Patents
Literature
Patsnap Eureka AI that helps you search prior art, draft patents, and assess FTO risks, powered by patent and scientific literature data.

165 results about "Automatic Data Processing" patented technology

Automatic Data Processing, Inc., commonly known as ADP, is an American provider of human resources management software and services. Until 2014, ADP was one of four American companies in the S&P 500 to have a AAA credit rating from both Standard & Poor's (S&P) and Moody's.

Automatic strapdown inertial navigation calibration test method of temperature control biaxial rate position turntable

The invention relates to the technical field of calibration test, and particularly discloses a strapdown inertial navigation automatic calibration test method of a temperature control biaxial rate position turntable. Comprising the following steps: S1, multi-dimensional error modeling and layered calibration architecture: constructing a comprehensive error model containing a sensor scale factor error, an installation non-orthogonal error, a zero offset error, a cross axis coupling error and a temperature related error; s2, a wide temperature range self-adaptive compensation mechanism: carrying out heat preservation at a preset temperature point and executing turntable positioning and rate movement; s3, performing automatic data processing and parameter estimation; and S4, performing real-time error correction and dynamic verification: performing real-time error correction based on the estimated parameters, and evaluating navigation performance indexes such as position, speed and attitude precision. Through technical innovation, high-precision, automatic and wide-temperature-range calibration of the strapdown inertial navigation system is realized, and the method is suitable for aerospace, intelligent equipment and other scenes with strict navigation precision requirements, and has remarkable engineering application value and market competitiveness.
Owner:BEIJING TIANJIAN ZHIDAO TECH CO LTD

User abnormal behavior monitoring method and device, equipment, medium and product

The invention discloses a user abnormal behavior monitoring method and device, equipment, a medium and a product. Relates to the technical field of deep learning, network security and financial science and technology, and comprises the following steps: obtaining logs generated by a user within a set time, dividing and clustering according to a target time period to obtain a clustering log set, analyzing the clustering log set to obtain a corresponding behavior event label set, and combining and inputting the two into a pre-trained long and short-term memory model to obtain a behavior event label set; and obtaining at least one target behavior operation predicted for each piece of target mark data and a corresponding target behavior occurrence probability, and carrying out abnormal behavior monitoring on the target user according to a matched abnormal monitoring rule based on the target behavior operation and the occurrence probability thereof. Through fusion of the deep learning model and clustering analysis, the monitoring accuracy is improved, the manpower and time cost is reduced through an automatic data processing mode, the monitoring efficiency and the real-time performance are improved, and thus the reliability of user abnormal behavior recognition and safety evaluation is improved.
Owner:INDUSTRIAL AND COMMERCIAL BANK OF CHINA

Employment post recommendation method based on human resource database

The invention relates to the technical field of human resource management and information, and discloses an employment post recommendation method based on a human resource database, and the method comprises the following steps: S1, data collection; s2, data processing; s3, keyword extraction; s4, performing similarity calculation; s5, post filtering and sorting; s6, post recommendation; and S7, effect evaluation: through automatic data processing and similarity calculation, resumes most matched with post demands can be quickly screened out, the workload of recruiters is reduced, accurate matching degree evaluation is beneficial to realizing optimal configuration of talents and posts, employee loss and recruitment cost waste caused by mismatching are reduced, and the efficiency of recruitment is improved. The recruitment will and the matching degree of the job seekers can be improved through accurate recommendation, so that the recruitment success rate and efficiency are improved, more high-quality job seekers are attracted through efficient post recommendation and accurate matching, and the talent reserve and competitiveness of enterprises are enhanced.
Owner:JIANGSU ENZE DIGITAL IND GROUP CO LTD

Automatic data processing method based on artificial intelligence

The invention relates to the technical field of data processing, in particular to an automatic data processing method based on artificial intelligence. Comprising the following steps: collecting original data such as health archives, chronic disease archives and contract signing information through an AP I interface; performing intelligent denoising, feature extraction and data enhancement on the original data by using a sparse coding algorithm; analyzing data by using a deep learning algorithm, and identifying health risks, chronic disease trends and follow-up visit requirements; a health assessment report and an intelligent follow-up visit plan are generated through a fuzzy logic algorithm, and accurate health management suggestions are provided; and displaying a decision result by using a causal graph model, collecting feedback, performing iterative optimization, and continuously improving a health management scheme. According to the invention, intelligent acquisition, processing, analysis and management of health data are realized, the system has the advantages of high efficiency, accuracy and intelligence, and the health management effect and user experience are significantly improved.
Owner:MEDISHARE

