355 results about "Datafication" patented technology

The invention discloses a method for mining flight number regulatory factors through historical data/ through analyzing the regulatory factors by three aspects, the regulatory factors of height, speed and horizontal position are extracted, and datamation of a regulator regulatory command is carried out; and the regulatory factors are introduced for correcting a planned track, thus the accuracy of an aircraft plan prediction track is improved.

The invention provides a digitalized coal yard system based on Internet of Things and an artificial intelligence system, relates to the technical field of fuel management, digitalized factories and power generation, and particularly relates to a digitalized management system of a coal yard. The method is based on the Internet of Things. The invention discloses a digital coal yard system of an artificial intelligence system. Digitization and intelligentization of coal yard and fire coal data are achieved by means of an artificial intelligence system, coal quality test equipment and entrance detection equipment are combined by means of coal yard related equipment and an information acquisition intelligent terminal, fire coal digital management is achieved, a data reference basis is providedfor coal blending combustion and fire coal planning, and actual economic benefits are brought to enterprises. According to the invention, a management chain from entry to evaluation is required to beestablished, and closed-loop management of fuel is realized, so that a coal yard management platform and a coal-fired data center are provided on the basis of an overall scheme architecture, and digitalization, visualization and intelligentization of coal yard management of power generation enterprises are realized through construction of the coal yard management platform and the coal-fired data center.

The invention relates to the field of exploration and development of oil and gas fields, in particular to a fracture fractal characteristic optimization computation method. After datamation of a facture zone, parameters of statistical boxes are defined by setting boundary parameters and initial positions, the statistical boxes are moved constantly through program writing, fractal dimension values of the positions where the statistical boxes are located are calculated, and therefore programmed calculation of fracture fractal characteristics is realized. The fracture fractal characteristic optimization computation method has high practical value on the aspects of fracture fractal characteristic quantitative evaluation, fracture fractal characteristic quantitative description and the like, is low in prediction cost and high in operability, and greatly reduces the expense of manpower; evaluation results have certain guiding significance in the aspects of predicting the distribution characteristics of oil and gas exploration and development key areas, fracture dominant distribution areas and low-level-sequence faults and the like.

The embodiment of the invention provides a micro-service architecture of a process industry datamation operation platform. The micro-service architecture comprises a micro-service business architecture and a micro-service technology architecture, wherein the N micro-services are realized by abstracting a whole process industrial model through a high-cohesion low-coupling design mode and DDD domainmodel abstraction, N is greater than 1; the implementation of the high cohesion and low coupling design mode is abstracted through a DDD tactical mode, each domain defines a model, logic and an interface of the domain, relationships among the models are distinguished through UML, and the models with close relationships are placed in the same domain. According to the embodiment of the invention, the problem of MES service rigidity of the traditional process industry is solved, the service expansibility is obtained again, and a comprehensive and reasonable datamation operation platform can be constructed.

The invention discloses a tuyere information deep learning-based blast furnace condition abnormity supervision and prediction method, which comprises the following steps of: extracting a blast furnace tuyere image, and carrying out denoising preprocessing on the tuyere image by adopting a mode of combining adaptive median filtering and gamma transformation; enhancing the picture contrast by combining a gray binarization algorithm and gray up-shift, then carrying out unsupervised classification on a sample image, automatically generating a label, and constructing a tuyere image database; and establishing a TI-ResNet model to extract the characteristics of the blast furnace smelting process, and finally utilizing the trained TI-ResNet model to supervise and predict the real-time or off-line furnace condition of the blast furnace based on the blast furnace tuyere monitoring data obtained in real time or off line. According to the method, closed-loop automatic datamation and automatic tagging can be realized, the established TI-ResNet model is automatically trained based on the updated data set, and online or offline furnace condition abnormity supervision and prediction can be performed by applying the established intelligent algorithm and model.

The invention discloses a residential quarter power load control method and device based on non-invasive power consumption data. The method comprises steps of inputting normalized data into an LSSVM model based on digitized electric equipment operation states, obtaining the operation states of all electric equipment in a future period of time, and combining the unit time power consumption of the electric equipment in a starting state and a continuous state to form a short-term load prediction curve; dividing a power load into a transferable load, a reducible load and a rigid load for the electric equipment in a stop state according to scheduling potential requirements, and constructing a power consumption curve of a reducible load; and forming a peak evaluation line of day-ahead schedulingby combining a short-term load prediction curve and a power consumption curve, and applying the peak evaluation line to the day-ahead scheduling of a cell so that safety of the circuit load is improved. The device comprises an electric equipment selection unit, a non-intrusive power load multi-target decomposition unit, a datamation operation state unit and an LSSVM prediction unit.

