1008 results about "Qualitative analysis" patented technology

Disclosed in the present invention are a danger test case generation method for a visual perception algorithm, and a related device. The method comprises: acquiring images captured by a visual sensor of a self-driving vehicle, cleaning and marking the collected images, and obtaining an observation data set according to no-reference image quality evaluation features; according to the observation data set and by means of performing fusion with domain knowledge, constructing a causal structure diagram that indicates the influence of environmental factors on perception performance; separating key environmental factors from the causal structure diagram, and quantitatively calculating the degree of influence of each environmental factor on visual perception performance; and on the basis of qualitative analysis of a causal relationship between a key environment variable and the visual perception performance, and quantitative estimation of a causal effect, proposing a challenge index, so as to generate, in batches, danger test cases for perception. The present invention has significant advantages in multiple aspects such as causal relationship mining, challenge index measurement, dangerous-scenario recognition and search space modeling, such that the performance of a visual algorithm for self-driving in a complex environment is evaluated and verified more accurately.

The present application relates to a carbon stock monitoring technique, and specifically relates to an evaluation method and system for the carbon sink effect of a coastal wetland. The evaluation method comprises: acquiring a remote sensing image set, within a preset time period, of a coastal wetland to be subjected to evaluation; respectively identifying evolution data of different types of coastal wetlands in the remote sensing image set, wherein the evolution data comprises conversion data between different types of wetlands, and net change data, other than the conversion data, of each type of coastal wetland; and on the basis of the conversion data and the net change data, evaluating the carbon sink effect of the coastal wetland to be subjected to evaluation, so as to obtain a carbon sink effect evaluation result. In addition to performing qualitative analysis on a mature wetland area in the prior art, the present application further takes into comprehensive consideration factors which represent a carbon sink effect, such as evolution data and evolution types before and after the evolution of a coastal wetland to be subjected to evaluation, so as to comprehensively perform carbon sink effect evaluation on said coastal wetland, thereby more accurately obtaining the carbon sink effect of said coastal wetland.

The invention relates to the field of landfill methane emission remote sensing monitoring, and discloses a landfill methane emission flux measuring and calculating method and device and a medium, and the method comprises the following steps: based on regional satellite TROPOMI observation data, carrying out qualitative analysis on annual average methane emission signals of a landfill, and determining a target landfill according to a qualitative analysis result; based on data of a satellite-borne hyperspectral imager, the methane emission flux of the target landfill is quantitatively measured and calculated, and the position of a methane emission hot spot area in the target landfill is determined; and positioning the position of an emission source in the target landfill through an active methane laser detection lens carried by an unmanned aerial vehicle platform, and independently calculating the methane emission flux of the target landfill by adopting an upper and lower section method. Based on the method, the annual average methane emission condition of the landfill can be rapidly and accurately evaluated, the methane emission flux of the whole landfill is obtained, and the internal emission hot spot area of the landfill is positioned.

The invention relates to a pier damage early warning analysis method under the action of flood, and solves the technical problems of high disaster recognition cost, low bridge damage recognition precision, untimely early warning and alarming and the like based on monitoring equipment in the existing concrete bridge flood-disaster-resistant technology. According to the method, by means of an established plastic damage simulation model, expensive sensors do not need to be arranged on a bridge structure, only basic information of the bridge structure and flood information such as the flow speed, the water level and the scouring depth are obtained, and damage and failure analysis of the bridge pier structure under the action of different influence factors by the flood action can be studied; structural damage state qualitative analysis and modal integrity damage index quantitative analysis are combined to determine bridge pier structure damage grades and damage failure judgment criteria, and early warning values corresponding to different damage grades of a bridge pier are inverted, so that accurate damage identification and rapid grading early warning of the bridge pier structure under the flood effect are realized. The flood disaster resistance of the bridge structure is improved, safe operation of the bridge is guaranteed, and the service life of the bridge is prolonged.

