150results about How to "Avoid subjectivity" patented technology

The invention relates to the technical field of industrial clusters, and discloses an industrial cluster industrial chain construction method and device, equipment and a medium, and the method comprises the steps: obtaining supply associated data and property right associated data of an enterprise of an industry category to which a target industrial cluster belongs; constructing a directed contact network based on the supply association data; constructing an undirected contact network based on the property right associated data; calculating property right connection degrees among the nodes in the undirected connection network, and accumulating the property right connection degrees to paths with corresponding node relations in the directed connection network according to a preset weight to generate a multi-source data enhanced network; and traversing all node paths in the multi-source data enhanced network, calculating the accumulated connection strength of each node path, and determining the path with the highest accumulated connection strength as the industrial cluster core industrial chain. According to the method, the universality, professional interpretability and objective accuracy of the constructed industrial chain are improved.

The invention relates to the technical field of coal mill powder pipes, in particular to a powder leakage defect automatic identification method based on digital twinning and AI video analysis, and the method comprises the steps: obtaining operation parameters and environmental parameters of a coal mill powder pipe, calculating a powder leakage risk characterization coefficient, and judging whether there is a potential risk of powder leakage; image data of the surface and the surrounding area of the powder pipe in the initial starting period are collected through an AI video analysis module, powder leakage characteristic parameters are extracted, a characteristic change curve segment is drawn, similarity comparison is conducted on the characteristic change curve segment and the reference characteristic curve segment, and whether a suspected powder leakage area exists or not is judged; actual operation parameters and model prediction parameters of the powder pipe in a stable operation period are obtained based on a digital twin model, the fluctuation degree of parameter deviation is calculated, and whether the powder leakage defect exists or not is comprehensively judged by combining a suspected powder leakage area judgment result; the early-stage accurate identification of the powder leakage defect is realized, the detection efficiency and precision are improved, and the operation and maintenance cost and the safety risk are reduced.

The invention provides a diabetic patient life management method and system in combination with traditional Chinese medicine knowledge, and relates to the field of medical health data processing, the method comprises the following steps: obtaining multiple groups of sample data, the sample data at least comprising personal information of sample patients and diabetic traditional Chinese medicine syndromes, and the personal information of the sample patients at least comprising diabetes index data; based on the multiple groups of sample data, multiple key traditional Chinese medicine syndrome discrimination units are determined, and a diabetes traditional Chinese medicine syndrome diagnosis scale is generated; based on the multiple groups of sample data, determining music types matched with different diabetes mellitus traditional Chinese medicine syndromes; determining the diabetic traditional Chinese medicine syndrome of the current user based on the personal information of the current user and the filling information of the diabetic traditional Chinese medicine syndrome diagnosis scale; based on the diabetic traditional Chinese medicine syndromes of the current user and the music types matched with different diabetic traditional Chinese medicine syndromes, music, traditional Chinese medicine health maintenance skills and traditional Chinese medicine recipes are recommended, and the method has the advantage of improving the quality of life management of diabetic patients.

The invention relates to the technical field of straightening equipment, and discloses an automatic matching straightening machine for shaft workpieces, which comprises a machine body, a plurality of linear sliding rails for a plurality of mechanisms to linearly move are arranged on the machine body, and strip-shaped tooth grooves matched with moving gears are formed in the two sides of the interior of the machine body; one side of the machine body is provided with a PLC (Programmable Logic Controller) control cabinet for calculating input shaft workpiece data information and generating a control signal, and the PLC control cabinet is used for controlling each mechanism on the machine body in an operation process. By adding and arranging the movable detection mechanism, when the shaft workpiece is straightened, the movable detection mechanism adopts a lever type detection structure, can be tightly attached to the surface of the shaft workpiece, sensitively captures bending deformation information of the workpiece, realizes accurate acquisition of deformation, avoids subjectivity and errors of manual detection, and improves the straightening accuracy of the shaft workpiece. And full-length movement detection can be realized along a linear sliding rail, all parts of the shaft workpiece are covered, and the condition of missing detection of a deformation position is avoided.

This utility model relates to a training system and hand probe device for security personnel, comprising: a training uniform, a mannequin, and a hand probe device; the training uniform is worn on the mannequin, and a wireless communication tag is affixed to a predetermined position on the inside of the uniform; the hand probe device communicates wirelessly with a client, and one or more wireless communication tag readers are installed within the hand probe device. This utility model facilitates in-depth analysis and accurate feedback of training content, effectively avoids the subjectivity and arbitrariness of manual assessment, ensures the objectivity and consistency of assessment results, and helps improve the quality and effectiveness of security personnel training.

