1440results about How to "Reduce negative impact" patented technology

The invention provides a distributed interface defect detection method and system for a micro-service architecture, and relates to the technical field of micro-services, and the method comprises the steps: collecting interface calling data through deploying a distributed tracking probe, and constructing a service calling topological graph; inputting the feature sequence matrix into a long-short term memory neural network to extract a time sequence dependence feature, calculating an attention weight coefficient between nodes in combination with a graph attention network, and fusing node features to generate a state vector; calculating a fault situation vector of the service node based on the fault propagation prediction model, constructing a fault propagation path diagram, and carrying out fault source positioning and early warning; and dynamic scheduling of the micro-service nodes is realized by dynamically calibrating the early warning threshold and continuously optimizing the prediction model. According to the method, the fault prediction accuracy is improved, the fault propagation risk is effectively reduced, and the system reliability is enhanced.

The invention discloses a method for realizing high-efficiency low-consumption micro-aerobic hydrolytic acidification of petrochemical wastewater by regulating and controlling the aeration rate in combination with a space-time diagram neural network and reinforced learning, and relates to a method for realizing high-efficiency low-consumption micro-aerobic hydrolytic acidification of petrochemical wastewater by regulating and controlling the aeration rate. The method comprises the following steps of: 1, collecting and cleaning data; 2, constructing a graph data set; 3, training the ST-GNN model; 4, constructing a deep Q reinforcement learning model; 5, the trained ST-GNN model is embedded into an automatic control system of a sewage treatment plant, and the model outputs the optimal aeration rate of the current time step and predicts the micro-aerobic hydrolytic acidification effect through interaction of the current working condition and historical data; and adjusting operation parameters of aeration equipment according to the output of the model, and carrying out hydrolytic acidification treatment. The method is high in regulation and control efficiency and low in operation error, and can be applied to the field of digital and intelligent management of sewage treatment plants.

The invention provides a crop accurate management method and system based on a crop growth model. The method comprises the following steps: collecting environment data of a crop growth period by integrating a remote sensing technology, a field intelligent sensor and an unmanned aerial vehicle, and carrying out space-time alignment to form a comprehensive environment data set; and dynamically adjusting parameters of the crop growth model by using a Bayesian rule, evaluating the influence of environmental uncertainty on crops in combination with Monte Carlo simulation, and providing yield prediction with a confidence interval. Based on the prediction, a particle swarm optimization algorithm is applied to formulate management schemes such as irrigation, fertilization, pest control and harvesting opportunities, and meanwhile, a multi-objective optimization strategy is adopted to balance economic benefits and environmental protection. After the scheme is implemented, the crop growth response is monitored in real time so as to reinforce learning and automatically adjust management measures, and precise agricultural management is realized. According to the technical scheme provided by the embodiment of the invention, the crop management precision and efficiency are improved.

The invention relates to the field of production fault analysis, in particular to a fault monitoring analysis method and system for lubricating oil production. The method comprises the following steps: acquiring a multi-dimensional working monitoring parameter and an omnibearing working image; performing abnormal outlier filtering processing on the multi-dimensional working monitoring parameters, and performing time sequence evolution simulation to generate time sequence state evolution data; performing continuous frame optical flow motion analysis on the omnibearing working image, performing dynamic parameter mapping based on time sequence state evolution data, and constructing a dynamic production twinborn model; obtaining a preset production standard demand log; carrying out dynamic process deviation detection based on a preset production standard demand log dynamic production twinborn model, and carrying out production fault analysis so as to obtain stage production fault data; performing potential fault traceability speculation on the staged production fault data to obtain an abnormal fault potential node; and constructing a potential fault mark twinborn model based on the abnormal fault potential nodes. According to the invention, efficient and accurate fault analysis of lubricating oil production is realized.