The invention provides a dynamic iterative long video understanding method based on a large language model. The method comprises the following steps: step 1, carrying out mathematical modeling and analysis on a video understanding task; 2, preprocessing a video input by a user, and performing preliminary reasoning through a question and answer Agent; 3, self-supervised information feedback is carried out, and an evaluation Agent is introduced in each step in the reasoning process to recognize answers; 4, quantitative analysis is carried out by adopting the question and answer accuracy and the average retrieval frame number as evaluation indexes, and the effectiveness of the method is verified; any video and question provided by the user are adopted for qualitative analysis, and whether the result meets the expectation or not is verified. According to the method, intelligent analysis and reasoning of video contents are realized by simulating a dynamic optimization process of a human logical thinking chain. The method is widely applied to the fields of video intelligent analysis, video question-answering systems, video content recommendation and the like, and is beneficial to promoting the technical development of rapid understanding and accurate reasoning of long videos.

The invention discloses a water quality change trend online identification and early warning method, system and device and a storage medium. The method comprises the following steps: acquiring historical water quality data and identifying periodic and seasonal fluctuations of the historical water quality data; constructing an off-line model group, performing trend identification, and outputting a trend identification result; performing normalization processing analysis on the trend identification result to obtain a trend analysis result, comparing the trend analysis result with a trend reference result, and optimizing the surface water quality trend identification offline model group; acquiring real-time water quality data and identifying periodic and seasonal fluctuations of the real-time water quality data; carrying out qualitative analysis on the water quality change trend; performing quantitative analysis on the water quality change trend by using the optimized offline model group to obtain a trend change index of each model; according to each model trend change index, calculating to obtain a comprehensive water quality change index; and quantifying the water quality change trend grade and generating corresponding early warning information. The real-time performance, the accuracy and the stability of water quality trend identification can be remarkably improved.

A system and method for automated qualitative analysis of computerized conversational agent (CCA) conversational data. In an embodiment, the system comprises a system configuration manager for establishing CCA characteristics and factors to be included in analyses, a data ingestion engine for ingesting conversations from a CCA, a conversation indicator extractor for identifying and classifying key aspects of conversations, a fallback analyzer for identifying the type and frequency of CCA failures, a topic modeling engine for identifying trends in conversations, and a CCA score generator for generating score assessments for qualitative aspects of the CCA's performance.

The invention relates to a hydrogen energy system risk factor identification and accident severity prediction method fusing XGBoost-SHAP and LSTM, and belongs to the technical field of hydrogen energy safety. The method comprises the following steps: marking a plurality of hydrogen energy accident cause factors and hydrogen energy accident consequence grades of a hydrogen energy accident report data set; an XGBoost algorithm is adopted to construct a risk factor importance evaluation model, and a core risk factor is obtained in combination with an SHAP interpretability analysis method; an LSTM hydrogen energy accident risk severity prediction model is established, and rolling prediction of a hydrogen energy system risk level is realized according to core risk factor time sequence data; and judging whether the predicted risk level of the hydrogen energy system exceeds a threshold value or not, and if so, triggering graded early warning and outputting a key cause factor interpretation report. According to the method, the subjective deviation of traditional qualitative analysis is remarkably reduced, the capability of capturing the risk factor time sequence dependency relationship is enhanced, and technical support is provided for real-time risk early warning.

The invention discloses a method for increasing the phenol yield through catalytic pyrolysis of a decommissioned fan blade, and relates to the technical field of waste composite material resourceful treatment.The method comprises the steps that decommissioned fan blade fragment materials obtained after crushing and magnetic separation are subjected to multispectral imaging, multispectral data are obtained, and pretreatment is conducted; performing spectral feature extraction on the preprocessed multispectral data by using a convolutional neural network; identifying and separating the fragment materials based on spectral characteristics and automatic separation equipment; carrying out activation and carbonization treatment on the separated balsa wood fragments to prepare a carbon-based catalyst; carrying out catalytic pyrolysis on the separated fragment material by utilizing an automatic adjusting reactor and a carbon-based catalyst; collecting a product generated by catalytic pyrolysis, and carrying out qualitative and quantitative analysis on phenols to obtain a qualitative analysis result and a quantitative analysis result. According to the method, through a mode of combining multispectral imaging and the convolutional neural network, different types of composite materials are accurately identified and classified.

