128results about How to "High risk" patented technology

The screen display glass film tearing equipment comprises a screen display glass loading unit, a film tearing unit and an adhesive supply unit, the screen display glass loading unit comprises a carrying table and a moving mechanism, the carrying table is used for positioning screen display glass downwards from a to-be-torn film, the film tearing unit is located below the to-be-torn film and comprises a film tearing head and a power device, and the film tearing head comprises a film tearing seat, a clamping jaw and a roller; the power device comprises a first power piece and a second power piece. On one hand, on the basis of movement cooperation of the clamping jaw and the rolling wheel, aligned gradual stripping of the rolling position and the stripping position of the to-be-torn film is kept, and on the other hand, the overturning angle is increased based on follow-up overturning of the extending section, so that the success rate of forming the stripping angle by inward overturning of the to-be-torn film is greatly increased; the probability that the glue is separated from the to-be-torn film or the corner of the to-be-torn film is torn is effectively reduced; on the other hand, diagonal film tearing is formed based on the relative movement of the screen display glass and the clamping jaw, the risk that the protective film is torn or falls off is reduced, and the whole film is torn off more efficiently in a more labor-saving mode.

The invention relates to the field of water treatment intelligent dosing control, and provides an intelligent dosing control method and system based on multi-source data fusion and time sequence prediction.The method comprises the steps that a raw water working condition, colloid electrical property balance and floc form attribute set are extracted, and the basic dosing matching amount is determined; obtaining a dynamic delay constant according to the volume of the sedimentation tank and an instantaneous flow value, and generating a causal mapping sample set by combining the three types of attribute sets and effluent turbidity signals of the sedimentation tank; generating a dynamic weight factor sequence according to the causal mapping sample set, and performing point-by-point inner product on the causal mapping sample set to generate a process condition sensitive feature set; and generating a predicted effluent turbidity value based on the process working condition sensitive feature set, performing reverse game optimization through the effluent target turbidity, generating an agent supplementing correction increment, and performing amplitude limiting truncation in combination with the basic agent adding proportioning amount to generate an agent adding control instruction. According to the invention, multi-source heterogeneous working condition sensing features and space-time causal alignment logic are fused, and an intelligent dosing decision and feedback compensation closed-loop mechanism is constructed.

The invention provides a submarine pipeline corrosion rate prediction method, system and device and a medium, and the method comprises the steps: obtaining monitoring data along a target submarine pipeline and pipeline body data; constructing a microbial corrosion random kinetic model based on the monitoring data, and simulating and generating a random microbial corrosion current component; calculating a pipe wall temperature field which is non-uniformly distributed along the axial direction of the pipeline based on the monitoring data and the pipeline body data; calculating an electrochemical corrosion current component based on the pipe wall temperature field and the electrochemical parameters of the pipeline material; performing multi-physics field coupling calculation on the random microbial corrosion current component and the electrochemical corrosion current component to generate a corrosion space-time distribution field; and performing corrosion risk analysis based on the corrosion space-time distribution field to obtain a corrosion risk prediction result. The method can improve the corrosion prediction accuracy of the submarine pipeline.

The invention discloses a two-stage space-time diagram network and multi-source information fusion time sequence probability prediction method and device, and relates to the technical field of artificial intelligence and big data analysis. The method comprises the following steps: acquiring historical wind speed sequence data and corresponding target variable sequence data; preprocessing the data, and constructing a training sample according to a preset time sliding window; constructing a time sequence probability prediction framework of the two-stage space-time diagram network and multi-source information fusion; based on the fluctuation correlation of the historical sequence data, constructing an adjacent matrix between nodes; inputting the training sample and the adjacent matrix between the nodes into a wind speed prediction model, training the model through a designed threshold perception loss function of a wind speed-power nonlinear relationship, and outputting a multi-node wind speed prediction probability of a first stage; and inputting the multi-node wind speed prediction probability and the multi-source environmental factor data into the gradient boosting tree model for second-stage prediction, and outputting a multi-node wind power prediction result. According to the invention, prediction errors can be reduced.

