1145 results about "Data dimension" patented technology

The invention relates to the field of internet attack detection, in particular to a data security event real-time monitoring method and system, and the method comprises data collection, multi-modal fusion, threat detection, causal reasoning, dynamic response and feedback optimization. Compared with the traditional security analysis which depends on isolated data dimension or simple rule association, is difficult to capture a cross-data-source complex attack mode, and is faced with the limitations of low calculation efficiency, slow link traceability, storage access bottleneck and the like in mass data association analysis, the scheme integrates multi-source heterogeneous data into a dynamic association network through graph structure modeling, so that the security analysis efficiency is improved. Hidden association and behavior patterns among users, equipment and IPs are deeply mined by utilizing a GNN framework, the suspicious degree among entities can be accurately quantified, and hidden attack chains can be identified; and meanwhile, a hybrid storage architecture and a query optimization technology are adopted, so that a security analyst can backtrack a complex attack path in a second level while breaking through the bottleneck of large-scale graph data access performance, and the threat hunting efficiency and the high-level attack traceability are remarkably improved.

The invention relates to the technical field of power equipment state monitoring, in particular to a power equipment operation state evaluation and prediction method based on big data, which comprises a multi-source data acquisition module, a feature engineering processing module, an intelligent evaluation and prediction module and a decision support output module. By setting a multi-source sensing end, when the operation state of the power equipment is evaluated, the definiteness of state evaluation of different types of equipment is ensured by formulating multi-modal data fusion standard parameters and setting different state sensing weights for different types of equipment; and meanwhile, real-time state sensing is performed by fusing electrical parameters, mechanical vibration, thermal distribution and environmental stress data, so that whether a sensing blind area problem caused by a single data dimension occurs in an equipment evaluation process or not can be detected in real time, the comprehensiveness and accuracy of equipment operation state evaluation are ensured, and state sensing fragmentation errors are further reduced.

The invention discloses an injection molding process fault diagnosis model training method and system based on a large language model and a fault diagnosis method. The model training method comprises the following steps: collecting and cleaning process parameters under the fault working condition of the injection molding machine, converting the process parameters into a natural language text, combining the natural language text with a fault label to construct a textualized data set, and dividing the textualized data set into a training set and a verification set according to a proportion; and in combination with the text data dimension and the fault category number, loading the pre-trained large language model and configuring a diagnosis model structure in a quantitative mode. And inputting the training set into a model to extract semantic features, processing the semantic features by a feature conversion module to generate a high-order feature vector, and inputting a classification head to output a fault category probability. And back propagation is carried out by using a loss function, and model parameters are efficiently and finely tuned in combination with low-rank adaptation and a layered freezing strategy. And repeating training until the performance reaches the standard, and outputting a final diagnosis model. The method is efficient in training, and can effectively reduce the maintenance and use cost of the model.

The invention relates to a spare part service life prediction method, device and equipment and a computer readable medium. The method comprises the steps of collecting multi-mode state data of a target spare part; verifying the historical consistency of the multi-modal state data; and under the condition that the historical consistency verification of the multi-modal state data is passed, inputting the multi-modal state data into a target residual life prediction model so as to predict a degradation track of the target spare part based on the multi-modal state data by using the target residual life prediction model, the target residual life prediction model is a neural network model obtained by training by taking a physics degradation mechanism of the spare part as priori knowledge; and determining the predicted remaining life of the target spare part based on the degradation trajectory. According to the method, the evaluation one-sidedness caused by insufficient single data dimension is avoided, the prediction credibility is improved through a data verification and physical mechanism constraint model, and the technical problem of low life prediction accuracy caused by spare part life counterfeiting is effectively solved.