The invention provides a method for simultaneously detecting various micro-plastics in water, and belongs to the technical field of micro-plastic detection. The method comprises the steps of sample pretreatment, thermal cracking-gas chromatography-mass spectrometer measurement, qualitative analysis and quantitative analysis. The method comprises the following steps: taking a water sample, uniformly shaking, filtering with a filter membrane, taking the filtered filter membrane, adding acetone, carrying out ultrasonic elution, washing the filter membrane, and collecting an eluent; adding acetone into the eluted filter membrane, carrying out ultrasonic elution again, washing the filter membrane, collecting the eluent, combining the two eluents, heating and concentrating in a water bath, adding acetone, ultrasonically mixing, transferring into a cracking cup, heating and volatilizing, and determining by a thermal cracking-gas chromatography-mass spectrometer. Carrying out qualitative analysis through analysis of cracking products with different types of micro-plastic characteristics, and then carrying out quantification through an external standard method; the method provided by the invention can accurately quantify the six microplastics in the effluent, and has the advantages of simple pretreatment, small sampling amount, high accuracy and lowest detection limit of 0.012 [mu] g / L.

The invention discloses a quantitative analysis method for an artificial rain and snow enhancement effect based on fine calculation of an influence zone, which comprises the following steps: acquiring the influence zone in an artificial spreading catalyst diffusion zone according to artificial ice crystal concentration or silver iodide concentration; carrying out extraction and qualitative analysis on the radar products in the influence area; performing space-time matching on the influence area and the radar product, and calculating a mean value and distribution of radar parameters in the influence area; performing spatial distribution and time sequence change analysis on the radar parameters, and calculating parameter change and change rate of the radar product in the influence area; and quantitatively analyzing the parameter change and the change rate, and giving a rainfall enhancement operation effect. The method not only can improve the precision of quantitative analysis of the artificial rain and snow enhancement effect based on fine calculation of the influence area, but also has good interpretability, and can be directly applied to a quantitative analysis system of the artificial rain and snow enhancement effect.

The invention relates to a driver takeover performance regulation and control method based on a trust state, and belongs to the technical field of intelligent driving. The method comprises the steps that S1, takeover performance classification is carried out, S11, qualitative analysis is carried out on takeover data, specifically, the performance of a driver in the takeover process is evaluated from the four indexes of takeover time, minimum collision time, collision probability and braking application; s12, determining the takeover performance of the driver, specifically, calculating the performance score of each takeover link by adopting a grey relational degree calculation method and taking the four indexes as input; and S2: takeover performance prediction: on the basis of real-time trust measurement, effectively predicting the takeover performance of the driver under different trust and physiological levels by using a machine learning algorithm. According to the invention, the takeover performance can be accurately predicted for timely performance regulation and control so as to obtain the optimal takeover performance.

The invention discloses a partial discharge detection method and device, electronic equipment and a computer program product. The method comprises the steps that a to-be-detected image of the power transmission line is acquired, and the to-be-detected image at least comprises a visible light image, an ultraviolet image and an infrared image of the same part of the power transmission line; performing partial discharge qualitative analysis on the power transmission line by using the visible light image to obtain a partial discharge qualitative analysis result; performing partial discharge quantitative analysis on the power transmission line by using the ultraviolet image and the infrared image to obtain a partial discharge qualitative analysis result; the visible light image, the ultraviolet image and the infrared image are subjected to feature point matching, a target image is obtained, and the target image is used for displaying a discharge part determined according to the partial discharge qualitative analysis result and the discharge degree determined according to the partial discharge qualitative analysis result. According to the invention, the technical problem of low accuracy of anomaly detection is solved.

