573 results about "System identification" patented technology

A computer system uses a machine-learned language model to generate an SQL query for a user query. The system receives a user query comprising a task for performing a database query. The system identifies an embedding for the user query to represent the user query. The system generates a prompt for input to a machine-learned language model, and the prompt specifies the user query, metadata associated with the identified data table and a request to generate one or more SQL statements for performing the database query on the data table. The system provides the prompt to a model serving system and receives an output generated that includes the requested SQL statements for performing the database query. The system presents a response to the user query using the received SQL statements.

The invention relates to a dynamic cooperative path planning and autonomous landing control method for an unmanned aerial vehicle and an unmanned ship, and the method comprises the following steps: collecting the state data of the unmanned ship and the unmanned aerial vehicle and the high sea condition environment data, and carrying out the data fusion processing; an improved fast extended random tree algorithm is adopted to plan a safe navigation path for the unmanned ship, the generated path of the unmanned ship is optimized based on an unmanned ship motion model considering environmental interference, and a model prediction control algorithm is adopted to plan a path for the unmanned ship to fly to a predicted landing point of the unmanned ship. Dynamic cooperation between the unmanned ship and the unmanned aerial vehicle is realized through information interaction between the unmanned ship and the unmanned aerial vehicle; the unmanned aerial vehicle recognizes an unmanned ship landing identifier through a visual servo guide system, calculates the position and attitude deviation relative to a landing point, adjusts flight control parameters according to interference conditions by using an adaptive control algorithm, and performs trajectory prediction compensation in combination with an unmanned ship motion model to realize autonomous landing. Compared with the prior art, safe landing of the unmanned aerial vehicle on the unmanned ship under the high sea condition is achieved.

The invention discloses an intelligent warehousing system based on supply chain management, and particularly relates to the technical field of warehousing identification and supply chain information processing, and the system comprises an information collection module, a trigger judgment module, a data verification module, a risk assessment module and a state grading module. Collecting target carrier identification data through a multi-source device, performing credibility scoring according to stability, consistency and a historical confidence level, and judging whether to enter a verification process or not; in the verification stage, an identification consistency index and a supply chain synchronization credibility index are generated, and a risk score is output by the model; implementing credible marking, image checking or multi-source reconstruction according to the scoring level, and realizing identification result hierarchical control and operation closed loop; according to the method, the identification vector is constructed through multi-source acquisition, so that the state of the target carrier is accurately acquired; the identification processing efficiency is improved by adopting a hierarchical judgment mechanism; a differential response strategy is executed based on the risk score, a recognition credibility closed loop is constructed, and the recognition accuracy and operation safety of the system are effectively improved.

The invention belongs to the technical field of plastic part quality detection, and discloses a plastic part gold stamping mark accurate positioning method and system based on visual identification, and the method comprises the steps: collecting environment illumination parameters, equipment operation parameters and image data, and processing the image data to obtain regional image data; performing edge detection and fracture repair operation on the regional image data to obtain identification edge feature data; calculating to obtain a position deviation quantized value according to the identification edge feature data; based on the position deviation quantized value, in combination with preset inclination direction information, adjusting an image visual angle and correcting an angle deviation to obtain corrected image data; executing edge path tracking on the corrected image data to obtain path complete data; obtaining an identifier positioning result based on the path complete data in combination with the environment illumination parameters and the equipment operation parameters; and carrying out stability evaluation on the identification positioning result, and obtaining a final system identification stability result in combination with preset detection fluctuation characteristics.

The invention relates to the technical field of data processing, and discloses a secondary equipment hidden danger mining method and system based on a wave recording file and monitoring data. The method comprises the steps of calculating a conditional probability and intervention probability difference identification causal relationship by analyzing a recording file in combination with equipment topology and protection logic to construct a correlation graph, and performing Fourier transform and wavelet decomposition on a sampling sequence to extract multi-scale features; small signal test excitation is injected, a system identification estimation transfer function is fused with monitoring data to form a health feature vector to judge a health state, and a correlation map and the health state are input into a map neural network to calculate weighted attention coefficients and aggregate neighbor information to predict a fault propagation path; and establishing a degradation model, correcting the failure rate, predicting the residual life and generating a graded early warning report. According to the method and the device, the transformation from passive post analysis to active predictive maintenance is realized, and the timeliness, accuracy and systematicness of hidden danger identification of the secondary equipment are improved.

