3153 results about "Confidence score" patented technology

The invention provides a dynamic path planning method and system in an intelligent traffic system, and relates to the technical field of intelligent traffic. Constructing a dynamic road network traffic capacity model based on a space-time diagram convolutional network; generating a multi-branch trajectory prediction result with a confidence score, adaptively starting an encryption parameter synchronization mechanism in combination with vehicle density, and generating a candidate path set through multi-agent collaborative game optimization; performing multi-dimensional deviation degree evaluation based on actual driving data and planning expectation; synchronously generating a multi-mode cooperative guidance signal; the system comprises a multi-source data fusion unit, a space-time modeling engine, a hierarchical decision-making system, a path verification and execution module, a closed-loop feedback controller, an event response system and a multi-mode man-machine interface. According to the method, the global resource utilization efficiency is improved through cooperation of data-driven modeling and hierarchical game decision, and the real-time performance, the safety and the system adaptability of path planning are improved through a closed-loop feedback and event response mechanism.

In a described embodiment, a system for information processing is provided including a data acquisition module configured to receive feedback corresponding to one or more outputs generated by a language model. The system further includes a cognitive reasoning module configured to evaluate the reasoning process of the language model, emulate cognitive functions including metacognitive processes, and generate an assessment based on an analysis of the received feedback, wherein the assessment includes classifying the one or more outputs into components, assigning quality scores for each component, and identifying an improvement corresponding to the one or more outputs. Additionally, the system includes a process adjustment module coupled to the cognitive reasoning module for adjusting the reasoning process of the language model based on the assessment is provided. A refinement module coupled to the process adjustment module is provided for iteratively refining the reasoning process based on subsequent updates to the generated assessment until a performance threshold is met.

The invention discloses a clean workshop production environment quality control method and system, and relates to the technical field of environment control, and the method comprises the steps: constructing a multi-layer sensing network, deploying temperature and humidity, particle concentration, pressure difference and VOC gas sensors, and carrying out the preprocessing data of each node through edge calculation; fusing the data based on a dynamic weight distribution algorithm, adjusting the weight according to the confidence score, and generating an environment quality comprehensive index; an LSTM pollution diffusion prediction model is established, a diffusion path is calculated in combination with airflow field simulation when pollution suddenly occurs, and an emergency response partition strategy is generated; fresh air system control parameters are optimized through reinforcement learning, a dynamic ventilation frequency adjusting model is established based on a real-time environment quality index and historical energy consumption data, and energy consumption is minimized through a Q-learning algorithm on the premise that cleanliness is guaranteed; a double-threshold early warning mechanism is set, local supercharging purification is started when a comprehensive index exceeds a first-level threshold, a second-level threshold is linked with adjacent areas to form a dynamic isolation barrier, and an intervention scheme effect is simulated through a digital twin system.

The invention provides a decision generation and execution method and system based on an AI agent, and the method comprises the steps: analyzing a user demand document through a natural language processing technology, and extracting key information to construct a structured cue word; then inputting the cue word into a private domain AI agent based on a large model, and generating a preliminary decision scheme in combination with a professional domain database; automatically generating adversarial introspection probe cues, and guiding an AI agent to carry out consistency, risk and constraint conformity evaluation on the preliminary scheme; the system collects feedback response of the AI intelligent agent, analyzes the feedback through a pre-trained graph neural network, and calculates a confidence score of a decision scheme; when the confidence reaches a preset threshold value, automatically generating an execution script according to the decision scheme; and the execution script automatically operates the target system through the preset API and generates an execution document. The whole process realizes a closed-loop intelligent decision-making process from demand understanding, scheme generation, self-verification and automatic execution, and the decision-making efficiency and reliability are remarkably improved.

The invention provides a flow analysis and threat detection method and device based on machine learning, and the method comprises the steps: collecting a real-time flow data package of a target network environment, carrying out the protocol analysis and session recombination, and generating a real-time flow feature data set containing multi-dimensional flow features; loading a pre-trained multi-level threat classification model, inputting the real-time traffic feature data set into a feature extraction layer of the model, carrying out normalized coding on traffic features of corresponding dimensions through feature coding channels, generating a real-time feature vector sequence, inputting the real-time feature vector sequence into a primary classifier of the model, and classifying the real-time traffic features according to the real-time feature vector sequence; and performing abnormal probability calculation and cluster division on the real-time feature vector sequence through a mixed detection unit, outputting a primary threat tag and an abnormal confidence coefficient corresponding to each real-time feature vector, inputting the primary threat tag and the abnormal confidence coefficient into an aggregation classifier, performing dynamic weighted aggregation, and generating a comprehensive threat score so as to judge whether a threat response strategy is triggered or not. According to the invention, the accuracy and timeliness of threat detection in a complex network environment can be improved.

