59 results about "Association model" patented technology

The invention provides a dynamic self-adaptive multi-modal sentiment analysis fusion method and system, and relates to the technical field of multi-modal sentiment analysis. The method comprises the following steps: synchronously acquiring voice, text, facial expression and limb movement data of a target user to form a multi-modal data set; the method comprises the following steps: firstly, extracting emotional characteristics of each mode, and constructing a cross-mode correlation model to capture a collaborative and complementary relationship among different modes; and calculating a real-time confidence score and a complementarity index of each modal based on the weight matrix of the cross-modal correlation model. Then, according to the scores and the indexes, a weighted average or maximum entropy algorithm is dynamically selected to fuse multi-modal emotion features, and a comprehensive emotion feature vector is generated; and finally, inputting the vector into a pre-training deep learning model, and outputting an emotional state category of the user. According to the method, the user emotion can be accurately and comprehensively captured, efficient emotion recognition and classification are realized, and the robustness and flexibility of an emotion analysis system in a complex scene are improved.

The invention discloses a mapping prediction method and system based on a hardware resource load and system operation relationship. The method comprises the following steps: collecting hardware index data in real time when an operating system operates; the method comprises the following steps: preprocessing hardware index data, performing association analysis on each index data by adopting an association rule mining algorithm, generating association rules, evaluating the association rules, screening out the association rules meeting conditions, and constructing a multivariable association model; based on a correlation analysis result, a load prediction model is constructed and trained, and the trained model is deployed in the system for load prediction; and dynamically adjusting a system hardware resource allocation strategy according to a prediction result, carrying out task migration and load balancing according to a predicted load condition, and automatically adjusting hardware resources through an automatic script or a scheduling tool. Through real-time monitoring and deep correlation analysis of indexes such as the CPU, the memory, the storage I / O and the network bandwidth, the resource utilization rate and the operation efficiency of the system are improved, and the stability and the reliability of the system are improved.

The invention relates to an intelligent maintenance decision method and system based on a knowledge graph, and relates to the technical field of intelligent operation and maintenance and decision support and information, and the method comprises the steps: obtaining the operation state data and historical maintenance data of industrial equipment; constructing an industrial knowledge graph and generating an incidence relation model; an optimal maintenance path is obtained based on the analysis of the relationship between the fault type and the maintenance path; optimizing a maintenance task allocation scheme through the optimal maintenance path, the incidence relation model and the maintenance resource constraint condition; carrying out maintenance time window dynamic adjustment analysis to obtain an optimal maintenance strategy; and finally, performing multi-objective optimization iterative analysis to obtain a final maintenance decision. According to the scheme, various factors can be comprehensively considered, and the scientificity and the accuracy of maintenance decision making of the industrial equipment are improved.

The invention discloses a bearing life prediction method and system based on dynamic knowledge embedding, and the method comprises the following steps: S1, encoding bearing field data, expert experience and monitoring data into a structured triple, building a dynamic knowledge graph frame, and designing a sliding window confidence mechanism to achieve the online updating of a graph node relation; s2, extracting knowledge embedding vectors by using a relational graph convolutional network, and extracting vibration signal features by using a hierarchical convolutional network; s3, mapping the knowledge embedding vector and the vibration characteristics to a unified semantic space through a linear projection layer; s4, constructing a Transform encoder based on multi-head self-attention, and establishing a dynamic correlation model between vibration characteristics and knowledge embedding; s5, designing a full-connection network output life prediction result and feeding back the optimized knowledge graph; and S6, adaptively adjusting the size of the sliding window based on the change rate of the working condition, dynamically balancing the contribution weight of new and old knowledge in combination with a gating mechanism, and ensuring the adaptability of the model to the complex working condition.