The invention discloses a short video advertisement putting optimization evaluation method based on deep learning, and relates to the technical field of advertisement putting, and the method collects user behavior data in real time, constructs a dynamic user portrait, enables an advertisement system to adjust the advertisement content and putting strategy in time according to the interest change of a user, improves the correlation of advertisements, and improves the advertisement putting efficiency. Meanwhile, user behavior mode data and advertisement content labels are subjected to multi-dimensional matching, and the matching degree of the advertisements and user interests is calculated by combining cosine similarity with a weighting algorithm, so that advertisement recommendation is more personalized and accurate, the advertisement click rate and conversion rate are greatly improved, and the advertisement recommendation efficiency is improved. Meanwhile, the optimal opportunity of advertisement display is defined by analyzing the exit tendency of the user and the advertisement clicking tendency, it is guaranteed that the advertisement can be displayed at the moment when the user is most likely to interact and click, and the problem of low conversion rate caused by poor opportunity in a traditional method is solved.

The invention discloses a method for dynamically adjusting a tea fermentation environment by utilizing fuzzy logic control. The method comprises the following steps: S1, collecting and obtaining environment parameter data of each layer in real time; s2, fuzzy processing is carried out on the temperature, humidity and oxygen concentration in each time period through a fuzzy logic controller, and fuzzy control output of each time period is generated; s3, combining a hybrid neural network architecture and a meta-learning technology to construct an environment parameter change model; s4, optimizing the fuzzy rule base by using the environment parameter change model; s5, converting the fuzzy control output of each time period into a control instruction; s6, optimizing the fermentation environment through a cross-layer parameter equalization strategy to obtain the optimal state of the environmental parameters in the fermentation process; and S7, displaying environmental parameters of each spatial level and time stage in real time, and supporting switching between a manual mode and an automatic mode. The method combines fuzzy logic control and a deep learning technology, realizes accurate dynamic adjustment of the tea fermentation environment, and has the advantages of high adaptability and the like.

The invention discloses a data acquisition method and system for virtual digital platform construction, particularly relates to the field of virtual digital interaction, is used for solving the problems of user interest capture and cognitive fatigue, and aims at accurately capturing long-term interest of a user in scenes such as a virtual exhibition and an online shopping platform and effectively coping with a short-term cognitive fatigue phenomenon. Through a fusion strategy of a time-varying covariance matrix and a graph neural network, multi-modal behavior data of a user is monitored in real time, modal weights are dynamically adjusted, and multi-dimensional features are fused. In combination with time sequence analysis and a clustering algorithm, the system compares a current behavior with a historical baseline, and accurately extracts deviation data. The cognitive fatigue state of the user is evaluated in real time through a deep learning model, high-risk and low-risk feedback signals are generated, and recommendation optimization based on long-line interest is triggered. According to the technical scheme, it is ensured that the pushed content is consistent with the long-term demand of the user, cognitive burden caused by information overload is avoided, recommendation accuracy and user experience are improved, and the loss rate is reduced.

The invention relates to the technical field of agriculture, in particular to a corn stress resistance environment monitoring and management method, which comprises the following steps of S1, collecting environment data of a corn planting area in real time; s2, transmitting the environment data to a data center through a wireless network; s3, preprocessing the environment data transmitted to the data center; s4, establishing an adversity stress assessment model based on the preprocessed environmental data; s5, evaluating the stress resistance of the corn under different environmental stresses; s6, predicting the type and strength of adversity stress which will occur in the future and the influence of the adversity stress on the corn, and forming stress response prediction; and S7, generating a corn growth management decision suggestion. According to the invention, through real-time environment monitoring and accurate adversity stress assessment, in combination with growth characteristics and weather prediction of corn, irrigation, fertilization and pest control strategies are dynamically adjusted, so that accurate management of corn growth is realized, stress resistance is improved, resource utilization is optimized, and yield is increased.

The invention discloses an image recognition system based on machine vision, which comprises a deep learning model, and is characterized in that an image recognition module comprises an image data sensing module for receiving and processing original image data, capturing an image from a camera or an image file, and performing preliminary format conversion and preprocessing; the image feature extraction module is used for converting the image into a form which can be understood by a machine based on a convolutional neural network; the online learning framework is used for dynamically adjusting model parameters according to data input in real time; the environment adaptability adjusting module is used for dynamically adjusting image processing parameters, changing a feature extraction weight, adjusting a learning rate and adjusting an identification strategy according to environment changes; the recognition and classification module is used for executing object recognition and classification tasks based on the extracted features and the learned model; the parameter mapping unit is used for mapping the environment parameters to specific parameter adjustment of the model; and the environment adaptability development unit is used for extracting useful information from the environment data and converting the useful information into an instruction of an adaptability adjustment strategy.

