343results about How to "Avoid one-sidedness" patented technology

The invention discloses a quality safety optimization method and system based on a multi-modal vertical large model technology, and relates to the technical field of quality safety optimization systems.The method comprises the steps that quality safety related data are collected from a multi-modal data source and preprocessed; fusing data through features and decision levels; a vertical large model of an improved Transform architecture is constructed by using fusion data, a quality feature extraction layer and a safety rule embedding layer are provided, and adaptive learning rate and gradient clipping training are used; inputting the new data into the large model to analyze the quality safety condition, including defect prediction, risk assessment and problem early warning; and according to an analysis result, generating an optimization suggestion through rule reasoning and reinforcement learning. According to the invention, multi-modal quality safety data can be comprehensively collected and preprocessed. The vertical large model is high in pertinence, quality defects, safety risks and potential problems are accurately analyzed, the optimization suggestion module is combined with rules and reinforcement learning, suggestions with expected effects and priorities are generated, and the quality safety level and the resource utilization efficiency are improved.

The invention relates to the technical field of user behavior analysis, and discloses a method for analyzing abnormal user behaviors based on logs and flow data, and the method comprises the steps: collecting user behavior data, including historical user behavior data and real-time user behavior data; based on historical user behavior data, constructing a group behavior baseline and an individual behavior baseline, and obtaining key behavior characteristics of the user; the deviation degree DEV of the key behavior characteristics of the user deviating from the group behavior baseline and the matching degree SimScore of the real-time behavior sequence of the user and the personal behavior baseline are calculated; according to the deviation degree DEV and the matching degree SimScore, whether the user behavior is abnormal or not is judged, and the risk level of the abnormal behavior is determined; triggering corresponding abnormal alarm and response measures according to the risk level; according to the method, the abnormal behavior of the user can be identified more accurately by fusing the log and the flow data and combining group and individual behavior baselines, and the accuracy and efficiency of anomaly detection are improved.

The invention relates to the technical field of concrete pouring, in particular to a concrete pouring homogeneity detection system and method based on sensing data, and aims at achieving efficient and accurate concrete pouring homogeneity evaluation and defect detection. The system comprises a multi-sensor sensing module, a multi-sensor data conversion and transmission module and a concrete homogeneity evaluation module, the multi-sensor sensing module comprises a temperature sensor, an ultrasonic sensor and a vibration sensor; the multi-sensing data conversion and transmission module is used for acquiring multi-sensing data and performing data type conversion and transmission on the multi-sensing data; and the concrete homogeneity evaluation module is used for constructing a concrete pouring homogeneity evaluation model to detect and evaluate the homogeneity and defects in the concrete pouring process. According to the invention, detection and evaluation of the concrete pouring homogeneity are realized through combination of multi-sensing data, and the accuracy of detection of the concrete pouring homogeneity is improved.

The invention discloses an intelligent power plant joint inspection system and method based on video AI and a robot, and the method comprises the steps: dividing an intelligent power plant into a plurality of subareas, evaluating the danger levels of the plurality of subareas according to historical data, and obtaining the danger levels of the plurality of subareas; setting an inspection cycle according to the danger levels of the plurality of partitions, and setting a plurality of robots to acquire operation data according to the inspection cycle to obtain inspection data of the plurality of partitions; acquiring a plurality of monitored videos, and performing video analysis on the acquired monitored videos by using an AI technology to obtain an abnormal position; according to the abnormal position, distributing an inspection robot of a corresponding partition to carry out fixed-point inspection to obtain fixed-point inspection data; and performing fault detection on the periodic inspection data and the fixed-point inspection data by using the fault recognition model, and performing fault early warning according to a fault detection result. The invention relates to the technical field of power plant inspection, and solves the technical problems of unreasonable inspection resource distribution and untimely fault early warning in an existing combined inspection system.