Assistant decision-making system and method for water transportation engineering project management based on intelligent agent

The invention discloses an agent-based water transportation engineering project management aid decision-making system and method. The system comprises a data acquisition unit; the data storage unit is used for storing the collected data; the data preprocessing unit is used for preprocessing the data acquired by the data acquisition unit; the knowledge graph construction unit is used for constructing a knowledge base; the updating and maintaining unit is used for regularly updating and maintaining the knowledge base so as to reflect the latest industry specifications, engineering cases and scientific achievements; the intelligent model unit is used for establishing a model; and the model training unit is used for training the model. According to the invention, improvement is carried out from four aspects of automatic data processing, efficient and accurate integration of a comprehensive knowledge graph, establishment of an intelligent model, training for application and decision support and optimization, an efficient, accurate and high-adaptability auxiliary decision-making system and method are provided, and the efficiency and quality of project management are greatly improved.
Owner:NANJING QIANCHUANGREI CLOUD INFORMATION TECH CO LTD

Large model enhanced telephone fraud high-risk user identification method and system

The invention discloses a large model enhanced telephone fraud high-risk user identification method and system, and relates to the technical field of artificial intelligence and information security. The objective of the invention is to improve the accuracy of telephone fraud identification by means of multi-level automatic data processing, multi-model training optimization and multi-model probability fusion, and can significantly reduce the calculation cost and resource consumption. According to the technical key points, a multi-dimensional feature system is constructed by analyzing call data of a user; through multi-model training optimization, high-risk probabilities of different models for different users are obtained, multi-level features of user behaviors are deeply mined, and a machine learning model, a deep learning model and a large language model are covered; the output probability values of a plurality of models are combined through a Stacking voting integration method, and the advantage of each model is utilized to prevent a single model from falling into a local optimal solution. According to the method, advantages and characteristics of different models are effectively integrated, and the overall performance and robustness of an identification system are remarkably improved. According to the method, the fraud identification accuracy is improved, and the calculation cost and the resource consumption are remarkably reduced.
Owner:HARBIN INST OF TECH

Coastal zone sediment feature monitoring method and device and computer equipment

The invention relates to a coastal zone sediment characteristic monitoring method, a coastal zone sediment characteristic monitoring device and computer equipment. According to the coastal zone sediment feature monitoring method, the consistency and accuracy of data are ensured through rasterization processing and a digital format conversion method, and the reliability of an analysis result is improved. The sediment characteristic result of the to-be-detected area is predicted by establishing the quantitative relation between the sediment characteristics and the unmanned aerial vehicle data, the sediment characteristics of the area which is difficult to reach can be rapidly monitored, and the labor cost and the danger degree of sediment sample collection are reduced. Meanwhile, due to the automatic data processing and analysis process, the working efficiency is improved, manual intervention is reduced, and meanwhile the system has high practicability and is suitable for various environment monitoring and analysis scenes.
Owner:EAST CHINA NORMAL UNIV

Service report generation method and device, equipment and medium

The invention relates to the technical field of artificial intelligence and the field of financial science and technology, and discloses a business report generation method, which comprises the following steps: acquiring business data, inputting the business data into a text generation model, and generating a plurality of business description texts; inputting the business data into an image generation model to generate a plurality of business display images; performing association matching on the service description text and the service display image to obtain a text and an image which are associated with each other; and integrating the mutually associated text and image to generate a complete report. According to the method, the text generation model and the image generation model are combined, and the generated text and image are intelligently matched and integrated, so that the content richness and readability of the report are improved. Meanwhile, through automatic data processing and generation steps, the generation efficiency is improved, and the accuracy and consistency of data description and image display in the report can be ensured.
Owner:PING AN TECH (SHENZHEN) CO LTD

