21results about How to "Quick decision" patented technology

The application discloses a data center electric energy utilization efficiency value simulation calculation method and system of indirect evaporative cooling air conditioner, comprising the following steps: based on a quantum computing platform, constructing an IT load of a data center, a quantum simulation model of an indirect evaporative cooling unit and a dynamic environment thereof, and establishing a dynamic correlation between a cooling unit state and a complex environment variable through quantum many-body simulation. The application breaks through the limitations of traditional optimization methods in a multi-dimensional control space through the optimization capability of quantum computing, can quickly calculate the optimal configuration of the cooling system, especially in high load and extreme environment; by using a quantum machine learning method, not only can the load change be accurately predicted, but also the control strategy can be adjusted in real time, energy waste is reduced, and the response speed and accuracy of the system are improved.

The invention relates to a video coding method and device, electronic equipment, a program product, a storage medium and a bit stream storage method. The method comprises: recursively performing a block division operation for a current block until a preset condition is satisfied, the block division operation comprising: dividing the current block into a predetermined number of sub-blocks; a cost difference value between the maximum rate-distortion cost and the minimum rate-distortion cost in preset rate-distortion cost is obtained, and the preset rate-distortion cost is the rate-distortion cost of each sub-block in the pre-analysis stage; taking each sub-block as a current block in response to the condition that the cost difference value is greater than a first difference threshold value; responding to the condition that the cost difference value is smaller than or equal to a first difference threshold value, determining that a preset condition is met; performing a coding mode decision operation for the current block to determine a coding mode for the current block; and encoding the current block using the encoding mode.

The invention discloses a transformer substation site selection data processing and feedback method, system and device based on unmanned aerial vehicle-AI cooperation and a medium, and belongs to the technical field of intelligent site selection of electric power engineering, and the method comprises the steps: controlling an unmanned aerial vehicle to shoot a transformer substation site selection region according to a preset flight route, and obtaining a site selection region image; performing preprocessing and feature extraction on the site selection area image to obtain key environment element information; inputting the key environment element information into a pre-trained site selection environment evaluation model to obtain an evaluation result, including a terrain suitability grade, infrastructure proximity and a comprehensive site selection feasibility score; according to the evaluation result and a preset engineering constraint rule base, matching an avoidance suggestion; and displaying the avoidance suggestions. According to the method, site selection suggestions can be provided for decision makers in a shorter time, the advancing speed of substation construction projects is increased, the advantages and disadvantages of site selection can be judged more objectively and accurately, and the risk of site selection errors caused by human factors or insufficient data is reduced.

The application discloses a deepwater oilfield development yield prediction method, an electronic device, an apparatus and a storage medium, wherein the method comprises: predicting the natural yield of old wells, the yield increasing potential of old wells, the yield of new wells, planned yield loss and non-planned yield loss for each prediction year respectively; wherein predicting the non-planned yield loss comprises: determining the development stage to which a well area belongs, wherein for the well area in the aging stage, a historical curve graph of the non-planned loss rate and time relationship is determined first, the non-planned loss rate in the prediction year is calculated by fitting the relationship between the non-planned yield loss rate and the production time of the aging stage in the curve graph, the non-planned loss rate in the prediction year is corrected by using a correction factor to determine the final non-planned loss rate in the prediction year, so as to determine the non-planned yield loss in the prediction year; and the deepwater oilfield development yield is calculated according to the above prediction results.

This invention discloses an active distribution network integrated optimization scheduling method and system based on SVM-L2O, belonging to the field of distribution network optimization scheduling technology. The method includes: solving a multi-timescale integrated scheduling model based on acquired historical wind power output and load data to obtain unit start-up and shutdown strategies and continuous output decision variables, and constructing a training dataset; training a support vector machine for the start-up and shutdown strategies of each unit in each time period to obtain a surrogate model predicting the unit start-up and shutdown strategies; removing start-up and shutdown related constraints from the model based on the generated start-up and shutdown strategies to obtain a simplified model; constructing an L2O neural network, using Lagrange multipliers to incorporate the constraints of the simplified model as penalty terms into the loss function, training the L2O neural network to obtain a surrogate model predicting continuous output decision variables; acquiring wind power output and load data in real time, generating optimal scheduling decisions through the two surrogate models, and realizing integrated and efficient solution of multi-timescale distribution network scheduling.