The invention provides a photovoltaic power station design system and method based on ecological collaborative optimization, and relates to the technical field of data processing. The system comprises an initial configuration module which is used for generating an initial layout structure of a photovoltaic module, performing energy-saving and consumption-reducing calculation and economic analysis according to generating capacity data, and obtaining initial energy-saving and consumption-reducing data and initial economic analysis data; the secondary optimization module is used for optimizing the parameters of the photovoltaic module based on the economical efficiency analysis data and determining energy-saving and consumption-reducing data and economical efficiency analysis data through the generating capacity optimization data; the ecological evaluation module is used for determining ecological benefit data of the photovoltaic power station according to the ecological influence parameters; and the collaborative optimization module is used for setting a power generation income weight and an ecological benefit weight so as to optimize the photovoltaic module layout structure and generate a photovoltaic power station design scheme based on ecological collaborative optimization. The method is used for realizing collaborative optimization of power generation benefits and ecological benefits of the photovoltaic power station, so that the power station gives consideration to ecological protection while improving the power generation efficiency.

The invention discloses a building curtain wall BIM forward design method, and relates to the technical field of building curtain wall design, and the method specifically comprises the following steps: obtaining environment dynamic information of each region in real time, and respectively generating an air flow equilibrium coefficient and a thermal effect index of each region; and constructing a heat effect risk model for the generated air flow equilibrium coefficient and heat effect index of each region, generating a heat effect risk coefficient of each region, and predicting a risk level of a heat effect caused by unbalanced air flow in each region of the air layer in the double-layer curtain wall. Dividing each area of the air layer in the double-layer curtain wall into a high-risk area, a medium-risk area and a low-risk area according to the prediction result; and taking corresponding air flow optimization and heat effect control measures according to the division result of each area of the air layer in the double-layer curtain wall. The heat effect problem caused by unbalanced air flow of the double-layer curtain wall is solved, and the effects of optimizing the heat preservation performance and reducing energy consumption are achieved.

The invention relates to the technical field of photovoltaic power generation power prediction, in particular to a photovoltaic power generation power high-precision prediction method and system. According to the technical scheme, the method comprises the following steps: data acquisition and preprocessing: historical photovoltaic power generation power data are widely collected, the time span covers at least one year in the past so as to obtain power generation power change information under different seasons, weather conditions and time periods, and meanwhile, meteorological data corresponding to the power generation power change information are collected; and cleaning the collected data, and removing missing values through data integrity check. The power generation efficiency and economy are improved, the operation and maintenance plan can be optimized, and the energy storage utilization efficiency is improved; the power grid stability and reliability are enhanced, scheduling is assisted, resource configuration is optimized, power market operation is greatly improved, support is provided for transaction decision making, renewable energy consumption is promoted, the system adaptability and the intelligent level are improved, real-time tracking and updating can be achieved, and intelligent management of a power station is assisted.

The invention relates to the technical field of traffic emergency evaluation, and discloses a comprehensive traffic network toughness evaluation method based on multiple indexes, which comprises the following steps of: in a pre-stage, selecting a plurality of key indexes for evaluating the traffic network toughness; an in-event stage: when an emergency occurs, acquiring real-time traffic data based on the evaluation model; and a post-event stage: after the emergency event is ended, analyzing the influence of the event on the traffic network, and evaluating the recovery capability of the traffic network based on the evaluation model in combination with the restoration time of the facility, the traffic flow recovery condition and the emergency resource allocation record. A topological structure index, a traffic flow index, a facility reliability index and an emergency response capability index are adopted, the robustness of the traffic network under different dimensions can be comprehensively evaluated, through multi-dimensional quantitative analysis, the impact resistance, the recovery capability and the emergency management capability of the network can be comprehensively evaluated, and the evaluation accuracy is improved.