The invention discloses a traffic monitoring system based on the intelligent traffic Internet of Things. The traffic monitoring system comprises a monitoring and collecting module, a violation analysis module, a database, a controller, a signal processing module and an update and coverage module; and the monitoring and collecting module is used for real-time monitoring and collecting traffic violation information of vehicle drivers and transmitting the traffic violation information to the violation analysis module. According to the traffic monitoring system disclosed by the invention, data analysis is performed on the traffic violation information of the vehicle drivers, secondary formula weight processing is performed on the traffic violation information and behavior conditions accordingly, so as to endow the vehicle drivers with different attention at different levels, and the attention conditions are updated and covered in time through subsequent behavior conditions, in this way, the monitoring of traffic conditions is implemented to the corresponding source drivers, and targeted supervision is performed based on real-time updated level signals to improve the overall traffic monitoring effectiveness and the driving supervision intensity.

The invention discloses a numerical control machine tool feed shaft thermal error monitoring method based on digital twinning. The method comprises the following steps: creating a virtual digital model of an entity numerical control machine tool feed shaft based on three-dimensional modeling software and MATLAB scripting language; creating a driving data acquisition module based on the MATLAB scripting language and Simulink, and acquiring geometric model driving data from a numerical control system; creating a thermal error data acquisition module based on the Simulink, and obtaining thermal error prediction data; connecting all the modules mentioned above through data input and output interfaces on the basis of Simulink, building a feed shaft digital twinning body model, and achieving three-dimensional real-time presentation of feed shaft thermal errors; and creating a user-oriented interactive interface based on the MATLAB scripting language and the Simulink. According to the method,machine tool feed shaft thermal error monitoring can be displayed from datamation to visualization, and a specific implementation method is provided for application of the digital twinning technologyin the field of numerical control machine tool thermal error monitoring.

The invention provides a water level and flow estimation method for free surface flow, which is characterized by comprising the following steps: a, performing data processing on river cross section information, and establishing a linear relationship among a water level, a cross section area, a cross section wetted perimeter and a hydraulic radius on each calculation cross section; carrying out datamation processing on the model parameters, the initial conditions and the boundary conditions; b, substituting the linear relation and data of the model parameters, the initial conditions and the boundary conditions into a one-dimensional hydrodynamic basic control equation, performing numerical solution, and deducing a next moment value according to the boundary conditions and a known moment value in sequence until calculation requirements are met; and c, outputting section flows and section water levels at different moments and water level processes and flow processes of different sections.Reliable technical support is provided for engineering planning, design and flood analysis and management.

The invention belongs to the technical field of equipment operation guarantee, and particularly relates to an equipment fault diagnosis method. The method comprises the following steps: determining the category, rated parameters and initial life cycle of research equipment; establishing an expert system model rule base according to object category characteristics; establishing an object historical database; introducing an artificial neural network to model a high-dimensional nonlinear problem; fault diagnosis is realized by using a BP neural network; according to the equipment fault diagnosis method, technologies such as big data and an artificial intelligence algorithm are introduced to digitalize, model and standardize equipment rated parameters, equipment operation conditions, equipment operation and maintenance history and experience and the like, meanwhile, a diagnosis system is endowed with intelligent learning and changing capabilities, and debugging parameters are fed back and corrected according to result output; and finally, the full life cycle state of the equipment is displayed and reflected through a visual platform, and data support is provided for fault early warning, diagnosis analysis and fault maintenance decision, so that the fault rate of the equipment is reduced.

The invention discloses a construction site fire operation management system based on video intelligent analysis and an implementation method thereof. The method comprises the following steps: comparing and analyzing human, object and environment images obtained through videos with a reference image in a construction site fire area according to three stages of before-fire, during-fire and after-fire, including environment monitoring, personnel wearing monitoring, personnel tracking monitoring, personnel identity recognition monitoring and smoke and fire monitoring. The monitoring tool uses a camera designed by an AI algorithm acceleration chip with built-in image recognition, smoke recognition, object recognition and face recognition algorithms to perform video shooting and intelligent analysis application. A video is transmitted to the background construction site fire operation management software system through the camera for data comparison and real-time management, and the background construction site fire operation management software system comprises a user data system, a data analysis and verification system, an alarm system and a report system so as to achieve the intelligent and datamation effect of construction site fire operation management.