The invention discloses a power distribution network overhead line risk refined early warning method and system. The method comprises the following steps: collecting meteorological time sequence data and power distribution network topology and line parameter data; and preprocessing the data, and constructing a prediction data set. And establishing a fault probability prediction model based on the meteorological data and the line parameters. Calculating the fault probability by using the mathematical model, correcting the model, training in combination with static topology and dynamic meteorological data, and constructing a fault probability network model. And analyzing the importance of the nodes and lines of the power distribution network, and evaluating the load loss proportion of the nodes. And carrying out normalization processing on the importance indexes. And comprehensively calculating the predicted fault probability, the node loss load and the importance index to obtain a branch risk parameter. Fine early warning is carried out according to a set early warning threshold value, and dynamic adjustment is carried out to adapt to the actual operation condition. The method has the advantages that comprehensive risk assessment is provided, and the accuracy of fault prediction and the timeliness of risk early warning are improved.

The invention discloses a coal mine geological disaster and environment early warning method based on multi-source monitoring data fusion. The method comprises the following steps: determining a mine water disaster early warning evaluation index, a mine pressure disaster early warning evaluation index and a geological environment evolution early warning index; a corresponding first early warning threshold value is set; data are acquired and preprocessed, and a mine water disaster early warning model, a mine pressure disaster early warning model and a geological environment evolution early warning model are established; collecting new data to carry out iterative optimization on the model, and correcting an early warning threshold value; and integrating the iteratively optimized models into an early warning index system library, collecting and fusing various monitoring system and production dynamic data of the mine, and inputting the data into the early warning index system library for coal mine geological disaster and environment early warning analysis. The method solves the problems that in the prior art, multi-source monitoring data cannot be fully fused, an early warning model lacks self-learning and optimization capabilities, and an early warning threshold cannot be dynamically adjusted along with the change of a mining environment.

The invention relates to the technical field of side slope monitoring and early warning, in particular to a mine site side slope remote online real-time monitoring and early warning system which comprises a multi-source data monitoring unit, a data processing and analyzing unit, a side slope instability judging unit, an instability grading early warning unit and an early warning verification pushing unit. The method comprises the following steps: collecting monitoring data of a plurality of data sources to obtain time sequence monitoring data of each data source, carrying out noise reduction on the time sequence monitoring data, then decomposing the time sequence monitoring data, calculating a time-frequency feature vector through an energy density function, and optimizing the time-frequency feature vector through feature screening; calculating a slope stability evaluation index by optimizing the time-frequency feature vector, constructing an instability risk index to judge a slope instability risk level, constructing an early warning index, and combining the early warning index with the slope instability risk level to establish a graded early warning mechanism to obtain a slope instability early warning level; and verifying the slope instability early warning grade, and performing early warning according to the slope instability early warning grade passing the verification. According to the invention, the false alarm rate of slope monitoring and early warning can be reduced.

The invention discloses a high-voltage cable distributed continuous monitoring big data analysis processing method, and relates to the technical field of high-voltage cable operation monitoring and fault early warning. Calculating a partial discharge pulse average value, a current harmonic component and a voltage fluctuation amplitude in sequence by combining a temperature change rate and the like; calculating a predicted temperature influence index according to the temperature change rate, the temperature data and the operation state data, sequentially calculating a predicted partial discharge influence index, a predicted current influence index and a predicted voltage influence index in combination with the predicted temperature influence index, and calculating an operation basic index according to the basic parameter data; and finally, calculating a cable operation risk index according to the operation basic index and the predicted voltage influence index, setting a risk index threshold set, judging whether to trigger early warning or not according to a comparison result, and generating an adjustment instruction and a risk assessment report so as to guarantee safe operation of the high-voltage cable.