The invention discloses a multi-target track association method and system based on interactive attention map matching and a storage medium, and the method comprises the steps: preprocessing track data, and obtaining an input track; utilizing a track historical feature extraction network to obtain embedded features of each track; a multi-graph structure is utilized to model tracks, nodes represent one track, edges represent message passing between the tracks, and the number of the edges is limited through graph cutting; features of neighbor nodes are aggregated by using a self-attention mechanism and a cross attention mechanism, and finally embedded representation of the nodes is obtained; and constructing a score matrix, and performing a Sinkhorn algorithm on the matrix to obtain an association probability matrix. And track association is carried out by using the multi-target track association model based on interaction attention map matching, and an association task is completed. According to the method, the spatial-temporal characteristics of the track can be fully mined, the track association accuracy is improved, and the track association error rate is reduced.

The invention provides a method, a device, equipment and a medium for generating an engineering project management digital model, and the method comprises the steps: collecting original data related to engineering project features, carrying out the preprocessing, forming a standardized project data set, constructing a space-time reference frame based on the data set, fusing a multi-dimensional feature tensor of multiple engineering features, and carrying out the construction of a space-time reference frame. The method comprises the steps of generating a project progress node and an integrated feature tensor, fusing the project progress node and the integrated feature tensor to generate a multi-source association graph containing entity relationships and feature semantics, generating a verified engineering project management digital model according to the project progress node, the integrated feature tensor and the association graph, and dynamically updating and optimizing the model in response to change data in project execution. According to the method, the problems of data dispersion, lack of association and static stiffness of the model in a traditional method are solved, automatic construction and dynamic evolution from multi-source heterogeneous data to an intelligent decision-making model are realized, and the accuracy, real-time performance and intelligent level of project management are remarkably improved.

The invention discloses a marketing strategy optimization method based on consumer group behavior analysis, and the method comprises the following steps: deeply integrating and analyzing multi-source heterogeneous data in real time, such as biological characteristic data, physical environment and spatial data, social contact and content interaction deep analysis data, and voice and dialogue analysis data; carrying out association modeling on the behavior data, psychological characteristics, physiological states and social environment factors, and constructing a dynamic holographic user portrait; a large language model and a multi-mode generation model are utilized, marketing content with high personalization and situation adaptation is generated in real time based on a user portrait and a real-time context, and an interactive co-creation mode of the user and AI is explored; and according to an evaluation result, performing online updating and optimization on each link by using a machine learning algorithm to form a continuously improved closed loop. According to the invention, a more accurate and personalized marketing strategy can be provided, the sense of participation of users is enhanced, and the marketing effect and enterprise competitiveness are improved.

The invention discloses a business document design and user-defined field modeling method supporting dynamic expansion. The method relates to the technical field of custom field modeling, and comprises the following steps: constructing a core foundation and a metadata system; a non-intrusive expansion and data association model; performing high-performance query and index optimization; and performing dynamic verification and visual application. Structural stability and flexible expansion are realized through separate design of the core table and the expansion table, field definition, storage, verification and form rendering are driven by metadata, complex query and cross-receipt field multiplexing are supported, data consistency and full-link connection are guaranteed, business receipt design and self-defined field modeling expandability are improved, and the method is suitable for large-scale popularization and application. The problem of low expandability of business document design and custom field modeling in the prior art is solved.

The invention provides a data processing method and system based on network security service, relates to the technical field of network data security processing, and realizes structured expression and behavior extraction of potential threats in encrypted communication by establishing a new data structure and behavior association model. By introducing a context causal chain modeling mechanism, associating the originally isolated security events into a complete attack path; by establishing a set of event grading mechanism based on comprehensive scoring of service criticality, response cost and attack propagation path, threat processing does not distribute resources blindly and averagely, but performs intelligent scheduling according to priority, so that the resource utilization efficiency is improved; a structured and executable defense instruction or blocking strategy can be generated according to an analysis result, man-machine cooperation or full-automatic response is supported, and response efficiency and strategy adaptability are remarkably improved. And a set of intelligent data processing solution which is oriented to a network security service practical application scene and has high availability and high expansibility is constructed.