The invention relates to a method for evaluating the cyclic adsorption performance of a carbon dioxide adsorbent, which comprises the following steps: S1, performing multiple adsorption and desorption tests on a to-be-tested adsorbent after impurity removal treatment in a thermogravimetric analyzer to obtain a thermogravimetric cycle curve; s2, parameters E1, F1, Hi and Ii are obtained according to the thermogravimetric cycle curve and a formula; s3, obtaining a first fitting curve and a second fitting curve; s4, evaluating the performance of the adsorbent to be tested according to one or more of E1, Ei, H2, I2, F1, Fi, the first fitting curve function and the second fitting curve function. By adopting the method, a relatively standard evaluation method for evaluating the performance of the adsorbent based on the thermogravimetric analysis test can be established, a plurality of adsorbents can be qualitatively analyzed by selecting proper parameters according to actual use conditions, proper adsorbents are selected by comparing qualitative analysis results, and the method is wide in use range and high in applicability.

The invention discloses a pre-oxidation furnace temperature real-time control system and method based on data processing, and relates to the field of pre-oxidation furnace temperature control, and the pre-oxidation furnace temperature real-time control system based on data processing comprises a data feature acquisition module, a data analysis module, an optimal temperature prediction module and a temperature real-time control module. According to the method, the analysis precision of temperature, transmission speed and tension data is improved, a more reliable temperature change trend and a more reliable stability analysis result are obtained, and a random forest regression model is trained by collecting historical data including a transmission speed stability analysis result, a tension stability analysis result and a corresponding temperature adjustment value and utilizing the data, so that the accuracy of the temperature change trend is improved. The complex interaction between the features is better captured, so that the prediction precision is improved; the temperature set value is dynamically adjusted according to the temperature change trend and quantitative transmission speed and tension stability analysis results, and transmission speed stability and tension stability changes can be responded.

The present invention discloses a two-stage transient stability prediction method based on an improved convolutional residual memory network and a gated cyclic unit, comprising: in the first stage, the underlying measurement data required for modeling and simulation is obtained, and a transient stability prediction model based on the improved convolutional residual memory network is established for qualitative and quantitative analysis; in the second stage, the underlying measurement data required for modeling and simulation is obtained, and a generator power angle trajectory prediction model based on a gated cyclic unit is established, and the unstable samples in the qualitative analysis and the samples of the confidence interval with a certain confidence level in the quantitative analysis are predicted for the power angle trajectory, and the final transient stability prediction result is determined by comprehensively judging the results of the qualitative analysis, the quantitative analysis and the power angle trajectory prediction. The present invention can improve the accuracy of transient stability prediction, and at the same time, improve the reliability of transient stability prediction without losing the response speed.

The invention belongs to the technical field of medical informatization, and particularly relates to a medical insurance medication rationality interception system and method based on deep reinforcement learning and an FP-Growth algorithm, and the method comprises the following steps: S1, receiving electronic prescription data transmitted by a hospital HIS system in real time; s2, according to original diagnosis information in the prescription, performing standardization processing to obtain a diagnosis set; according to the original medicine information in the prescription, cleaning and integrating to obtain a medicine set; s3, based on an FP-Growth association rule algorithm, performing diagnosis-drug association analysis and drug-drug association analysis on the diagnosis set and the drug set, and identifying a low-association prescription according to a preset condition and marking the low-association prescription as a suspicious prescription; s4, starting deep reinforcement learning analysis on the suspicious prescription through DRL decision optimization, and outputting a prescription reinforcement learning feature set; and S5, outputting a prescription qualitative analysis result and a corresponding confidence score according to the prescription reinforcement learning feature set.