The utility model provides a roadbed compaction inspection device, which belongs to the technical field of road construction equipment, and comprises a walking frame, a rolling mechanism and a soil sampling mechanism, by arranging the rolling mechanism, the rolling mechanism can apply counter weight to a roller in the walking process of the walking frame, so that the compaction degree of the surface layer of a road surface can be judged by utilizing the indentation of the roller, and the soil sampling mechanism is used for sampling soil. The number of the balance weight parts or the weight of the whole balance weight can be adjusted according to needs. And moreover, the soil sampling mechanism is used for sampling soil to form the test hole, so that the subjectivity of manual excavation of the test hole is avoided, and the consistency of the size of the test hole is ensured. The soil sampling mechanism can quickly sample soil, so that the compaction degree of the inner layer can be conveniently obtained. In conclusion, the roadbed compaction inspection device can improve the roadbed compaction detection efficiency and the reliability and precision of the detection result.

The invention discloses an MICP intensity prediction method and system based on machine learning and multi-feature fusion, and relates to the field of solidified data analysis. An accurate quality prediction mapping model and an abnormal compensation parameter mapping model are constructed based on historical data; the system has the capabilities of predicting curing quality from process parameters and intelligently recommending an optimal disposal scheme from an abnormal state; by setting a dual-threshold quality control mechanism and a real-time abnormity monitoring and early warning system, various abnormal conditions in the curing process can be actively identified and timely responded, and complete closed-loop processing from parameter deviation detection to automatic compensation measure execution to hardware standby switching can be realized. The stability of the solidification process and the consistency of the engineering quality are effectively guaranteed, the requirement for manual intervention and the misjudgment risk are greatly reduced, powerful technical support is provided for standardization, normalization and industrialization development of the sand solidification technology, and the engineering efficiency and economic benefits are remarkably improved.

This invention discloses a power distribution IoT communication and equipment management system based on dynamic optimization algorithms. It adopts a four-layer architecture: a perception layer, an edge layer, a platform layer, and an application layer. The end devices in the perception layer are used to collect power distribution data and execute control commands. The edge devices in the edge layer, and their managed sub-devices, are used for protocol conversion, data preprocessing, and executing dynamic optimization algorithms. The platform layer is used for message parsing, algorithm optimization, device management, and data storage. The application layer provides a visual user interface. Through dynamic optimization algorithms and a full lifecycle device management scheme, the system significantly improves the reliability of power distribution IoT data transmission, optimizes network resource utilization, enhances equipment operating efficiency, ensures the real-time performance of critical services, and features strong compatibility, security, and concurrent processing capabilities.

This utility model discloses a teaching device for a front-end module robot of semiconductor equipment, including a front-opening transfer box. Several stepped grooves are provided on the left and right sides inside the transfer box. An auxiliary positioning plate is installed between the stepped grooves on the left and right sides. The surface of the auxiliary positioning plate has long guide grooves and short guide grooves that match the end effector of the robotic arm. Limiting blocks are provided on the outer sides of the long and short guide grooves. The long and short guide grooves are arranged parallel to each other on the auxiliary positioning plate. A tapered hole is provided at the bottom of the auxiliary positioning plate. This utility model ensures compatibility between the front-opening transfer box, the pre-alignment platform, and the wafer fixing platform; through the limiting design, the insertion posture of the robot's end effector is precisely controlled, improving teaching accuracy and repeatability, and avoiding errors caused by subjective judgment.

This paper provides a method, apparatus, device, and storage medium for automatically acquiring rock mechanical parameters. The method includes: reading stress-strain data obtained from uniaxial compression experiments on rocks; interpolating the stress-strain data to form a stress-strain curve; dynamically extending the stress-strain curve towards both ends, starting from a target point, until the goodness of fit of the regression line formed by the current extension is lower than a set threshold; segmenting the stress-strain curve using the stress peak point, strain peak point, and endpoint of the regression line as segmentation points; calling a first rock mechanical parameter calculation module to process the stress-strain curve and obtain a first type of rock mechanical parameters; and calling a second rock mechanical parameter calculation module to process the segmented stress-strain curve and obtain a second type of rock mechanical parameters; and merging the two types and outputting the results. The embodiments described in this paper can improve the efficiency and accuracy of acquiring rock mechanical parameters.