The invention discloses an ultra-short-term photovoltaic power generation power prediction method and system based on a mixed correlation coefficient and a multi-scale TCN-transformer, and the method comprises the steps: obtaining ultra-short-term photovoltaic power generation power historical data and corresponding meteorological data, and carrying out the feature selection of the photovoltaic power generation power historical data and the meteorological data through the mixed correlation coefficient, screening out characteristic variables which have great influence on the photovoltaic power; dividing into a training set, a verification set and a test set; the method comprises the following steps of: improving a transform model so as to form a multi-scale CN-transform model; training is carried out on a multi-scale TCN-transform model by using the data of the training set; and verifying the trained multi-scale TCN-transformer model by using the verification set data, and checking whether the model is trained to an optimal state or not. And inputting the data of the test set into the trained multi-scale TCN-transformer model, and obtaining a final photovoltaic power prediction result. According to the method, the correlation between the photovoltaic power and the meteorological factors is comprehensively analyzed by combining two methods of the Pearson's correlation coefficient and the unified information coefficient, and the one-sidedness of a single correlation analysis method is avoided.

The invention belongs to the technical field of intelligent control, and discloses a building energy-saving intelligent integrated control system and method. Comprising the steps of collecting building comprehensive data of a building internal space area; preprocessing the building comprehensive data to obtain standard building data; establishing a building dynamic model according to the standard building data, and predicting by using the dynamic model to obtain an energy consumption change curve and a comfort change curve of the internal space area of the building in a future fixed time period; solving to obtain a series of optimal control strategy sequences by taking the energy consumption change curve and the comfort change curve of the internal space area of the building in the future fixed time period as constraints; the optimal control strategy sequence obtained through solving is distributed to all actuators, and integrated intelligent control over heating equipment, refrigeration equipment, ventilation equipment, illumination equipment and the like is achieved; not only is the energy-saving level of the building improved, but also a comfortable environment is created for the indoor space, and the comprehensive performance of the building is comprehensively enhanced.

The invention relates to the technical field of enterprise supervision, in particular to a method for constructing an enterprise classification and grading supervision index system. According to the technical scheme, the method comprises the following steps of 1, determining a supervision target and a supervision range, and clearly supervising enterprise types and enterprise projects; 2, collecting various data related to the enterprise, including but not limited to financial data, operation data, market data and compliance data; and step 3, screening out key indexes having significant influence on enterprise classification and grading. According to the method, comprehensive and accurate evaluation is realized through multi-dimensional index screening and scientific classification, comprehensive weight determination and accurate quantitative evaluation; dynamic changes are adapted by means of regular updating, dynamic feedback early warning and flexible adjustment factors; and refined supervision and resource optimization are assisted by scientific threshold setting, enterprise development is promoted, and a benign interaction situation between supervision and enterprises is formed.

The invention provides an intelligent planning and budget evaluation method for high-standard farmland construction in hilly and mountainous areas. The method comprises the following steps: collecting current live data of a to-be-planned area; establishing an evaluation model of each planning index for predicting and evaluating each planning index value after different planning schemes are implemented, integrating the values into a multi-objective optimization algorithm, generating a plurality of different planning schemes based on live data, and finding an optimal planning scheme through iteration; values of decision variables are extracted from the optimal planning scheme, layer parameters are adjusted, and optimized planning maps are obtained and fused to obtain a final planning map; and generating an image set according to the final planning image, providing data for a metering center, and generating a budget file according to the data of the metering center and the budget template. According to the method, scientific, reasonable, efficient and accurate planning of the high-standard farmland in the hilly and mountainous areas is realized through the evaluation model and the multi-objective optimization algorithm, and meanwhile, budget management and resource allocation of the farmland construction project are performed in combination with budget evaluation.

The invention discloses a building construction safety environment monitoring analysis method and system, and relates to the field of data analysis, the main scheme is that a safety risk index G is calculated according to a field risk comprehensive coefficient GA, an equipment and progress comprehensive coefficient GB and an emergency and material comprehensive coefficient GC, one-sidedness caused by single factor evaluation is avoided, and the safety risk index G is calculated; the method is advantaged in that potential risk association and chain reaction can be discovered, a coping strategy can be made in advance, the construction safety management level is improved on the whole, and a problem of low safety risk assessment result accuracy caused by lack of detection and analysis of other important parameters and lack of integration of data from different sources is solved.