The invention discloses a listed company operation risk early warning method based on multi-source auditing and text semantic fusion, and relates to the technical field of auditing, and the method comprises the steps: S1, crawling and converging multi-source heterogeneous data of listed company financial newspapers, auditing suggestions, supervision announcements, inquiry letters, news public opinions and market transactions; according to the method, unstructured texts are subjected to cleaning, blocking and semantic vectorization processing, each text segment is embedded into a high-dimensional semantic space, a vector index is established, a bottom-layer knowledge base of an RAG framework is formed, in the stage, it is ensured that the data structure is uniform, the source is traceable, standardized input is provided for subsequent semantic retrieval and modeling, and the reliability of the system is improved. S2, a query expression is constructed based on a target company, a time window and a risk topic, dense semantic retrieval and sparse BM25 retrieval methods are comprehensively used, a time decay and source credibility weighting mechanism is introduced, and the problems that a traditional method is single in data dimension and information is split are solved.

The invention belongs to the technical field of computer information processing, and relates to a scientific research performance information analysis and evaluation system and a processing method thereof.The scientific research performance information analysis and evaluation system comprises a data collection module, a weight distribution module, a real-time feedback module and an execution engine function module; weight distribution receives the first signal and analyzes a current strategic target priority identifier and a historical performance evaluation record contained in the first signal, a weight parameter space dynamically matched with a target priority is constructed through an online learning algorithm, and a second signal containing a real-time weight mapping relation is generated; real-time feedback is carried out, a multi-dimensional performance evaluation matrix is constructed based on the weight mapping relation in the second signal, and a third signal is generated; the execution engine receives the third signal, analyzes an abnormal positioning code of the third signal, and aggregates intervention records in a period to form a fourth signal; according to the method, the defects that traditional performance information analysis depends on static weight, the data dimension is single, and real-time dynamic adjustment is lacked can be overcome, and the analysis efficiency is improved.

The invention belongs to the technical field of machine room safety monitoring, and discloses an image review method fusing semantic understanding and visual recognition, which comprises the following steps: calculating visual / semantic feature dynamic credibility in real time through an exponential weighted moving average algorithm in combination with environment interference and equipment state parameters; resNet50 is adopted to extract visual features in global and local branches, and a BERT model is adopted to encode semantic features; correcting the feature correlation degree according to the scene, calculating a dynamic weight, carrying out heterogeneous calibration through an attention mechanism, and calling priority rules such as'physical security features are higher than behavior features' for arbitration during conflicts; the method is advantaged in that low-credibility feature interference fusion is avoided, abnormity identification accuracy in a complex scene of a machine room is improved, multi-modal data cooperation demands are adapted, scene labels are marked based on time, work orders and historical data dimensions, an exclusive sub-model is constructed for a high-density scene through DBSCAN density clustering, and low-frequency scene parameters are migrated to a similar model.

The invention discloses a tumor chemoradiotherapy reaction automatic prediction system, and particularly relates to the technical field of medical automation, the tumor chemoradiotherapy reaction automatic prediction system comprises a data acquisition module, a data preprocessing module, a feature extraction and selection module, a model training module, a prediction analysis module, an early warning module and a feedback module; the multi-source data acquisition module comprehensively gathers patient information, the quality is improved through the preprocessing module, a foundation is built for the feature extraction and selection module to accurately screen key features, the data dimension is greatly reduced, and the model training efficiency is remarkably improved; the model training module applies a machine learning algorithm to deeply mine a data complex relationship, so that the prediction is more accurate and reliable; on the basis, the prediction analysis module outputs detailed chemoradiotherapy reaction prediction and provides confidence evaluation to help doctors to make decisions and select; and the early warning module is responsible for predicting, warning abnormity in time and helping doctors to plan intervention in advance.