The invention discloses a method and a system for improving Mura defect classification precision, electronic equipment and a storage medium, which are used for realizing accurate classification of Mura defects of low-gray-scale images. The method for improving the Mura defect classification precision comprises the steps of obtaining an image on a display screen to be detected; performing texture filtering processing on the image to obtain a filtered image; performing graying processing and defect segmentation processing on the filtered image to obtain a to-be-detected image; inputting the to-be-detected image into the Mura classification model to obtain a classification result; wherein the Mura classification model is obtained through the following training method: obtaining first data collected by a plurality of sensors; preprocessing the first data to obtain second data; extracting feature data in the second data; fusing the feature data according to an orthogonal sequence fusion algorithm to obtain a fusion result; and training according to a fusion result to obtain a Mura classification model.

The invention discloses a multi-language translation method and system, and relates to the field of electrical digital data process.The method comprises the steps that cultural feature information and semantic structure information are obtained; splitting the source language text into a plurality of semantic units based on the semantic structure information; retrieving cultural connotation information of which the association degree with the semantic unit is greater than a preset threshold value; determining that the semantic unit is a culture sensitive semantic unit; extracting a target language expression mode based on the cultural connotation information; performing semantic combination on the target language expression mode and standard translation results of other semantic units except the culture sensitive semantic unit in the source language text to obtain a translation result; judging whether the semantic coherence of the translation result meets a preset condition or not; if the preset condition is met, outputting a translation result; and if the preset condition is not met, re-executing the step of semantic combination. The accuracy of the cultural connotation and the emotional color contained in the transmission source language is improved, and then the cultural adaptability of the translation result is improved.

The invention discloses a pilot dangerous driving behavior monitoring method based on multi-modal data fusion, and belongs to the field of multi-modal data fusion monitoring, and the method comprises the steps: obtaining the physiological data of a pilot in the take-off and landing states through a multi-element sensor, judging the fatigue state of the pilot, and obtaining the dangerous driving behavior of the pilot. An eye tracker and a camera are used for conducting data collection on a pilot in the take-off and landing states, behavior data of the blinking frequency, the eyelid closure degree, the pupil change, the yawning frequency, the nodding frequency, the average moving speed of an operating lever and the moving direction of the pilot are obtained, and the fatigue state of the pilot is judged; the method comprises the following steps: constructing a multi-modal data fusion network based on Transform, and training the multi-modal data fusion network; the driving behavior of a pilot is monitored by using the trained network based on the Transform multi-modal data fusion; through a multi-channel interaction technology, the comprehensiveness and accuracy of information are improved, the influence of environment and individual differences is reduced, and the stability and robustness are enhanced.

The invention discloses an alternating current charging pile ordered charging power regulation and control method, and relates to the technical field of alternating current charging pile charging power regulation and control, and the method specifically comprises the following steps: obtaining the operation state information of each alternating current charging pile in real time, and generating a voltage fluctuation influence index and a load dynamic response index of each alternating current charging pile; constructing a power influence evaluation model for the generated voltage fluctuation influence index and the load dynamic response index of each alternating current charging pile, generating a power influence evaluation coefficient of each alternating current charging pile, performing analysis after generation, and evaluating the influence degree of the three-phase voltage phase difference fluctuation on the charging power of each alternating current charging pile. And the alternating current charging piles are divided into low-influence charging piles, medium-influence charging piles and high-influence charging piles according to the evaluation result. According to the method, the problem that the charging power is influenced by three-phase voltage phase difference fluctuation is solved, and the efficient and stable effects of dynamic evaluation and accurate regulation and control of the power of the charging pile are achieved.

