70 results about "Adaptive assessment" patented technology

The invention provides an information system engineering supervision project risk adaptive assessment method and system. According to the project management scheme, a dynamic knowledge graph is formed by constructing a data model fusing a building information model and a geographic information system. The three-dimensional coordinate track of the construction machinery is captured in real time by using an ultra wide band positioning device array, and the space occupied hot area distribution is generated by using a multipath interference suppression technology. An operation simulation environment is established based on a digital twinning technology, and a space-time risk topology network is established to early warn path conflicts and safety spacing problems. And according to network node density characteristics, dynamically adjusting a risk assessment parameter weight, and assessing an equipment collision probability and a construction process conflict index. Finally, the stress threshold value and the signal sampling frequency are adjusted according to the composite risk level result feedback, and construction management and safety guarantee are optimized. According to the technical scheme provided by the invention, the efficiency and safety of information system engineering supervision project risk adaptive assessment can be improved.

The invention discloses a mining rock mass structure degradation monitoring method and system based on deep learning, particularly relates to the technical field of mine safety monitoring, and is used for solving the problems of monitoring lag and misjudgment caused by the fact that an existing static model cannot automatically adapt to rock mass damage dynamic evolution. The method comprises the following steps: constructing a dynamic damage incremental data set by collecting multi-source heterogeneous monitoring data under mining disturbance in real time, extracting newly-added damage features, and calculating a distribution offset degree between the newly-added damage features and historical features; when the deviation degree exceeds the limit, verifying and screening a damage feature subset according with a mechanical law based on a rock constitutive equation, and blocking non-physical noise interference; a geological structure evolution mode is matched through damage path dependence modeling, and a potential damage path thermodynamic diagram is generated in combination with a space gradient; performing cross-stage association on the thermodynamic diagram and a historical feature library by adopting a knowledge distillation mechanism to generate a dynamic weight matrix fused with a mining time sequence; and finally, updating the damage assessment model through a parameter reweighting mechanism to realize adaptive assessment of the rock mass degradation risk.

The invention discloses a virtual reality scene three-dimensional reconstruction method and system based on multi-source data fusion, and relates to the technical field of underground commercial and traffic integrated space scene three-dimensional reconstruction. The system constructs a multi-dimensional data set through synchronous acquisition of point cloud, images, poses, positioning and semantic text information; a three-dimensional convolutional neural network is adopted to establish an AI reconstruction fusion model, and a three-dimensional model is generated; the system calculates a structural integrity evaluation coefficient JGPG, a fusion consistency evaluation coefficient RHPG and a VR interaction adaptability evaluation coefficient VRJH, compares the coefficients with corresponding thresholds, triggers an optimization strategy, and finally completes model adaptability optimization and packaging output, thereby improving the reduction degree and interaction performance of a virtual reality scene.

The invention discloses a power transmission image compression quality evaluation method based on multichannel fusion, belongs to the technical field of smart power grids, and solves the problem of how to enhance adaptive evaluation performance of image quality in scenes with different compression ratios. A multichannel feature processing module introduces learnable offset to realize dynamic alignment and effective fusion of multichannel features; the multi-scale attention fusion module is combined with multi-scale feature extraction and an attention mechanism, learnable position codes are introduced, and the sensitivity to local structure changes is enhanced while the global perception ability is ensured; the self-adaptive quality evaluation module captures different scale features and local information by constructing residual connection and a multi-branch structure, performs weighted fusion on multi-channel fusion features in combination with a dynamic weight generation mechanism, and realizes accurate judgment of the quality of a complex scene image under different compression levels; while the image compression distortion perception capability is improved, the adaptive evaluation performance of the image quality in scenes with different compression ratios is effectively enhanced.

The invention relates to a pile foundation reinforcement method and system based on a karst area, and belongs to the technical field of foundation treatment and reinforcement. The pile foundation reinforcement method comprises the steps that a karst area pile foundation monitoring network is established, and karst cavity distribution characteristic parameters and underground water dynamic change parameters are obtained; constructing an adaptive evaluation model, and setting an initial real-time feedback correction parameter vector; based on a spatio-temporal evolution rule, generating a karst development comprehensive complexity index of dynamic evolution; a grading response mechanism is established, and pile foundation reinforcement early warning and response measures of corresponding grades are triggered; and constructing an intelligent decision-making system, and continuously optimizing an evaluation model and a reinforcement strategy through a feedback mechanism. According to the method, the karst development comprehensive complexity index is generated by introducing the underground water dynamic change parameters and combining the karst cavity distribution characteristic parameters, the evaluation of the geological environment is expanded from a static time point to a dynamic evolution process, and the comprehensiveness and accuracy of the evaluation are improved.

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 discloses a text narrative-guided virtual reality motion sickness monitoring and relieving system, and relates to the technical field of virtual reality, the text narrative-guided virtual reality motion sickness monitoring and relieving system comprises an adaptability monitoring module, the adaptability monitoring module comprises a data acquisition unit, and the data acquisition unit is used for acquiring physiological information of a user in virtual reality training in real time; the data is transmitted to the adaptability evaluation unit; the dynamic adjustment module is used for receiving the sensing data acquired by the data acquisition unit and dynamically adjusting parameters of the virtual reality equipment according to the received data; by monitoring physiological information and perception data of a user in real time, signs of motion sickness can be rapidly recognized, the real-time monitoring is combined with dynamic adjustment of visual and vestibular stimulation in a VR environment, the risk of motion sickness caused by mismatching of sensory input and actual body movement can be effectively reduced, and the motion sickness can be rapidly recognized through the dynamic adjustment. The system can preventively adapt to individual differences of users and reduce motion sickness.