The invention discloses a power grid dynamic scheduling decision-making method and device based on multi-modal prediction, electronic equipment and a storage medium, and belongs to the field of power system regulation and control operation, and the method comprises the steps: obtaining internal state data and external working condition data of each target power grid device, and a future load change curve of a related power transmission and distribution line, and an equipment feature matrix is constructed through space-time alignment. And inputting the feature matrix into a multi-modal neural network, and outputting the health index, the remaining service life and the fault probability. When the equipment health index is lower than a threshold value, a multi-objective optimization model is constructed, a preventive scheduling strategy is generated, and scheduling is executed; and when the equipment fault probability exceeds a set threshold value, updating the power grid line weight based on load prediction, generating a topology reconstruction scheme of the minimum power failure range, and scheduling according to the topology reconstruction scheme. By implementing the method and the device, the problem that the long-term degradation trend and the short-term sudden risk of the equipment cannot be accurately predicted due to single data dimension in the prior art can be solved.

The invention relates to the technical field of intelligent assessment, and discloses a dam risk assessment method, device and equipment based on multi-source data fusion, and the method comprises the steps: determining a monitoring project type of dam multi-source monitoring data, building a risk assessment index system through selecting a key index of the monitoring project type, and obtaining a risk assessment result; the method comprises the steps of dividing a dam region by combining measuring point spatial distribution to obtain a dam partitioning result, processing single measuring point actual measurement data of the same region in the dam partitioning result through a dam risk assessment model to obtain a region basic probability distribution value, and further obtaining a risk assessment result. According to the method, the limitation of single data dimension is broken through by constructing a risk assessment index system, accurate mastering of risk heterogeneity of different regions is realized through region division, a dam risk assessment model combining a cloud model and an evidence theory is adopted, the problem of dimension unification of multi-source data is solved, the risk assessment comprehensiveness is ensured, and the risk assessment efficiency is improved. And the accuracy of risk assessment is also improved.

The invention relates to the technical field of cultural tourism guide, in particular to a marine culture intelligent guide system based on artificial intelligence and the Internet of Things, which integrates multi-source data acquisition, context semantic understanding, user portrait construction, personalized content recommendation and adaptive content presentation, and the system acquires user voice, position, facial image and environment information, so as to realize the intelligent navigation of the marine culture. Accurate data acquisition is realized; the system combines semantic understanding and user portraits, dynamically generates interest models, recommends personalized marine culture contents to users, ensures effective information transmission through a self-adaptive presentation module, optimizes resource allocation through a distributed processing module, guarantees stable operation of the system, constructs a user-environment-cultural relic three-dimensional perception network, improves the acquisition precision by 65%, and improves the real-time performance of the system. The data dimension is obviously expanded, a comprehensive data basis is provided for intelligent navigation, and efficient and personalized cultural tourism experience is achieved.

The invention discloses a large-amount consumption scene intelligent customer obtaining method, system and device based on AI multi-modal data and a medium, relates to the technical field of multi-modal data processing, and solves the technical problems of low customer obtaining efficiency, poor customer conversion quality and lagging credit risk management and control in a large-amount consumption scene. According to the technical scheme, the method is characterized in that a trans-modal feature fusion model based on a Transform model and a'large-amount consumption demand prediction-credit adaptation degree evaluation 'dual-prediction model are constructed by fusing four types of multi-modal data of client texts, images, behaviors and time sequences; the technical problems of single data dimension, disjunction of demand and qualification pre-judgment and insufficient strategy dynamics in traditional customer acquisition are solved, accurate identification of potential customers and pre-management and control of credit risks are realized, and customer acquisition efficiency, customer conversion quality and risk management and control capability of a large-amount consumption scene are improved.

The invention relates to the technical field of food and beverage, in particular to a food and beverage network sales trend prediction model construction system and method based on multi-source data fusion and deep learning. Comprising a data acquisition unit; a data processing unit; the model construction unit is used for constructing a deep learning prediction model, and an improved LSTM-Transform fusion algorithm is adopted to realize nonlinear mapping modeling of the food and beverage sales trend by integrating time sequence feature modeling and a global dependency relationship analysis technology; a model training verification unit; and a prediction output unit. According to the method, multi-source data such as network sales platform data, social media emotion texts, weather information and industry information are integrated, cross-correlation features such as time dimension features, text emotion features and price elasticity-weather influence are extracted in combination with a feature engineering technology, influence factors of food and beverage sales are comprehensively covered, and the sales quality is improved. The problem that a traditional scheme is single in data dimension is solved.

