45 results about "Adaptive assessment" patented technology

The invention belongs to the technical field of marine environment prediction, and discloses a neural network-based sea wave spectrum intelligent correction method and system. The method comprises the following steps: setting a target sea area and acquiring environmental data; performing numerical calculation on the sea wave spectrum in the target sea area through a sea wave numerical mode; a sea wave spectrum correction model comprising a numerical calculation module, an actual measurement processing module and an intelligent correction module is constructed through a deep learning method; and carrying out precision verification and adaptability evaluation on the constructed sea wave spectrum correction model. According to the model, the problem of errors caused by physical process simplification in the simulation process of a traditional method is solved. Meanwhile, the problem that an existing data assimilation method is limited by observation data is solved. According to the method, the simulation precision of the sea wave mode can be effectively improved, and the method has good sea area adaptability.

The invention relates to the technical field of tourism big data, in particular to a multi-modal tourism route personalized generation method and system based on deep learning, and the method comprises the steps: constructing and incrementally updating a tourism knowledge hypergraph, extracting hidden time sequence preference and cross-entity cooperation signals of a user through a space-time perception graph neural network, and generating an interest drift model; performing deep fusion and intention analysis on the interest drift model and a context signal sensed in real time, and decoding to generate a candidate route concept skeleton by introducing an attention competition mechanism; and carrying out multi-dimensional simulation deduction and adaptability evaluation on the candidate route concept skeleton, carrying out iterative optimization through a reinforcement learning strategy based on deduction feedback, and finally outputting a personalized tourist route with optimal robustness, so that the robust tourist route which is highly personalized and adapts to environmental changes can be generated, and the robustness of the tourist route is improved. Therefore, recommendation accuracy and user experience are improved.

The present invention relates to an adaptive assessment method and apparatus for nuclear power plant component reliability, a storage medium, and an electronic device. The method comprises the following steps: constructing a Kriging initial model; gradually updating the Kriging initial model on the basis of first-layer samples of ICE to obtain a Kriging surrogate model; gradually updating the Kriging surrogate model on the basis of last-layer samples of the ICE; after the updating of the Kriging surrogate model is completed, obtaining a current Kriging model; and on the basis of the current Kriging model, assessing the reliability of a component to be assessed. In the present invention, first-layer adaptive Kriging gradually updates and explores a failure domain on the basis of the first-layer samples of the ICE until a set stopping criterion is satisfied, and on the basis of a currently constructed Kriging model, the last-layer samples of the ICE are also updated accordingly. Thus, it is ensured that an estimated failure probability converges unbiasedly to a real failure probability, and unnecessary updating of Kriging is avoided, thereby greatly improving calculation efficiency and saving calculation costs.

The invention relates to a self-adaptive evaluation and precise learning path generation system based on a knowledge graph. The method comprises the following steps: constructing a standard knowledge graph and an error region knowledge graph; performing misunderstanding mode matching based on the learning interaction data of the students, updating the misunderstanding knowledge graph of the students, and generating a personal misunderstanding knowledge graph of the students; setting a graph conversion operation from the student personal misunderstanding knowledge graph to a standard knowledge graph, and determining a target graph conversion operation sequence through a search algorithm by taking the student personal misunderstanding knowledge graph as an initial state and taking a sub-graph corresponding to a learning target in the standard knowledge graph as a target state; the target image conversion operation sequence is a personalized learning path. The problems that cognitive errors are difficult to eradicate and learning paths are poor in adaptability can be effectively solved, and meanwhile by means of scientific cost evaluation and an intelligent search algorithm, it is ensured that the generated learning paths conform to student individual cognitive characteristics and have high efficiency and feasibility.

The invention discloses a radar system clutter background modeling and adaptive suppression method and system, and relates to the technical field of radar signal target detection. The radar system clutter background modeling and adaptive suppression method comprises the following steps of covariance matrix construction, clutter model construction, clutter adaptive suppression and adaptive suppression processing optimization. According to the method, covariance matrix stability evaluation is carried out through the constructed covariance matrix, whether covariance matrix correction is carried out is judged, then the initial clutter model is established according to the covariance matrix and the preset probability distribution model, then clutter model adaptability evaluation is carried out, whether clutter model optimization is carried out is judged, and clutter model optimization is carried out. According to the method, the radar signal is subjected to self-adaptive suppression processing, and finally the judgment result of self-adaptive suppression processing optimization is obtained based on the signal-to-noise ratio of the radar signal after self-adaptive suppression processing, so that the clutter suppression effect in the radar signal is improved, and the problem of poor clutter suppression effect in the radar signal in the prior art is solved.

