Fusing to form a head posture variable quantity, and analyzing the dispersion degree of the head posture variable quantity based on an MAD algorithm to judge the complexity of an interaction scene; selecting to execute resource optimization or enhance an interaction response strategy according to the complexity, such as improving the speech recognition accuracy and adapting to a complex sound field; further introducing a proportionality coefficient of illumination intensity, movement speed and noise intensity, constructing a long-short-term memory neural network model to predict interaction complexity, realizing dynamic interaction mode adjustment through a gating mechanism and a regularization method, and judging whether to improve the interaction mode according to prediction output. And the self-adaption and high-reliability interaction capability of the AI glasses in a complex environment is ensured.

The invention discloses a message-driven enterprise multi-service system centralized to-do processing method and system, and the method comprises the steps: S1, obtaining resource investment and task processing data, and obtaining a resource consumption and task state cluster through clustering; s2, using a regression algorithm to analyze correlation between the two, and determining a resource utilization rate change trend; s3, when the threshold value is exceeded, calculating a task completion rate statistical characteristic to obtain a resource optimization index; s4, constructing an interactive model by using a decision tree in combination with historical data, and judging an input strategy adjustment point; s5, rendering visual resource distribution; s6, abnormal tasks are screened, and an optimization area is determined; and S7, updating an instrument panel to obtain a decision view. Through data clustering, correlation analysis and dynamic adjustment, the resource and task matching degree is improved, and decision scientificity and efficiency are enhanced.

The method for automatically and intelligently extracting the data of the atlas database comprises the following steps: performing data cleaning on original data to obtain cleaned data; performing cross-modal semantic alignment word segmentation processing on the cleaning data to obtain semantic alignment word segmentation data; performing entity relationship extraction on the semantic alignment word segmentation data, analyzing an influence relationship between entities through a Granger causality test algorithm, verifying the logicality of the influence relationship, and generating entity relationship pair data containing causality intensity; performing graph construction processing of incremental graph optimization on the entity relationship pair data to obtain a dynamic optimization knowledge graph; and carrying out migration fusion of field adaptation on the dynamic optimization knowledge graph to obtain a graph database of field fusion. According to the method, the defect that causal logic is difficult to mine at present, so that the map relationship lacks the deep decision support capability is overcome.

The invention discloses a worker personalized training and self-adaptive evaluation method and system based on an AI large model, and relates to the technical field of building construction worker training and management. Constructing a post skill library based on the knowledge graph; constructing a to-be-trained personnel post matching database based on the knowledge graph; entity pairs of the post skill library and the post matching database of the to-be-trained personnel are screened through a heuristic rule, linking is completed, the matching degree of the entity pairs is calculated through a similarity algorithm, and personalized training content is generated; designing a self-adaptive evaluation mechanism according to personalized training content, analyzing performance data through a machine learning algorithm, predicting learning ability and knowledge mastering degree, dynamically adjusting an evaluation standard, and customizing an assessment index for an operator; and training operators, collecting performance data in real time, performing evaluation according to an adaptive evaluation mechanism, and presenting an evaluation result in a multi-dimensional form. The safety management level of a construction site and the skill level of constructors are improved.

The invention relates to the technical field of nuclear power data asset automatic management, in particular to a nuclear power digital twinning data warehouse structure system, which comprises a data processing layer, and is characterized in that the data processing layer reads original data of a nuclear power industrial internet platform, performs data standardization processing on the original data to obtain standard data, and sends the standard data to the nuclear power industrial internet platform; constructing a nuclear power industry theme library according to the standard data; the data integration layer performs data coding mapping, data classification and data fusion on the data of the nuclear power industry theme library to form a thematic library; the semantic enhancement layer marks the data of the nuclear power industry theme library and the data in the thematic library formed by the data integration layer, and constructs a structured feature tag library for the data associated with feature tags; the analysis application layer reads data of the feature tag library, and constructs a digital twinborn algorithm library and a digital twinborn sample library through algorithm analysis and sample training. The system supports equipment operation and maintenance from regular maintenance to predictive maintenance based on bottom support and four-layer progressive architecture of a nuclear power industrial internet platform.

The invention relates to a method for predicting the lifespan of an individual, comprising I. providing biological input data of the subject, ii. providing a list of confounding variables, iii. predicting an age-related mortality or disease, preferably the time to death and / or the mortality risk and / or the risk of age-related disease, for the subject by analyzing the data with an algorithm, wherein the algorithm comprises a neural network, which is trained on at least one reference dataset comprising biological data of at least one reference subject by applying: a) a selector layer to filter input data of i., and b) an adversarial learning framework, that removes from the input data the information related to the confounding variables, wherein preferably the adversarial learning framework, is a neural network comprising three elements: a feature extractor (FE), a predictor (P), and a confounder predictor (C). The invention further relates to a device or system comprising means for carrying out the steps of the method according to the invention, a computer program and a computer-readable storage medium.

The invention provides an intelligent course matching and promotion path recommendation method and device based on post portraits. The method comprises the steps of obtaining internal multi-source heterogeneous data of an enterprise and performing preprocessing to obtain a standardized multi-dimensional feature data set; constructing a dynamic post capability portrait by adopting a semi-definite programming method of an asymmetric random block model; analyzing a causal relationship between capability dimensions by applying a linear time primitive algorithm to obtain an employee capability assessment report; a constraint solution algorithm meeting excessive dissipation is adopted to calculate the capability gap matrix to obtain a personalized capability improvement requirement; screening and combining the learning resources through a weighted matching algorithm to obtain a personalized learning recommendation plan; and adopting a promotion path planning algorithm to construct multi-dimensional promotion possibility evaluation to obtain personalized promotion path suggestions. According to the invention, a closed-loop feedback mechanism of learning, evaluation and promotion is realized, and a systematic solution is provided for enterprise talent development.