The invention discloses a human face sensitive data protection method based on an elastic anti-interference privacy protection mechanism, belongs to the field of information processing, and provides a dynamic self-adaptive sampling strategy based on information entropy in a data preprocessing stage, and the sampling rate is adjusted according to the distribution characteristics of a human face data set and the weight of sensitive information. And the model performance is maximized on the premise of ensuring user privacy. In order to obtain a better privacy protection effect, an entropy adjustment differential privacy mechanism is designed, and Gaussian noise of different degrees is adaptively added according to an information entropy value of face data after a face data set is dynamically and adaptively sampled, so that refined privacy protection of face sensitive data under differential privacy constraint is realized. In a model training stage, an elastic anti-interference training method is provided, diversified adversarial samples are dynamically generated in different stages of model training, and the over-fitting risk of the model is reduced while the robustness of the model to various types of adversarial attacks is enhanced.

The invention belongs to the technical field of computer vision, and particularly relates to a medical image classification method based on priori knowledge enhanced masks and alignment modeling. Comprising the following steps: acquiring an image text pair data set and preprocessing the image text pair data set to obtain a preprocessed image text pair data set; performing preliminary training on a visual encoder and a text encoder according to the preprocessed image text pair data set to obtain a preliminarily trained visual encoder and a preliminarily trained text encoder; training the visual encoder for the second time in combination with the text encoder to obtain a trained visual encoder; classifying the medical images by adopting the trained visual encoder; the model provided by the invention can be better generalized to various downstream medical image recognition tasks, and the accuracy of the downstream medical image recognition tasks is improved.

The invention discloses an underground water level prediction method and system based on a space-time attention gating neural network. The method comprises the following steps: constructing a historical underground water level space-time sequence data set; performing principal component analysis on the space-time sequence data set to obtain a dimension-reduced space-time sequence data set; for the spatio-temporal sequence data set after dimension reduction, constructing a plurality of spatio-temporal characteristic matrixes through a sliding window method; training an underground water level prediction model by using the plurality of spatial-temporal characteristic matrixes to obtain a trained underground water level prediction model; obtaining time-space sequence data of historical underground water level of a to-be-measured position, constructing a time-space characteristic matrix of the underground water level, and predicting the underground water level of the to-be-measured position by using the trained underground water level prediction model; according to the method, rapid and accurate prediction of the underground water level is realized, and the generalization ability, the prediction precision and the interpretability of an underground water level prediction model are greatly improved while the modeling cost is reduced.

The invention provides a method for preparing high-purity and fine-particle-size lithium sulfide based on carbon thermal reduction. The method comprises the following steps: weighing lithium sulfate monohydrate, an insoluble inorganic carbon source and cysteine in a set proportion to form a raw material mixture; mixing the raw material mixture with water according to a set solid-to-liquid ratio, performing ultrasonic dispersion to obtain homogeneous dispersion liquid, and enabling the dispersion liquid to pass through a nitrogen circulating spray dryer to obtain uniform and dry precursor powder; in a vacuum environment, carrying out segmented calcination to obtain a crude product lithium sulfide; and in a dry and anhydrous environment, washing the crude product lithium sulfide for multiple times by using absolute ethyl alcohol according to a set liquid-solid ratio to obtain an alcoholic solution containing lithium sulfide, and then obtaining lithium sulfide fine powder through a nitrogen circulating spray dryer. The invention solves the problems of side reaction, low purity, large product particles, uncontrollable particle size and the like of lithium sulfide prepared by a carbon thermal reduction method in the prior art.

The invention provides a solid-state laser radar and IMU (Inertial Measurement Unit) robust tight coupling system under the assistance of point cloud intensity, which comprises the following steps of: firstly, pre-processing a solid-state laser radar point cloud by the system, eliminating point cloud defect points, correcting a point cloud intensity value and performing down-sampling; and then geometric feature extraction and intensity feature extraction are carried out on the preprocessed point cloud, and intensity calibration of the laser radar point cloud is carried out. And then compensating the motion of the point cloud by using the high-frequency prior information predicted by the IMU. For geometric and intensity feature point clouds, a classical registration method and a fast plane fitting method are respectively adopted to calculate residual errors, and an intensity feature assisted point cloud residual error measurement model is constructed. And a robust strategy based on an IGGIII robust weight function is designed by using a residual error estimation value in a filtering algorithm. According to the invention, on the premise of keeping relatively low calculation cost, the positioning and mapping capabilities and robustness of the small-view-angle laser radar tight coupling system in a complex environment are improved.

