192 results about "Statistical analyses" patented technology

The invention discloses a box-type transformer substation monitoring method based on unsupervised learning, and the method comprises the following steps: S1, collecting multi-source sensing data in the operation process of a box-type transformer, and generating a standardized input data set; s2, selecting a data sample in a normal operation state, constructing an unsupervised learning model, and obtaining a feature representation set; s3, inputting data, extracting current operation state characteristics, and recognizing a voiceprint abnormal state by combining outlier detection; s4, performing window sliding and statistical analysis on the time sequence data, and outputting a trend abnormal interval and an abnormal index type; s5, constructing a variable association graph structure, and identifying potential abnormal variables and propagation paths; s6, integrating the various types of abnormal information and the feature representation set, and constructing a voiceprint map library; and S7, integrating and processing the abnormal result and the voiceprint map database, and executing visual display and intelligent early warning. According to the invention, box transformer substation abnormity monitoring and early warning based on unsupervised learning are realized, and the fault identification accuracy and response efficiency are improved.

The invention discloses a seawater parameter correlation analysis method and device, electronic equipment and a storage medium, and relates to the technical field of ocean monitoring. The method comprises the following steps: acquiring satellite remote sensing data of a target sea area and performing space-time quality screening; preprocessing the satellite remote sensing data to generate correction data for temperature inversion; analyzing tidal dynamic characteristics of the target sea area; inverting a sea surface temperature field based on the pre-processed data, and performing enhancement analysis by fusing tidal dynamic characteristics; establishing a coupling strength quantitative index of the tidal power and the temperature field; collecting and complementing historical observation data of the power plant; the relevance between the temperature and the liquid level parameters is counted and analyzed; and the correlation of the seawater parameters is judged by integrating the coupling strength quantitative index and the data statistical result. The invention provides a two-channel decision-making mechanism with cooperation of a physical mechanism and operation data statistics, and the mechanism not only improves the operation efficiency of the cooling system of the power plant, but also reduces the misjudgment rate of abnormal working conditions, and provides an enforceable optimization strategy for warm drainage management.

The invention relates to the technical field of data analysis, and discloses a business analysis and decision support method and system, and the method comprises the steps: collecting purchase-related business data from a plurality of data sources, and carrying out the preprocessing; storing the preprocessed data in a centralized data warehouse, and performing management based on a preset data governance strategy; performing multi-dimensional analysis on the structured data based on a statistical analysis model and a machine learning algorithm, and generating a key performance indicator KP I and a trend prediction result; providing a customized visual display interface according to a user role, and presenting the KP I and a trend prediction result through an interactive instrument panel; and generating a purchase optimization suggestion based on the analysis result, evaluating the influence of different purchase strategies through analogue simulation, and outputting corresponding decision support information. The system effectively solves the problems of weak analysis capability, insufficient decision support and the like in an existing purchase decision system, and is suitable for multiple application scenes such as enterprise purchase management and the like.

The invention discloses an AI visual passenger flow volume statistics and analysis system based on YOLOv7, and belongs to the field of computer vision and data statistical analysis. Through multi-model collaborative optimization, the system realizes the functions of passenger flow statistics, personnel attribute analysis, abnormal behavior detection and multi-dimensional data mining. The method specifically comprises the steps of real-time passenger flow counting, peak period distribution and hot spot area analysis based on YOLOv7 and SORT algorithms; utilizing a PaddleClas module to extract the gender, age and clothes attributes of the pedestrian so as to construct a user portrait; and early warning is carried out on abnormal behaviors such as running, gathering and object throwing in combination with an ASTNet network. The system adopts a mixed data set training model, hardware resource consumption is reduced through a multi-task parallel processing architecture, and the real-time performance is improved while the detection precision is guaranteed. The multi-dimensional data analysis capability can provide accurate support for commercial operation optimization and public safety early warning, and the method is suitable for intelligent management of retail, scenic spots, transportation hubs and other scenes.