The invention discloses a memory writing method and device, a storage medium and a program product, and relates to the technical field of memory access, and the method comprises the following steps: determining a memory step length of an initial image tensor corresponding to a target image, determining a target vectorization width according to the memory step length and a memory data width of a target graphics processor, and determining a target data dimension of the target graphics processor, determining a target thread grid corresponding to the initial image tensor according to the target data dimension, performing image tensor slicing by using the target thread grid to obtain a target image tensor, and writing the target image tensor into a memory. According to the method, the memory layout (step length) of the input tensor can be dynamically analyzed, so that the optimal vectorization width is adaptively determined, the memory access efficiency is maximized, slicing is performed according to the data dimension when the target graphics processor outputs the data, the method has adaptability and high efficiency, the GPU video memory bandwidth is fully utilized, and the memory bandwidth utilization rate is improved.

The invention discloses a virtual power plant control method and device for resource optimization, and relates to the technical field of virtual power plant control. The method comprises the steps of collecting multi-dimensional monitoring data of a virtual power plant, inputting the multi-dimensional monitoring data into a virtual power plant state prediction model, and performing state prediction to obtain a virtual power plant state prediction result; inputting the virtual power plant state prediction result into a virtual power plant resource allocation optimization model, and generating a resource allocation scheme to obtain a virtual power plant resource allocation scheme; inputting the virtual power plant resource allocation scheme into a virtual power plant digital twinborn model, and performing digital twinborn simulation verification to obtain a corrected virtual power plant resource allocation scheme; and inputting the corrected virtual power plant resource allocation scheme into a virtual power plant cooperative control model, performing control instruction generation, obtaining a virtual power plant control instruction, and issuing the virtual power plant control instruction to an execution terminal. The problems of single data dimension, insufficient prediction precision, extensive resource allocation, lack of closed-loop verification and complex cooperative control in the prior art are solved.

The invention relates to the technical field of artificial intelligence, and provides a marketing data generation method and device based on portrait data, equipment and a medium, marketing association data can be collected and purified based on a three-level data gateway, feature fusion is carried out by using a star-shaped collaborative network constructed based on a dynamic weight mechanism and a federated learning mechanism, and the marketing data generation efficiency is improved. The problems of data dimension limitation and data island are solved; scene recognition is performed based on a marketing data graph constructed by a secondary scene classification tree including a gift scene, and the problems of low utilization efficiency of unstructured data and insufficient crowd portrait granularity are solved; the marketing strategy is generated by using the target engine matched with the scene, so that the problems of scene engine deficiency and gift scene adaptation imbalance are solved; and generating the target marketing data according to the target marketing strategy and the marketing data graph. The problems of low operation efficiency and insufficient content accuracy are solved.

The invention discloses a central air conditioner energy consumption big data intelligent analysis method based on data mining. The method comprises the following steps that historical data of central air conditioner energy consumption is collected; performing data preprocessing on historical data of the energy consumption data of the central air conditioner; establishing an analysis engine, namely establishing an energy consumption model and establishing a load prediction model; establishing a central air conditioner energy efficiency detection strategy model; establishing a fault prediction model; after energy consumption data of the central air conditioner are collected for data preprocessing, energy efficiency detection is conducted through the energy efficiency detection strategy model of the central air conditioner according to predicted energy consumption and load data output by an analysis engine, fault prediction is conducted through the fault prediction model, and finally the data are summarized to obtain an analysis report. Through data mining and intelligent analysis, the problem that in the prior art, data dimensions are complex is solved, and the problem of overfitting of the position where the central air conditioner is located due to building specificity is solved.