The invention relates to a ceramic production line-based data transformation system. The system comprises an equipment layer transformation module, a data acquisition layer module, a basic platform module, a data middle platform module and an application layer module. The equipment layer transformation module outputs an optimization scheme for a raw material workshop, a forming workshop, a firingworkshop, a polishing and grading workshop, a quality inspection system, an energy management system and a process workshop on a ceramic production line. The data acquisition layer module performs data acquisition on the equipment layer transformation module through a gateway and a network protocol and uploads the data to the basic platform module. The basic platform module is provided with a cloud server and is used for analyzing the data and sending a data analysis result to the data middle station module. The data middle platform module is used for generating a data middle platform according to a data analysis result and feeding back the data middle platform to the application layer module. The application layer module is used for applying the data middle platform. Data production of the ceramic production line is realized through automatic data acquisition, terminal input data and informatization system data coorperation.

The invention provides a video conference big data analysis method, which comprises the following steps of: matching content generated by pre-conference preparation work with a predefined conference monitoring rule template to generate a corresponding monitoring rule tree; on the basis of the monitoring rule tree, extracting effective data in the video conference, and completing quantification ofreal-time datamation description indexes of the video conference; generating a quantitative evaluation result of the video conference based on the quantification of the datamation description index; and giving a real-time deviation prompt or abnormal warning for the condition that the quantitative evaluation result deviates from the standard range. A corresponding system is designed based on the method, so that the result output efficiency of the video conference is improved, and unnecessary resource waste is avoided.

The invention provides a data reading method, system and device and a medium, and the method comprises the steps: obtaining data, storing the data to a local disk and a ceph sharing disk through employing a micro-service, enabling the ceph sharing disk to store full data through employing a distributed file system, and enabling a part of data stored in the local disk to be exclusively shared by the corresponding micro-service; when the micro-service receives the query request, judging whether the service state of each pod is normal or not, and when the service state of each pod is normal, distributing the query request to the Pod with the normal service state to query the local disk, and summarizing and sequencing to obtain a query result; and when the service state of the pod is abnormal,querying partition data corresponding to the pod with the abnormal service state corresponding to the ceph shared disk, and summarizing and sequencing to obtain a query result. The ceph shared disk and the local disk are mixed for use, so that the stability of the system is improved; the performance of the local disk is exclusively shared by a single micro-service, so that the data reading efficiency is improved; and part of data is queried through each pod instead of all data, the whole is broken up into parts, and the overall query speed is provided.

The invention discloses a service evaluation method based on actual user usage, and belongs to the technical field of government affair service systems. The method comprises the steps: firstly, establishing mobile terminal user evaluation and evaluation data collection; establishing a data level label weight data arrangement strategy; and establishing a service status, existing problems and rectification effect display. According to the invention, the user evaluation is digitized by using the Internet technology, the government affair service level is improved by using digitized resources, andthe digitization of the user evaluation is achieved based on the establishment of complete evaluation grade assignment; based on the premise of evaluation datamation, data visualization is achieved,visual display is carried out for high-frequency usage scenarios and key indexes, phenomena and rules contained in data can be found conveniently, analysis and application of evaluation data are established, and data support is provided for enhancing poor evaluation service rectification and establishing a reward and punishment system in the later period.

The invention provides a PID drawing analysis method based on deep learning, a computer system and a storage medium. The method comprises the following steps: establishing a recognition model set; traversing the PID drawing image with a first identification frame to obtain a pipeline identification data set; traversing the PID drawing image by using a second identification frame to obtain a device identification data set; performing data fusion in the pipeline identification data set and the device identification data set by applying a non-maximum suppression algorithm to obtain pipeline data and device data; and traversing each pipeline by using a clustering association Attract algorithm, identifying a device associated with the pipeline, and forming a corresponding relationship between the pipeline and the device in the PID drawing. The method has the beneficial effects that the pipelines and the devices on the PID drawing image are identified through the deep learning algorithm, and the pipelines and the correspondingly associated devices are summarized, so that the pipelines and the devices in the PID drawing can be rapidly and intelligently identified and analyzed, a large amount of manual identification, the statistics and arrangement time is shortened, and datamation of the PID drawing is realized.

The invention discloses a system and method for intelligently managing museum collections based on the Internet of Things and indoor GIS. The system includes a system management platform, a data warehouse, RFID labels, museum environmental factor sensors, mobile terminals and a GIS vector electronic map. The museum environmental factor sensors are arranged in the periphery of museum collections. The RFID labels are arranged on the museum. The museum environmental factors are intended for acquiring environment information of the museum collections, transmitting the environment information to a management platform, and storing the environment information to the data warehouse. The mobile terminals acquire the information of the museum collections by reading the RFID labels. The GIS vector electronic map is intended for managing, updating and maintaining data pertaining to internal architectural structure of the museum, organizational structure of the museum and the geographical position and spatial layout of various collections in combination of the data warehouse, and providing the positioning and navigation in the museum. According to the invention, the system increases the capacity of managing the museum and working efficiency of management workers.