The invention discloses an attention reminding algorithm for intelligent driving based on multiple modes, and relates to the technical field of intelligent driving and active safety, and the algorithm comprises the steps: firstly, collecting data in real time through a multi-mode sensor group, carrying out the alignment, and then calculating the quantization features, such as the fixation deviation degree, the steering wheel disturbance entropy and the heart rate variability; then, mapping scores by adopting an S-type function, analyzing a historical sequence by utilizing a long short-term memory network to generate a dynamic weight, and performing adjustment and weighted calculation on a single-mode score in combination with an environment complexity weight to obtain a comprehensive attention score; and finally, according to the continuous driving duration, calculating a linear decreasing dynamic reminding threshold value, executing dual logic judgment in combination with the environmental risk level, and triggering graded feedback through sound and light or vibration. According to the method, the problems of poor adaptability and high false alarm rate of traditional single-mode monitoring in a dynamic environment are effectively solved, the robustness of the system is improved, and adaptive evaluation and accurate early warning of driver distraction behaviors in a complex scene are realized.

This application relates to an interview assessment method, apparatus, computer device, storage medium, and program product based on a large language model. It obtains initial interview content for a target subject, then uses a large language model to perform completeness assessment, credibility assessment, ability internalization assessment, and preliminary ability assessment. Based on the preliminary ability assessment results, it conducts personalized follow-up questions to obtain the target interview content. Finally, it uses the large language model to perform a comprehensive ability assessment to determine the overall ability assessment result for the target subject. Through multi-dimensional and multi-level analysis, it improves the accuracy and objectivity of interview assessment; by utilizing the semantic understanding capabilities of the large language model, it achieves intelligent follow-up questioning and adaptive assessment, improving the intelligence level of interview assessment. This not only significantly reduces manual costs but also improves the efficiency of interview assessment. It achieves intelligent, standardized, and highly efficient interview assessment.

A machine learning system and a machine learning method capable of selecting a pretrained model to be used in transfer learning in a short time without actually executing the transfer learning includes a pretrained model acquisition unit which acquires a pretrained model from a pretrained model storage unit storing a plurality of pretrained models obtained by learning a transfer source task under respective conditions; a transfer learning dataset storage unit configured to store dataset related to a transfer target task; a pretrained model adaptability evaluation unit configured to evaluate adaptability of each pretrained model acquired by the pretrained model acquisition unit to the dataset related to the transfer target task; and a transfer learning unit configured to execute, based on an evaluation result of the pretrained model adaptability evaluation unit, transfer learning using a selected pretrained model and the dataset, and outputs a learning result as a trained model.

The invention discloses a power distribution network and virtual power plant interaction evaluation method fusing an entropy evaluation method and an LSTM, and the method comprises the steps: constructing a multi-dimensional evaluation index system based on a hierarchical structure; the hierarchical structure comprises a target layer, a performance layer, an element layer and an index layer; the index layer is composed of evaluation indexes representing all elements; generating an initial weight of the evaluation index based on an improved entropy method; according to the improved entropy method, an interval decision matrix is formed based on probability distribution of analysis interval values to capture uncertainty of the evaluation indexes; optimizing the initial weight of the evaluation index based on an LSTM network to obtain an optimized weight; and based on the optimized weight and the corresponding evaluation index, interactive evaluation of the power distribution network and the virtual power plant is carried out. According to the method, the LSTM network and the entropy evaluation method are fused, and accurate and adaptive evaluation of power distribution network-virtual power plant interaction is realized through a multi-dimensional index system and dynamic weight optimization.

The invention provides an adaptability assessment method and device based on a multi-modal environment. The method comprises the steps of collecting multi-modal information of a to-be-assessed object in a specific scene; the multi-modal information comprises any two or more of image information, voice information, physiological information, related text information and behavior sequence information; performing time synchronization alignment on the multi-modal information; and inputting the synchronously aligned multi-modal information into a pre-trained adaptability evaluation model based on a multi-modal neural network to obtain an evaluation result of the to-be-evaluated object. By using the scheme of the invention, the adaptability of individuals in a specific environment can be accurately evaluated. Moreover, the adaptability evaluation model can be flexibly adjusted according to different application scenarios, so that the multi-modal data under different application scenarios can be adaptively processed, and a reliable technical means is provided for individual habit adaptability evaluation.