The invention discloses a weather system identification method based on multi-source meteorological information. The method comprises the following steps: S1, acquiring historical multi-source meteorological data of a target area; s2, cleaning and complementing the original meteorological data; s3, marking the type and position of a weather system, and constructing a training set; s4, training a single-source meteorological feature extraction model; s5, fusing the single-source features, and training an integrated recognition model; s6, deploying the trained model to a reasoning environment; and S7, inputting real-time meteorological data, and outputting an identification result. According to the invention, efficient fusion and accurate identification of multi-source weather information are realized, and the real-time performance and accuracy of weather system identification are significantly improved.

The invention relates to the technical field of data processing, and discloses a child autism behavior recognition method and system based on data analysis and a medium. The method comprises the steps of collecting and preprocessing child multi-modal behavior data; extracting nonlinear features to obtain a time sequence feature matrix; identifying a repeated behavior mode through a three-dimensional convolutional network; analyzing behavior time sequence change by using a time convolutional network; fusing a plurality of feature representations to obtain a comprehensive feature vector; a multi-classifier system is applied to identify autism behavior types and evaluate severity. By extracting the nonlinear time sequence features, constructing the deep spatial-temporal feature extraction network and designing a feature fusion mechanism and a multi-classifier integration system, the method can overcome the limitations of a single mode, a linear feature and a single algorithm in the prior art, and improves the accuracy and interpretability of autism behavior recognition.

The invention discloses an incomplete multi-mode crisis event detection method based on a memory pool and a mode perception expert system, and relates to the field of machine learning, and the method specifically comprises the steps: building a prompt strongly related to an event instance based on the memory pool, and complementing a missing mode through a large model; a CNN encoder, a ResNet encoder and a CLIP encoder are utilized to construct a double-flow encoder, and text and visual feature extraction is achieved; capturing fine-grained event information and clues; the distribution difference between a complemented sample and a complete sample is identified based on a modal perception expert system, and the quality of fusion representation is improved; and inputting the mixed features into the classification head to complete a crisis event detection task. According to the invention, through the prompt construction module based on the memory pool, a large model is introduced to realize careful completion of a missing mode, and the distribution difference between a completion sample and a complete sample is accurately identified based on a mode perception expert system, so that a multi-mode data missing scene can be effectively coped with, and the accuracy and timeliness of crisis event detection are improved.

The invention relates to the technical field of thermal management control, and particularly discloses a thermal management controller regulation and control method and system based on dynamic thermal inertia prediction. According to the method, the dynamic thermal inertia model is constructed through system identification, and the future temperature field evolution and thermal accumulation risks of the system are accurately predicted. On the basis, a multi-layer nested compensation strategy composed of pre-compensation, main compensation and residual compensation is generated in three dimensions of a compensation angle, a compensation order and a compensation domain, and prospective accurate intervention is achieved. In order to evaluate the control effect, an artifact intensity entropy value is introduced as a quantitative index, and a model and a strategy are corrected in real time through an outer ring optimization mechanism to form self-correction. When continuous thermal unbalance caused by hardware design defects is detected, the system can further start hardware cooperative regulation and control, local heat capacity and a heat dissipation path are optimized fundamentally, cross-level cooperative optimization from a control algorithm to a physical structure is achieved, and finally high-precision, low-energy-consumption and self-adaptive system-level thermal management is achieved.