The invention discloses a waterworks intelligent dosing optimization system and method based on data driving, and belongs to the technical field of water treatment, and the system comprises a historical data intelligent clustering module which obtains and preprocesses historical operation data, employs a minimum distance clustering algorithm to automatically generate a clustering center representing a typical working condition, and sends the clustering center to a cloud server; calculating a corresponding expert recommended dosage, and constructing an expert experience knowledge base; the real-time parameter dynamic matching module is used for acquiring real-time operation parameters, performing window processing, performing Euclidean distance matching on the real-time operation parameters and a clustering center in a knowledge base, and finding out a reference dosage corresponding to the most similar working condition; and the dosage optimization decision module is used for performing feedback correction on the reference dosage according to the comparison relationship between the real-time effluent quality and the standard value, and generating a final dosage instruction under the constraint of the minimum dosage. According to the invention, accurate and dynamic control of the dosage is realized, and the medicament consumption is obviously reduced on the premise of ensuring the stability of the effluent quality.

The invention discloses a necking detection method based on geometric feature self-adaption. The necking detection method comprises the following steps that S1, the longest main axis of a simulation graph is determined; s2, selecting N feature points on the longest main shaft; s3, obtaining the minimum key size of the simulation graph at each feature point; and S4, judging whether the simulation graph has a necking risk or not based on each minimum key size. By identifying the geometric centroid and the longest principal axis of a graph, adaptively selecting feature points and performing omnidirectional scanning, the measured minimum critical dimension is compared with a set safety threshold, and a risk point which is most likely to generate necking on the graph is accurately positioned, so that the automation and objectification of risk detection are realized, and the risk detection efficiency is improved. Subjectivity and experience dependence of manual marking are avoided, and consistency of detection results is guaranteed; meanwhile, the method has good adaptability to complex or deformed contours, missing detection and misjudgment are effectively avoided, and the yield and reliability of chip manufacturing are improved.

This invention discloses a method and apparatus for constructing an engineering model of a closed-loop control system. The method involves obtaining the process given amplitude of the closed-loop control system and its process output parameters, including a steady-state value, a first peak value, a first peak time, and a second peak time. A first difference between the second peak time and the first peak time is calculated. Based on this first difference, a time constant for the engineering model of the closed-loop control system is set. Based on the steady-state value and the process given amplitude, the gain of the engineering model is set. Based on the first peak value and the process given amplitude, the identification coefficients of the engineering model are set. The engineering model is then determined based on the time constant, gain, and identification coefficients. Compared with existing technologies, this invention enables rapid construction of an engineering model of a closed-loop control system based on relevant process given parameters.

The invention belongs to the technical field of burn wound analysis. According to the skin burn analysis method and system based on contrast agent blood perfusion, firstly, a fluorescence sequence after a contrast agent is injected is obtained, and a preprocessing sequence is generated through area cutting and down-sampling; a fluorescence intensity time curve of each pixel point is extracted, peak time is determined, and statistics is carried out to construct a peak time histogram; performing smooth denoising, extreme value detection and weak peak removal on the histogram, and adaptively selecting a threshold value for distinguishing normal and burnt tissues; generating an initial mask by using the threshold value, and performing connected domain analysis and morphological post-processing to obtain a target burn area mask; and finally, generating a pseudo-color image in combination with peak time. According to the method, the time dynamic characteristic of blood perfusion is fully utilized, the burn area can be accurately segmented and the microcirculation disturbance degree can be visually presented without depending on skin textures or a large amount of training data, and the objectivity and accuracy of burn depth evaluation are remarkably improved.

The invention provides a Laplace-DLTS defect parameter extraction method and a Laplace-DLTS defect parameter extraction system. The Laplace-DLTS defect parameter extraction method comprises the following steps: acquiring capacitance transient data obtained by a deep energy level transient spectrum test; carrying out preprocessing on the capacitance transient data; constructing a Laplacian transformation kernel function according to the capacitance transient data, and performing discretization processing to obtain a discrete Laplacian transformation model; regularization constraint parameters are introduced to construct a target function, a corresponding emissivity spectrum is obtained through numerical solution, and the regularization constraint parameters are adaptively determined according to signal characteristics of capacitance transient data; performing automatic peak identification on the emissivity spectrum based on a preset criterion; and according to the identified effective defect peak, automatically extracting and outputting physical parameters of the corresponding defect. By introducing the adaptive regularization constraint parameter, the regularization degree can be dynamically adjusted according to the actual signal characteristics of the capacitance transient data, the instability problem of noise amplification and solution is effectively suppressed, and the resolution capability and reliability of the emissivity spectrum analysis result are improved.