The invention discloses a robot path planning method and device based on multi-dimensional space modeling and a medium, and the method comprises the steps: carrying out the three-dimensional topology dynamic modeling of building structure data, so as to obtain an initial weighted three-dimensional connected graph; based on the elevator state parameters, weight dynamic updating is conducted on weight nodes of the initial weighted three-dimensional connected graph, and the weighted three-dimensional connected graph is determined; based on the weighted three-dimensional connected graph, through analysis of an improved A * algorithm, a robot global advancing path plan is obtained; according to the robot advancing path planning, robot local advancing path planning is obtained through robot reversing strategy decision analysis; and based on the robot global travel path planning and the robot local travel path planning, through asset counting trajectory analysis, determining a counting scanning line spacing, and performing building asset counting. According to the method, the technical problem that the dynamic constraint condition in the three-dimensional space cannot meet the instant requirement in the existing SLAM technology is solved.

The invention discloses an electric power field operation safety monitoring method and system based on AI driving. The method comprises the following steps: synchronously acquiring voice, operation video and equipment state identification information, and de-noising to generate a multi-modal sequence; using a multi-modal cross reconstruction model to reconstruct other modals for any modal, and identifying suspicious fragments according to reconstruction errors; multi-layer consistency matching is executed on the suspicious fragments, and the consistency matching degree and mismatch attribution are calculated through time soft alignment, semantic embedding unification and semantic graph reasoning; dispersing the voice, action and equipment state elements into an event sequence, and matching the event sequence with a preset process causal graph to position an abnormal event; and finally, abnormal nodes and induced nodes are analyzed in combination with a Bayesian algorithm, and whole-process safety monitoring is realized. According to the method, password inconsistency, action out-of-order, object mismatching and equipment response abnormity in electric power operation can be intelligently identified and traced, and the real-time performance and accuracy of operation safety are improved.

The invention discloses a personalized operation guide intelligent generation method based on a multi-modal behavior path chain, and relates to the technical field of software, the method comprises the following steps: defining an interaction object, and setting an ID and a basic attribute of the interaction object; the user triggers an interaction object and uploads interaction record data; performing user path modeling by using the interaction record data, and inputting user path modeling data into an AI large model to analyze a user operation intention; and generating an operation guide by combining the interaction record data of the user, the user path modeling data and the user operation intention. According to the method, interaction event nodes are defined, user operation behaviors are recorded, identity information is associated, a user path chain database is constructed, an AI algorithm is adopted to analyze user path chain data to visualize the operation guide, and dynamic optimization of the operation guide is achieved. The technical problems that a traditional static guide depends on manual writing, when a product has a personalized page generation function, the user portrait cannot be dynamically adapted, and operation traceability visualization is insufficient are solved.

The invention discloses an AI-based modern apprentice system personalized teaching system and method for medical students. Firstly, multi-dimensional data collection is carried out, and an initial data set is constructed by covering theoretical and practical scores, learning preference styles and the like; analyzing data by using an AI algorithm combining an analytic hierarchy process and machine learning, calculating a comprehensive capability value and defining a learning hierarchy; personalized teaching plans are formulated for students at different levels, such as high-level matching of high-difficulty practice tasks and subject research, low-level strengthening of basic knowledge and the like. And new data is collected every week to dynamically adjust the level and the teaching plan. According to the system and method, multiple factors are comprehensively considered, accurate teaching is achieved through AI, and the teaching effect and student ability are improved.

The invention relates to the technical field of architectural design, in particular to an architectural design application behavior monitoring and algorithm analysis project man-hour statistical analysis system, which comprises a page behavior recording module, a task trajectory generation module, a project identifier collection module, a personnel time consumption verification module and an error offset tracking module. According to the method, a clear task execution structure is formed by extracting a task window and an operation path sequence in design software, reconstructing a task behavior chain and removing irrelevant operation content, continuous operation time periods are aggregated in combination with task affiliation information, and an accurate mapping relation between behavior data and project content is established; and matching the effective man-hour with the person in charge, collecting and comparing the effective man-hour with the person in charge, identifying a time offset section between a behavior record and declaration data, quantifying an offset rate, and judging the reasonability of man-hour declaration, thereby realizing dynamic verification and precision improvement of the corresponding relationship between man-hour distribution and tasks.

The invention relates to the crossing field of engineering cost management and building informatization (BIM) technology, and discloses a BIM-based multi-specialty collaborative engineering cost allocation and settlement auditing system, which comprises an engineering cost allocation and settlement auditing system, and the engineering cost allocation and settlement auditing system comprises a sensing layer, a platform layer, a core layer, an application layer and a guarantee layer. According to the BIM-based multi-specialty collaborative project cost allocation and settlement auditing system, a five-layer system architecture (a sensing layer, a platform layer, a core layer, an application layer and a guarantee layer) is constructed, so that the whole process from data acquisition, standardized processing and intelligent algorithm analysis to multi-role collaborative application is realized; according to the method, cost allocation and settlement auditing services under multiple specialties and multiple scenes are supported, and multi-dimensional cost intelligent allocation and automatic anomaly detection based on BIM components are realized by integrating a BIM semantization engine, a dynamic allocation algorithm engine and an AI auditing engine.