Clinical test quality evaluation method and system based on artificial intelligence

The invention discloses a clinical test quality evaluation method and system based on artificial intelligence, and relates to the technical field of clinical test quality evaluation. Through a series of automatic data processing and model evaluation processes, automatic operation is basically realized from data acquisition to final report generation, manual complex evaluation calculation on a large amount of data is not needed, and the evaluation efficiency is greatly improved; evaluation is carried out through an artificial intelligence algorithm and a rule-based expert system, so that the influence of subjective factors on an evaluation result is effectively reduced, and the consistency and accuracy of the evaluation result are improved; according to the method, multiple types of high-dimensional data are processed through an artificial intelligence algorithm, key feature subsets are extracted through feature extraction and screening, a trained deep learning model is used for evaluation, the method adapts to constantly changing large-scale and high-dimensional data conditions by constantly optimizing model performance, and the requirement for efficient and accurate evaluation is effectively met.
Owner:BEIJING SINOCRO PHARMASCIENCE CO LTD

Spring probe system for rapid registration of articular cartilage based on 3D printing

The invention discloses a spring probe system for rapid registration of articular cartilage based on 3D printing, and relates to the technical field of medical imaging and orthopedic surgery navigation. The problem that the joint registration precision is insufficient due to the fact that cartilage cannot be developed in traditional CT imaging is solved. Through personalized customization of the 3D printing guide plate, convenient installation of positioning holes, adjustability of the spring probe assembly and real-time data monitoring, and automatic data processing of the intelligent registration module, manual operation is reduced, the operation efficiency is improved, the spring probe assembly is reasonable in structure and adjustable in elastic force, stable operation of the system in an operation is guaranteed, and the operation safety is improved. Multi-position CT scanning is combined with an advanced image processing and registration technology, an accurate initial model is constructed, a spring probe assembly collects data and is combined with an elastic deformation compensation model to correct registration errors in real time, the registration accuracy is improved, reliable support is provided for orthopedic surgery navigation, the surgery success rate can be improved, and patient wounds and surgery risks are reduced.
Owner:PEKING UNIVERSITY THIRD HOSPITAL (THE THIRD CLINICAL MEDICAL SCHOOL OF PEKING UNIVERSITY)

Automatic construction system for financial data management

The invention discloses an automatic construction system for financial data management, and relates to the related technical field of financial data management, and the system comprises a user interface module which is used for providing an intuitive graphical interface, and enabling a user to construct an application process in a mode of dragging a component; the business logic module is used for calculating the production cost of the product and automatically generating an asset balance sheet, a profit sheet and a cash flow sheet; and the financial trend prediction module needs historical financial data as input, the user inputs financial data and related characteristics, and the model outputs a prediction result. An automatic data processing and report generating system can be rapidly constructed through an automatic tool, the labor burden is relieved, a low-code platform system allows a user to customize and adjust the financial process in a visual mode, the individual requirement can be met without compiling a large number of codes, and the user experience is improved. The LLM technology can provide natural language understanding and intelligent analysis ability, and assists non-professionals in deep financial insight and strategic decision making.
Owner:HANGYIN CONSUMER FINANCE CO LTD

Business data processing method and system based on visual lane modeling

The invention relates to the technical field of visual lane modeling, and discloses a business data processing method and system based on visual lane modeling, and a multi-task prediction model based on multi-source historical business chain data training graph neural network and Transform fusion. A plurality of groups of lane layout and event configuration schemes are generated in combination with user real-time operation captured by a design interface, an optimal scheme is screened through simulation evaluation and then is visually displayed, finally, visual lane modeling is executed according to user feedback, and through automatic data processing, high-precision model prediction, real-time interaction optimization and visual modeling, the optimal lane layout and event configuration scheme is obtained. According to the method, the service chain design efficiency and quality are improved, meanwhile, artificial experience deviation is avoided through model prediction based on historical data, the comprehensive requirements of complex equipment development for real-time performance, reliability and resource efficiency are met, and efficient technical support is provided for landing of model-based system engineering in the field of complex equipment.
Owner:GHOSTCLOUD