The invention provides an automatic bait casting system for training and breeding juvenile plectropomus leopardus, which comprises a basic data module connected with an automatic bait training device and used for acquiring original data of a breeding pond and extracting feeding basic data; the dynamic association module is used for carrying out multi-level cross association modeling, causal inference association, sub-mode mining and classification adaptation to obtain an ingestion-turbidity dynamic association model and outputting an ingestion-turbidity relationship; the hunger index module is used for constructing a hunger index model and outputting the hunger index of each culture pond; the feeding strategy module is used for calculating the next feeding interval, the strip-shaped bait-live bait proportion, the actual time point of next feeding and the bait amount per hour and judging whether extra meal or increase of the next feeding interval is needed or not to obtain a self-adaptive feeding strategy; and the feeding driving module is used for controlling the running action of the automatic bait training device. Scientific feeding can be achieved, the feeding survival rate, the growth rate and the bait training effect are remarkably improved, feed waste is reduced, and intelligent and automatic management of the whole process is achieved.

The invention relates to the field of vulnerability mining, in particular to a vulnerability mining method based on a large model, and the method comprises the steps: constructing a label combination library for a working condition terminal, and subsequently constructing a correlation model for a label combination based on a credible log fragment corresponding to each label in the label combination; based on the occurrence probability of each label combination and combined with the constraint discrete features of the association model corresponding to the label combination, effective sub-labels are set for the label combination, a current label combination of a current log record is analyzed subsequently for a new log record, and adaptability analysis is performed on the log record according to the effective sub-labels corresponding to the current label combination, so that the log record is obtained. According to the method, potential laws of the operation process of the industrial control terminal are considered, the association model of the log records under the specific label combination is constructed, the log records are analyzed based on the effectiveness adaptability of the label combination, log fragments possibly representing that potential abnormal vulnerabilities exist in a system are rapidly marked when massive log records are faced, and the system reliability is improved. And the accuracy and efficiency of vulnerability mining are improved.

The invention discloses a business collaborative management system and method based on data analysis, and relates to the technical field of business collaborative management. According to the business collaborative management system and method, a change point analysis method and a local anomaly factor LOF algorithm are adopted, multi-dimensional density distribution of operation data is subjected to quantitative evaluation, discrete anomaly points and accumulation anomaly points are marked, and a business collaborative management result is obtained; the source of the abnormal point is judged through correlation analysis, so that the abnormal data processing capability is remarkably improved; the feature analysis module is combined with association rule mining and a multi-dimensional regression analysis method, analyzes formation conditions of abnormal points, extracts key influence factors, quantifies the influence degree of the key influence factors on supply chain operation, and establishes a factor association model; and the decision-making unit performs high-dimensional simulation on the supply scheme of the supply chain through a reinforcement learning algorithm, and generates a dynamic adjustment scheme including transportation resource optimization, inventory strategy adjustment and high-risk supplier substitution through multiple times of strategy iteration.

The invention provides an intelligent updating method of a master-slave version linkage database, and belongs to the technical field of database updating, and the method comprises the steps: converting different key elements of a clothing version into quantitative correlation parameters based on a multi-dimensional parameterization correlation model, and building a real-time binding relationship between a master version and a slave version based on a mapping rule of a database layer; the method comprises the following steps: constructing a multi-modal clothing process knowledge graph, fusing multi-modal data to deeply associate clothing pattern data with key elements to obtain a pattern adjustment vector set, and adopting a multi-dimensional change type intelligent identification and priority judgment engine to automatically identify a master pattern change type and judge an adjustment priority based on a real-time binding relationship. And in combination with a preset AI self-optimization clothing structure mathematical formula library and a model adjustment vector set, the sub-templates are driven to complete adaptive adjustment of corresponding parts so as to realize intelligent updating. Manual plate-by-plate adjustment is not needed, the plate type updating efficiency is greatly improved, and size deviation and process defects are effectively reduced.

The invention discloses a four-dimensional index-based scientific and technical literature knowledge automatic labeling method and system, and relates to the technical field of natural language processing, and the method comprises the following steps: constructing a four-dimensional index architecture; the method comprises the following steps: receiving multi-format scientific and technical literatures through a data input layer, and performing index analysis to obtain a document layer semantic structure, a paragraph layer semantic relation graph, a sentence semantic relation network and an entity semantic relation; performing semantic density calculation and knowledge enrichment region recognition to obtain a knowledge enrichment region recognition result; and establishing a cross-hierarchy semantic association model, performing entity boundary prediction and multi-level labeling on a knowledge enrichment area recognition result to obtain a structured semantic labeling result, and performing visual output and display. The technical problem that in the prior art, scientific and technical literature knowledge recognition is not accurate, hierarchical labeling is insufficient, and consequently the literature processing efficiency and accuracy are low is solved, and the technical effects that precise recognition and multi-hierarchical labeling of scientific and technical literature knowledge are achieved, and the literature processing efficiency and accuracy are improved are achieved.