The invention belongs to the field of artificial intelligence, and particularly discloses an AI virtual character intelligent generation effect analysis and evaluation method, which comprises the following steps of: firstly, comparing a test text with an expected reply, evaluating a semantic comprehension degree, and ensuring that vocabularies are accurate and similar to sentence structures; secondly, historical dialogues are analyzed, context relevance is evaluated, and communication coherence is ensured; by combining the two items, the language understanding ability is comprehensively judged, and the deficiency is warned in time. Meanwhile, the response duration is monitored stably, and smooth user experience is ensured. In addition, collapse times in a historical period are tracked, operation stability is evaluated, and faults are prevented. Finally, multi-dimensional data such as language understanding, response speed and operation stability are integrated, the intelligent generation effect is comprehensively evaluated, a scientific basis is provided for performance optimization and problem early warning of the virtual character, it is ensured that the overall performance of the virtual character in the application meets the expectation, and potential problems are early warned in time.

The invention discloses a network security early warning method and system based on big data, and relates to the technical field of network security, and the main scheme is that multiple types of data including network traffic, user behaviors, system logs and hardware state data are collected, and then index calculation is carried out based on the data; a network attack risk index, a user data exception risk index, a system security risk index and a hardware fault risk index are calculated, a network security comprehensive risk index is further calculated comprehensively, finally, a network security early warning threshold value is preset, the comprehensive index is compared with the preset network security early warning threshold value, and whether an early warning mechanism is triggered or not is judged according to a comparison result. And generating corresponding early warning information.

The invention relates to the technical field of cross-border e-commerce commodity operation, and provides a commodity operation management method and system applied to cross-border e-commerce, and the method comprises the steps: carrying out the data division of commodity operation data, obtaining a divided data set, carrying out the data set optimization of the divided data set, and obtaining an optimized data set; performing multi-source analysis on the commodity operation data, and constructing an operation network of the operation commodity; querying potential users operating commodities, extracting target potential users from the potential users, constructing a screening matrix of the target potential users, and performing user screening on the target potential users to obtain screened users; and carrying out user updating on the screened users to obtain updated users, constructing an initial operation strategy of the operation commodity, carrying out supply risk assessment on a target operation user to obtain an assessment result, and constructing a commodity operation management strategy of cross-border e-commerce. According to the invention, high efficiency of commodity operation management can be improved.

The invention discloses an energy storage system control method based on multi-target cooperative operation. The method comprises the following steps: acquiring state data of an energy storage system in a current control period and state data of the energy storage system connected with a power grid; based on the state data of the energy storage system and the state data of the power grid, calculating an operation state comprehensive evaluation value of the energy storage system in the current control period; and determining a priority regulation and control target based on the comprehensive evaluation value of the operation state in combination with the state data of the energy storage system and the state data of the power grid, and controlling the energy storage system to regulate and control the priority regulation and control target in the next control period. A plurality of regulation targets of the energy storage system are comprehensively considered, and the comprehensive evaluation value of the operation state is calculated according to the real-time state data of the system to determine the priority regulation target, so that the energy storage system is promoted to regulate the corresponding targets in a targeted manner in the next period, the relationship among different targets is effectively coordinated, the one-sidedness caused by single target regulation is avoided, and the regulation efficiency is improved. And overall collaborative optimization is realized.