The application belongs to the technical field of marine environment prediction, and discloses a sea wave spectrum intelligent correction method and system based on a neural network. The method comprises the following steps: target sea area setting and environment data acquisition; numerical calculation of the sea wave spectrum in the target sea area is performed through a sea wave numerical model; a sea wave spectrum correction model comprising a numerical calculation module, a measured data processing module and an intelligent correction module is constructed through a deep learning method; and the constructed sea wave spectrum correction model is subjected to precision verification and adaptability evaluation. The model solves the error problem caused by the simplification of the physical process in the simulation process of the traditional method, and at the same time, gets rid of the problem that the existing data assimilation method is limited by the observation data. The application can effectively improve the simulation precision of the sea wave model, and has good sea area adaptability.

The application relates to an endoscope operation evaluation system. The system comprises a data acquisition module, a data analysis module and an operation evaluation module; the data acquisition module is used for synchronously collecting target data during the execution of a target operation task by an operator, so as to obtain target data of the entire operation process; the target data comprises image data and motion sensing data of an instrument; the data analysis module is used for constructing a time sequence data feature sequence of the entire operation process based on the received target data of the entire operation process, and analyzing the constructed time sequence data feature sequence to determine target data corresponding to each operation stage in the entire operation process; and the operation evaluation module is used for determining an endoscope operation evaluation result of the entire operation process based on the target data corresponding to each operation stage. The system solves the problem that the existing endoscope operation evaluation system cannot adaptively evaluate different operation stages and the evaluation result is inaccurate.

The invention discloses a complex environment adaptability assessment method based on a digital-real collaborative test, and belongs to the technical field of complex environment adaptability assessment of equipment test identification. Comprising the following steps: collecting complex environment data and physical data of an evaluated object to construct and generate a digital twinborn model of the evaluated object in a complex environment, and performing digital model verification on the digital twinborn model to obtain a target model; establishing interactive connection between the target model and an actual physical system, and monitoring interactive data in real time to realize data-real collaboration; if the difference between the interactive data of the two is greater than a preset difference threshold value, correcting the target model through the generated data of the actual physical system until a preset condition is completed, and generating a corrected model; and simulating simulation working conditions of the evaluated object in different complex environments through the correction model, evaluating the complex environment adaptability of the evaluated object based on the simulation working conditions, and generating an evaluation report.

The invention relates to the technical field of assessment model construction, in particular to a self-adaptive assessment model construction method and device based on machine learning, equipment and a computer storage medium. According to the method, a data-feature-model-feedback machine learning driven closed-loop system is constructed, firstly, real-time cleaning and feature extraction of multi-source heterogeneous data are achieved through stream processing and machine learning, and a high-quality and efficient data foundation is laid; based on the feature set and the real-time environment data, differential assessment indexes and weight thresholds are dynamically optimized through clustering classification and reinforcement learning, so that assessment is accurately matched with dynamic requirements of a power grid; further, by means of a graph neural network and a time sequence prediction model, conduction modeling and advanced early warning of supply chain risks are achieved, and risk response is promoted to be converted into active from passive; and finally, through incremental learning and lightweight deployment, the continuous self-optimization and real-time reasoning capability of the model is ensured.

The application provides a multi-dimensional cognitive state vector simulation agent digital textbook dynamic adaptability evaluation method, and relates to the technical field of artificial intelligence assisted education. The method comprises the following steps: extracting teaching entities and semantic relationships between the entities in a source file of a digital textbook to be evaluated through a multi-modal analysis model, and constructing a knowledge graph; initializing multiple groups of virtual learning agents based on a pre-trained large language model, and configuring differentiated cognitive state vectors for each group of virtual learning agents; driving each group of virtual learning agents to traverse the teaching knowledge graph according to a topological sorting by using a knowledge boundary mask mechanism, obtaining understanding feedback of each node by each group of virtual learning agents, and generating confusion degrees and thought chains in the understanding feedback process; calculating a cognitive block index and an adaptability distribution curve of the source file of the digital textbook by using a weighted summation algorithm, and generating an evaluation report. The application simulates human cognitive processes by using a large language model agent, and evaluates the quality and adaptability of a digital textbook.