IT class project cost financial independent accounting system

The invention belongs to the technical field of IT type project cost financial management, and discloses an IT type project cost financial independent accounting system, which comprises a project management module, a receivable management module, a payable management module, a purchase management module, a financial system data exchange module, a human resource data exchange module and an early warning management module. According to the system, integrated management is adopted, project cost is monitored in real time and dynamically adjusted, the system collects and updates cost data in real time, rapid adjustment is carried out once deviation is found, it is ensured that the cost is controlled within a prediction range, project management flexibility and response speed are improved, cost hyper-branched risks are reduced, and meanwhile through automatic data processing and accounting processes, the project management efficiency is improved. The cost accounting accuracy and efficiency are remarkably improved, personal errors are avoided, manual calculation is simplified, a project manager can efficiently master the cost condition, powerful data support is provided for project decision making, and the scientificity and effectiveness of project management are ensured.
Owner:KARAMAY HONGYOU SOFTWARE

Method for generating rotor fault diagnosis model based on multi-transformation domain and diagnosis method

The present invention discloses a method for generating a rotor fault diagnosis model based on multiple transform domains and a diagnosis method. The former includes: collecting vibration signal data of a modular rotor fault of a gas turbine in multiple categories to construct a training and test data set; transforming each data to the short-time Fourier time-frequency domain using the STFT transform domain, transforming it to the Morlet wavelet time-frequency domain using the Morlet wavelet transform domain, and transforming it to the complex network phase space domain using the complex network recurrence plot method; inputting the training data set transformed by the three transform domains into a preset model, and using the CNN network layer for feature extraction; using the LSTM network to perform feature structure learning on the output features, and training to obtain a rotor fault model; using the test data set transformed by the three transform domains to verify and adjust the rotor fault model to obtain a rotor fault diagnosis model for fault detection. The present invention can realize automatic data processing, reduce manual input, and improve the efficiency and accuracy of fault diagnosis.
Owner:NORTHWESTERN POLYTECHNICAL UNIV

Green building performance analysis method and system based on BIM and AI large models

The invention discloses a BIM and AI large model-based green building performance analysis method and system, and the method comprises the steps: constructing a three-dimensional information model of a building based on a BIM technology, carrying out the performance simulation of the three-dimensional information model, obtaining the performance simulation data of the building, carrying out the deep learning and processing of the performance simulation data through employing the AI large model, and obtaining the performance simulation data of the building. And obtaining a building performance analysis result, and generating and displaying a building performance optimization suggestion according to the building performance analysis result. According to the method, the three-dimensional information model is constructed by using the BIM technology, and the full-life-cycle information of the building is integrated, so that the performance analysis is more comprehensive and accurate. Meanwhile, the AI large model technology is combined, hidden information and rules in the data can be deeply mined, and the analysis accuracy is further improved. And through an automatic data processing flow, the manual operation is greatly reduced, and the analysis efficiency is improved. The introduction of the AI large model enables the data processing to be intelligent and adaptive, and the processing strategy can be automatically adjusted according to the data characteristics.
Owner:CHINA XINXING CONSTR & DEV CO LTD

Optical cable rapid positioning system and method thereof

The invention relates to the field of optical fiber sound wave sensing and positioning, in particular to an optical cable rapid positioning system and a method thereof, the positioning system does not depend on real-time network communication, can stably operate even in an environment without a communication network, shows obvious advantages, and can realize rapid positioning by playing characteristic sound waves with specified frequency components. The interference of environmental noise can be effectively reduced, the positioning accuracy can be remarkably improved, even in a noisy environment, the accuracy of a positioning result can be ensured by applying a high-strength characteristic signal and filtering noise interference of a non-target frequency band, and the accuracy of a positioning result can be ensured by adopting an offline acquisition-online processing mixed framework. The environmental adaptability and the automatic data processing capability of the system are obviously improved, and the complexity and the potential error rate of manual operation are greatly reduced; the problems that an existing optical cable positioning system and method depends on GPS positioning and a real-time communication network and is easily influenced by subjective judgment, the calculation efficiency of all-point analysis is low, and the number of participants is too large are solved.
Owner:ZHEJIANG UNIV +1