A computing system for adaptive electronic message classification employs a multi-agent architecture comprising a media feature analysis system, a user context refinement system, and a response synthesis system. The media feature analysis system generates pillar scores including message type, intent, and link risk scores with associated confidence values using trained classification models. When pillar scores and confidence values do not satisfy predetermined threshold conditions, the user context refinement system dynamically constructs contextual prompts using the pillar scores and confidence values as input parameters. User responses generate score modification data that refines the pillar scores and contextual response data for recommendation generation. The response synthesis system generates refined classifications and personalized recommendations using the refined pillar scores and contextual response data. An orchestration system coordinates agent interactions using learned uncertainty points and implements asymmetric influence algorithms with variable weighting based on content and URL analysis concordance.

The invention provides a service data security protection method and system for digital enterprise management, and the method comprises the steps: obtaining an access request sequence initiated by a target user at a service operation terminal, generating a dynamic access control strategy vector according to a historical behavior track associated with an access operation identifier, and carrying out the dynamic access control strategy vector; analyzing the dynamic access control strategy vector through a strategy decoder, and generating a real-time access permission instruction; based on the real-time access permission instruction, performing homomorphic encryption mapping on a sensitive data segment in the request context information to generate a ciphertext transmission channel, and performing security parameter synchronization on the ciphertext transmission channel and the cross-department conjoint analysis model; and calling a federated learning framework to carry out multi-modal feature fusion on the real-time operation flow of the service operation terminal, generating an abnormal operation confidence score, triggering a cross-level interception protocol when the abnormal operation confidence score exceeds a dynamic threshold, and rolling back the current session state to a security baseline version. According to the invention, the accuracy and response timeliness of anomaly detection can be improved.

The invention belongs to the technical field of multi-target global dynamic production scheduling, and discloses a manufacturing resource dynamic production scheduling data comprehensive processing method, which comprises the following steps: acquiring multi-source heterogeneous data, constructing a field mapping table, constructing an equipment fingerprint database in combination with historical equipment performance data, dynamically adjusting confidence coefficient weight, and further judging an equipment state. Based on an equipment state judgment result, integrating operator report data and multi-source heterogeneous data through a preset rule base trigger event, and generating an abnormal event flow with a context tag; based on the abnormal event type and the equipment state judgment result, a recommendation scheme is constructed through a production scheduling knowledge graph, and a production scheduling instruction set is generated; according to the production scheduling instruction set, generating a local optimization scheme and a global optimization strategy, and forming a final execution scheme; calculating a resource utilization rate and a bottleneck process index through the 3D virtual workshop model, and generating a difference analysis report; according to the method, global resource scheduling and closed-loop iteration are realized, and the production efficiency and the system robustness are improved.

The invention discloses a visual detection system and method for tiny flaws of industrial products, and belongs to the technical field of product detection, multi-source image data of a target industrial product under multiple detection angles and illumination conditions are acquired, and an image information matrix is established; performing region segmentation and texture enhancement on the image, and extracting local texture direction inconsistency parameters; carrying out normalization analysis on the pixel ratio under different spectrum channels, and calculating a multispectral reflectance ratio abnormal index; constructing a deep convolution recognition model; reasoning the image by using the model, and outputting a defect judgment result and a confidence score; judging whether the area is a flaw area based on a dynamic threshold mechanism, and outputting a detection report containing flaw position information and a visual heat map; according to the method, multi-dimensional fusion identification of texture structure disturbance and spectral response abnormity is realized, the micro defect identification precision is effectively improved, and the method has high robustness, automation and engineering practicability and is suitable for high-precision quality control requirements of various industrial scenes.

The invention relates to the technical field of image recognition, in particular to an image classification system and method based on the image recognition technology, and the system comprises an image collection module which is used for obtaining original image data to be classified; the preprocessing module is used for carrying out denoising, normalization and size standardization processing on the image; the feature extraction module is used for extracting multi-level features of the image by adopting a deep convolutional neural network; the classification decision module is used for weighting fusion features based on an attention mechanism and outputting a classification result; the output module is used for displaying the classification labels and confidence scores; according to the method, the input quality is optimized by dynamically selecting a preprocessing strategy, the multi-scale representation capability is enhanced by adopting a parallel convolution path and a feature pyramid structure, the robustness of the system is improved by integrating an adversarial sample detection and defense mechanism, and the dynamic scheduling and mixing precision acceleration of computing resources are realized by introducing an edge computing optimization technology. And the operation efficiency is obviously improved on the premise of ensuring the classification precision.