The invention provides a data analysis method and system for old people with multiple diseases, and belongs to the field of data analysis. The problem of complex data analysis is solved; the method specifically comprises the following steps: S1, acquiring age and disease information of old people to obtain a disease table; acquiring life information of the elderly; s2, obtaining confidence coefficients among the diseases according to the disease information, and calculating to obtain influence values of the diseases; sorting the diseases according to the influence values, and obtaining a case matrix according to a disease table of the old; calculating to obtain a disease proportion and a disease value of a single disease; s3, obtaining an association model according to the age and the disease value of the elderly, classifying the disease value, and obtaining an association relationship between the life information and the disease value of the elderly in combination with the life information of the elderly; s4, the illness condition of the old people is predicted, and diseases are prevented and treated; by analyzing the data, the incidence relation between the living habits of the old people and the diseases is obtained, and suggestions are provided for disease prevention and treatment of the old people.

A computer includes a processor and a memory, and the memory stores instructions executable by the processor to associate detected objects from sensor data with tracked objects in a tracking list stored in the memory by executing an association model, determine kinematic states of the tracked objects by executing a Bayesian filter, and update which of the tracked objects are stored in the tracking list by executing a track-management model. The association model includes association weights and outputs probabilities that the detected objects are the same as the tracked objects. An association-model gradient of the association model is computable. The association-model gradient is of the probabilities with respect to the association weights. The Bayesian filter includes Bayesian parameters. A Bayesian-filter gradient of the Bayesian filter is computable. The Bayesian-filter gradient is of the kinematic states with respect to the Bayesian parameters. A track-management gradient of the track-management model is computable.

The present invention belongs to the field of equipment state deduction and prediction, and discloses a collaborative fusion digital twin deduction and evaluation method for an integrated industrial system. The specific steps of the deduction and evaluation method include the following: establishing a unit association model of four relationships between devices, further considering the mutual influence between devices in the model, and calculating the specific influencing parameters of the association model, establishing a correlation coefficient matrix, and constructing a deduction and evaluation model of the industrial system based on the matrix. Through a comprehensive evaluation of the entire industrial system, the operating status of the industrial system can be fully understood and grasped, potential problems can be discovered and solved in a timely manner, and the normal operation of the industrial system can be guaranteed.

This invention discloses a method and system for automatic annotation of scientific and technological literature knowledge based on a four-dimensional index, belonging to the field of natural language processing technology. The method includes: constructing a four-dimensional index architecture; receiving multi-format scientific and technological literature through a data input layer, performing index parsing to obtain document-level semantic structure, paragraph-level semantic relationship graph, sentence semantic relationship network, and entity semantic relationships; performing semantic density calculation and knowledge-rich region identification to obtain knowledge-rich region identification results; establishing a cross-level semantic association model, performing entity boundary prediction and multi-level annotation on the knowledge-rich region identification results to obtain structured semantic annotation results, and performing visualization output. This invention solves the technical problems of inaccurate scientific and technological literature knowledge identification and insufficient hierarchical annotation in existing technologies, leading to low efficiency and accuracy in literature processing. It achieves accurate identification and multi-level annotation of scientific and technological literature knowledge, improving the efficiency and accuracy of literature processing.

The invention relates to intelligent classification of coal mining materials. The method comprises the following steps: acquiring multi-source data associated with coal mining, and performing feature fusion on the multi-source data to obtain a three-dimensional association model; the three-dimensional association model is an association model for equipment information, material information and equipment maintenance information of coal mining, generating an association map by using the three-dimensional association model based on a pre-constructed unified data category model, and inputting the association map into the trained map neural network model to obtain a map neural network model; and obtaining a material classification result output by the graph neural network model. According to the scheme, the material management efficiency and the intelligent level are improved.