The invention relates to a multi-factor dynamic correction investment benefit intelligent evaluation system, in particular to the field of investment evaluation, and aims to capture macroscopic event and project risk index impact in real time and dynamically generate factor impact coefficients through an event-driven factor correction module, so that the response speed and sensitivity of a model to project sudden change are remarkably improved, and the evaluation efficiency is improved. The self-adaptive weight optimization module utilizes a deep reinforcement learning framework to continuously optimize factor weight distribution based on revenue after risk adjustment in a rolling time window so as to realize self-adaptive adjustment of an investment strategy and optimization of a revenue-risk ratio, and the abnormal conduction early warning module constructs a dynamic directed graph and combines a graph neural network technology to realize early warning of the abnormal conduction. According to the method, abnormal factor conduction paths can be perspectively recognized, systematic engineering risks can be effectively warned, a strategy execution module fuses weight optimization results and risk warning signals, rebalance is executed under the condition that investment cost and risk control constraints are strictly met, and finally a project configuration scheme giving consideration to revenue, robustness and real-time performance is generated.

The invention relates to the technical field of optical storage charging stations, and discloses an optical storage charging station optimized operation method considering stepped carbon transaction and multi-agent collaboration, which comprises the steps of collecting carbon emission data of each agent in a charging station, considering interaction between the charging station and a power grid, and establishing a stepped carbon transaction mechanism; comprehensively considering the interest appeal and operation safety of each main body, and establishing a comprehensive optimization objective function by taking the maximization of the comprehensive benefit of the charging station as an objective; schedulable resources in the charging station are abstracted into intelligent agents, the intelligent agents cooperate with a carbon transaction mechanism, a multi-agent reinforcement learning framework is constructed to solve a comprehensive optimization objective function, and a multi-agent cooperative optimal operation scheduling strategy is obtained. According to the method, the nonlinear stepped carbon transaction mechanism close to the real carbon transaction market is established, the optimal scheduling strategy obtained based on the carbon transaction mechanism has perspectiveness, the benefits of the power grid and the optical storage charging station can be balanced, and the overall market competitiveness and risk resistance of a power system are effectively improved.

The present application relates to a multi-modal large model-based industry electricity abnormality intelligent analysis method and system, comprising the following steps: S1: obtaining power system multi-source data and preprocessing to obtain standardized time series data set; S2: based on the standardized time series data set, feature extraction is carried out, and a feature data set is constructed; S3: based on the feature data set, an industry electricity abnormality knowledge graph is constructed in combination with a multi-level correlation relationship network; S4: a multi-modal abnormality detection model is constructed by fusing time series Transformer, graph neural network and knowledge embedding module, and is trained based on the feature data set and the power knowledge graph; S5: the trained multi-modal model is deployed on a distributed stream processing platform to realize real-time abnormality detection and multi-dimensional intelligent analysis; S6: the real-time abnormality detection and multi-dimensional intelligent analysis results are visualized. The present application can realize all-round intelligent monitoring of industry electricity abnormalities facing complex industry actual demands.

The invention provides a business risk detection method and device, equipment, a medium and a program product, and relates to the field of financial science and technology or the field of big data. The method comprises the steps of obtaining multi-modal business data of a target industry chain, processing the multi-modal business data in each industry to generate a joint feature vector corresponding to each industry, determining business association information among the industries according to the joint feature vectors corresponding to all the industries, and sending the business association information to the target industry chain. Generating a risk detection result of the target industrial chain based on the business association information; according to the method, the multi-modal business data of the multi-industry associated enterprises in the target industry chain is acquired and subjected to targeted processing, the joint feature vector of each industry is generated so as to accurately mine the business associated information between the industries, efficient detection and accurate identification of the target industry chain risk are finally realized, and the efficiency and accuracy of industry chain risk detection are improved.

This invention provides a dynamic calibration method, system, device, and medium for evaluating the implementation of power grid standards. The method includes extracting features corresponding to pre-acquired standard scenario feature vectors to obtain real-time scenario feature vectors; comparing the real-time scenario feature vectors with the standard scenario feature vectors to obtain feature deviation; and dynamically adjusting the static implementation evaluation benchmark of the standard based on the feature deviation using piecewise function differential calculation to obtain a dynamic evaluation benchmark. This method and system, by combining feature extraction from real-time scenario feature vectors, calculation of feature deviation, and piecewise function-based differential processing, achieve dynamic adjustment of the static implementation evaluation benchmark of the standard. This allows the output dynamic evaluation benchmark to be scientifically and differentially tightened or maintained according to the degree of scenario deviation, significantly improving the accuracy of evaluation results and the timeliness of risk warnings under different operating conditions.