The invention discloses an intelligent decision-making system and method for a rainwater collecting recycling system. The rainwater collecting recycling system structurally involves a rainwater pretreatment group, a reservoir, a purification tank and a clean water tank, wherein the rainwater pretreatment group conveys pretreated rainwater to the reservoir, and the reservoir sequentially conveys the water to the purification tank and the clean water tank through pipeline connection; the decision-making system involves a multi-dimensional data acquisition group, a host and a multi-dimensional controller group, wherein the multi-dimensional data acquisition group acquires multi-dimensional parameter data and transmits the data to the host, and the host outputs an optimal control value to control the multi-dimensional controller group; and the method comprises the steps of filtering current unit time data, predicting future unit time data and updating prediction model, control model and system model data. According to the decision-making system and the method, the labor for manual management is greatly reduced, the comprehensive management cost is reduced, the datamation, real-time andintelligent degrees of sponge measure management are improved, and the social benefit and economic benefit of sponge city construction are improved.

The invention discloses a conditional random field algorithm prediction result backflow training method for automatic news splitting. The method comprises the steps of 1, carrying out datamation on anews program video; step 2, training a conditional random field model and carrying out label prediction on the news program video needing label prediction to obtain a news story of the news program video; 3, collecting in-out point information of news stories of the news program video; 4, periodically utilizing the collected in-out point information of the news stories, combining a heuristic rule,automatically correcting scene layer feature data in the old scene layer feature data table, and storing the corrected scene layer feature data into a CRF training data table; and 5, retraining the conditional random field model according to the last training time and the data size in the CRF training data table. According to the method, the accuracy of the conditional random field algorithm canbe improved, and the label prediction time of the subsequent manual correction scene layer algorithm is saved.

The invention discloses a federated learning income distribution method and system. The method comprises the following steps: evaluating the validity of the data contributed by each data provider inthe federation; measuring type parameters of federated learning participants; calculating pricing of the federated learning model, calculating payment for each data provider based on one or more of model income, data validity parameters and type parameters of the data providers, enabling participants to report the type parameters of the participants to the federated system, selecting an optimization target, and calculating the financing interest rate of the federated learning system. The invention aims to calculate how to effectively, reasonably and fairly allocate income generated by a federated learning model to each participant, so that federated learning is digitized, recordable and easy to adjust in practical application, and income and expenditure adjustment or product updating is facilitated.

The invention discloses a scene scanning positioning method, a storage medium and a system, and the method comprises the following steps: pasting a user-defined identifier on the surface of an object,the user-defined identifier comprising azimuth information and size information; The indoor entity content environment is scanned, a result obtained through scanning is digitalized, when the user-defined identifier is scanned, azimuth information and size information on the user-defined identifier are recognized, and the spatial position of current equipment is calculated according to the azimuthinformation and the size information. The design cost is reduced, and the three-dimensional scene modeling accuracy is improved.

The invention discloses a cockroach mating behavior analysis method and a system, and a storage medium. The cockroach mating behavior analysis method comprises the following steps: acquiring a cockroach video and a training set video; performing target detection through a neural network model according to the cockroach video and the training set video, and extracting individual information and behavior information; performing target tracking on the cockroaches after the target detection operation; generating a target tracking video, and generating a data statistics result in combination with the individual information and the behavior information; performing data visualization and result analysis on the data statistical result to generate a cockroach prevention and control or artificial breeding scheme; according to the method, the cockroach mating and breeding behaviors are researched and controlled from the source, so that cockroach prevention and control and breeding work are not guided by only depending on experience, scientization, datamation and refinement are achieved, and the method can be widely applied to the technical field of animal behavior research.

The present invention relates to an audio/video editing method and an equipment by using mobile data recording medium. In the production of audio/video programs, a kind of mobile data recording medium that can be drawn and inserted is adopted as the carrier of video program data and used for the whole flows of photographing, recording, playing and storing; the equipment is composed of a kind of mobile data recording medium and a main set system, and the equipment carries the storage in a non-contact magnetic read-write way or through the electronic read-write method of a kind of conductor storage medium. The data files are recorded in a non-linear way to receive read-write operations of the operating system; the main set system is a computer system based on a CPU and an operating system platform or an embedded micro-processor system. The mobile data recording medium connects with the main set system through computer ports and a physical plug mechanism as well as electric signals; and carries pulling and insertion of the mobile data recording medium. The mobile recording medium keeps the independency and the integrality of data in the whole flow of the program production.