The present application relates to the field of flood control, in order to improve the efficiency of obtaining scheduling scheme, provide a kind of plant network river joint scheduling method based on machine learning algorithm and rain flood numerical model, including:1, the SWMM model of target area is established;2, calibrate SWMM model parameters;3, prefabricate multiple plant network river joint scheduling scheme;4, construct city rain flood scene database;5, construct plant network river joint scheduling effect evaluation system;6, construct city plant network river joint scheduling scene database;7, construct rainfall condition-joint scheduling scheme-benefit index learning model;8, obtain the optimal joint scheduling scheme of plant network river under current rainfall condition using the trained rainfall condition-joint scheduling scheme-benefit index learning model.The efficiency of obtaining scheduling method can be improved by using the above steps.

The invention discloses a remote detection method for soot blowing system pipe structure defects, and relates to the technical field of thermal equipment detection. The problems that in the prior art, detection needs to be stopped, real-time monitoring cannot be achieved, and defect information is not visually presented can be at least partially solved. The method comprises the following steps: deploying an electromagnetic ultrasonic guided wave sensor array around a welding seam to perform signal excitation and synchronous acquisition; performing dual noise reduction processing by adopting synchronous average and wavelet transform to extract defect signals; constructing a space model to position defects based on the signal arrival time difference; and generating a defect image by utilizing C-scanning imaging and performing quantitative evaluation. According to the invention, on-line remote detection without shutdown is realized, the signal-to-noise ratio is obviously improved through dual noise reduction, accurate positioning and visual display of defects are realized by combining time difference analysis and C scanning imaging, and safe operation of a unit is guaranteed.

The invention discloses a sub-item cost prediction method and device based on label driving and a storage medium, and relates to the technical field of project cost prediction, and the method comprises the steps: collecting target project feature information, matching corresponding option labels for the target project feature information according to a preset classification rule, processing the labels through feature coding, and generating labeled features. And then, disassembling the target project into each sub-item project, calling a target model corresponding to each sub-item, and predicting the unit price of each sub-item in combination with the tagging features to obtain a target unit price. And through a deterministic calculation rule, target unit price and project quantity data are coupled, and sub-item project cost summary data are output. And finally, based on error distribution information obtained by model training, adjusting the cost summary data, and calculating to obtain a prediction result of the total cost of the project. The problem that the efficiency of frequently modifying indexes of an early-stage scheme and the cost prediction precision are difficult to balance is solved through feature tagging, item splitting and unit price pre-processing, cost calculation and error tuning feedback.

The embodiment of the invention relates to the technical field of intelligent driving, and provides a display method and device based on a driving scene, a medium and electronic equipment. The method comprises the steps of displaying a current rendering asset corresponding to a sensing object in a display screen based on a current rendering style; wherein the sensing object comprises at least one of a dynamic sensing object and a static sensing object; determining a to-be-applied risk level corresponding to the current driving scene based on the collected driving scene information; in response to the difference between the to-be-applied risk level and the current effective risk level, determining a target rendering style based on the to-be-applied risk level; and based on the target rendering style, determining a target rendering asset corresponding to the perception object, and displaying the target rendering asset in a display screen. According to the method provided by the invention, corresponding rendering styles and rendering assets can be adopted according to different risk levels, so that personalized visual experience and safety requirements in extreme scenes are effectively balanced.

The application provides a quality control method and system for medical text information generated by a natural language processing model. The method includes generating structured data of medical text information based on a natural language processing model; inputting the structured data and its corresponding original medical text into a large language model configured to determine multiple quality scores of the structured data, including: evaluating the degree of support of the original medical text for the structured data to determine an uncertainty quality score; determining an abnormal input detection quality score based on a complexity classification of the original medical text; evaluating the logical consistency of a second medical text associated with the original medical text with the structured data to determine a logical consistency quality score based on the logical consistency; and evaluating whether the structured data conforms to the rationality of medical logic based on a pre-constructed medical knowledge base to determine a rationality quality score; and generating a comprehensive quality control score for the medical text information according to the multiple quality scores of the structured data.