The present application relates to the technical field of traditional Chinese medicine preparation, and particularly relates to a method and system for optimizing a frying process of traditional Chinese medicine decoction pieces. Formula information and process requirements of target traditional Chinese medicine decoction pieces are obtained; a frying process scheme of similar traditional Chinese medicine decoction pieces is retrieved from a traditional Chinese medicine frying expert knowledge base; initial parameters are generated by fusing the frying process scheme; first-round frying is performed; process data are collected by a multi-modal sensor; adjustment suggestions are proposed by experts; parameter adjustment schemes are generated in combination with the expert suggestions and the process data; interactive optimization is performed for multiple rounds; and optimal frying process parameters are recorded and stored in the knowledge base. By constructing a formula information-driven knowledge retrieval mechanism, a multi-modal sensing monitoring system, a parameter adjustment strategy combining expert evaluation and data analysis, and an interactive iterative optimization framework, a closed-loop optimization system is formed, and technical problems such as difficulty in knowledge reuse, single process monitoring, lack of systematic support for parameter adjustment, and insufficient human-machine cooperation in traditional Chinese medicine frying processes are solved.

The invention discloses an indoor construction progress visual mapping method fusing semantic recognition and spatial positioning. The method comprises the following steps: collecting multi-frame image data of each component of an indoor construction scene by adopting a panoramic camera; outputting a semantic segmentation result corresponding to each component in each frame of image; synchronously acquiring camera pose data and scene sparse point cloud data in one-to-one correspondence with the timestamps of each frame of image; constructing to obtain a semantic sparse point cloud map containing component category information; performing similarity transformation based on the scale factor and the camera pose data, and mapping a semantic sparse point cloud map from an SLAM world coordinate system to a pixel coordinate system of an architectural planar graph; repeated projection of the same component caused by continuous acquisition of multiple frames of images is removed; performing weighted summation to obtain a progress value of indoor construction; and visually displaying the progress value and the component mapping result on the architectural plane graph. The indoor construction progress monitoring system has the advantage that the problem of difficulty in automatic, precise and visual monitoring of the indoor construction progress is solved.

This invention relates to the field of tobacco procurement information technology, and discloses an intelligent processing system for weighing information and a weighing and sealing device for tobacco leaf pre-inspection. The system includes data acquisition, processing, interaction, and execution control modules. The data acquisition module performs time-series alignment of continuous weight data and identity data. The data processing module uses a peak-valley range algorithm to determine stability and lock the net weight, while simultaneously performing tare deduction and compliance verification. The data interaction module, based on visual anchor point positioning technology, establishes a non-intrusive transmission channel with external business systems, automatically corrects control coordinates, and simulates data entry. The execution control module, based on a finite state machine, drives seal generation and data entry when verification is successful, and triggers an audible and visual alarm and forcibly blocks the entry signal and sealing command when verification fails. This invention solves the problems of difficult integration with heterogeneous systems and error-prone manual data entry, achieving automated and accurate acquisition of weighing data and closed-loop quality control.

This invention relates to the field of bid document management technology, and in particular to an automatic bid document review method and system based on natural language processing. The method includes: identifying target sections; determining historical performance and financial information; judging whether false performance exists; analyzing the complete sentences containing target keywords; calculating material scores; determining price deviation; and determining the review result. This invention achieves multi-dimensional and comprehensive review of bid documents by intelligently analyzing multiple sections such as qualifications, risks, materials, and pricing. This effectively improves the comprehensiveness and depth of the review. Utilizing natural language processing technology, it can accurately identify and extract key information from bid documents, overcoming the subjectivity and limitations of traditional manual review. Quantitative assessment based on risk level significantly improves the accuracy and relevance of risk identification. By comprehensively weighing material scores and price deviation, it significantly improves review efficiency.