An aquatic cleaning system includes a pool cleaner having a housing, a drive system for moving the housing, and a debris basket associated with the housing. The debris basket is designed to receive debris from the aquatic environment. The system includes a data capture system including an imaging device operably coupled to the cleaner. The system also includes a detection system having a storage medium storing a trained model, and a processor designed to receive data elements from the data capture system and input the data elements into the trained model to identify a detected object within the aquatic environment as being debris or non-debris. The system also includes a control system in communication with the detection system and the drive system to move the pool cleaner toward the detected object identified by the detection system when the detected object is identified by the detection system as being debris.

The invention discloses a TITAN product thunderstorm forecast field correction method and system based on multi-scale ensemble learning. The method comprises the following steps: S1, forming a unified multi-source meteorological data set and a TITAN product set; s2, constructing a meteorological target dichotomy label; s3, preprocessing the multi-source meteorological data set, and matching meteorological target dichotomy tags to generate a sample data set; s4, calculating a multi-scale feature set reflecting macro and micro features of the thunderstorm system and the non-thunderstorm system based on the sample data set; s5, generating a comprehensive multi-scale feature expression; s6, forming a plurality of sub-models with differentiated scale sensing capability; s7, training to form a final thunderstorm system identification model; s8, constructing a TITAN product forecast field reconstruction module; and S9, generating a forecast result reflecting the spatial distribution, the development trend and the potential influence area of the thunderstorm system in real time. According to the method, the time-space evolution feature capturing precision of the thunderstorm system and the prediction stability and reliability are improved.

A system and method for multi-level compaction of floating-point numbers and associated metadata within datasets. The system identifies floating-point numbers and their associated metadata, pre-encodes numbers into binary string representations, and encodes metadata into compact binary form. These encoded elements are linked together and indexed to indicate they represent floating-point numbers with metadata. The dataset is organized into multiple compaction levels based on semantic relationships between metadata elements. The system creates specialized indices for metadata-based retrieval, maintains relationship maps, and implements inheritance policies across hierarchical levels. During retrieval, the system reconstructs both the original floating-point values and their associated metadata, preserving hierarchical relationships. This approach enables more intelligent data organization, richer contextual information preservation, and more powerful query capabilities while maintaining efficient floating-point compaction.

In a general aspect, benchmarking for data quality monitoring is described. In some embodiments, a system identifies a base data set to be used as input to a machine learning (ML) model. The system generates a modified base data set by causing synthetic anomaly injection operations to be performed on data of the base data set. The system causes the ML model to run, using the base data set as input, to determine a first output of the ML model, and to run, using the modified base data set as input, to determine a second output of the ML model. The system determines a set of performance metrics representing performance of the ML model at detecting data anomalies and outputs a representation of the set of performance metrics.

The invention discloses a construction method, a construction system, a recognition method and a recognition system for a fine tree species recognition model, belongs to the field of forest management and ecological protection, and solves the problems that the overall contribution of the whole group of time sequence features to model performance cannot be comprehensively examined, and due to the resolution limitation of remote sensing images and the randomness of forest species distribution space and quantity, the model performance cannot be comprehensively examined in the prior art. And the performance of the remote sensing tree species classification model is obviously reduced. The method comprises the steps of 1, constructing a high-dimensional multi-source feature data set; 2, performing feature optimization based on the high-dimensional multi-source feature data set to obtain an optimal classification feature set; 3, collecting actual measurement sample data, and constructing a deep learning sample library in combination with the optimal classification feature set; and step 4, presetting a fine tree species identification model, and inputting the deep learning sample library to train the preset fine tree species identification model to obtain the fine tree species identification model. The method is used for obtaining the accurate and newest tree species distribution map.

The invention discloses an intelligent analysis and management method and system for an integrated controller, relates to the field of integrated control, and aims to complete complex air conditioning system identification model training and off-line optimization of an optimal PID parameter strategy by using historical data at a cloud end with sufficient computing power. And generating an expert strategy library containing various working conditions and corresponding optimal control parameters thereof. Then, a lightweight proxy model with small calculation amount and high reasoning speed is trained based on the strategy library; the proxy model is deployed on a resource-constrained edge controller. Therefore, the edge end does not need to execute complex online optimization calculation, and only needs to input the real-time working condition data into the agent model, so that the current optimal PID parameter can be quickly deduced. According to the cloud training and edge reasoning architecture, online, real-time and intelligent self-tuning of controller parameters is realized, and a gap between an advanced algorithm and industrial landing is effectively filled up.