The invention provides an industrial production Internet of Things data anomaly detection method, medium and system, and belongs to the technical field of industrial production Internet of Things. Industrial equipment sensor data is collected and preprocessed to establish a multi-dimensional data set, and principal component analysis and a mutual information algorithm are used to construct a dimension reduction feature data set; a virtual sensor algorithm is utilized to make up for data missing to form an extended data set, a simulation statistical mechanical anomaly analysis model is established based on a statistical mechanical law to convert the microscopic state of massive high-dimensional sensor data into a macro thermodynamic parameter, and a statistical mechanical feature vector is calculated through a virtual particle ensemble simulation equipment operation state. A state evaluation model and a dynamic threshold function are adopted to identify an abnormal mode and perform grading marking, a feedback optimization mechanism is constructed to continuously improve the system performance, and the technical problem that a traditional algorithm has a curse of dimensionality and cannot perform effective anomaly detection due to extremely high data dimensionality of an industrial equipment sensor is solved.

The invention belongs to the technical field of industrial flue gas purification, and discloses an ammonia desulfurization optimization control system based on a machine learning algorithm, which comprises a feature extraction module, a working condition clustering module, a dynamic optimization module and a self-adaptive feedback module, the feature extraction module is used for collecting multi-dimensional operation parameters in a coal burning process, performing data dimension reduction through a PCA algorithm, and extracting key working condition features; the working condition clustering module identifies different operation working condition modes; the dynamic optimization module can construct a multi-modal optimization neural network based on different operation condition modes, and generates optimal control parameters in real time. Through PCA dimension reduction processing of the feature extraction module and in combination with a working condition clustering algorithm, automatic mode recognition and strategy switching under complex working conditions are achieved, fluctuation of desulfurization efficiency is reduced, and meanwhile the problems that the ammonia water adding amount depends on experience setting, raw material waste and secondary pollution are likely to be caused, and the operation and maintenance cost is large are solved.

The invention discloses a sparse Bayesian direction of arrival estimation method based on subspace compression and dictionary optimization, and belongs to the field of array signal processing. According to the method, the data dimension is reduced through the subspace compression technology, and the noise immunity is improved; signal power and noise power are automatically estimated in combination with a sparse Bayesian model, and dependence on information source number information is avoided; the calculation efficiency and the numerical stability are improved through a support set adaptive pruning strategy; and finally, a dictionary fine tuning mechanism is introduced, direction continuous optimization is realized on the basis of an original discrete grid, an off-grid error is eliminated, and direction-of-arrival estimation with sub-resolution precision is realized. The method is a novel method combining subspace compression, sparse Bayesian inference, adaptive pruning and angle optimization, can give consideration to estimation precision, calculation efficiency and application robustness, and is especially suitable for direction estimation under the complex actual conditions of low signal-to-noise ratio, few snapshots, unknown signal source number and the like.

The invention provides a rare earth element content quantitative estimation method and device, equipment and a storage medium. The method relates to the technical field of hyperspectrum, machine learning and quantitative estimation. The method comprises the following steps: acquiring hyperspectral data of each sample, eliminating gross error points, performing data dimension reduction and K-means clustering analysis to obtain effective spectral data of each sample, performing denoising processing, averaging to obtain an average spectral curve, and extracting spectral characteristics; analyzing the correlation between the characteristic data of each wave band and the element content by utilizing Pearson correlation, selecting a high-correlation wave band range, carrying out importance test on the high-correlation wave band range by utilizing a random forest, and screening out a characteristic wave band corresponding to each element; and constructing a data set by using the characteristic wave bands corresponding to the elements and the chemical test contents of the elements, and training and evaluating the machine learning model based on the data set to obtain a quantitative estimation model. The rare earth element content can be quickly scanned and evaluated in time.