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 invention relates to the technical field of sports performance judgment, in particular to a method for judging performance validity of various complex scenes based on a large model, which comprises the following steps: S1, integrating multi-source data, collecting data from multiple fields, preprocessing the collected data, and integrating the processed data into a structured data set; s2, recording and processing environmental conditions, generating a score data set containing the environmental conditions, analyzing environmental condition data, extracting key factors influencing score evaluation, and inputting the key factors as features into the large model; s3, constructing a dynamic adaptability evaluation model; and S4, high-dimensional feature processing: extracting key features in the data by adopting a principal component analysis method, reducing the dimensionality of the features, and improving the interpretability and understandability of the model. By effectively integrating data in multiple fields, especially processing multivariable data in a complex scene, adaptability and accuracy to different data sources 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.

A sponge facility layout optimization method based on adaptability evaluation comprises the following steps: constructing a layered index system, integrating soil substrate characteristics, natural conditions and region positioning factors, and dynamically distributing index weights by using an analytic hierarchy process; quantifying the effect variation of the sponge facility improvement measures on each subitem index and grading; based on the three-dimensional mapping relation between the index current situation level and the measure effect direction, generating an adaptability scoring matrix through an expert scoring mechanism; an adaptive priority coefficient is calculated in combination with weight weighting, and quantifiable decision parameters are generated after linear standardization processing. According to the method, spatial heterogeneity response, cost-benefit collaborative optimization and multi-objective decision are creatively fused, the dependence of a traditional evaluation method on fixed indexes is broken through, and scientific grading recommendation of facility improvement measures is realized; and quantifiable and extensible technical support is provided for differentiated layout of sponge facilities in an urban complex environment and optimal configuration under resource constraints.

The invention discloses a worker personalized training and self-adaptive evaluation method and system based on an AI large model, and relates to the technical field of building construction worker training and management. Constructing a post skill library based on the knowledge graph; constructing a to-be-trained personnel post matching database based on the knowledge graph; entity pairs of the post skill library and the post matching database of the to-be-trained personnel are screened through a heuristic rule, linking is completed, the matching degree of the entity pairs is calculated through a similarity algorithm, and personalized training content is generated; designing a self-adaptive evaluation mechanism according to personalized training content, analyzing performance data through a machine learning algorithm, predicting learning ability and knowledge mastering degree, dynamically adjusting an evaluation standard, and customizing an assessment index for an operator; and training operators, collecting performance data in real time, performing evaluation according to an adaptive evaluation mechanism, and presenting an evaluation result in a multi-dimensional form. The safety management level of a construction site and the skill level of constructors are improved.

The invention provides an SAR image vegetation coverage inversion method and system based on multi-dimensional feature optimization and model optimization, a storage medium and electronic equipment, and the method comprises the following steps: carrying out the preprocessing of a Sentinel-2 image, calculating a normalized difference vegetation index (NDVI) through a wave band calculation formula, and carrying out the calculation of the NDVI; a reference vegetation coverage (FVC) of a research area is obtained by combining a pixel bipartite model (DPM), and then an optimal SAR feature combination is selected by applying an improved genetic algorithm ET-GA, using XGBoost as an adaptability evaluation function and using a root-mean-square error (RMSE) as an evaluation index. According to the method, SAR features are extracted through multiple feature decomposition methods, multi-dimensional feature optimization, intelligent algorithm optimization and a deep learning model are combined, the core problems of feature redundancy, insufficient precision, low efficiency and the like of SAR data in vegetation parameter inversion are solved, and an innovative technical scheme is provided for the field of remote sensing quantitative inversion.

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 a power system master station fault positioning method and device and a computer program product, and the method comprises the steps: S1, collecting node fault feature data of a master station control system, and carrying out the coding of the node fault feature data; s2, fusing a simulated annealing mechanism and a genetic algorithm, establishing a dynamic parameter adjustment mechanism based on adaptability evaluation according to the encoded node fault feature data, and generating an improved global search algorithm; s3, taking the minimization of the fault isolation area as a target function, constructing an optimization model containing network topology constraints, and carrying out optimal solution iterative calculation by adopting the improved global search algorithm; and S4, obtaining an optimal fault node clearing scheme, and performing isolation operation on the fault nodes. According to the invention, the precision and efficiency of power system master station fault positioning are effectively improved, the manual intervention intensity of operation and maintenance personnel is significantly reduced, and a core technical support is provided for rapid self-healing of a smart power grid.

The invention discloses a version controllable data set automatic evolution method based on a large language model, which mainly comprises a data crawling module, a data analysis module, a data annotation module and a task form processing module, and reduces the demand of manual intervention by introducing an automatic updating mechanism. Specifically, the multi-agent system can monitor version update of a third-party library in Python ecology and update a data set according to the latest library version. The automatic updating mechanism not only improves the maintenance efficiency of the data set, but also ensures the timeliness of the data set, and provides reliable technical support for the adaptability evaluation of the LLMs in a dynamic development environment.

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 embodiment of the present invention discloses a situational awareness method, apparatus, device and storage medium based on a Bayesian network. The method includes: for each microservice in the system, determining the target group attribute field according to the preset historical data corresponding to the current microservice and the data performance of the relevant attribute field, and determining at least two target group intervals corresponding to the target group attribute field; using the target group intervals corresponding to all microservices in the system as target nodes, updating the historical Bayesian network model to obtain a target Bayesian network model; and performing zero-trust situational awareness based on the target Bayesian network model. The embodiment of the present invention adopts the above-mentioned technical solution. Compared with using all the data generated by the system as the input nodes of the Bayesian network model, the number of Bayesian network model nodes can be adaptively controlled to meet the real-time adaptive assessment of user risks in zero trust under the premise of low resource consumption, thereby achieving the technical effect of realizing zero trust.

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.