The invention discloses a vibration control method for an offshore wind turbine structure, which comprises the following steps of: a, implementing real-time multi-source data acquisition which is realized by deploying a series of sensors on the offshore wind turbine structure and in the surrounding environment so as to obtain environmental load parameters, structural response parameters and running state parameters of the offshore wind turbine; and b, inputting the acquired data into a composite environment and structure state decoupling and feature extraction module, preprocessing the acquired data by the module, and identifying an environment load spectrum in real time. According to the vibration control method for the offshore wind turbine structure, through multi-source information fusion, online system identification and self-adaptive multi-target control, broadband, multi-mode and self-adaptive suppression of vibration of the offshore wind turbine structure is achieved, and the limitation of a traditional fixed parameter damper in a complex dynamic marine environment is overcome; complex excitation sources such as wind, waves and ocean currents and the coupling effect of the excitation sources are effectively handled.

Techniques for receiving, storing, analyzing, and utilizing raw content are disclosed. The system receives raw text from a user, including a first tag and second tags. The system identifies and removes formatting attributes in the raw text, including whitespace characters, to generate a normalized input. The system stores the normalized input in target dataset(s) and parses the normalized input for the first tag and the second tags. In this case, the first tag corresponds to one or more topics, and the second tags represent a computing system associated with corresponding portions of the normalized input. The system analyses the first tag and the second tags to identify the topics. The system generates one or more topic maps for the target dataset(s) based on the first tag and the one or more second tags. The topic map(s) include one or more references to content items within the target dataset(s).

Techniques for identifying a document layout are disclosed. In one embodiment, attribute data associated with an electronic document is accessed. A machine learning model is then applied to the attribute data. The machine learning model is configured to classify the electronic document based on the attribute data and feature sets of a plurality of document classes. Based on the document class predicted by the machine learning model, the system identifies a layout associated with the document class. The layout specifies layout elements and content types associated with the layout elements. The system extracts and stores information from the electronic document according to its content type.

The invention discloses an equipment asset depreciation prediction method based on machine learning, and the method comprises the following steps: S1, collecting an asset original value, a depreciation code, an age limit, a starting date and a historical net value, and generating an asset state input sequence in a unified time domain through normalization; s2, inputting the normalized asset state into a Shenchang differential equation model, and constructing a differential system of the asset state evolving along with time; s3, identifying parameter changes in the asset depreciation period, extracting change time and amplitude, and constructing a disturbance event sequence; s4, constructing a time gating function and a disturbance coupling function according to the disturbance event sequence; s5, injecting the disturbance coupling function into a differential system, and resolving to obtain a depreciation evolution path; and S6, mapping the prediction path to an actual time interval, and outputting a depreciation trend prediction result. According to the invention, fine prediction of the depreciation trend of the equipment and dynamic response of strategy change are realized, and the intelligent level of asset management is improved.

The invention relates to the technical field of semiconductor material photoelectric detection, and discloses a whole-course calibration method of a microwave photoconductive attenuation tester, which comprises the following steps: steady-state optical calibration: establishing reference mapping from light intensity to absolute carrier concentration; performing sweep frequency perturbation measurement at each concentration working point to obtain multiple groups of complex response data; separating an instrument transfer function from sample differential response sensitivity by adopting a system identification algorithm; an integral differential sensitivity reconstruction curve is converted into an absolute calibration model by using an anchor point; starting closed-loop feedback control to lock a specific phase, and verifying the model; and outputting an absolute calibration model and an instrument transfer function as a static reference and a dynamic operator. According to the invention, the absolute concentration anchor point is established through steady-state optical calibration, integral reconstruction is carried out on the differential response sensitivity decoupled by dynamic frequency sweep measurement, and finally, the anchor point is utilized to determine the integral constant, so that the accuracy and reliability of carrier concentration quantitative analysis are improved.