The invention relates to the technical field of power grid energy storage, and discloses a breeze power generation energy storage management method and system based on big data analysis. The method comprises the steps of obtaining future wind speed and other environmental data of an area where breeze power generation equipment is located; monitoring the current state of the energy storage module in real time, and extracting historical power generation data and a power grid transmission power sequence; obtaining a wind power parameter value through statistical analysis of the wind speed, setting a reference value of the energy storage module according to the wind power parameter value, and judging the variation tendency of the generating capacity; combining the current energy storage value, the reference value, the change tendency and historical data to formulate a charging and discharging state; predicting an electric power prediction value of the breeze power generation equipment, and calculating a first plan value of a second energy storage parameter of the energy storage module in combination with the historical transmission power sequence and the electric power parameter change interval; according to the charging and discharging state and the first planned value, a first charging and discharging strategy of the energy storage module in the first preset time is generated, the accuracy of breeze power generation energy storage management and the stability of a power grid are improved, and refined charging and discharging management is achieved.

The invention provides a material management method and system suitable for an offline multi-terminal environment, and relates to the technical field of material management, and the method comprises the steps: obtaining network data; obtaining material data of a plurality of terminals in an offline state; performing statistical analysis on the material data to generate a material operation statistical index; carrying out visual analysis on the material operation statistical indexes to obtain a material consumption visual chart; according to the material consumption visualization chart, predicting a material demand index through a material prediction model; determining an optimal material distribution scheme through a material distribution algorithm according to the predicted material demand indexes in combination with inventory constraints and demand constraints; and based on the optimal material distribution scheme, material distribution is carried out through an automatic material distribution process so as to realize material management. According to the invention, the efficiency and accuracy of material management can be improved, so that managers can make scientific and reasonable decisions even in a network-free environment.

The invention relates to the technical field of computer data processing, and discloses an immigrant archive multi-dimensional information integration and intelligent query method, which comprises the following steps: collecting and standardizing multi-source heterogeneous immigrant archive data to generate to-be-processed data; based on the to-be-processed data, constructing an initial event knowledge graph containing element nodes, event nodes and relationships; performing causal relationship discovery and correction on the initial event knowledge graph, and performing mining, confidence updating and logic completion on the causal relationship between events by fusing data statistical analysis and a business process normal form learned from historical data to generate a time sequence causal graph; and receiving a natural language query request of a user, and executing query and reasoning on the time sequence causal atlas. According to the method, the business process logic hidden behind the data can be revealed, intelligent questions and answers for complex problems such as event reasons and influences are supported, and the intelligent level of query and the interpretability of results are improved.

The invention relates to the technical field of source network load storage, transportation and maintenance management, and discloses an intelligent operation and maintenance management system for a source network load storage multi-energy system, and the system comprises a data collection module which is used for collecting the real-time operation data, equipment state data and historical operation and maintenance data of the source network load storage multi-energy system, the real-time operation data comprises generating capacity, load capacity, energy storage state and energy transmission efficiency, the equipment state data comprises equipment operation parameters, fault early warning information and health degree indexes, and the data acquisition module is further used for acquiring the real-time operation data and the equipment state data of the building energy management system. Through a cross-system data integration and fusion statistical analysis and machine learning feature extraction technology, collaborative operation and maintenance of a source network load storage system and a building energy management system are realized, an operation and maintenance strategy is dynamically optimized based on key parameters such as an equipment health index and load fluctuation, and resource investment is precisely regulated and controlled in combination with an operation and maintenance cost optimization algorithm. And the total operation and maintenance cost and the fault recurrence rate are reduced.

The present disclosure provides a data processing method, apparatus, electronic device, storage medium, and program product, relating to the field of big data technology, particularly to technical fields such as data statistics, analysis, experimentation, and computer technology. A specific implementation scheme comprises: utilizing multiple query code blocks to process source data separately, obtaining multiple data tables, each of which has different data indicators, and the source data includes interactive behavior data. An analysis code block is utilized to analyze a target data table to obtain analysis results. The target data table is obtained by linking multiple data tables.

The application relates to a business document information extraction method based on variant attention and hierarchy, and belongs to the field of natural language processing. First, the document is classified, the data is processed into supervised training data required by a model, and is input into a variant attention and hierarchy network model for training, and a hierarchical network structure is used to extract features of word-level, sentence-level and paragraph-level document information; the document required to be extracted and the label of the content of the document required to be extracted are input into the trained hierarchical variant attention network model for information extraction; and finally, the extracted information is statistically analyzed. The application realizes accurate business document information extraction technology, and finally, the document information is extracted through the technology, and then the document information is statistically analyzed to realize special business related information extraction.