This invention relates to a CPSS system, control method, and application based on cloud-edge collaborative control. The system includes a physical layer, an information layer, and a social layer. The physical layer collects user electricity consumption information and power generation information from power generation equipment, uploads the information to the information layer, executes dispatch instructions, and feeds back the execution results to the information layer. The information layer receives electricity consumption and power generation information, processes and calculates the information using cloud-edge collaborative technology, performs decision simulation based on the calculation results, generates dispatch instructions and guidance instructions, and sends them to the physical layer and user layer respectively. It also optimizes the simulation decisions based on the execution results fed back from the information layer and user layer. The social layer includes operators and users. Operators execute guidance instructions to adjust user electricity consumption behavior and feed back the execution results to the information layer. Through cloud-edge collaborative technology, the computing pressure on the cloud is reduced, and the supply relationship between users and operators can be quickly resolved.

An automated scoring system for medial temporal lobe atrophy (MTA) based on YOLO deep learning includes: a coronal slice selection module, an improved YOLOv8 model construction module, an optimal coronal slice automatic selection module, and a medial temporal lobe atrophy detection and automatic scoring module. This invention provides an automated MTA scoring technique that balances accuracy, versatility, and ease of use. By using a lightweight deep learning YOLO object detection framework and combining it with an appropriate loss function, computational overhead is reduced while maintaining algorithm performance. Furthermore, a user-friendly front-end interface improves the efficiency and accuracy of clinical MTA scoring. This invention provides an efficient, accurate, and consistent automated MTA scoring system with significant clinical application value and promising prospects, and is expected to play an important role in the early diagnosis and monitoring of neurodegenerative diseases such as Alzheimer's disease.

The invention provides a space image display method and device for a flat panel display device and the flat panel display device, and the method comprises the steps: obtaining a space image obtained through the shooting of a target scene by a binocular camera, and constructing a three-dimensional model of the target scene according to the space image; setting a virtual camera according to a preset initial pose; determining a first area matched with the visual angle of the virtual camera in the three-dimensional model according to the initial pose; and obtaining a first plane image according to the first area, and controlling the plane display device to render the first plane image.

The invention belongs to the technical field of information system integration and intelligent transportation, and relates to a rail transit visualization system integration system based on multi-agent collaboration and an integration method thereof, and the system comprises an agent community, an agent shell layer and a subsystem layer. The subsystem layer comprises a plurality of subsystems, an agent shell is constructed for each subsystem, subsystem agents are formed, an agent shell layer is formed, the subsystem agents communicate with one another through message middleware, and the agent community is formed. By constructing the intelligent agent shell for each heterogeneous subsystem and establishing the intelligent agent community, a data circulation barrier is broken through, automatic association analysis of multi-source data is realized, operation and maintenance personnel do not need to repeatedly switch among a plurality of independent systems, manual data comparison is not needed, the fault positioning time is greatly shortened, and the fault positioning efficiency is improved. And the operation and maintenance response speed and the processing accuracy are fundamentally improved.

This invention relates to the field of underground communication and video transmission in coal mines, and particularly to an adaptive bitrate control method for video backhaul in underground image communication in coal mines. The method includes: acquiring original video frames and generating a layered backhaul video stream; encapsulating and sending the layered backhaul video stream; the receiving end generating and sending a feedback message; the sending end determining the switching window and predicting the interruption duration; generating a synchronization digest within the switching window and sending it in groups along with the digital information of the base layer bitstream; performing verification on the synchronization digest within the switching window; ensuring the joint configuration vector satisfies the overhead budget constraint within the switching window and during the reconstruction loop; and after the switching window ends, exiting cross-link replication transmission and repeated control telegram transmission, and encoding, encapsulating, and sending subsequent original video frames according to the updated target bitrate and keyframe interval. This invention achieves continuous and decodable transmission of base layer information and rapid synchronization recovery under switching disturbances.

The invention discloses a transformer substation planning method and system, a storage medium and equipment, and the method comprises the steps: obtaining the historical power utilization data of a user in a target region, and recognizing a typical load time sequence curve through clustering analysis; predicting the peak load of each block in the target area based on a load density method, and generating time sequence load data in combination with a typical load curve; establishing a transformer substation planning optimization model, and outputting the site selection of the transformer substation in the target area by taking a power balance constraint and a power supply radius constraint as constraint conditions and taking the minimization of the total cost as a target; an improved genetic algorithm is adopted to optimize site selection of the transformer substation, and the optimal position of the transformer substation in the target area is screened out from the candidate site set; and dividing the power supply range of each transformer substation in the target area based on the Thiessen polygon, and determining the capacity of the transformer substation according to the total peak load in the power supply range. According to the method, load characteristic complementarity is considered, substation locating and sizing are optimized, the station number and capacity are reduced, loss is reduced, and planning economy is improved.