This application discloses a method, apparatus, and electronic device for operating a microcontroller, belonging to the field of microcontrollers. The method for operating the microcontroller includes: obtaining the microcontroller's execution state based on a first bootloader firmware when the microcontroller restarts; performing a security verification on a target executable firmware based on a second bootloader firmware if the execution state indicator meets a first condition; and restoring the microcontroller based on an initial bootloader firmware and an initial executable firmware if the execution state indicator does not meet the first condition. The microcontroller operation method of this application can reduce the risk of device failure or malfunction due to power outages, software operation failures, or logical or version compatibility issues in the executable firmware itself during the process of upgrading the bootloader firmware via the executable firmware, thereby improving the resilience and reliability of upgrading the bootloader firmware via the executable firmware.

The application relates to the field of biomedical technology, and discloses a diagnostic agent for identifying melanoma molecular subtype typing and application, wherein the diagnostic agent comprises a first antibody specifically combined with a SOX10 protein and a second antibody specifically combined with an EGR1 protein; the diagnostic agent can be applied to preparation of a diagnostic product for evaluating the prognostic effect of a melanoma patient, preparation of a diagnostic product for predicting the treatment sensitivity of melanoma to a BRAF inhibitor, and preparation of a diagnostic product for guiding an individualized treatment scheme of melanoma. The diagnostic agent for melanoma molecular subtype typing can be directly transformed into clinical practice, and can assist in realizing real individualized treatment.

The invention discloses a weak current equipment intelligent operation and maintenance management system fused with the Internet of Things, and belongs to the technical field of weak current equipment operation and maintenance. The system comprises a data acquisition module, a data preprocessing module, a health degree dimension division module, a risk prediction module, a fault analysis module and a visual early warning module. The method comprises the following steps: acquiring health parameters, operation parameters and a topological relation connection diagram of weak current equipment through an Internet of Things sensor, performing cleaning, standardization and feature processing on the health parameters and the operation parameters to generate equipment state feature data, evaluating the health degree based on the equipment state feature data, and dividing the health degree into a health state dimension and an unhealth state dimension; according to the health state dimension and the non-health state dimension, differentiated risk prediction is carried out on the weak current equipment by adopting one of an ARIMA model and an LSTM model, a fault root cause is positioned by combining a topological relation connection diagram and a related model, and a result is visually presented and early warning information is pushed. Intelligent and precise operation and maintenance of the weak current equipment are realized, the operation and maintenance efficiency is improved, and the fault risk is avoided in time.

The application discloses a kind of nuclear power plant operation event trend analysis and prediction method and device, for the accuracy of existing statistical analysis method is insufficient in complex nuclear power environment, lack of multivariate nonlinear consideration and real-time analysis capability is short of etc., the application fuses deep learning and big data analysis technology, realizes event trend identification and high-risk area prediction.It includes: collecting operation log, sensor data and other multi-source event data, is stored after cleaning, standardization preprocessing;Extract the key features of event occurrence time, type, severity, etc., and construct a feature set;Through the analysis of time series data based on standardized event data extraction multi-LSTM based on standardized event data extraction multi-neural network model, identify long-term trends and periodic changes;Combined with deep learning and regression analysis, predict the probability of event occurrence and severity, locate high-risk period and area;Generate real-time warning information and provide prevention suggestions.

The application relates to the technical field of agent testing, and particularly provides an agent dynamic behavior safety testing method and system based on a risk transmission quantitative model, which comprises the following steps: collecting agent behavior data, containing a plurality of risk operation information and risk correlation relations; constructing a behavior risk correlation graph taking risk operations as nodes and correlation relations as edges, marking risk attributes and time limit factors on the nodes, and marking risk transmission strength on the edges; constructing a risk rule library based on the risk marking results and a preset risk judgment logic; inputting the behavior data, the behavior risk correlation graph and the rule library into a trained quantitative model to calculate risk transmission probability, influence range and critical nodes; real-time monitoring of behavior trajectories, task suspension, backtracking reasoning chain and intervention record generation when a multi-dimensional risk threshold is triggered; and test report generation by fusing multi-dimensional data. The application solves the problems of missed judgment and response lag in traditional testing, and improves the pertinence and reliability of safety testing.

This invention discloses an automated settlement system for cross-regional power trading based on smart contracts. A feature recording module records multi-dimensional settlement characteristics of settlement data packets from power generation companies. A data preparation module, responding to the power generation company's need to send settlement data packets, generates a sending request based on the multi-dimensional settlement characteristics. A sending module processes the settlement data packets based on the sending request, encapsulating the access sequence number and key segment sequence number for synchronous transmission. A verification module verifies the settlement data packets, and the verified data packets are used to generate a trading contract through a contract trading module. Based on the trading contract, a transaction fund transfer instruction is generated. This invention automates the entire power trading settlement process, reconstructs the trust system for power trading settlement, and lays a solid foundation for building a new generation of transparent, intelligent, and efficient power market operation ecosystem.