The invention provides an interval dynamic slicing method based on big data, a storage medium and electronic device.The interval dynamic slicing method based on the big data comprises the steps that real data of a real network is collected; estimating a probability density function based on the data distribution; calculating a cumulative distribution function; and performing nonlinear score conversion based on a cumulative distribution function. According to the method, the probability density function (PDF) and the cumulative distribution function (CDF) of the original data are statistically analyzed, so that automatic and self-adaptive data interval division is realized, and time delay scoring and network quality evaluation are more scientifically carried out.

The application discloses a kind of consumer purchase willingness measurement method, system based on EEG technology, comprising: EEG signal acquisition equipment gathers the EEG signal generated after receiving stimulus, the original signal collected is introduced into EEGLAB module in Matlab and is preprocessed, then is transmitted to data analysis system;Data analysis system carries out the extraction of electroencephalogram, and the electroencephalogram is converted into the data that can be statistically analyzed, and then the data is transmitted to discriminant identification system;Discriminant identification system carries out consumer purchase willingness analysis by KNN algorithm.The application first extracts the electroencephalogram of consumer frontal lobe part by EEG equipment, then extracts characteristic value, and uses KNN machine learning model to detect the change of consumer purchase willingness, the application can intelligently detect the change of purchase willingness when consumer receives different external stimulus, improve the efficiency and accuracy of analysis.

The application discloses a virtual production-based equipment monitoring method and device, equipment, medium and product, and relates to the technical field of virtual production. The method comprises the following steps: acquiring running state data and running video data corresponding to a plurality of hardware devices respectively; matching the running state data of the hardware devices with monitoring indexes of the device types corresponding to the hardware devices, displaying the matching results between the running state data of the hardware devices and the monitoring indexes; displaying video pictures corresponding to the running video data of the hardware devices; and performing data statistical analysis on the running performance data of the hardware devices, and displaying the statistical analysis results of the running performance data in the form of a chart. The method realizes the automation of data detection of each device in the shooting field of virtual production in the hardware aspect, improves the monitoring efficiency of the hardware devices in the shooting field of virtual production, and reduces the workload of the on-site staff.

We provide the system. [Solution] A means of analyzing input sentiment data in real time using a natural language processing engine, A means of generating personalized self-care suggestions based on analyzed emotional data, A means of presenting the generated suggestions to the user, A means of anonymizing the input data and processing it statistically while protecting the user's privacy, A system that includes this.

The application provides a full node acquisition seismic record rapid field processing monitoring method, which comprises the following steps: step 1, a processing scheme is established in advance, a standardized naming process is established, and processing parameters are determined; step 2, a standardized data naming and operation management mode is designed according to the actual situation of a work area; step 3, a block observation system is established, conventional monitoring is performed, and beam merging and stacking are carried out; step 4, quantitative statistical analysis is performed, and integrated information feedback is carried out; step 5, an auxiliary trace head is set, rapid monitoring data extraction is carried out by using the auxiliary trace head, and the monitoring process is assisted; and step 6, monitoring results and a monitoring profile are obtained. The full node acquisition seismic record rapid field processing monitoring method meets the needs of rapid field construction, reduces the workload of field monitoring personnel, saves labor and cost, and accelerates the overall monitoring progress.

The invention provides a power distribution network planning and construction whole process management and control method and system and a storage medium, and relates to the technical field of power systems. The method comprises the following steps: acquiring power grid business data corresponding to the whole process management and control requirements of power distribution network planning and construction from a plurality of heterogeneous business systems; based on a data warehouse technology, performing storage management on the power grid business data to obtain a database corresponding to the management and control requirements of the whole planning and construction process of the power distribution network; according to data statistical analysis requirements, data statistical analysis is carried out on the data in the database, statistical analysis results corresponding to different data statistical analysis requirements are obtained, and the data statistical analysis requirements comprise an early-stage planning requirement, a project implementation progress analysis requirement and a project achievement evaluation analysis requirement; and outputting and displaying statistical analysis results respectively corresponding to different data statistical analysis requirements. The method is used for achieving the effect of improving the data statistics efficiency and accuracy, and then efficient management and control over the whole planning and construction process of the power distribution network are achieved.