The invention relates to the technical field of carbon calculation management, in particular to a carbon calculation management method and system based on an authoritative certification carbon factor, and the method comprises the steps: firstly confirming a to-be-managed enterprise, and obtaining an original enterprise parameter set from an enterprise total ammeter, a key production equipment controller and an environment monitoring sensor end according to a preset detection period, and a qualified enterprise parameter set is further screened out, refined decomposition is carried out based on an environment temperature sequence and a total load sequence in an original enterprise parameter set, the total emission amount of the enterprise is obtained, and therefore a visual model capable of reflecting the carbon profit and loss state and progress in real time is constructed. According to the method, through multi-source data fusion, accurate load decomposition and dynamic factor correction, the accuracy and credibility of carbon emission calculation are systematically improved, and a reliable basis is provided for enterprise carbon asset management and emission reduction decision making.

The invention relates to the technical field of computer systems, and provides a computer network information security monitoring system and a use method, and the system comprises an infrastructure and data collection module, a deep learning analysis module, a reinforcement learning strategy optimization module, a security strategy management module and a visual operation and maintenance and decision support module. The infrastructure and data acquisition module is responsible for collecting and transmitting data, the deep learning analysis module is used for identifying abnormal behaviors and predicting threat trends, the reinforcement learning strategy optimization module optimizes security strategies through autonomous learning, and the security strategy management module adjusts protection measures according to the optimization strategies. And the visual operation and maintenance and decision support module provides a visual system state view to assist operation and maintenance personnel to make decisions. According to the invention, through combination of deep learning and reinforcement learning technologies, active protection is realized, functions of firewall dynamic configuration, visual operation and maintenance, decision support and the like are provided, and comprehensive and efficient safety protection services are provided for users.

The application discloses a kind of automobile glass screen quality evaluation method and system combined with multispectral imaging, the method comprises the following steps: collecting glass screen image of different wave band and carrying out spectral response calibration, obtain calibrated multispectral data cube;Based on the calibrated multispectral data cube, the spectral transmittance distribution characteristics of each wave band in the region divided on glass screen are calculated, and spectral transmission characteristic curve is constructed;Based on the spatial frequency distribution of spectral transmittance, the optical uniformity evaluation characteristics of each wave band on the surface of glass screen are calculated, and optical uniformity evaluation index is constructed;By calculating the spectral reflectance distribution of each wave band, the spectral characteristic value of the region divided on glass screen is obtained and material characteristic fingerprint matrix is constructed, the similarity of to-be-measured product and standard sample on material characteristic fingerprint is calculated;Based on the similarity of spectral transmission characteristic curve, optical uniformity evaluation index and material characteristic fingerprint, the quality grade of glass screen is multidimensional comprehensive score.

The invention relates to the technical field of three-dimensional point cloud compression and video coding, in particular to a VVC intra-frame prediction fast mode decision-making method suitable for V-PCC, and the method comprises the steps: constructing model input; extracting content features and boundary features input by the model, and splicing to obtain shared features; performing intra-frame mode type prediction on the shared features, performing secondary prediction according to a prediction type judgment result, and outputting candidate modes; the encoder performs final encoding decision according to the candidate mode; according to the intra-frame mode searching method and device, the intra-frame angle prediction, the matrix intra-frame prediction and the enabling prediction of the intra-frame sub-partition tool are jointly decided in the intra-frame prediction stage, and the candidate mode which is more likely to appear is pushed to the encoder according to the prediction probability, so that the intra-frame mode searching complexity is reduced, the coding efficiency is improved, and the coding time is shortened.

Systems and methods for determining the concentration of a plant component in a developed food product prior to or during the manufacture of the food product are disclosed. The method may include: receiving, by a computing system, protein data of a plant component; retrieving at least one model, the at least one model having been trained to generate an output indicative of a desired concentration of a plant component to be used for developing the food product, the at least one model comprising at least one of a pH model, a temperature model, and a protein content model; providing the received protein data as input to the model; receiving an output from the model; and generating instructions for developing the food product, the instructions including a desired concentration range of the plant ingredient.