The present application provides a kind of geologic multi-source constraint adaptive full waveform inversion method and system, constructs multiple complementary constraint norms, organically fuses multiple modal prior information, forms unified multi-source constraint framework, compared with traditional single type prior constraint, the present application can more comprehensively utilize available prior information, guide inversion to the direction that both conforms to geophysical data and geological understanding converges;While introducing adaptive regularization parameter strategy based on Bayes theory, realize the adaptive update of weight factor, avoid the subjectivity and randomness caused by the dependence of regularization parameter on experience selection in traditional method, make the inversion result more stable, and do not need tedious manual parameter adjustment, can dynamically adjust the constraint strength according to the data noise level, enhance the guiding role of prior constraint in low signal-to-noise ratio, more rely on observation data in high signal-to-noise ratio;At the same time, through the combination of model compression and forward simulation calculation, the calculation efficiency is greatly improved.

This invention belongs to the field of equipment inspection technology and discloses an intelligent inspection and positioning method and system based on Bluetooth and NFC. The method includes: receiving Bluetooth signals from available Bluetooth devices through an intelligent inspection and positioning terminal, and sorting valid inspection points based on the access time of each Bluetooth signal to generate a time series representing the inspector's movement route, thereby automatically tracking the inspector's movement route; when at least two assigned inspection areas are identified, comparing the number of shared inspection points between different assigned inspection areas with an intersection threshold value to determine key inspection areas or ordinary inspection areas, and then generating an inspection route. This invention reconstructs the inspector's movement route based on the time series of Bluetooth signal access, improving the authenticity and objectivity of the inspector's movement route, and by transforming inspection planning into a dynamic response, improving the overall efficiency and targeting of inspection work.

The invention belongs to the technical field of power grid disaster prevention and reduction, and particularly relates to a risk assessment method and device for deicing jump of a power transmission line, electronic equipment and a computer readable storage medium. The method comprises the following steps: determining risk influence factors influencing the deicing jump of the power transmission line, and constructing an original parameter data set containing a plurality of deicing working conditions; establishing a conductor deicing model under a plurality of deicing working conditions and carrying out analogue simulation to obtain a risk consequence index; constructing a standardized decision matrix, respectively calculating the comparison intensity and conflict of each risk influence factor, and calculating the comprehensive information amount and objective weight of each risk influence factor to obtain an objective weight vector; and identifying the key dominant factors based on the objective weight vector and carrying out working condition optimization in combination with the risk consequence indexes under each deicing working condition to obtain the optimal deicing working condition with the lowest comprehensive risk. According to the method, the CRITIC method is applied to power transmission line deicing jump risk assessment, and the deicing working condition with small risk can be selected.

The invention belongs to the technical field of shale oil and gas development, and discloses a shale oil-gas-bearing potential multi-parameter collaborative evaluation method. The method integrates six experimental technologies of nitrogen adsorption, carbon dioxide adsorption, carbon and oxygen isotope, rock pyrolysis and XRD total rock / clay analysis, and comprises the core steps of obtaining multi-dimensional data such as a pore structure, mineral composition, organic matter characteristics, an isotope ratio and the like after standardized pretreatment of a shale sample, and performing parameter correction, weight distribution and collaborative modeling to obtain a shale sample. And quantifying the oil-gas potential index and grading. The method solves the problem that traditional single parameter evaluation is insufficient in accuracy, data are comprehensive and reliable, and key technical support is provided for shale oil and gas exploration and development and reservoir evaluation.

The invention belongs to the technical field of post quantum cryptography, and discloses a Crystal-Kyber algorithm parameter determination method, a computer readable medium and electronic equipment, and the method comprises the steps: obtaining scene features of a target scene, querying a mapping relation obtained in a Q table learning stage based on the scene features, and obtaining a parameter combination matched with the target scene. In the Q table learning stage, a parameter combination corresponding to each scene feature is trained by exploring expected long-term reward values under different parameter combinations. The dynamic decision-making capability of Q table learning is combined with the parameter characteristics of the Crystal-Kyber algorithm, and the parameter combination of the Crystal-Kyber algorithm is adaptively adjusted according to the attack intensity, hardware state, service type and other characteristics of the target scene, so that the parameter combination adaptive to the application scene can be effectively selected, and the service performance of the application scene is improved. The dynamic balance requirement of'safety-performance-resource 'in different application scenes is met, and the parameter combination determination process is objective and efficient.