The present invention proposes a traffic data statistical analysis method, system and computer program product based on a large model, which belongs to the field of computer network security and data analysis technology. The method includes: obtaining the resource set currently requested by the client; identifying the resources to be counted and the clients to be checked; analyzing the traffic transmission characteristics, network text characteristics, and / or encryption characteristics of the resources to be counted within a preset time period; the large model outputs a security screening result for the clients to be checked; based on the security screening result, security measures are executed for subsequent resource requests of the clients to be checked. The system includes a cloud server. The solution of the present invention can use the existing large model based on network security to identify network fraud, malicious traffic and disguised attack data streams for the deceptive data of the client, thereby improving the value of the statistical results of the traffic data analysis and avoiding delays and blockages in cloud resource services.

The invention discloses a storage equipment lease management system and method, and relates to the technical field of storage equipment lease management, and the system comprises a historical lease data collection and analysis module which collects the historical data of storage equipment in the lease process, carries out the statistical analysis of the historical data through a clustering analysis algorithm, and obtains a lease result; the historical data is transmitted to an inventory and demand prediction module for prediction and analysis; according to the system, the historical rental data acquisition and analysis module is arranged, historical data of the storage equipment in the rental process are effectively integrated, comprehensive business insight and decision support are provided, the management efficiency and the decision accuracy are improved, and the system can be used for monitoring and managing the equipment and predicting and processing the equipment failure. The storage equipment lease management system can monitor the equipment state in real time, perform fault prediction, take maintenance and prevention measures as soon as possible, reduce the downtime of the equipment, and accurately analyze the inventory condition and future demand of the equipment by using the inventory and demand prediction module.

The invention relates to the technical field of park management and risk assessment, and provides an industrial park safety assessment method and system based on accident statistical analysis, and the method specifically comprises the steps: collecting failure data related to historical accidents, and carrying out the preprocessing of the failure data; building a historical data analysis model, carrying out the real-time safety tracking and monitoring of the entrance and exit of products in the industrial park, and evaluating and calculating the real-time safety capacity of the industrial park; and accessing the real-time safety capacity to a security sentry box monitoring background and a product transport vehicle driving navigation background, and executing a dynamic safety transport management strategy. The method solves the problems that in the prior art, the industrial park is a multi-enterprise and multi-worker dense personnel area, and in the transportation and loading and unloading process of dangerous goods in the industrial park, the dangerous goods are exposed in a high-temperature, flammable and explosive dangerous environment and a crossed area where personnel are concentrated and traffic is busy, so that the dangerous goods cannot be transported and unloaded. And the possibility that people are injured when a safety accident occurs is greatly increased.

The invention discloses a pyrazine-flavor-based multi-mode intelligent identification method for a Maotai-flavor liquor process. The method comprises the following steps: pretreatment: pretreating Maotai-flavor liquor samples of different brewing processes; collecting sensory data of electronic noses and electronic tongues of Maotai-flavor baijiu of different brewing processes; establishing a liquid phase detection method for the characteristic components of the alkylpyrazine in the Maotai-flavor liquor; verifying a component analysis method through precision, stability and repeatability experiments; component quantitative analysis based on liquid chromatography fluorescence detection; performing clustering and difference evaluation on Maotai-flavor liquor samples of different brewing processes by adopting multivariate statistical analysis; establishing a Maotai-flavor liquor process identification model: utilizing VIPgt in multivariate statistics; establishing different machine learning multi-classification models for different brewing processes of Maotai-flavor liquor according to the common characteristics of 1, and performing multi-model comparison; and based on the optimal performance classification model, establishing an SHAP model of the Maotai-flavor liquor brewing process identification model, and globally explaining the identification model by adopting an SHAP algorithm.