The invention relates to the technical field of project security risk assessment, in particular to a project security risk adaptive assessment method based on big data screening, comprising the following steps: S1, acquiring multi-source public security data, accessing a global data source based on a preset rule, completing format conversion, dynamic verification and standardization processing, and outputting standardized data; s2, performing feature extraction on the standardized data, and outputting a project risk feature vector; and S3, constructing a risk assessment model based on the risk feature vector, dynamically adjusting parameters, and adaptively updating the model when the data drifts or the prediction error exceeds the limit. By introducing an automatic incorporation mechanism of data drift detection, incremental learning and emerging risk factors, the model can perceive data distribution change, risk mode upgrade and scene difference in real time, and automatically adjust parameters, supplement features or switch model versions without manual intervention. And the accuracy and stability of risk assessment in a public safety project are ensured.

This invention provides a progressive stress resilience assessment system based on a large-scale intelligent agent; it primarily addresses the problems of limited interaction methods and lack of dynamic adaptability in existing psychological state assessments. The system employs a digital human interactive agent, an emotion perception and scoring agent, an emotion guidance and planning agent, an empathy expression generation agent, and a scale scoring agent. The emotion perception and scoring agent calculates negative emotion scores based on questions and answers. The emotion guidance and planning agent generates the next question based on semantic understanding and score feedback, achieving an adaptive assessment path. The empathy expression generation agent generates system responses with emotional connection and guidance based on multiple inputs from the current question, user answers, and the next question. The digital human interactive agent presents outputs via voice and facial expressions, achieving natural interaction. The scale scoring agent manages and scores the scale items for the ruminative thinking and stress resilience stages, ultimately obtaining the stress resilience assessment result.

The invention belongs to the field of power distribution network line loss, and provides a power distribution network line energy conservation and loss reduction optimization method and system, and the method comprises the steps: obtaining line operation data and distribution transformer operation data of a regional power distribution network under multiple voltage levels, and carrying out the fusion processing; identifying and repairing the fused data by using an abnormal data identification model; performing multi-dimensional analysis on the basis of the repaired data in combination with a pre-established simulation system, and determining influence factors; and determining an optimization scheme from the optimization scheme sample case library based on the influence factors. According to the method, the accuracy of line loss reduction adaptability evaluation is improved by identifying and repairing abnormal data, and influence factors and an optimal scheme are determined more accurately and quickly through multi-dimensional analysis of a simulation system.

The invention relates to the technical field of automatic driving, in particular to an automatic driving decision-making method based on surrounding vehicle prediction and risk self-adaptive assessment, which comprises the following steps of: firstly, generating a candidate track in a Frenet coordinate system based on a high-precision map and a self-vehicle state, and then applying regularization constraint of speed and acceleration change rate to the predicted track so as to obtain a risk self-adaptive assessment result; the problems that planning and prediction are separated, and the predicted trajectory is discontinuous and unsmooth are solved by taking the planned trajectory of the self-driving vehicle as the input of a predictor (predicting the future trajectory of the surrounding vehicle), so that the safety and the performability of the driving trajectory of the self-driving vehicle are improved. The risk propagation of time discount is further introduced to aggregate single-step hazards, weight self-adaption (high-risk amplification of a safety item and low-risk maintenance of comfort) is implemented on a cost function according to an overall risk, and the risk sensitivity and time sequence stability of candidate trajectory scoring are improved from the source.

The invention relates to the technical field of electric power systems, in particular to an electric power system planning scheme decision-making method based on feasibility and economy deduction, and the method comprises the steps: constructing a decision-making deduction-oriented electric power system operation simulation model, and constructing multi-dimensional boundary conditions based on multi-dimensional influence factors; the multi-dimensional influence factors comprise at least two of load, new energy market and cost; based on the multi-dimensional boundary condition and the power system operation simulation model, operation simulation and adaptability evaluation are performed on the planning scheme for several times, so that the optimal decision of the planning scheme is realized. According to the method, the adaptability evaluation of the planning scheme under the future uncertainty change can be realized, so that the effective deduction decision of the planning scheme is realized, and the safe power supply and the high-quality development of service new energy are ensured.