The invention discloses an intelligent on-line monitoring method and system for oil abrasion particles of hydraulic forcible entry equipment. The method comprises an on-line monitoring method and an on-line monitoring system. According to the online monitoring method, an electrostatic, inductive and optical multi-source sensor data acquisition module, a feature engineering processing module, a multi-modal feature fusion module, an abrasive particle quantitative and qualitative analysis module and an abrasion analysis module are included, and the online monitoring system comprises the online monitoring method, a monitoring sensor installation module and an abrasion intelligent decision-making module. According to the method, quantitative monitoring and abrasion mode analysis of metal abrasive particles, non-metal abrasive particles, ferromagnetic metal abrasive particles and non-ferromagnetic metal abrasive particles in oil of the hydraulic type forcible entry equipment can be synchronously completed through multi-mode fusion monitoring, online monitoring of the abrasion particles of the hydraulic type forcible entry equipment is achieved, and an intelligent maintenance decision is given.

The invention discloses a complex production line reliability analysis method combining a fault operation and maintenance knowledge graph with a fault tree, and the method comprises the steps: constructing a multi-level production line fault operation and maintenance knowledge graph based on a production line-equipment-fault-method, inputting fault information, carrying out the fault matching query of a production line layer, constructing an available equipment sub-graph, and carrying out the fault matching query of the equipment sub-graph; a production line fault tree is constructed by analyzing the logic relation between the production line faults and the factors causing the faults, and finally qualitative analysis is conducted on the production line fault tree, the production line fault rate is quantitatively calculated, and reliability analysis of the production line is achieved. The method is simple and easy to implement, reliability analysis of a current production system can be improved from an equipment level to a whole production line level considering coupling between equipment, a mode layer is reversely standardized and verified by utilizing characteristics of the production line and fault knowledge, production management personnel are helped to understand the rule of equipment or system fault generation, and the reliability of the production system is improved. And a reasonable maintenance strategy is formulated.

The invention relates to the technical field of fault diagnosis and intelligent manufacturing, in particular to a steel wire rope defect identification and quantitative analysis method based on deep transfer learning. According to the technical scheme, the method comprises the following steps that leakage magnetic field signals LF and magnetic flux signals LMA of a steel wire rope are synchronously collected through a double-channel magnetic probe, and multi-channel data high-speed synchronous collection is conducted on the signals; and carrying out double-signal feature extraction on the LF signal and the LMA signal, wherein the extracted features comprise defect image information # imgabs0 #, a defect enclosed area # imgabs1 #, a defect wave crest number # imgabs2 #, a defect width # imgabs3 # and a defect height # imgabs4 #. Through deep transfer learning and multi-modal signal fusion, the problems that qualitative analysis is inaccurate and quantitative means are deficient in traditional steel wire rope defect detection are solved, the method has the advantages of high precision, strong generalization, high efficiency and automation, innovative technical support is provided for safe operation and intelligent operation and maintenance of industrial equipment, and the method is worthy of popularization and application. And steel wire rope defect identification and quantification are facilitated.

The invention relates to the technical field of agriculture, in particular to a Raman spectrum and deep learning-based pesticide residue detection method and electronic equipment. The method comprises the following steps: acquiring Raman spectrum data of a sample to be detected; inputting the Raman spectrum data into a pre-trained qualitative analysis model, and outputting the category probability of the pesticide components in the to-be-detected sample; inputting the Raman spectrum data into a pre-trained quantitative analysis model, and outputting the content proportion of the pesticide components in the to-be-detected sample; wherein the qualitative analysis model realizes conjoint analysis of spectral global features and local features based on a multi-modal fusion deep learning network; the quantitative analysis model realizes spectral decomposition and concentration regression based on a deep learning architecture of multi-scale feature fusion. The detection defects of an enzyme inhibition method and a chromatography method are overcome, the problem that the potential mode of the Raman spectrum cannot be accurately and stably found through machine learning is solved, and higher detection precision and higher detection speed are achieved.