This invention provides a liquid metal-based thermal grease, its preparation method, and its application. The liquid metal-based thermal grease comprises the following raw materials in parts by weight: 100 parts liquid metal, 2-5 parts silicone oil, 0.1-20 parts thermally conductive powder filler, and 0.1-3 parts other additives. The high-reliability liquid metal-based thermal grease provided by this invention possesses excellent high thermal conductivity, high processability, and high reliability. It can replace traditional thermal grease to solve the heat dissipation and cooling problem of high-power chips, thereby extending the lifespan of electronic products.

This invention belongs to the technical field of energy storage systems. To further improve the efficiency and peak-shaving flexibility of energy storage systems, a liquefied air energy storage system coupling hydrate cooling, air separation, and liquefied natural gas is proposed. In the energy storage phase, the liquefied air energy storage system compresses and heats air. After expanding to atmospheric pressure, the liquefied air enters a gas-liquid separator. The separated gaseous air serves as return air to provide cooling energy, while the separated liquid air is stored in a liquefied air tank. The cooling energy for air cooling is provided by the return air, liquefied natural gas, and circulating hydrates. In the energy release phase, a portion of the liquid air in the liquefied air tank is pressurized and enters a distillation unit for air separation, producing liquid nitrogen and liquid oxygen. The remaining liquid air is used for power generation. The heating fluid is provided by circulating hydrates. This invention improves the system's economic efficiency and overall energy utilization efficiency.

This invention relates to the field of pattern recognition technology and discloses a method and system for evaluating and correcting phase factors based on numerical weather prediction. The method includes: collecting numerical weather prediction data for a target area at the current forecast lead time, and obtaining historical initial phase forecast results and current phase data; performing phase pattern recognition processing to determine the phase transition zone based on the current initial phase forecast results and wet-bulb criticality; performing phase boundary offset comparison to obtain the phase boundary offset direction and correction buffer zone; marking freezing rain protection candidate grid points; prohibiting the deletion of freezing rain protection candidate grid points as spatially isolated anomalies when they are located within the correction buffer zone; and performing freezing rain protection correction on the freezing rain protection candidate grid points to obtain the corrected phase forecast results. This application improves the retention capacity and correction accuracy of freezing rain risk grid points within the phase transition zone, and enhances the stability of phase forecast results.

The invention provides a stewed noodle automatic production line product defect analysis method and system based on multi-source detection, and relates to the technical field of product defect detection.The stewed noodle automatic production line product defect analysis method comprises the steps that a plurality of product defect detection nodes are inserted into a stewed noodle automatic production line, and a product image sequence is obtained; meanwhile, collecting real-time production data, extracting rheological characteristic parameters of the stewed noodle dough, performing multi-dimensional characteristic space mapping comparison with an intrinsic characteristic parameter set of a product quality sample to obtain multi-dimensional characteristic space mapping comparison information, and performing defect prediction and defect grading judgment in combination with a product image sequence, so as to obtain a multi-dimensional characteristic space mapping comparison result. And outputting the product defect grade and the risk coefficient, and performing product defect reminding. The technical problem that the dough defects cannot be comprehensively and accurately analyzed due to the lack of systematic modeling and dynamic sensing capabilities for the product quality evolution process in the prior art is solved, and the technical effects of improving the dough defect detection accuracy and enhancing the production line operation stability and the product quality consistency are achieved.

The invention discloses a vacuum flash tower based on vacuum deep distillation and a crude oil processing system and method, and belongs to the technical field of petroleum refining. According to the method, vacuum residue at the bottom of a vacuum tower is subjected to secondary flash evaporation by additionally arranging a vacuum flash evaporation tower, and light components (mainly wax oil) in the vacuum residue are further recovered. The vacuum flash tower adopts a combined design of an upper packed tower section and a lower plate tower section, the packed tower section is used for absorbing light components, and the plate tower section is used for prolonging the residence time of residual oil. And part of vacuum third-line wax oil extracted from the side line of the vacuum tower enters the top of the flash tower as an absorbent, absorbs flash light components and then is refined back to the vacuum tower, so that the product quality is ensured. The vacuum flash tower and the vacuum tower share a vacuum system, and the tower pressure is maintained at 4 kPa. According to the method, the vacuum residue extraction rate is remarkably increased, vacuum equipment does not need to be additionally arranged, the problem that light-component metal and residual carbon exceed the standard in a traditional process is solved, and economic benefits are remarkable. The method is suitable for heavy crude oil processing and has the advantages of low equipment investment, simple operation and the like.