The invention relates to the technical field of environmental analysis, and discloses a new pollutant identification method and device, computer equipment and a storage medium, and the method comprises the steps: determining a target execution strategy through determining the application sequence of each non-target analysis method and each computational toxicology method in a high-throughput fusion method; the method can be realized by reasonably selecting and switching execution strategies whether searching corresponding chemical substances from the toxic effect or evaluating the toxic effect of the chemical substances from the found chemical substances. Furthermore, a target execution strategy is utilized to perform new pollutant risk assessment and calculate a plurality of risk values, various characteristics of the new pollutants and performance in an actual environment are comprehensively considered, and the potential risk of the new pollutants can be quantitatively reflected from different angles. And finally, multiple target new pollutants are further determined in combination with multiple risk values, and objects which have great threats to the environment and human health and need to be managed and controlled preferentially are screened out from numerous possible new pollutants.

The EV charging and discharging optimization method considering user will and battery loss comprises the steps that a V2G model is constructed according to driving characteristics and user habits of an EV owner, subjective factors and objective factors influencing decision making of an electric vehicle user are analyzed, and modeling is carried out; the method comprises the following steps: adding discharge income and battery loss cost into comprehensive charging cost, and firstly, carrying out modeling quantification on the battery loss cost based on temperature and discharge depth; secondly, analyzing a three-dimensional relationship among the temperature, the discharge depth and the battery life, and finally, considering seasonal characteristics of temperature loss; and adding dynamic adjustment of user willingness and loss seasonal characteristics in an optimization strategy, constructing a typical scene, and optimizing the comprehensive charging cost of the user side and the peak-valley difference of the power grid side by using a dung beetle algorithm. According to the optimization method, charging and discharging behaviors are optimized by introducing user willingness, and the user satisfaction is improved; battery loss is considered, battery life is prolonged, and maintenance cost is reduced; in combination with seasonal characteristics, the overall efficiency of the system is improved, and stable operation is ensured.

The invention provides a light curtain fault detection method and system, and relates to the technical field of light curtain fault detection, and the method comprises the steps: detecting the first signal intensity of a light beam emitted by an emitter end of a light curtain in real time, and the second signal intensity of the light beam received by a receiver end; if it is detected that the second signal intensity is smaller than or equal to the first signal intensity, and the difference between the second signal intensity and the first signal intensity exceeds a first preset threshold value, the calibration tool is controlled to conduct offset detection on the light curtain, and offset is obtained; if it is detected that the offset exceeds a second preset threshold value, light curtain fault early warning is carried out; and if it is detected that the second signal intensity is greater than the first signal intensity and the difference between the two is greater than or equal to the first signal intensity, performing light curtain fault early warning. By implementing the method, fault detection can be carried out in real time in the working process of the light curtain, the fault detection efficiency is improved, and potential safety hazards are reduced.

The invention provides a tunnel multi-modal information processing and predicting method based on a Transform technology. The method comprises the following steps: S1, acquiring various sensor data of a tunnel and a vehicle; s2, constructing vehicle composite features according to the sensor data; s3, synthesizing the composite features into a corresponding one-dimensional data sequence, performing one-dimensional convolution processing, inputting processing results into a plurality of corresponding multi-layer perceptron to obtain composite feature weights, and obtaining weighted features according to the composite feature weights, adding position information to the convolution processing result of each one-dimensional data sequence, then carrying out cross-modal fusion, and carrying out projection transformation on the cross-modal fusion result to obtain a corresponding single-modal feature; and S4, weighting the single-mode features by using the weighted features, and inputting a weighted result into the constructed Transform model to obtain a tunnel risk prediction result. The method has the advantages of high prediction accuracy and high efficiency.

The invention relates to an automobile part quality early warning method and device, computer equipment and a computer readable storage medium. The method comprises the following steps: according to historical quality defect data of an automobile part, carrying out early warning detection on the automobile part under a preset early warning dimension to obtain an early warning detection result; the preset early warning dimension comprises at least one of the number of defective products, the growth rate of the defective products and the predicted change rate of the defective products; the historical quality defect data comprises the number of defective products of the automobile parts in a plurality of periods; carrying out fusion processing on the early warning detection results under each early warning dimension to obtain a comprehensive early warning detection result of the automobile part; and performing graded quality early warning on the automobile parts according to the comprehensive early warning detection result. By adopting the method, the early warning accuracy can be improved.