A behavioral authorship verification system captures and analyzes multi-modal behavioral patterns during content creation to authenticate human authorship. The system comprises a processor executing behavioral analysis modules that generate comprehensive behavioral fingerprints distinguishing genuine human authors from AI-generated content and impostor authorship. A sentence progression mapping module detects sentence boundaries and captures intermediate composition states including additions, deletions, and modifications. A multi-modal input analysis module monitors keystroke dynamics including flight time and dwell time while detecting paste events and input method transitions. A behavioral pattern recognition engine generates user-specific baselines from historical sessions and computes deviation scores using statistical distance metrics. An anomaly correlation module aggregates behavioral deviation signals using weighted fusion algorithms to detect sophisticated mimicry attempts. An authorship scoring engine synthesizes outputs into unified confidence scores while maintaining temporal authorship chains. The system enables real-time authorship verification during content creation rather than post-hoc analysis.

The invention discloses a heterogeneous sensing early warning system based on decoupling perception and adversarial robust learning, and the system comprises a feature extraction module which processes heterogeneous sensor original data collected in real time through a multi-layer decoupling encoder, separates target related features and environment interference features, and suppresses noise pollution from the source; the multi-dimensional collaborative fusion module adopts a cross-domain adversarial robustness learning framework to carry out space-time sequence alignment and deep fusion on decoupling features to generate high-robustness joint representation, and a data missing problem is processed through a cross-modal generative feature completion mechanism; and the cognitive enhancement closed-loop decision module constructs a cognitive heuristic confidence evaluation model based on joint representation, realizes graded early warning by combining real-time quality scoring and behavior prediction, and dynamically optimizes system parameters through a feedback mechanism. According to the method, the problems of poor target detection robustness, high delay and low accuracy in a complex dynamic environment are solved, the detection precision is remarkably improved, the false alarm rate is reduced, and the all-weather adaptive capacity is enhanced.

The invention discloses an electric power field knowledge question-answering system construction method based on a large language model, and relates to the field of electric power field knowledge question-answering, and the method comprises the steps: judging the data type of electric power field knowledge, and carrying out the processing of the electric power field knowledge according to the judgment result through matching with a processing technology, and generating an entity relation triple; constructing a power field knowledge graph; optimizing the power field knowledge graph based on the attention network, outputting an answer causal path of the fault problem by using the optimized power field knowledge graph, and marking a confidence score of the answer causal path; and inputting the solution causal path and the confidence score into a language model to obtain a fault question answering result, and optimizing the question answering result according to the consistency of the fault question answering result and the power field knowledge graph. According to the method, on the premise that the fault diagnosis logic is rigorous and the result is traceable, knowledge in large-scale unstructured literatures in the power industry is activated, so that accurate question and answer services can be provided for operation and maintenance personnel in real time.

Embodiments described herein relate to systems and methods for automatically generating content for a generative content interface of a collaboration platform. The system may perform an intent analysis on a natural language user input to the generative content interface to determine an intent confidence score with respect to each of a set of request classifiers, the set of request classifiers comprising a first request classifier associated with a request for an action, a second request classifier associated with a request for information, and a third request classifier associated with a request for a contact. Based on the intent confidence scores of the request classifiers, the system may select a content store in which to search for content to satisfy a user's query.

The invention discloses a speech recognition and natural language processing integration method and system, and the method comprises the steps: carrying out the multi-modal data fusion according to a speech signal of a user, context text information and environment sensor data, and obtaining a fused multi-modal feature vector; inputting the multi-modal feature vector into a speech recognition model based on an adaptive deep neural network, and performing speech-to-text processing to obtain text output; inputting the text output into a semantic analysis model based on a graph neural network, and performing context semantic analysis and user intention recognition to obtain semantic representation of the user intention and a confidence score of the semantic representation; and according to the semantic representation and the confidence score thereof, dynamically adjusting parameters of the speech recognition model and the semantic analysis model by using a feedback optimization technology based on reinforcement learning, and generating a model optimization strategy. According to the embodiment of the invention, the accuracy of speech recognition and the semantic comprehension capability of natural language processing can be improved.