The present application relates to the technical field of geological disaster monitoring and early warning, in particular to a complex high-position landslide risk dynamic identification system based on multi-source InSAR cooperation, comprising: a data acquisition module for constructing a normalized feature vector representing the state of each monitoring node; an association modeling module for quantifying the physical influence degree between heterogeneous nodes; a state prediction module for iteratively updating the hidden state of each heterogeneous node using a spatio-temporal graph neural network model, and interpreting the hidden state as incremental displacement; a risk assessment module for calculating the risk precursor index of each heterogeneous node deviating from the normal evolution mode based on the hidden state, and determining and issuing graded early warning according to the preset threshold system; the present application effectively alleviates the overfitting problem of pure data-driven models when data is sparse, significantly improving the generalization ability and physical interpretability of the prediction results.

The invention relates to a multivariate evidence correlation analysis method in the judicial field, and belongs to the technical field of intelligent processing of documents. The method comprises the following steps: loading judicial case file data and extracting an evidence content text; constructing an evidence rule template according to judicial domain knowledge and expert opinions; extracting evidence elements based on the rule template and constructing an evidence library; building a multivariate evidence information network, calculating the condition probability of association information among evidence elements based on a Bayesian network, and forming a multivariate evidence association analysis model; optimizing the multivariate evidence information network through a random strategy reinforcement learning algorithm; and calculating an information probability value of the multivariate evidence subnet, and selecting the most valuable multivariate evidence information network. According to the method, a multivariate evidence correlation analysis event of a judicial case is converted into an updating and optimizing task of a multivariate evidence information network, the complex correlation problem among multivariate evidences is simplified, a correlation model among the multivariate evidences is given, and certain auxiliary support is provided in a judicial decision support system.

Provided are a transaction data processing method and system. The method comprises: acquiring a target proportion vector of a target across different item categories, and constructing a target proportion vector model sample on the basis of the target proportion vector; constructing an association model on the basis of the target proportion vector model sample and an association probability of the target being associated from one item category to another item category; constructing a transition model on the basis of the target proportion vector model sample, the association probability, and a transition association probability of the target being transitioned from one item category to another item category; performing parameter fitting on parameters of the transition model on the basis of the target proportion vector model sample to obtain the transition association probability; and computing target-related decisions for the different item categories on the basis of the transition association probability. Therefore, changes in proportions of a target in different item categories caused by participation of an acting object can be efficiently and accurately identified, and the accurate identification of the changes in proportion allows for optimization of resource allocation and supports effective risk management.

The invention relates to the field of data processing, in particular to an intelligent detection method and system for the impact performance of a forging blank, and the method comprises the steps: firstly, carrying out micro impact and thrust experiments on a sample forging, obtaining a basic data set containing parameters such as geometric dimensions, a force displacement curve and impact energy, and carrying out grouping storage according to material types and shapes; secondly, constructing an inflection point size correlation model and a target fracture energy and impact energy correlation model based on each group of data, and respectively representing correlation relations between inflection point coordinates and geometric dimensions and between fracture energy and impact energy; the model and the identity label of the forge piece group are associated and stored in a database. And when a detection request is received, a micro-impact experiment is executed on a requested forge piece, and impact performance parameters are predicted through the correlation model in the database. According to the method, efficient and accurate detection of the impact performance of the forge piece is achieved through combination of experimental data and an intelligent model, and the method is suitable for forge piece blanks of different material types and shapes.

The method for gene-environment analysis can include: determining an environment-variable association model, identifying causal variables associated with environmental parameters, determining a target set of causal variable values, and evaluating an organism based on the target set of causal variable values. In variants, the method can function to identify environmentally adaptive variable values (e.g., environmentally adaptive alleles), predict an optimal set of variable values (e.g., optimal genotype) for a target environment, and / or evaluate an individual organism relative to the optimal set of variable values (e.g., for breeding, for organism selection, etc.).