A system is provided which may include (a) a knowledge database with required knowledge data associated with one or more goals of a user, (b) a skill database including required skill data associated with the one or more goals, (c) an AI bot module configured to generate first user environmental data, first user knowledge data; and first user skill data, (d) an environmental assessment module configured to match the first user environmental data to a current goal, (e) a knowledge assessment module, configure to obtain required knowledge data from the knowledge database based on the current goal and generate a first knowledge assessment as an output, (f) a skill assessment module, configured to select first required skill data from the skill database based on the current goal and generate a first skill assessment, and (g) an awarding module, configured to generate an award associated with the current goal

The invention relates to the technical field of computers, in particular to a resume screening method, system and equipment based on a large model, which can efficiently and accurately provide resumes meeting position requirements. The large model-based resume screening method comprises the following steps: extracting keywords including at least one of names, phone numbers, email addresses, education backgrounds, professional skills and working experience, and integrating the extracted keyword information into a structured data table; performing full text analysis, including identifying a plurality of entities related to keywords and relationships among the entities, performing semantic understanding on the content of the resume and extracting semantic features, analyzing the overall subject of the resume through subject modeling, and identifying professional skill information; integrating a full-text analysis result into a structured data table; the risk analysis comprises at least one of false information detection, contradictory information detection, industry adaptability evaluation and occupational stability evaluation; an overall evaluation is generated, including evaluation scores based on weights of multiple factors related to the position, and advantages and disadvantages.

The invention discloses a computer target detection data set quality evaluation method, and aims to solve the problems of complex evaluation dimension, insufficient tool support and poor application scene adaptability in the prior art. The evaluation method comprises the following steps: (1) constructing a hierarchical structure of an evaluation index system; (2) evaluation indexes; (3) constructing a judgment matrix; (4) calculating a priority weight; (5) checking and adjusting the consistency; (6) global weight calculation; and (7) calculating a weighted total score. The system comprises an evaluator module, an image processing module, an annotation processing module, an evaluation index algorithm module, a report generation module and an analytic hierarchy process module. According to the invention, comprehensive analysis of the data set quality is realized; the workload and error of manual evaluation are obviously reduced; high-adaptability evaluation is realized; the scientificity and reliability of evaluation are effectively improved; and high-quality data guarantee is provided for development of a target detection algorithm.

The application provides a network-constructing inverter power grid adaptability evaluation management method and system, the method comprises the following steps: obtaining historical operation data of the inverter when the inverter operates in the power grid, and filtering the historical operation data; determining the operation problem corresponding to the abnormal operation of the inverter, obtaining test items and test backgrounds corresponding to the test items; functionally debugging the test equipment based on the test items and the corresponding test backgrounds; testing the target inverter through the test equipment; obtaining power grid information needing to apply the target inverter, matching the test items according to the power grid information, and taking the test background corresponding to the test items as the power grid background; and adaptively evaluating the target inverter based on the power grid background and the test data, and obtaining an adaptability evaluation result. The application can guarantee the normal operation of the inverter, provide a powerful guarantee for the stable operation of the new energy power generation system, and meet the application requirements under different power grid conditions.

The invention discloses a wireless vibration sensor battery life self-adaptive evaluation method and system, and belongs to the technical field of wireless vibration sensor battery predictive maintenance. In order to solve the technical problem that the battery residual life of a sensor in different working modes and wide-temperature-zone environments cannot be accurately evaluated due to dependence on voltage monitoring in the prior art, the invention provides a solution integrating accurate metering, mechanism modeling and intelligent learning. According to the method, the actual power consumption of the battery is directly and accurately metered through the coulombmeter module, and a traditional voltage monitoring mode is replaced; a dynamic power consumption model for deeply associating sensor configuration information with environment temperature is constructed, and dynamic correction of power consumption evaluation is realized; and a three-dimensional self-learning mechanism of transverse cluster comparison, longitudinal time sequence iteration and working condition closed-loop verification is designed, so that the system can be self-adaptive to battery aging and hardware drift for a long time. Finally, in combination with future temperature prediction, the high-precision remaining working time of the battery is output.