The invention relates to the field of chip detection, and discloses a high-efficiency chip detection system and method, which are used for realizing long-term performance degradation detection of a chip. Comprising the following steps: synchronously acquiring power pin electric signals and chip surface thermal imaging data to generate an electrothermal coupling characteristic data set in a working state of a to-be-tested chip, and extracting impedance and heat conduction characteristic parameters through impedance spectroscopy analysis and thermal time constant calculation. And analyzing an internal signal transmission path based on impedance characteristic parameters to obtain path characteristic parameters, establishing a mathematical model of dynamic current and working voltage of the chip by combining the two, generating a system identification result, and finally generating a chip detection result and fault positioning information by integrating various parameters. According to the invention, system benchmark testing and environmental interference monitoring and compensation are carried out, and high precision and high robustness of a detection result are realized.

The invention discloses a unified access method and system for peripheral equipment of a swan monk system based on hardware abstract virtualization, and relates to the technical field of peripheral equipment management of an operating system. A structured data set S is constructed by detecting a peripheral equipment access event and collecting equipment description information and physical response data of the peripheral equipment; the method comprises the following steps: carrying out data fusion modeling, obtaining an equipment access qualification index Iconn, evaluating the stable state of equipment, carrying out packaging processing on peripheral equipment in the stable state, then carrying out function stability analysis, obtaining a function stability index Fstab, carrying out coupling modeling on the function stability index Fstab and the equipment access qualification index Iconn, obtaining the equipment access qualification index Iconn, and carrying out data fusion modeling on the equipment access qualification index Iconn. According to the method, the peripheral operation state is evaluated, and the peripheral connection state is regulated, so that the peripheral access compatibility is enhanced, the system identification accuracy and the access success rate are improved, and intelligent management of the peripheral access full life cycle is realized.

The invention discloses a low-altitude economic monitoring and collaborative countering method and device. The method comprises the following steps: S1, acquiring original monitoring data of a flying target; s2, fusing the monitoring data to generate a target threat level; s3, executing response operation; according to the invention, through a multi-modal sensor depth cooperation and Bayesian decision-making multi-modal data fusion model, a trajectory entropy evaluation algorithm is introduced, the detection efficiency of unknown targets outside a preset route is improved, the recognition precision of low-altitude targets is improved, and the supervision requirement of low-altitude economic high-density flight is met; based on a dynamic threat assessment and countering strategy decision tree linkage mechanism, response delay is reduced, collaborative scheduling among equipment is realized, the countering success rate is improved, and accidental damage to cooperative unmanned aerial vehicles is avoided; a federated learning driven model optimization framework is adopted, so that the system identification precision is increased along with deployment time; and good real-time processing capability is still kept on edge equipment with limited computing power.

In a general aspect, data quality monitoring and reporting are described. In some implementations, a system identifies a plurality of documents that include unstructured data and identifies a prompt indicating instructions for analyzing the unstructured data in the plurality of documents. The system causes a machine learning (ML) model to analyze the unstructured data in the plurality of documents according to the prompt. The system receives results from the ML model in a structured format according to the prompt and outputs a representation of the results.

The invention relates to the technical field of semantic processing, and discloses a semantic processing system and method for home elevator intelligent customer service, and the system comprises a data collection module, a semantic processing module, a response generation and optimization module, and a communication and log module. The method comprises the steps of collecting natural language request information input by a user through voice, performing semantic analysis and intention recognition on preprocessed information based on a deep learning model, and synchronously recording an interaction log of a whole link according to an intention recognition result and the emergency degree and priority of optimized response content. In order to solve the problems that a traditional keyword matching system is poor in semantic comprehension ability and prone to misjudgment of user intentions, the context and real intentions of natural language requests can be deeply understood by introducing a semantic analysis model based on deep learning and combining a confidence degree evaluation mechanism, and when the system recognizes the low confidence degree condition, the user intentions can be accurately judged. And multiple rounds of clear conversations can be automatically triggered or interaction channels can be switched.