The invention relates to the technical field of industrial internet, and discloses a big data driven tea industry full-chain intelligent model and visualization method, which comprises the following steps: firstly, constructing a full life cycle process topology network according to a process formula of a production batch and production line metadata, and mapping heterogeneous sensing data into a unified event stream; then establishing a polymorphic coupling digital twin containing biochemical reaction and material rearrangement operators according to a stacking processing link; local linearization and spatial modal decomposition are carried out on the twin body, a mask matrix representing a monitoring blind area is extracted, and a recessive quality out-of-control proportion index is calculated in combination with real-time state energy distribution statistics; and finally constructing a structured digital certificate based on the index and writing the structured digital certificate into the block chain. According to the method, the structural unobservable risk in the pile processing process can be quantified, and visual early warning and credible evidence storage of hidden quality fluctuation are realized.

The invention discloses a drainage basin cascade water-light complementation optimization scheduling method for electric power market transactions, and relates to the technical field related to electric power scheduling, and the method comprises the steps: carrying out the independent power generation fitting modeling of hydraulic power generation and photovoltaic power generation based on environment factors, equipment states and historical data; combining the price fluctuation and demand data of the electricity market to construct a plurality of typical electricity consumption scenes, and fitting to generate different bidding strategies; solving is optimized by taking market income maximization, supply and demand balance, cascade complementary stability and equipment health as targets; and formulating a joint bidding strategy and a corresponding optimal scheduling scheme. The technical problems that in the prior art, scheduling does not fully consider the power market environment, dual uncertainty of photovoltaic output and electricity price is difficult to deal with, and economic benefits are limited due to insufficient water and light resource collaboration are solved, and a complementary strategy of multi-market collaboration and risk optimization is achieved. And the technical effect of improving the overall income and anti-risk capability of watershed cascade water-light complementation in the electricity market is achieved.

A cloud-native resource scheduling optimization method based on predictive perception and deep reinforcement learning, the specific process includes: collecting cluster operation data and constructing scheduling samples; generating future load prediction results based on historical load sequences; constructing a prediction-enhanced scheduling state representation; determining the target node using continuous preference output and action mask; performing task allocation and life cycle management; updating the scheduling policy based on a multi-objective reward function; achieving policy convergence through experience replay and target network updates; online deployment and incremental reasoning. The present application introduces the future load prediction results of the nodes into the scheduling state representation, so that the scheduling decision is not only based on the current node resource state and task demand, but also combines the resource pressure change trend in the future period of time, thereby improving the early identification ability of the scheduler for potential high-load nodes.

The application relates to the technical field of building construction monitoring, and discloses a steel structure building construction whole-process mechanical property evaluation method based on digital twinning. The method comprises the following steps: a digital twinning model is established by fusing multiple source information, and is linked in real time with a sensor network arranged on site. Collected deformation, temperature, wind speed and other data are processed by a dynamic fusion and abnormality recognition algorithm, model parameters are continuously corrected, and real-time dynamic high-fidelity mapping of the mechanical state in the construction process is realized. Based on the updated model, an intelligent analysis module performs collaborative calculation, autonomously identifies construction abnormalities, quantitatively predicts potential risks, and generates process optimization decision instructions to be fed back to the site. The method constructs a closed-loop regulation and control mechanism from data sensing, model analysis to decision execution, realizes accurate online evaluation of construction mechanical properties and active prediction control of safety risks.

The invention provides an optimal scheduling method for a wind power and pumped storage combined operation system. The method comprises the following steps: solving a decision model based on a real-time data set and a risk preference coefficient to obtain a decision value set comprising an electric energy market standard, a frequency modulation capacity standard and a frequency modulation mileage standard of a power generation monomer, and scheduling the combined operation system; the objective function of the decision model aims at minimizing the total electricity purchase cost of the electric energy market and the frequency modulation auxiliary service market; the decision-making model is based on a historical data set, and the power market model and the joint operation system model are constructed by adopting multi-agent reinforcement learning and a deep neural network. The method is high in dynamic adaptability and robustness, facilitates improvement of declaration efficiency and result accuracy of the power market, can achieve collaborative scheduling of various energy sources, improves system stability, equipment utilization rate and energy utilization rate, reduces power generation cost and improves power generation benefits. And meanwhile, the coping capacity and the anti-risk capacity of the system for sudden load increase are improved.