The invention relates to a traffic signal lamp fault diagnosis method and system based on artificial intelligence, and the method comprises the steps: obtaining hardware sensor data, visual monitoring data and communication data of traffic signal lamps, carrying out the integrated label processing, and obtaining a label multi-source data set; performing feature extraction on the label multi-source data set to obtain a hardware state feature set, a display anomaly feature set and a communication fault feature set; performing multi-modal fusion analysis on the hardware state feature set, the display anomaly feature set and the communication fault feature set according to a preset signal fault diagnosis model to obtain a fault diagnosis result and a confidence score; and performing strategy matching on the confidence score and a preset strategy library to obtain an initial control strategy, and performing instruction optimization on the initial control strategy according to a fault diagnosis result to obtain a fault processing control strategy. According to the invention, comprehensive analysis of multi-source data can be realized, and comprehensiveness and accuracy of fault diagnosis are improved.

The invention discloses an index anomaly detection and adaptive optimization method and system based on multi-model fusion, and relates to the technical field of intelligent operation and maintenance of a power system. According to the method, a dynamic causal network diagram is constructed based on an operation data stream, wavelet coherence analysis and a Bayesian-space-time diagram structure are fused, an edge weight is updated in real time, and a propagation probability is calculated; calling a plurality of anomaly detection models in parallel, dynamically adjusting fusion weight according to the confidence score and the propagation risk coefficient, and generating a fusion anomaly score result; and for a high-risk index section, extracting time frequency characteristics and topological structure characteristics, inputting a lightweight model to generate a confidence coefficient correction factor, calculating an abnormal influence value, and driving monitoring resource adaptive allocation. According to the method and the system, the model adaptability, the anomaly detection precision and the response efficiency in a complex power scene are improved.

The invention discloses a data processing method and system based on a bidding and tendering management platform. The method comprises the following steps: obtaining a bidding and tendering data set and constructing an initial supplier set; dynamically screening the initial supplier set based on a preset qualification verification rule to generate a compliance supplier set; performing multi-dimensional semantic analysis on bidding document contents in the compliance supplier set to generate a risk assessment report; and generating a recommended supplier sequence based on the risk assessment report and the bid invitation party demand information. The method has the following advantages and effects: semantic mapping and dynamic weight distribution among data are realized; based on dynamic rules and real-time data updating, response delay caused by manual intervention is reduced; through confidence scoring, a quotation rationality model and performance matching degree calculation, a quantifiable risk assessment report is generated, and subjective deviation is reduced; and the recommendation logic is dynamically adjusted in combination with the customized demand of the bid invitation party, and the intelligent level and the result credibility of the bid invitation and tendering process are improved.

The invention discloses a visual identification method and system, and the method comprises the steps: obtaining a visible light image, infrared thermal imaging and depth point cloud data of a target scene, and generating a time-space consistent multi-modal heterogeneous feature tensor; inputting the multi-modal heterogeneous feature tensor into a spatial frequency sensing optimizer to generate a detail-enhanced optimized feature matrix; on the basis of the optimized feature matrix, adopting an adversarial generative network to synthesize a multi-scale shielding sample, and generating an identification feature vector with enhanced adversarial robustness; inputting the identification feature vector into a self-adaptive decision engine to generate an environment self-adaptive dynamic decision parameter; and constructing a multi-scale verification pyramid according to the dynamic decision parameters, fusing the confidence score of each level through a self-correction module, and outputting a final recognition result. According to the embodiment of the invention, high-robustness and high-accuracy visual identification can be realized.

The invention discloses a multi-mode instruction analysis system for a humanoid robot. Comprising a voice input module, a visual input module, a voiceprint feature extraction module, an object recognition and pose estimation module, a multi-modal alignment network based on a space-time attention mechanism, a scene semantic tree construction module, an instruction node mapping module, a confidence evaluation module and a decision module. According to the system, accurate alignment of voice and visual information is realized through a space-time attention mechanism, environment information is represented in combination with a scene semantic tree structure, and the instruction analysis accuracy is improved. And dynamically evaluating the confidence coefficient by adopting a fuzzy instruction backtracking algorithm, and if the confidence coefficient is lower than a threshold value, starting multi-round dialogue clarification to reduce misoperation. According to the method, multi-modal data are fused, the historical interaction learning ability is optimized, the understanding efficiency and interaction robustness of complex instructions are remarkably improved, the method is suitable for scenes such as family service and logistics storage, and the intelligent level of man-machine cooperation is enhanced.