The invention discloses an SVC (static var compensator) control method of a high-power power supply system based on a predictive active disturbance rejection mechanism, which comprises the following steps of: establishing a combined operation time domain model of the high-power power supply system and a static var compensator, and acquiring delay parameters in advance by utilizing a system identification method; predicting and calculating a reactive instruction signal of the static var compensator based on the voltage reference signal of the load side of the power supply system and the direct current side current; inputting the predicted reactive instruction into a linear active disturbance rejection controller, estimating the total disturbance of the system in real time through an extended state observer, generating a compensated control signal in combination with a proportional differential combination control law, and driving the system to output a tracking and predicting reactive instruction; and the tracking prediction reactive instruction acts on the static var compensator to form closed-loop anti-interference control. Through cooperation of prospective reactive power instruction generation based on a load side voltage reference signal and disturbance real-time compensation of a linear active disturbance rejection control framework, a grid side reactive power impact value is reduced, and bus voltage stability is enhanced.

The invention discloses a business handling method and device, computer equipment and a storage medium, and the method comprises the steps: receiving a user business request, and extracting business information containing a user identity, a target business and an association condition from the business request; based on the service request, searching a service rule, a mutual exclusion relation and a constraint condition related to the service information in a pre-constructed service knowledge graph; inputting the business rule, the mutual exclusion relation and the constraint condition into a local fine-tuning large model, and generating a business handling path containing a conflict judgment and processing strategy through thinking chain reasoning; according to the business handling path, generating a structured operation instruction which can be identified and executed by a business system; and sending the operation instruction to the service system to promote the service system to execute a service corresponding to the operation instruction. And the business handling efficiency and success rate are improved.

The invention discloses a mooring type low-altitude monitoring countering unmanned system based on deep learning target recognition. The mooring type low-altitude monitoring countering unmanned system comprises a mooring unmanned aerial vehicle platform module, a multi-source sensing and data fusion module, a deep learning target recognition and classification module, a self-adaptive countering decision and execution module, a dynamic tracking and collaborative aiming module and a ground command and control module. The mooring unmanned aerial vehicle platform module forms a stable air monitoring and countering base point; the multi-source sensing and data fusion module provides high-quality input for system identification; the deep learning target recognition and classification module recognizes and predicts a target behavior through deep learning; the self-adaptive countering decision and execution module realizes precise countering; the dynamic tracking and collaborative aiming module applies counter energy to a dynamic target; the ground command and control module provides a human-computer interaction interface and displays global information. The low-altitude active defense system has the advantages that technologies such as multi-source fusion perception, deep learning AI recognition and self-adaptive precise countering are deeply fused, and the low-altitude active defense system is formed.

Methods and systems for process chamber qualification for maintenance process endpoint detection are provided. Data collected by one or more sensors of a process chamber of a manufacturing system is identified. The identified data is collected during performance of initial maintenance operation(s) of a maintenance process. A current state of the process chamber is determined, based on the identified data, after the performance of the initial maintenance operation(s) based on the identified data. In response to a determination that the current state does not satisfy one or more chamber maintenance criteria, a set of subsequent maintenance operations to be performed to cause the current state of the process chamber to satisfy the criteria is identified. Performance of the set of subsequent maintenance operations is initiated at the process chamber.

The invention relates to a network security vulnerability analysis method and system based on large-model low-rank adaptation fine tuning training. According to the method, firstly, a large language model is selected and pre-trained, a network security corpus is collected and preprocessed to construct a supervision fine tuning data set, then low-rank adaptive training fine tuning is performed on the pre-trained model based on the supervision fine tuning data set to obtain a network security vulnerability analysis large model, and finally, the model is utilized to monitor and analyze a network system in real time. And identifying and outputting potential security vulnerabilities and attack modes. Compared with the prior art, the method has the advantages of realizing efficient and accurate vulnerability analysis, effectively identifying novel vulnerabilities and the like.