This invention discloses a YOLO-based method for detecting surface defects on printed circuit boards, belonging to the fields of computer vision and intelligent manufacturing technology. The method includes the following steps: deploying an industrial area scan camera at the inspection station of an automated production line; when a PCB enters the inspection station, the camera is triggered by a sensor to acquire and store images; the acquired image data is processed using data cleaning, data augmentation, and target annotation methods; the processed PCB defect dataset undergoes detailed statistical analysis to optimize the model training strategy; based on the data analysis results, optimization is performed using the YOLOv5 target detection framework to establish a surface defect detection model suitable for PCB production scenarios. This invention can effectively improve the automation level and detection accuracy of defect detection, is suitable for modern large-scale batch production of PCBs, and has good engineering application prospects and industrial promotion value.

This invention discloses a phased array ultrasonic defect intelligent identification and data analysis system, relating to the field of PAUT (Polymerization and Angiography). It includes: an acquisition module for driving a phased array ultrasonic sensor array to perform weld seam scanning according to preset scanning rules, simultaneously acquiring and outputting ultrasonic echo time-series data across the entire depth range of the weld seam; and a preprocessing module for receiving the ultrasonic echo time-series data, performing data correction, noise filtering, and initial screening of effective signals, while simultaneously receiving feature anchoring parameters output by a mapping module, refining the signals in the corresponding regions, and outputting the results. This invention enables continuous, blind-zone-free scanning across the entire thickness and width range of the weld seam, simultaneously completing accurate echo signal correction and defect feature extraction, improving defect identification accuracy through closed-loop adaptive processing, accurately determining defect types and calculating their spatial location, size, and other core parameters, and simultaneously completing defect data statistical analysis and welding process correlation.

The application discloses a power grid real-time event detection and positioning method and system based on synchronous phasor data. Firstly, linear regression and Chebyshev detector are used for abnormal detection and cleaning of PMU synchronous phasor data, and a DBSCAN clustering algorithm is used for detecting clustering change points to classify events. Then, PMU data is statistically analyzed from five dimensions, and PMU scores are calculated. Finally, subgraph construction and scanning are performed to obtain the event location. The simulation results prove the effectiveness of the application in event detection, classification and positioning. The results of industrial data prove the necessity of abnormal detection and the effectiveness of the event detection algorithm. The application can provide a very effective PMU-based power grid real-time event detection tool, and can help power system operators to improve decision-making efficiency.

The application relates to the field of data processing and provides a data analysis system. The system comprises a communication data management platform, a data analysis query system and a service management system; the communication data management platform and the data analysis query system are in communication connection; the service management system is connected with the analysis query system and the communication data management platform; wherein the communication data management platform is used for generating communication index information according to received user call logs, user network access logs and mobile terminal measurement reports, and the communication index information is stored in a distributed manner; wherein the data analysis query system is used for regional hotspot analysis, regional fault statistical analysis, user fault complaint analysis and call detail query; wherein the service management system is used for realizing service request receiving, service request processing and service request response, system configuration file reading and other service process synchronous notification.

The invention discloses an educational performance assessment questionnaire generation and data statistical analysis method, and relates to the technical field of educational management, and the method comprises the steps: constructing a question bank, distributing educational scene attribute tags for questions in the question bank, and building a mapping relation table of keywords and tags; providing a sample confirmation interface, receiving investigation object attributes input by an organizer, and carrying out statistical analysis on the total sample quantity; calling a data interface of the school roll system, obtaining the total number of the investigated objects under each attribute dimension, calculating the sample size of each attribute, and generating a sample size distribution list; receiving keywords, question types and quantity input by an organizer, screening questions, and intelligently assembling the questions into a questionnaire; obtaining a contact way of the investigation object in the sample size distribution list, and directionally issuing a questionnaire; and recovering the questionnaire, rejecting invalid data, combining dimensions based on sample attributes selected by an organizer, calculating a question option proportion and an average score under each dimension, and generating a report. The method can be used for performance assessment scenes in the education field.

The application provides a genomic radial layout visualization recommendation method, and relates to the technical field of information visualization and visual analysis. The method comprises the following steps: statistically analyzing existing radial layout visualization data to obtain statistical characteristics and data types of tracks; encoding a natural language request into an embedding vector through an embedder model, calculating a graph annotation-configuration semantic vector, and calculating the similarity between the two; selecting the view configuration record with the highest similarity according to a preset number; constructing a configuration set network based on the view configuration record, and optimizing the layout of the configuration set network; designing a user interface and an interaction mode based on the optimized configuration set network and the statistical characteristics and data types of the tracks, and recommending the design result to the user. The method can make radial layout visualization recommendations based on natural language requests, which helps to improve the practicability of the visualization method; further, the method can improve the interactivity of the user-recommendation method and the efficiency of visual creation.