Method and system for pre-judging fatigue driving of online car-hailing driver

The invention discloses an online car-hailing driver fatigue driving pre-judgment method and system. The invention relates to the technical field of online car hailing. And collecting driver departure data O and driver order receiving data M which are arranged according to a time sequence. O = [O1, O2,..., ON]; m = [M1, M2,..., MN]; o1, O2,..., ON and M1, M2,..., MN are historical data of driver departure data O and driver order receiving data M respectively. Executing exponential smoothing according to the trend and the seasonality of the driver departure data O and the driver order receiving data M in the time sequence; by adopting the Holt-Wittes seasonal model, the method can accurately capture the periodicity and tendency characteristics of the driving and order receiving behaviors of the driver, and significantly improves the prediction accuracy. The automatic data processing and prediction process greatly shortens the prediction period, improves the operation efficiency, and enables the platform to respond to the potential risk of fatigue driving of the driver more quickly.
Owner:BEIJING BAILONG MAYUN TECH CO LTD

Parasitic parameter result automatic analysis system based on FUZZ test

The invention relates to the technical field of automatic data processing of integrated circuit design, in particular to an automatic parasitic parameter result analysis system based on an FUZZ test. The fuzzy test engine module adopts syntax tree variation to generate a test case library comprising illegal characters, extreme values and logic loops, the exception response module captures illegal operations in an analysis and simulation stage through the probe detection unit, and the correction decision unit executes data restoration or generates an exception report. And the incremental updating unit synchronizes the abnormal features to a model self-optimization module rule base. And the dynamic adaptation module converts the multi-process parasitic parameters into a standardized simulation model through the process parameter abstraction layer. All the modules form a closed-loop system for test case generation, anomaly detection and repair and rule dynamic optimization, automatic processing of an unexpected input scene is achieved, and robustness and multi-process compatibility of parasitic parameter analysis are improved.
Owner:青岛展诚科技有限公司

Data interaction method based on browser plug-in

The invention relates to the technical field of automatic data processing of computer software, in particular to a data interaction method based on a browser plug-in, which comprises the following steps: acquiring a starting instruction of a user, and starting the plug-in according to the starting instruction; the plug-in obtains an element of a target page selected by a user, and captures a unique identifier of the element; and the plug-in executes automatic data interaction based on the element according to a condition configured by a user. According to the technical scheme provided by the invention, complicated IT support and hardware configuration are not needed, and the unique identifier of the target page element is captured, so that the accuracy and consistency of subsequent element-based operation execution are ensured; the local encrypted and stored operation record ensures the security of the sensitive data, prevents data leakage, is also convenient for an administrator to examine and trace the operation history, and is beneficial to application in an efficient management environment.
Owner:YINCHUAN POWER SUPPLY COMPANY OF STATE GRID NINGXIA ELECTRIC POWER

Enhanced AI large model engineering automatic arrangement system

The invention relates to the field of AI, in particular to an enhanced AI large model engineering automatic arrangement system which comprises an automatic data processing module, a model development and training module, a hyper-parameter optimization module, a model evaluation and verification module, a resource management module and a monitoring and maintenance module. According to the scheme, an improved hyper-parameter optimization method is adopted to optimize hyper-parameters in AutoML, the core concept of the method is that a weight coefficient is used, the relative importance of a fitting error and a prediction error in a weighted error function is controlled, and the balance between over-fitting and under-fitting is achieved by adjusting the weight coefficient; a dynamic cloud scheduling method based on intelligent agents is adopted for resource scheduling, the method intelligently adapts to user requirements and selective service quality based on distributed learning in an edge cloud computing environment, more efficient task scheduling is achieved, and the automation level of the whole AI model life cycle is improved.
Owner:SHENZHEN LINGZHI SPACE-TIME DIGITAL CO LTD

Method for automatically identifying positions of unsaturated fatty acid and double bonds thereof