The invention discloses a general electromyographic signal processing method and system based on a large self-supervised model. The general electromyographic signal processing method comprises the following steps: step 1, acquiring a multi-source original multi-electrode channel EMG signal X from an electromyographic acquisition device; and finally, performing data unification processing, and finally converting into a space-time activity diagram with a fixed size of 224 * 224. On the basis of the space-time activity diagram and the fatigue state mark, constructing an AEMG for training according to heterogeneous unlabeled EMG data collected by a collection device; performing light-weight Adapter layer fine adjustment on the pre-trained large myoelectricity model to adapt to gesture recognition muscle force regression gait analysis or rehabilitation evaluation downstream tasks; aiming at the problem that the dimension and the structure of myoelectricity data are not matched due to different acquisition devices, acquisition parts and acquisition tasks, original signals are converted into space-time activity diagrams in a unified format through data unification processing, device differences are represented by combining a sensor embedding module, effective alignment of cross-source data is achieved, and the accuracy of the data is improved. And a basis is provided for large-scale data utilization.

The invention discloses a sudden drought identification method and system based on a space-time double-branch fusion model. The method comprises the steps that meteorological data are acquired and preprocessed; calculating a composite sudden drought index according to the obtained data; performing data dimension reduction on the obtained data through singular value decomposition (SVD); a deep learning model is adopted to construct a time branch model, a graph attention network GAT is adopted to construct a space branch model, and the time branch model and the space branch model are dynamically fused through a cross attention mechanism to construct a space-time double-branch fusion model; according to the method, data dimensions are compressed and model complexity is reduced by fusing multi-source variables and combining singular value decomposition (SVD), meanwhile, geographic neighborhood weights are dynamically learned by adopting Transforme and based on a graph attention network (GAT), dynamic fusion of spatial-temporal characteristics is finally realized through a cross attention mechanism, a sudden drought recognition result is generated, and the method has the advantages of being high in robustness, high in accuracy and high in reliability. The limitation of a traditional method on nonlinear feature capture, space-time modeling splitting and generalization ability is broken through.

The invention discloses a depressive symptom assessment method and system based on multi-modal physiological data, relates to the technical field of artificial intelligence, and solves the problems of relatively high subjectivity, single data dimension, insufficient linkage and lack of a dynamic induction mechanism during depressive symptom assessment in the prior art. The method comprises the following steps: performing emotion induction on a subject by using a VR scene, collecting multi-dimensional physiological signals, behavior performance and subjective feedback information at the same time, and realizing feature extraction and multi-modal feature fusion; a depression risk assessment model trained by a deep neural network model is utilized to predict the current emotional state, depression symptom severity and potential abnormal reaction characteristics of a subject, and self-iterative learning of the depression risk assessment model and regulation and control of a VR situation push strategy are realized. The problems of single emotion induction mode and unstable reaction are solved, and the defects of high subjectivity and limited data dimension in a traditional evaluation method are effectively overcome.

The invention relates to a real-time monitoring method for soil remediation by utilizing multi-spectrum of an unmanned aerial vehicle and sensing coupling of the Internet of Things, and belongs to the technical field of soil environment monitoring and remediation. The method comprises the following steps: constructing a space grid model of a monitoring area; a space-air-ground integrated monitoring network is arranged, image data are obtained through multi-spectral remote sensing of an unmanned aerial vehicle, and soil environment parameters are collected through a ground Internet of Things sensor; preprocessing and fusing the multi-source spatio-temporal data, and establishing a spatio-temporal matching model; constructing an inversion model of the soil heavy metal content, the organic matter content and the pollutant degradation degree based on the fusion data; and the repair efficiency is dynamically calculated and visualized, and real-time evaluation and early warning of the repair process are realized. According to the invention, space-air-ground data collaboration is realized, the real-time performance, accuracy and space coverage of monitoring are remarkably improved, the defects of high cost, low efficiency and limited data dimension of a traditional method are overcome, and whole-process and intelligent decision support is provided for soil remediation.