The invention relates to the technical field of air route design, in particular to a ship air route optimization method and device based on AIS data, and the method comprises the following steps: extracting a ship air route network based on historical AIS data; obtaining network structure node similarity and comprehensive node similarity between the ship route intersection nodes based on the position relation between the ship route intersection nodes in the ship route network and the ship traffic flow between the ship traffic network nodes; community division is carried out on the ship route intersection nodes based on the network structure node similarity and the comprehensive node similarity between the ship route intersection nodes; and merging the movable ship route intersection node with the minimum importance degree to the nearest ship route intersection node until a set merging termination condition is met. The problems that in the prior art, subjective experience and qualitative analysis of experts and maritime affair managers are relied on, then optimization is conducted, and objective basis and scientificity are lacked can be solved.

The invention discloses a new energy equipment sequence impedance multi-level frequency domain identification method, and relates to the field of power electronic equipment parameter and model frequency domain identification. Complex vector fitting is carried out on frequency domain response data of impedance measurement, an analytical model or an equivalent zero-pole model of power electronic equipment is obtained, and a basis is provided for grid-connected resonance stability analysis and impedance remodeling; comprising the following steps: S1, carrying out sequence impedance frequency scanning of single harmonic disturbance injection to obtain impedance frequency domain response data; s2, performing complex vector fitting to obtain a pole-residue type port frequency domain model; s3, evaluating'grey / black box 'characteristics according to the transparency of the control architecture information; s4, deducing a theoretical sequence impedance model of the grey box equipment, and identifying parameters based on a pole-residue expression; deducing an equivalent zero pole model for the black box equipment or the new energy cluster; compared with traditional qualitative analysis, accurate quantitative analysis and impedance remodeling are achieved, and analysis accuracy and engineering applicability are improved.

The invention discloses a building facade model monitoring method and system based on three-dimensional scanning, and relates to the technical field of building monitoring, and the method comprises the steps: collecting the three-dimensional data of a building facade, calculating the minimum sampling spacing between points, and screening a sparse point cloud set; and constructing a point cloud feature vector based on the sparse point cloud set, and constructing a label distribution model. According to the method, the point cloud data set with the label has the characteristics of complete semantic information and high classification accuracy, a reliable data basis is provided for subsequent building facade analysis and decision making, qualitative analysis can be carried out on the crack through point cloud segmentation and crack label identification, and the accuracy of classification is improved. In addition, quantitative evaluation of the crack can be assisted through a segmentation result, subsequent maintenance and decision making are facilitated, introduction of a local detail loss function is combined with a high-curvature point characteristic optimization model, and the feature extraction capacity of the local optimization model for the crack area is remarkably enhanced.

The invention belongs to the field of automatic testing, and particularly relates to an automatic testing system and method for aviation fly-by-wire flight control equipment, and the system comprises a system self-inspection unit, a system resource unit, a system interface adaption unit, and a system testing control unit. And the system self-checking unit controls the automatic test system to execute a self-checking function through operation software. The test efficiency and the test coverage rate can be remarkably improved, the problem of function test omission can be effectively solved, the fault of the tested airborne avionics equipment is analyzed by adding the YMECA fault analysis module and combining the definition event and the structure function of the fault tree, qualitative analysis is carried out on the fault, a professional basis is provided for fault diagnosis, the maintenance difficulty is reduced, and the test efficiency is improved. The aircraft maintenance guarantee efficiency is improved, and joint test of a plurality of airborne avionics devices and parallel test of a plurality of airborne avionics devices of the same model in a fly-by-wire flight control system of a certain type of fighter can be realized.