The invention discloses a method for automatically identifying unsaturated fatty acid and double bond positions thereof. According to the invention, the principle of regular fragmentation of unsaturated fatty acid in a collision dissociation mode of a liquid chromatography-tandem mass spectrometer after the unsaturated fatty acid is subjected to a Pattern-Buchi (PB) reaction is utilized; the invention develops an automatic data processing method for unsaturated fatty acid mass spectrum data acquired in two modes of a data dependent acquisition mode and a data non-dependent acquisition mode in liquid chromatography-tandem mass spectrometry, and can automatically identify unsaturated fatty acid and double bond positions thereof from huge DDA data of liquid chromatography-tandem mass spectrometry. And the quantitative analysis of the unsaturated fatty acid is realized by utilizing the strength information of the characteristic fragment ions in the DIA data, so that the accuracy and the efficiency of the qualitative and quantitative analysis of the unsaturated fatty acid are remarkably improved.
Owner:EAST CHINA UNIV OF SCI & TECH

Rapid inversion method for microscopic fracture parameters of cement stabilized macadam

The invention discloses a cement stabilized macadam mesoscopic fracture parameter rapid inversion method, and the method achieves the multi-dimensional improvement of model scale selection, automatic data processing, machine learning model construction, parameter result optimization and the like through the construction of an inversion process of a discrete element model-XGBoost model-particle swarm optimization model frame. The inversion efficiency is improved; the time and energy consumed by repeated manual trial calculation are reduced; the multi-objective optimization advantage of a vectorization particle swarm optimization algorithm is fully utilized, and the vectorization particle swarm optimization algorithm is combined with an XGBoost model, so that the optimal solution of a target vector is realized; compared with a manual trial and error method, the method has the advantages that multi-dimensional targets can be optimized at the same time, so that a real test result is approached at the fastest efficiency, and the precision of the cement stabilized macadam microscopic fracture parameters is greatly improved.
Owner:HOHAI UNIV

Industrial automatic control data processing system and method based on digital twin

The present invention discloses an industrial automatic control data processing system and method based on digital twin, which belongs to the field of industrial automation control technology. The present invention establishes a connection between the edge side and the cloud center through the edge side management module, automatically collects industrial data through the edge collection node, and stores the collected industrial data in the edge device; sends a data request to the cloud center through the data mapping module, and the cloud center receives the industrial data uploaded by the edge side and maps the received industrial data in the digital space based on the digital twin technology; analyzes and feedbacks the data collection status of the edge side through the cloud processing module; updates the data collection strategy of the edge side according to the analysis results fed back by the cloud center through the collaborative control module, and transmits the updated data collection strategy to the edge device, and adjusts the data collection business of the edge collection node. The data in the industrial production process is processed more flexibly, which reduces the resource consumption of operation and maintenance.
Owner:NANJING SUTONG TECH CO LTD

Rocket flight result rapid evaluation method

According to the rocket flight result rapid evaluation method, rocket flight data can be processed, an interpretation report is automatically generated, and working state rapid interpretation of pre-cooling before launching of a liquid rocket engine, fault diagnosis before ignition and in the flight process is achieved. According to the rapid judgment method for the rocket flight result, the analysis efficiency can be remarkably improved, and the time from the end of rocket flight to the obtaining of the engine analysis result is greatly shortened through automatic data processing, analysis process and rapid report generation. According to the evaluation method, the standard interpretation report is automatically generated, the problems of low manual analysis efficiency, incomplete analysis and the like are solved, and powerful support is provided for evaluation and improvement of rocket launching tasks.
Owner:BEIJING LANDSPACETECH CO LTD

Pressure test system suitable for energy storage monitoring system and test method thereof

The invention discloses a pressure test system suitable for an energy storage monitoring system and a test method thereof. The pressure test system is provided with a task management module, a data object module, a strategy control module, a communication management module, a message monitoring module and a data processing module. The system can provide powerful support for test and acceptance of an energy storage monitoring system, can process and simulate a large number of energy storage devices, provides a test platform capable of simulating operation of a large-scale energy storage system, supports various communication protocols and protocols, ensures interoperability of testing different types of energy storage devices and systems, and improves test efficiency. Communication of multiple channels and concurrent testing of multiple testing tasks can be simulated, automatic data processing is introduced, the testing efficiency can be greatly improved, manual intervention is reduced, human errors are avoided, and repeatability and accuracy of testing results are ensured. In addition, the test result is automatically analyzed according to the preset judgment logic, problems and abnormities can be rapidly recognized, and therefore fault diagnosis and problem solving are accelerated.
Owner:XUCHANG KETOP DETECTION TECH CO LTD