The invention relates to a method, device and equipment for determining the safety coefficient range of a karst cave slope and a medium. The method comprises the steps that the maximum value and the minimum value of the slope in the X direction and the Y direction are obtained; based on the maximum value and the minimum value of the slope in the X direction, the slope is divided in the X direction according to the vertical division interval, and a plurality of vertical units are obtained; based on the maximum value and the minimum value of the slope in the Y direction, unit bodies with random heights are generated in all the vertical units; according to the unit bodies, determining the distribution condition of the rock-soil body and the karst cave in each vertical unit, and constructing a slope karst cave simulation model; performing assignment calculation on the slope karst cave simulation model to obtain a slope safety coefficient; and a plurality of groups of slope safety coefficients are obtained through iterative calculation, and the range of the slope safety coefficients is determined based on each group of slope safety coefficients. Reliable data support can be provided for engineering design of the karst cave slope, and safety and engineering economy are both considered.

The invention provides a tunnel health evaluation method and system based on machine learning. The method comprises the following steps: constructing a tunnel health evaluation hierarchical structure model; obtaining criterion layer data based on the current tunnel index layer data, wherein the criterion layer data comprises lining crack, water leakage, lining material deterioration, lining back cavity, lining layer peeling and lining deformation data; calculating a lining deformation superposition amount according to the lining crack data and the water leakage data, and correcting the lining deformation data based on the superposition amount to obtain real lining deformation data; inputting real lining deformation data and other current tunnel criterion layer data into the machine learning model to obtain a current tunnel health evaluation result; wherein the machine learning model is constructed based on the criterion layer data and the target layer level, and the historical tunnel criterion layer data and the corresponding health level are utilized to train the machine learning model. According to the method, the superposition effect between the leakage water and the lining crack is considered, so that the accuracy of tunnel health evaluation is effectively improved.

The invention relates to a credibility evaluation method, device and equipment for an equipment digital model. The method comprises the following steps: aiming at any one output index in a plurality of output indexes related to equipment digital model credibility evaluation, under the same working condition, carrying out simulation operation on the digital model for multiple times, and carrying out tests on real equipment for multiple times to respectively obtain a group of experimental data of the output index; calculating the coincidence degree of the two groups of experimental data, and designing a credibility distance based on the coincidence degree; constructing a vector of a distance value on each dimension according to the credibility distance corresponding to each working condition; calculating an average value of the distances according to the vectors of the distance values on each dimension, and calculating the initial credibility of the equipment digital model by using the average value; and calculating a comprehensive distance according to the initial credibility of the equipment digital model under the plurality of indexes, and calculating the credibility of the to-be-evaluated equipment digital model by using the comprehensive distance. By adopting the method, the credibility evaluation of the equipment digital model can be realized.

The invention belongs to the technical field of energy control, and particularly discloses a building gas energy intelligent monitoring control system which comprises a gas data acquisition module, a pipeline state acquisition module, a gas state analysis module, a gas control analysis module, a database and a gas control execution terminal. According to the invention, real-time monitoring is carried out from three parameter dimensions of the gas flow, the external temperature of the gas pipeline and the internal pressure of the gas pipeline, so that the dynamic change of the gas system at different moments can be accurately captured, and the problem that the dimension of monitoring data at the monitoring level is relatively single at present is effectively solved; the one-sidedness of gas state judgment caused by only depending on a single index is avoided, meanwhile, through confirming the gas abnormal item, analyzing the gas abnormal guiding degree under the gas abnormal item and analyzing the abnormal control scheme of the gas abnormal item, the limitation of the management personnel on the processing timeliness of the gas use condition is relieved, and the safety of the management personnel is improved. And the flexibility of gas control is improved.