The application discloses a strawberry sugar content efficient nondestructive detection method based on an intelligent algorithm, and comprises the following steps: acquiring a plurality of strawberry spectrum data and sugar content reference values, and dividing the strawberry spectrum data into a training set, a verification set and a test set; performing wavelet denoising and polynomial baseline correction on the spectrum data to obtain preprocessed data; extracting key characteristic wavelengths from the preprocessed data, and constructing an initial SVM model based on the key characteristic wavelengths; optimizing the initial SVM model by using the training set to obtain an optimized SVM model; acquiring target strawberry spectrum data, and inputting the optimized SVM model to obtain a detection result. The application realizes rapid, nondestructive and accurate detection of the sugar content of strawberries, and provides technical support for intelligent development of the strawberry industry.

The invention relates to the technical field of computer information processing, in particular to an automatic compliance detection method, device and system. The method aims at solving the problems that in the prior art, due to the fact that compliance inspection depends on manual work, efficiency is low, standards are not uniform, and massive dynamic change rules are difficult to deal with. The method comprises the following steps: firstly, constructing and dynamically updating a structured compliance rule knowledge base; then, obtaining to-be-detected target content through a data interface, and performing analysis and key information extraction on the to-be-detected target content by utilizing a natural language processing technology; then, carrying out automatic matching and logical reasoning on the extracted information and terms in a compliance rule knowledge base so as to identify potential compliance risk points; and finally, generating a structured detection report, and listing risk contents, clauses and correction suggestions in detail. According to the invention, the efficiency and coverage of compliance detection are significantly improved, the risk of artificial omission and false detection is reduced, and the detection efficiency is improved.

This invention discloses a method, system, and electronic device for constructing an air ticket sales volume prediction model, relating to the field of aviation information technology. The method includes: acquiring historical sales information for each flight during a historical sales period; using the historical ticket price, the sales stage identifier, and the historical reference ticket price as input data, and the historical ticket sales volume as a label; using the cumulative parameter of ticket demand over time, the price elasticity coefficient, and the average ticket demand as model parameters to train an initial air ticket sales volume prediction model; and iteratively optimizing the model parameters using a basic particle swarm optimization algorithm until the number of iterations is not less than a preset number, thereby generating a target air ticket sales volume prediction model. This invention can improve work efficiency and reduce labor costs.

This invention belongs to the field of remote sensing technology and discloses a method for optimizing habitat quality parameters in the InVEST model based on Remote Sensing Ecological Indices (RSEI). This invention overcomes the technical bottleneck of traditional InVEST models, which rely on manual experience to set parameters and are difficult to update dynamically over time. By constructing a multi-source remote sensing data-driven RSEI, and utilizing its statistical characteristics and spatial distribution patterns across different land use types, it achieves objective quantification and dynamic updating of four key parameters: habitat suitability, threat weight, threat attenuation distance, and habitat sensitivity. Without requiring data from ecological monitoring stations, it directly incorporates continuous changes in ecological environment quality into the InVEST parameter system, resulting in higher objectivity, temporal consistency, and spatial autocorrelation in habitat quality calculations. This provides a novel technical approach for the automated and time-series assessment of regional-scale habitat quality.

The invention provides a freight heavy truck driving parameter design method, system and device and a medium, and belongs to the technical field of intelligent driving, and the method comprises the steps: S1, classifying the operation scenes of a freight heavy truck, and collecting the driving parameter data of a driver in each operation scene; s2, preprocessing the collected driving parameter data to obtain a driving parameter sample set; and S3, analyzing the driving parameter sample set by adopting a clustering algorithm, and extracting typical driving parameters in each operation scene. Accurate matching of the driving parameters and the freight scene is achieved, and adaptability, safety and efficiency of the intelligent driving system in a complex freight environment are improved.

The invention belongs to the technical field of power distribution network leakage current detection, and particularly relates to a CNN and FiLM-based leakage current type intelligent identification method. Comprising the following steps: S1, collecting real-time operation data of a typical power supply area, obtaining leakage current waveforms and related environment characteristic parameters under different working conditions, and constructing an original leakage current sample data set; s2, a CNN-based leakage current classification model is constructed, a FiLM condition modulation module is introduced, a multi-task learning framework is used at the tail of the network, a main task is leakage current type identification, and an auxiliary task is grounding system discrimination; s3, using a weighted cross entropy loss function to alleviate a class sample imbalance problem; an OneCycleLR dynamic learning rate scheduling strategy is introduced; s4, evaluating the performance of the model on the test set, and using the accuracy and the confusion matrix as evaluation indexes; according to the method, high-precision identification of multiple types of faults such as single-phase grounding, arc type electric leakage and direct current system electric leakage is realized, different grounding systems can be adapted, and the accuracy and robustness of system diagnosis are improved.