The invention discloses a coal power multi-path transformation and new energy combination decision-making method under low-carbon transformation. The method comprises the following steps: firstly, constructing a system comprising first-level effect indexes such as environmental influence, economic benefit, energy safety and technical innovation and corresponding second-level indexes; then, alternative schemes of various coal power transformation technology and new energy project type combinations are generated; then quantitatively evaluating the effect index of each scheme, and calculating a comprehensive utility value by using multi-criterion decision analysis; identifying potential risk factors, and performing uncertainty analysis through Monte Carlo simulation; and finally, according to the low-carbon transformation target and policy evaluation scheme conformity, selecting a scheme which most conforms to the policy target, and continuously monitoring and adjusting. The coal-electricity multi-path transformation and new energy combination decision-making method under low-carbon transformation is beneficial to promoting energy low-carbon transformation, optimizing resource allocation, improving economic benefits, promoting technical innovation, enhancing risk management capability and ensuring that a project is consistent with policy orientation.

The invention relates to a virtual power plant bidding strategy optimization method based on a chaotic game optimization algorithm. The method comprises the following steps: generating an initial bidding strategy of a virtual power plant through chaotic mapping; each virtual power plant receives feedback information of the market, games by considering factors of cost, income, fluctuation of photovoltaic power generation, scheduling cost and attenuation of an energy storage battery and service life of equipment, and adjusts a bidding strategy of the virtual power plant; punishment income is applied to bidding behaviors violating market ethics or benefit distribution constraints; calculating the income of the power plant according to the adjusted strategy, and updating the bidding strategy of each virtual power plant; and repeating the game process until a convergence condition is reached, and outputting a virtual power plant bidding strategy. Compared with the prior art, the bidding strategy of the virtual power plant is more flexible and adaptive by using the randomness and unpredictability of the chaotic system, and meanwhile, the fairness, sustainability and healthy market development of the system are ensured by introducing ethical constraint and equipment life management.

The invention discloses a cross-scene wireless gesture recognition method based on unsupervised learning, and the method comprises the steps: obtaining Doppler frequency shift data, and carrying out the preprocessing of the Doppler frequency shift data; inputting the preprocessed data into a shared feature extractor, and mapping the extracted features to the same hidden space through an adversarial auto-encoder; pseudo marks are distributed through classification prediction in the preheating stage, and distribution of the pseudo marks is perfected through a target-oriented centroid point after the preheating stage; constructing target-oriented multivariate normal distribution through all pseudo marks, and migrating a source domain to a target domain on a hidden space level in a bias adding mode to obtain a trained cross-scene wireless gesture recognition model; and analyzing a newly input target domain sample through the trained cross-scene wireless gesture recognition model, and predicting a gesture corresponding to the target domain sample in an unmarked manner. According to the method, the problem of difficulty in sensing data marking can be relieved, and stable and high-performance gesture recognition can be realized in different scenes.

The invention belongs to the technical field of water treatment processes and devices, and particularly relates to a pharmaceutical wastewater treatment process and a pharmaceutical wastewater treatment device. According to the treatment process of the pharmaceutical wastewater, the pharmaceutical wastewater is subjected to the following processes: an electric flocculation process, a catalytic ozonation process, a ceramic membrane separation process and a reverse osmosis process; the membrane aperture of the reverse osmosis process is 0.3-0.4 nm, the transmembrane pressure difference is 2.0-3.0 bar, reverse osmosis desalted fresh water and reverse osmosis strong brine are respectively obtained, the reverse osmosis desalted fresh water directly reaches the standard for reuse, and the reverse osmosis strong brine is returned to the electric flocculation process for repeated treatment. The pharmaceutical wastewater treatment process provided by the invention not only can realize synchronous removal of suspended matters and organic matters, but also can realize desalination and deep purification of pharmaceutical wastewater, and provides a feasible and sustainable solution for pharmaceutical wastewater treatment, and the invention also provides a treatment device thereof.