The invention discloses a bottom-up urban traffic carbon emission real-time estimation method and system based on a traffic monitoring video, and belongs to the technical field of intelligent traffic and urban low-carbon governance crossing. The multi-source data comprises meteorological monitoring data, traffic monitoring video data, vehicle parameter data and road geographic information system data; inputting the traffic monitoring video data into a vehicle type recognition model, and outputting a vehicle type recognition result; obtaining vehicle type aggregation data based on the vehicle type identification result; dynamic carbon emission factors are generated in combination with localized configuration of a motor vehicle emission simulator model; and estimating the urban traffic carbon emission based on the dynamic carbon emission factor and the power grid carbon emission coefficient. According to the method, the problems of poor real-time performance, data dimension splitting, insufficient model adaptability and the like of a traditional monitoring method are solved, and based on the real-time analysis capability of the traffic monitoring video, technical support is provided for urban traffic carbon emission accurate metering and intelligent emission reduction decision making.

The invention discloses a grain crop grain classification detection method and system based on small samples, and relates to the technical field of grain quality detection.The method comprises the steps that hyperspectral images of grain crop grains are obtained, quality categories are marked, and then multi-modal features are extracted to construct a classification data set; the data set is used for training a multi-modal fusion classification model, a feature fusion network carries out dynamic weighted fusion on multi-modal features by means of an attention mechanism, a high-dimensional fusion feature vector is generated, and a classifier detects a quality category according to the high-dimensional fusion feature vector. During detection, the multi-modal features of the to-be-detected grains are input into the trained model, and then the quality category can be obtained. The method effectively solves the problems that a single modal method is difficult to deal with complex differences among grain crop grain types, high in hyperspectral data dimension, few in samples, easy to over-fit and the like under the condition of small samples, dynamic focusing of key information is realized by introducing an attention mechanism to optimize modal fusion weight distribution, and the method is suitable for popularization and application. And the classification accuracy and the model robustness are improved.

The invention relates to the technical field of data processing, in particular to a user electronic medical record generation method for a health examination cabin, which comprises the following steps: acquiring to-be-processed examination data of a target user and a reference examination data set of a reference user; according to a deviation condition between the to-be-processed physical examination data of the target user in each data dimension and a normal data range, combining a historical physical examination data distribution condition to obtain a current contradictory index, and screening the data dimensions to obtain a contradictory dimension; according to the data change trend and the time distribution condition of each reference user under each contradiction dimension, a reference priority is obtained in combination with a data prediction result and a current contradiction index; within a preset time period, obtaining information richness according to the data periodicity feature and the data fluctuation feature of the reference user in each contradiction dimension; and obtaining the key data dimension, and further generating an electronic medical record of the target user. The credibility of the electronic medical record and the efficiency of finding problems when a doctor rechecks are improved.

The invention discloses a large language model training method, a training data acquisition method and an intention recognition method, and relates to the technical field of artificial intelligence. The raw data set includes a plurality of dialog data. The electronic equipment performs group division on the dialogue data in the original data set based on a preset data dimension to obtain a plurality of groups. The electronic device performs data sampling from the plurality of groups, and a set of sampled dialogue data is used as a training data set. And the electronic equipment takes the training data set as input of the large language model to carry out model training, and the trained large language model is obtained. Data processing such as grouping and sampling is performed on the original data set based on different data dimensions, the distribution of each obtained training data set in each data dimension is relatively balanced, and the large language model obtained by training based on the training data set has relatively high accuracy.

The application relates to the technical field of data processing, and particularly discloses a student psychological state recognition method and system based on multidimensional data analysis, which realizes the precision and efficiency of student mental health management. First, data cleaning and standardization processing are integrated to eliminate invalid information and unify data dimensions, thereby significantly improving analysis reliability. Through a collaborative analysis mechanism, different dimensional data features can be dynamically associated, and the adaptive adjustment function of the feature extraction process can automatically optimize algorithm weights according to data quality, thereby ensuring the extraction accuracy of key psychological indicators. Through data-driven closed-loop management, mental health monitoring is changed from passive coping to active prevention, the efficiency of school psychological crisis intervention is effectively improved, scientific support is provided for educational decision-making, and the precise allocation of mental health resources is promoted.