The application discloses a biological age evaluation method and system based on multi-modal clinical data, wherein the evaluation method comprises the following steps: step 1, data acquisition and multi-modal construction; step 2, data preprocessing and feature expression; step 3, reference population construction and feature screening; step 4, biological age prediction model training and verification; step 5, biological age acceleration index calculation; and step 6, standardization and risk assessment output. By fusing heart ultrasound examination data and blood biomarker data, the application realizes comprehensive characterization of the aging state of an individual, further calculates a biological age acceleration index, and uses the biological age acceleration index for cardiovascular disease risk assessment, so as to solve the problems that a single-modal biological age model in the prior art cannot comprehensively depict the aging process and cannot simultaneously reflect changes in organ function and changes in systemic physiological state.

The invention discloses application of an Fn1-PPARbeta / delta signal channel related to a cardiac liver disease. The cardiac liver disease model is constructed according to the conditions that the liver development of young individuals is delayed due to heart injury and both adult and young individuals have serious fatty livers. In the model, the Fn1 protein level in the heart and blood is obviously increased compared with the normal level. Based on a zebra fish heart ablation means, after heart ablation injury, the heart specific knock-down Fn1 can lead to reduction of the Fn1 protein level in blood and alleviation of liver development retardation and fat deposition. Through the screening of transcriptomics, the PPARbeta / delta protein in the liver is found to be a potential downstream effect factor of Fn1. The liver specific overexpression PPARbeta / delta protein can significantly relieve abnormal phenotypes such as liver fat deposition caused by heart injury, and after the liver specific knock-down PPARbeta / delta protein, the protection effect of knock-down Fn1 on the liver disappears under the condition of heart injury. Therefore, the Fn1 protein and the PPARbeta / delta protein can be used as targets for preventing and treating the cardiac liver injury, and are used for preparing medicines for improving the cardiac liver injury, so that a new way is provided for treating the cardiac liver disease.

The invention belongs to the technical field of livestock and poultry breeding and feed formulas, and particularly relates to feed for improving the meat quality of Songliao black pigs by cooperatively replacing soybean meal with fermented miscellaneous meal and application. The feed is prepared from the following components in parts by mass: 60 to 65 parts of corn, 8 to 12 parts of fermented peanut meal, 6 to 10 parts of fermented sesame seed meal, 3 to 5 parts of soybean meal, 4 to 6 parts of bran, 3 to 5 parts of rice bran, 1 to 2 parts of fish meal, 0.8 to 1.2 parts of stone powder, 0.6 to 0.9 part of calcium hydrogen phosphate, 0.3 to 0.5 part of table salt, 0.2 to 0.4 part of amino acid premix, 0.1 to 0.2 part of vitamin premix, 0.1 to 0.2 part of mineral premix and 0.05 to 0.1 part of compound enzyme preparation, wherein the total mass of the feed is 100 parts. Wherein the mass ratio of the fermented peanut meal to the fermented sesame meal is (1.0-1.5): 1, the proportion of the fermented peanut meal and the fermented sesame meal for synergistically replacing the soybean meal is 70%-85%, the crude protein content of the feed is kept at 16%-18%, and the feed meets the protein requirement of the Songliao black pigs in the fattening period. The feed can meet the growth and metabolism requirements of the Songliao black pigs, and the meat quality is remarkably improved while the breeding cost is reduced.

The invention discloses an automatic dosing machine for medical intravenous medicine, and relates to the technical field of medical instruments and intelligent medical equipment. Comprising an addition execution module, a visual verification module and a central control unit, the assembly execution module comprises a base, a stand column, a lifting guide and transmission assembly and an upper end mounting seat, the stand column is vertically arranged on the base, the lifting guide and transmission assembly is arranged on the stand column in a lifting mode, and the upper end mounting seat is fixedly connected to the lifting guide and transmission assembly; the upper end mounting seat is provided with a needle inserting assembly, a pushing and injecting assembly and a supporting and positioning part, and the visual verification module comprises an image acquisition device which is used for acquiring identification information of a medicine or a container to be added with the medicine. According to the invention, the automatic intravenous medicine adding and dispensing system based on visual verification and central control is constructed, so that the defects of the prior art in the aspects of medicine safety, occupational exposure risk, adding and dispensing precision, operation efficiency and the like are systematically overcome.