Method for rapidly solving plane segmentation via hole in multilayer integrated circuit board

The invention provides a method for rapidly solving a plane segmentation via hole in a multilayer integrated circuit board. The method comprises the following steps: calculating a connection relation of all elements in the multilayer integrated circuit board, determining a vertical position of each via hole, identifying a plane layer intersected with the via hole, recording connection information, allocating a priority value to each plane layer, sorting according to the priority values, and creating a data structure QMaplt; a QPair is used as a QPair; int, int, and intgt; , QSett, QSett; a Viagt; gt; the data structure is converted into QMaplt; via, QSetlt, Via, QSetlt; a QPair is used as a QPair; int, int, and intgt; gt; gt; and on the basis of the obtained relation that each via hole is cut by the plane, cutting holes segmented by the plane. According to the method, through an automatic data processing and optimization algorithm, the accuracy and efficiency of via hole segmentation are improved, the design and manufacturing cost is reduced, the production cycle is shortened, and powerful technical support is provided for design and manufacturing of a multilayer integrated circuit board.
Owner:XPEEDIC CO LTD

A dynamic resume evaluation method based on a multi-modal large model

The present application relates to the technical field of automatic data processing, in particular to a dynamic resume evaluation method based on a multi-modal large model. The method comprises: receiving a file containing the resume information of an applicant and a portfolio containing one or more visual works of the applicant; based on the file containing the resume information of the applicant, analyzing the file using a resume analysis module to generate a resume score; based on the portfolio of the applicant, analyzing the portfolio using a portfolio analysis module to generate a portfolio score; based on the file containing the resume information of the applicant and the portfolio of the applicant, calculating a consistency score using a consistency analysis module; and fusing the resume, portfolio and consistency scores to generate a final matching degree score to determine the matching degree of the applicant and the post. The present application solves the problem that traditional methods cannot evaluate visual materials and verify the authenticity of resumes, and provides a more accurate, objective and comprehensive candidate screening scheme.
Owner:BEIJING DA ZHI CHUANG HUI EDUCATION TECHNOLOGY CO LTD

Natural resource big data aided decision-making system based on virtual geographic environment

The invention relates to the technical field of big data auxiliary decision-making systems, and discloses a natural resource big data auxiliary decision-making system based on a virtual geographic environment. According to the method, multi-level and multi-angle analysis of the natural resource big data is realized, a flexible automatic data processing mode greatly improves the working efficiency, the accuracy and authenticity of the natural resource big data analysis result are ensured, and a decision basis is provided for protecting cultivated land resources, strictly managing natural resources and strengthening the macroscopic regulation and control of national economy. According to the characteristics and types of the environmental perception data, a visualization system of the environmental perception data in a virtual geographical environment lake is provided, different visualization methods are adopted to express monitoring data of an environmental wireless sensor, and a vector field construction method is utilized to realize dynamic change of vector data in a virtual geographical environment world. Real-time environment sensing video monitoring images and virtual geographical environment scenes are fused, and real-time observation and monitoring of the birds and the water body in the Poyang Lake are achieved.
Owner:江西省自然资源事业发展中心

A business data processing method and system based on visual lane modeling

The application relates to the technical field of visual lane modeling, and discloses a business data processing method and system based on visual lane modeling, wherein a multi-task prediction model of a graph neural network and a Transformer fusion is trained based on multi-source historical business chain data, a plurality of groups of lane layout and event configuration schemes are generated in combination with real-time operations of a user captured by a design interface, the optimal scheme is selected through simulation evaluation and filtering, and visual display is performed, and finally, visual lane modeling is executed according to user feedback, through automatic data processing, high-precision model prediction, real-time interactive optimization and visual modeling, the design efficiency and quality of a business chain are improved, meanwhile, model prediction based on historical data avoids artificial experience deviation, meets the comprehensive requirements of real-time performance, reliability and resource efficiency for complex equipment development, and provides efficient technical support for the landing of model-based system engineering in the field of complex equipment.
Owner:GHOSTCLOUD