The invention relates to the field of communication, and discloses an intelligent traffic scheduling optimization method, device and equipment and a storage medium, and the method is used for 5G network intelligent traffic scheduling optimization. The method comprises the following steps: receiving a service request, analyzing the service request to obtain a 5G standard service type, an application scene and a 5G network slice identifier, then obtaining an SLA parameter corresponding to the service request and a candidate link required by service transmission, and converting the SLA parameter into an SLA preference vector; acquiring global data of the candidate link, and predicting by using the network state prediction model to obtain a predicted network state of the candidate link; the SLA preference vector is used as optimization target guidance, the predicted network state is used as a constraint condition, and a global optimization routing strategy is calculated through a multi-target optimization algorithm; and generating a control message packet based on the global optimization routing strategy, issuing the control message packet to the network forwarding equipment, and adjusting parameters of the network state prediction model and the multi-objective optimization algorithm based on the actual performance data after execution.

The invention provides a tumor medical image classification method of zero sample evolution NAS based on double-index collaborative evaluation, which comprises the following steps: collecting tumor medical image data, and constructing a data set containing a tumor focus image and a normal tissue image; constructing an extended search space based on a cell structure, wherein the search space comprises a basic operation set, the cell structure and a network overall structure; steady-state evolution algorithm parameters are set, and steady-state evolution initialization is carried out to obtain an initial candidate architecture; taking a double-index comprehensive score calculated by the information rate and the FIM stability as a comprehensive index for evaluating the current candidate architecture, updating the candidate architecture through a steady-state evolutionary algorithm based on a dynamic optimization mechanism until the maximum evolutionary algebra is reached, and obtaining an optimal architecture; and training the optimal architecture by using the data set, and carrying out tumor medical image classification by using the trained optimal architecture. According to the method, the dependence on the annotated data is reduced, the consumption of computing resources is reduced, and meanwhile, the diagnosis efficiency and accuracy are improved.

The invention relates to a transformer top oil temperature prediction method based on a comprehensive thermal factor and a neural network, and the method comprises the steps: 1, selecting characteristic variables which affect the top oil temperature of a transformer through the actual measurement data of the transformer, and carrying out the correlation analysis, and obtaining a correlation heat map; 2, determining a characteristic number closely related to the top oil temperature thermal effect by combining a top oil temperature calculation formula in IEEE and GB1094, defining the characteristic number as a comprehensive thermal factor, and taking the comprehensive thermal factor and the top oil temperature as characteristic variables; 3, constructing a top oil temperature prediction model of a CNN-LSTM-Attention combined structure, constructing a linear connection layer as a comprehensive thermal factor by using the current and the environment temperature, and dividing a training set sample proportion to a verification set sample proportion to be 6: 2: 2; 4, the average absolute error and the average absolute percentage error serve as error evaluation indexes, and the top oil temperature prediction result is evaluated and analyzed. The method can accurately predict the top oil temperature of the transformer in a future period of time.

The invention belongs to the technical field of power distribution network data quality management, and particularly relates to a power distribution network multivariate time series data-oriented quality evaluation method, which comprises the following steps of: selecting power distribution network multivariate time series data quality evaluation dimensions based on power distribution network data characteristics and distribution characteristics; comprising integrity, normalization, consistency, timeliness, uniqueness and accuracy; designing an evaluation method of the power distribution network multivariate time series data quality evaluation dimension; designing a weight distribution scheme of each dimension, and determining the weight of each dimension; and according to the quality score of each dimension and the weight of each dimension, calculating the total score of the quality of the to-be-measured data, and evaluating the data quality grade. According to the method, multi-level, multi-azimuth and multi-angle analysis is carried out on the power distribution network data, so that one-sidedness and limitation in a traditional evaluation method are avoided, and the data quality can be reflected more truly by the result, thereby optimizing the enterprise decision flow, promoting the intelligent development of the power distribution network, and realizing more efficient and sustainable power data management.