The invention discloses a blue-green algae growth prediction method and an intelligent regulation and control device, and relates to the field of blue-green algae growth prediction and regulation and control, and the method comprises the steps: carrying out the collection of blue-green algae growth related data, data preprocessing, random forest model construction, SVM model construction, and model weight fusion of a final random forest prediction model and a final SVM prediction model to obtain a fusion model. And dynamically optimizing the fusion model, finally obtaining the dynamically optimized fusion model, obtaining a real-time prediction result according to the dynamically optimized fusion model by using the blue-green algae growth related data collected by the sensor module in real time, and adjusting the blue-green algae growth culture conditions in real time. According to the method, the advantages of the random forest model and the SVM model are combined, a fusion model with dynamic optimization and real-time adjustment functions is developed, and the accuracy and adaptability of blue-green algae growth prediction are remarkably improved. And meanwhile, data acquisition, processing and prediction modules are integrated, so that the accuracy of blue-green algae growth prediction and the automation degree of the system are remarkably improved.

The invention relates to the technical field of refrigerating systems, in particular to a micro-channel air conditioner phase change heat transfer evaporation heat exchanger. Comprising a flowing pipeline, the flowing pipeline is composed of a plurality of vertical pipelines and a plurality of bent pipelines connected with the vertical pipelines, and a continuous flowing path of a condensing agent is formed. And a mixing assembly specially used for stirring the condensing agent is arranged in the vertical pipeline. Fin assemblies are installed on the outer sides of the vertical pipelines, and the outer sides of the fin assemblies are wrapped by a complete shell. When the condensing agent flows in the flowing pipeline, the condensing agent can pass through the mixing assembly in each vertical pipeline to be fully mixed and uniformly distributed. The design ensures that the condensing agent in each vertical pipeline can reach an ideal uniform state. And then, the condensing agent flows through the fin assembly, and heat exchange is effectively carried out by utilizing the heat exchange area increased by the fins. By means of the layout, flowing of the condensing agent is optimized, and the heat exchange efficiency is remarkably improved.

The invention discloses a live broadcast e-commerce intelligent management platform and method based on big data, and particularly relates to the field of live broadcast e-commerce. User behaviors, transactions and commodity data in a plurality of historical data sources are collected, data deviation is corrected through data preprocessing and an anomaly detection algorithm, data quality is ensured, and user experience is improved. Inputting the corrected data into a machine learning model for training, evaluating prediction performance through cross validation, optimizing model hyper-parameters, collecting data of an e-commerce platform in real time, evaluating the accuracy of a recommendation system in combination with data updating abnormity and model performance stability, and dynamically adjusting model parameters, so as to improve the recommendation accuracy of the e-commerce platform. The performance of the recommendation system is analyzed in a fixed time period, the recommendation algorithm and model are continuously optimized, the accuracy and efficiency of the system are ensured, the operation efficiency, recommendation precision and user experience of live broadcast e-commerce are effectively improved, and prediction errors caused by data deviation are reduced.

The utility model is applicable to the technical field of power batteries, and provides a battery and a power utilization device, the battery comprises a box body, the box body is used for accommodating a battery monomer, at least two fixed beams are arranged in the box body at intervals, and a space for accommodating the battery monomer is formed between every two adjacent fixed beams; the fixed seat is arranged on the fixed beam; the limiting pieces are connected to the fixing seats on the different fixing beams; the limiting pieces are connected to different fixing beams, so that the deformation of the fixing beams is inhibited through the limiting pieces, the strength of the fixing beams is enhanced, and the deformation quantity of the fixing beams along with the expansion of the battery monomers is reduced; by arranging the fixing seats, the strength of the joints of the limiting pieces and the fixing beams is enhanced, the failure conditions such as breakage of the joints of the limiting pieces and the fixing beams are reduced, the strength of the fixing beams is further enhanced, and therefore expansion of the single batteries is better restrained, the battery performance is improved, and potential safety hazards are reduced.