The invention discloses a full-automatic test system for a single mainboard of a high-efficiency server, and relates to the technical field of server test. Comprising a test control module, a parallel computing module, a distributed test module, an intelligent diagnosis module and a data storage and analysis module, the test control module is respectively connected with other modules and is responsible for coordinating the working time sequence of each module and controlling the whole process of the test process from starting to ending; the parallel computing module enables multiple test tasks to be carried out simultaneously in a parallel processing mode for a CPU, a memory, a memory, a network and a USB which need to be tested on a server mainboard, the distributed test module distributes the test tasks to multiple independent test nodes to achieve multi-node cooperative work, the intelligent diagnosis module integrates an intelligent algorithm, and the intelligent diagnosis module achieves multi-node cooperative work. Abnormal data generated in the testing process are automatically analyzed, problem reasons are rapidly positioned, diagnosis results are generated, data storage adopts a database to store original data, intermediate results and final testing results in the testing process, data traceability is ensured, an analysis module carries out statistical analysis on the stored data, and the analysis result is obtained. A test qualified rate report and a fault distribution report are generated, and data support is provided for production optimization.

The invention relates to the technical field of electric power, in particular to a power transformer reliability evaluation method. The method comprises the following steps: S1, data collection: collecting operation state data, historical fault data and operation environment data of the power transformer; s2, data analysis: performing arrangement, classification and preliminary analysis on the collected data by using a statistical analysis method; s3, constructing a reliability evaluation model: constructing the reliability evaluation model of the power transformer based on a data analysis result; s4, reliability evaluation: inputting the actual operation data of the power transformer into the reliability evaluation model to obtain a reliability evaluation result of the transformer; and S5, presenting the reliability evaluation result to the user in a visual mode. According to the method, the reliability of the transformer is evaluated based on data analysis and mathematical modeling, the evaluation process is more objective and accurate, potential risks can be found in advance, and decision support is provided for maintenance and replacement of the transformer.

The invention belongs to the field of wind turbine generator torque control, and particularly relates to a wind turbine generator torque control performance evaluation method and system, and the method comprises the steps: obtaining SCADA time sequence data of a wind turbine generator as a sample, obtaining sample data, cleaning the sample data, generating a torque-rotating speed curve, solving the inflection point of the curve according to the slope, carrying out the segmentation, and obtaining a torque-rotating speed curve; control parameters are obtained; performing statistical analysis on the constant power section data to obtain constant power section parameters; taking the non-constant power section control parameters and the constant power section parameters as training samples; inputting the training sample into a single-classification machine learning model for training, optimizing parameters of the single-classification machine learning model to obtain an optimized learning model and an output result, and taking the output result as a fault threshold value; and processing actual SCADA data, inputting the processed data into the optimization learning model to obtain an output result, and comparing the output result with a fault threshold to obtain an evaluation result. The torque control performance evaluation method has the effect of improving the accuracy of the torque control performance evaluation result.

The invention discloses an intelligent student subsidy application auditing and approving system based on big data, and relates to the technical field of information processing management, and the system comprises the steps: obtaining a student address information recognition result through an information recognition module; the address information processing module splits and analyzes the address information to form standard address information, judges the hierarchical state of the standard address information, establishes an address hierarchical fixed matching detection model, and generates a processing signal; the address bidirectional matching module counts and analyzes all address abnormal signals, identifies the uppermost and lowermost addresses of abnormal address information, and generates a search result in combination with a preset forward / reverse derivation rule; the abnormal address information processing and decision-making module compares the consistency of each search result of each abnormal address information, applies a corresponding processing strategy, and further decides whether to execute automatic correction or abnormal prompt modification through a special situation judgment unit, so that automatic auditing and accurate processing of application information are realized, and the application information is more accurate. And the subsidy approval efficiency and accuracy are obviously improved.