The invention provides a dynamic evaluation method, medium and system for an answer effect under an AI platform, and belongs to the technical field of AI answer effect evaluation.The dynamic evaluation method comprises the steps that a multi-dimensional dynamic scoring system is established, differential weight distribution is set, a context awareness evaluation model is constructed by adopting a sliding window mechanism and a Transform architecture, and an evaluation result is obtained. A graph neural network and a bipartite graph matching algorithm are used to optimize correlation calculation, a StyleGAN generative adversarial network and a focus loss function are used to implement sample balance optimization, an online learning mechanism is deployed to execute model parameter fine tuning and batch training, and an abnormal behavior filtering module is constructed to identify and filter abnormal operations. And establishing a scene-based dynamic adjustment strategy to realize personalized evaluation, integrating multi-dimensional evaluation results and adjusting attention mechanism weight distribution by a fusion function, and finally realizing dynamic adaptability evaluation and personalized accurate matching of the AI platform answer quality.

The invention discloses a satellite physical information neural network training method adopting asymmetric comparative learning, and the method comprises the steps: firstly preparing a sample set containing satellite geometry, power, environment parameters and corresponding physical field quantities, and building an adaptive deep learning network; after physical constraints and performance targets are determined through problem analysis, an input-output dimension matrix and a scaling constraint equation are constructed, and a physically consistent augmented sample is generated; an asymmetric consistency loss mechanism is introduced into the PINN framework, and stable and rapid convergence of the model is realized through teacher-student sample directional constraint; and finally, based on the trained high-precision differentiable prediction network, satellite multi-working-condition automatic design optimization is carried out. According to the method, the generalization ability of the model is enhanced through dimension conduction correction, so that the out-of-distribution working condition prediction error is reduced by about one order of magnitude; the number of model training iteration steps is reduced by means of asymmetric loss, rapid iteration and on-orbit adaptability evaluation of a satellite design scheme are effectively supported, and an efficient technical approach is provided for intelligent design of a spacecraft under multi-physics field constraint.

The application discloses a virtual reality scene three-dimensional reconstruction method and system based on multi-source data fusion, relates to the technical field of underground commercial integration space scene three-dimensional reconstruction, and constructs a multidimensional data set through the synchronous collection of point clouds, images, poses, positions and semantic text information, adopts a three-dimensional convolutional neural network to establish an AI reconstruction fusion model, and realizes three-dimensional model generation; the system respectively calculates a structure integrity evaluation coefficient JGPG, a fusion consistency evaluation coefficient RHPG and a VR interaction adaptability evaluation coefficient VRJH, compares the coefficients with corresponding threshold values, triggers an optimization strategy, finally completes model adaptability optimization and encapsulation output, and improves the restoration degree and interaction performance of the virtual reality scene.

The invention discloses an investment decision risk assessment method and system based on multi-modal behavior perception, and the method comprises the steps: carrying out the feature extraction and dynamic weight fusion of data, recognizing the current risk state of an investor, and constructing a self-adaptive risk assessment mechanism through a reinforcement learning algorithm. Risk assessment parameters are dynamically optimized according to historical feedback of investors and market environment changes, and a personalized risk bearing capacity model is constructed; the system comprises a multi-modal data acquisition module, an intelligent sensing processing module and a self-adaptive evaluation module. According to the method, physiological signals, behavior patterns and environmental data are collected and fused, a time sequence attention mechanism is adopted to perform multi-modal feature fusion, a decision ability assessment model is established in combination with a cognitive load theory, risk assessment parameter adaptive optimization is realized by using reinforcement learning, the risk state of an investor is identified in real time, and personalized investment suggestions are provided. The problems that a traditional investment decision support system is single in data dimension and insufficient in evaluation staticization and individuation are solved.

This invention discloses a groundwater resource assessment method based on river-groundwater conversion relationships, belonging to the field of water resources technology. It retrieves raw hydrological data from a watershed hydrological database, generates groundwater sensitivity levels and raw hydrological feature fingerprints, and writes them into a storage ledger. Based on activity levels, an adaptive model generalization strategy is executed, storing the generalized groundwater model parameter set and generating a model storage fingerprint. This fingerprint is then associated with the raw hydrological feature fingerprint at the field level to generate a model credential fingerprint, which is written into the ledger. After verifying permissions, differentiated model calculations are performed, generating a response package fingerprint and updating the process stage. Post-verification is triggered, recalculating structural feature values ​​and verifying the rationality of parameter perturbations, generating a verification report fingerprint, and writing it into the ledger. This achieves a hierarchical adaptive assessment driven by river-groundwater conversion relationships. Through multi-level fingerprint association and distributed storage, the reliability, security, and computational efficiency of the assessment process are significantly improved.