The invention relates to the technical field of liquid chromatography, and discloses a mixed product liquid chromatography comprehensive analysis method which comprises the following steps: S1, mixing products: respectively mixing aldehyde compounds and ketone compounds with different mobile phases, and then injecting into an injection chromatographic system; s2, liquid chromatographic analysis: separating and analyzing a mixed product by using a liquid chromatograph; s3, performing qualitative analysis; on the basis of liquid chromatographic analysis, each peak in a chromatogram is identified. The method aims at qualitative and quantitative analysis of main substances (groups) in an organic reaction mixed product system; the method is suitable for analyzing the relative percentage content of products related to organic chemical reactions such as raw materials (nonylphenol) related to a core production process, nonylphenol formylation reaction, nonylphenol esterification reaction, phenolic ester Fris rearrangement reaction and the like, and samples in a refining process; the influence of absorption peaks and chromatographic line oscillation of other non-target substances on the content analysis result can be effectively avoided.

The invention discloses a commercial subject risk assessment method and system based on machine learning, and belongs to the technical field of knowledge maps. Basic features of an enterprise are obtained, a knowledge graph is constructed, and risk features are identified through graph mining; carrying out qualitative analysis and quantitative analysis on the enterprise to obtain a feature tag description; constructing a sample set, setting a misjudgment cost and a class weight based on the sample set, performing parameter tuning and verification set feedback, adjusting a decision threshold, performing binning on each feature, and obtaining a final risk score; and threshold selection and probability calibration are carried out to obtain risk grade division and decision suggestions of the enterprise, and risk label interpretation and large model auxiliary interpretation are carried out. The problems that manual collection and analysis of supervision policy documents consumes time and labor, careless omissions easily occur, and final risk judgment is prone to misalignment, misjudgment and frequent missed judgment are solved. According to the method, key rules can be accurately extracted, and hidden risk conduction links and potential risk points can be mined.

The invention provides a method for detecting nonmetallic inclusions in steel, which comprises the following steps: placing a steel material in ethanol, cleaning with an ultrasonic cleaner, and drying to obtain steel to be detected; acquiring a detection surface of the steel to be detected; according to the method, the SEM is adopted to observe the morphology of the non-metallic inclusions on the detection surface, the sizes of the non-metallic inclusions are measured and counted, and the EDS is adopted to detect the components of the non-metallic inclusions, so that accurate positioning and qualitative analysis of the non-metallic inclusions can be realized, and the accuracy of the detection result is improved.

The invention discloses a method for progressively extracting and identifying microplastics in bivalve in a deep sea methane leakage area according to sizes and levels. According to the method provided by the invention, biological tissues are subjected to freeze drying and dehydration, and micro-plastics contained in bivalve mollusks in an extreme environment are extracted in a lossless and classified manner by using a plurality of experimental steps such as a pH staged enhanced enzyme-hydrogen peroxide mixed digestion solution, hierarchical progressive vacuum suction filtration, identification according to size advantages and the like. The invention aims to realize quantitative and qualitative analysis of full-size micro-plastic in the bivalve according to size ranges. The characterization method is suitable for exploring microplastics enriched in each tissue of bivalve in a deep sea extreme ecosystem, and is matched with a captured seabed shellfish bed, so that the time history and historical accumulation of microplastics absorbed by the whole extreme ecosystem are deduced, and the problem of large-scale sampling, extraction and analysis in a deep sea extreme environment is solved; and a scientific inspection strategy is provided for the influence of the microplastic pollution history in a specific sea area.

The invention discloses a law enforcement case qualitative analysis method based on a large language model, and belongs to the technical field of law enforcement informatization. The system mainly comprises a data preprocessing module, a law article and case retrieval module, a prompt template generation module, a large language model reasoning module, a consistency checking module and a manual auditing and writing-back module. The method comprises the following steps: S1, data preprocessing; s2, retrieving law provisions and cases; s3, a prompt template is constructed; s4, large language model reasoning; s5, checking the consistency; and S6, performing manual auditing and write-back. In the step S1, sensitive information such as a natural person name, an identity card number, a contact way, a family address and the like in a case text is subjected to anonymization replacement or hash processing. The law enforcement case qualitative analysis method based on the large language model achieves the effects of improving accuracy, consistency and interpretability.