This invention provides an intelligent method and system for extracting and analyzing invoice information using deep learning, relating to the field of deep learning technology. First, based on the field flow and association logic of invoice business scenarios, it generates semantic traceability tracing trajectories for fields, collects scenario-related features of the invoice carrier to generate scenario feature guidance signals, and uses these signals to locate the physical presentation areas of key fields and extract their original information to form a set. Next, it constructs a dynamic field association model, inputting the set of original information for key fields and scenario-related features into the model, and uses deep learning algorithms to model dynamic dependency relationships to generate a dynamic field association graph. Finally, based on this graph, it integrates information to generate scenario-based structured invoice analysis results, including core field content, scenario association logic, and dynamic association descriptions, enabling efficient and accurate processing of invoice information.

The invention relates to the technical field of data authority management, in particular to a fine-grained data authority searching method based on an authority atlas and a dynamic index, which comprises a multi-level knowledge association model, a dynamic incremental index mechanism and an authority atlas and index collaborative optimization method. The multi-level knowledge association model hierarchically defines a user role, a data attribute and a context environment; a dynamic incremental index mechanism reduces the maintenance cost through distributed task decomposition and adaptive optimization; according to the collaborative optimization method, the consistency of local refreshing and caching is realized, and the response efficiency is improved. According to the method, the authority control precision and the search efficiency in a large-scale data scene can be remarkably improved, and a brand new solution is provided for complex authority management.

The invention discloses a dynamic nursing scheme generation method and system oriented to AIDS disease course evolution, and belongs to the technical field of public health. The AIDS patient disease course characteristic data is classified and analyzed, key information is accurately extracted, the nonlinear mapping model is constructed by means of the recurrent neural network, the influence of each characteristic on disease course evolution is quantified, the individual difference of the patient is comprehensively and accurately reflected, a data basis is provided for disease course stage division, nursing strategy making and scheme generation, and the accuracy and the reliability of the system are improved. In the whole process from disease course stage division to nursing scheme adjustment, a dynamic monitoring and feedback mechanism is introduced, disease course stages are scientifically divided according to multi-dimensional information, a specific nursing strategy is formulated for each stage and continuously optimized, and meanwhile, based on patient data collected in real time, the nursing intervention is accurately matched with the disease condition development requirement of a patient. The disease course change is evaluated in time through the correlation model, the nursing scheme is dynamically adjusted, and the nursing service can respond to the dynamic evolution of the condition of the patient in real time.

The present invention relates to the technical field of human-computer interaction evaluation, and specifically discloses a human-computer interaction simulation evaluation method and system. The method includes: constructing a task structure diagram based on task data and action parameters, and generating a roll interaction instruction set; configuring environmental parameters, constructing a deception simulation environment, and generating a perception stimulus set; parsing the perception stimulus and the task structure diagram, reorganizing the interaction interface, and generating a configured interaction structure diagram; constructing an association model and simulating a trust induction process, and generating a state regulation factor; collecting human factor data based on the state regulation factor, and generating a structured behavior label sequence; combining the label sequence and the task structure diagram for reasoning analysis, generating an adjustment control strategy, updating the interaction configuration, and completing feedback adjustment. The present invention can dynamically model the change of the interaction-induced trust state, and improve the perception ability and adjustment accuracy of the evaluation process for individual psychological cognition.

The invention discloses a cross-domain preference prediction recommendation method and system based on personality characteristics, and the method comprises the steps: obtaining the personality original data and historical behavior data of a user, and converting the personality original data into personality characteristic representation; on the basis of personality feature representation, through a pre-constructed personality preference association model, predicting the preference score of the user for the non-contact items; generating a first recommendation list according to the preference score; generating a second recommendation list according to the historical behavior data; dynamically adjusting the weights of the first recommendation list and the second recommendation list according to the recommendation scene and user feedback; and performing deep fusion on the first recommendation list and the second recommendation list according to the weight, and generating a final recommendation list. According to the method, through the personality preference association model, accurate prediction and recommendation of people, information and articles which are never touched by the user but are likely to be preferred by the user are realized, and the problems of'information cocoon house 'and'cold start' caused by the fact that a traditional recommendation method only depends on historical behaviors of the user are solved.