The invention discloses a casting surface treatment defect detection and quality evaluation method and system, and relates to the technical field of casting quality evaluation, and the method comprises the steps: collecting the surface data of a to-be-detected casting, and carrying out the data preprocessing, and obtaining a standardized input data set and a standardized data subset; calling a corresponding analysis sub-model for each subset, outputting quality features and confidence coefficients, and summarizing the quality features and the confidence coefficients into a sub-source result; environment state information is acquired to determine sub-model weights, and weighted fusion is carried out on sub-source results to obtain an evaluation result and an overall confidence coefficient; calculating space / feature / time consistency and judging according to a combination rule; when a re-checking condition is met, obtaining a re-checking label backflow updating data set, and training an updating model and parameters; and dynamically adjusting the threshold value and the weight value according to the performance index for subsequent evaluation. According to the method, multi-source data and environment information can be fused, weight self-adaption and closed-loop updating are parallel, accuracy and stability are improved, misjudgment and missed judgment are reduced, and complex working condition adaptability and long-term reliability are enhanced.

The invention discloses a health degree evaluation system and method based on a photovoltaic string, and belongs to the technical field of photovoltaic operation and maintenance intellectualization, and the method comprises the steps: firstly collecting SCADA operation data of a plurality of strings of a photovoltaic power station, including voltage, current, assembly temperature, environment irradiance and power factors; secondly, constructing a whole-station feature reference model, and generating a state vector fusing environment and load characteristics through a nonlinear projection algorithm; aiming at the target group string, extracting a health reference track, calculating a disturbance propagation factor, and identifying a health abnormal state; when the deviation degree exceeds a threshold value, dynamically screening heterogeneous reference group strings, constructing a health score distribution model, and further calculating a confidence score and a prediction residual error; if the score is low and the residual error is unstable, determining that the string is in a sub-health or hidden fault state, and generating an intervention instruction; the method has high accuracy, strong adaptability and good interpretability, and can be widely applied to intelligent diagnosis and refined operation and maintenance management of the photovoltaic power station.

The invention provides a root cause positioning method which can be applied to the technical field of artificial intelligence. The root cause positioning method comprises the following steps: acquiring data in a configuration management database, a network topology tool, a monitoring system and a work order system to form a multi-source heterogeneous data set; performing knowledge extraction on the multi-source heterogeneous data set, extracting equipment attributes, network topological relations, fault event entities and timestamps, and storing the equipment attributes, the network topological relations, the fault event entities and the timestamps as structured knowledge; mapping real-time index data in the structured knowledge into dynamic attributes of an entity, and constructing a dynamic knowledge graph; based on a graph neural network and in combination with time sequence features, learning a time sequence dependency relationship and a propagation path between fault events in the dynamic knowledge graph; and outputting a root cause entity, a confidence score and a fault propagation path of the fault event through a causal inference algorithm in combination with the multi-dimensional evidence. The invention further provides a root cause positioning device and equipment, a storage medium and a program product.

The invention relates to the technical field of agricultural intellectualization, in particular to an artificial intelligence decision-making system for unmanned agricultural operation, which comprises an acquisition module, a construction module, a monitoring module, an AI decision-making module, a data fusion decision-making module and an execution control module which are in mutual signal connection, the semantic analysis module is used for collecting peasant household interview records and farm work log text data and carrying out semantic analysis on unstructured texts by adopting a natural language processing technology; the construction module is used for receiving the empirical feature vector and constructing a multi-dimensional associated knowledge graph by adopting a graph neural network; and the AI decision module is used for receiving the environment feature matrix, training by adopting a deep reinforcement learning model in combination with a general agricultural data set, and generating a decision scheme with a confidence score. According to the method, collaborative decision-making of regional implicit knowledge and multi-source environment data is realized by fusing a dynamic weighting mechanism of a peasant experience knowledge graph and deep reinforcement learning.

Systems, methods, and devices to detect unauthorized third-party connections within a network infrastructure, such as by analyzing network traffic data using fuzzy matching and machine learning techniques. One aspect includes receiving network traffic data comprising records of communication events involving network identifiers, determining communication relationships between network entities identified by the network identifiers, accessing entity identifiers associated with known third-party systems, and determining associations between the network identifiers and the entity identifiers using a fuzzy matching process. Other aspects include identifying communication relationships involving the third-party systems based on the associations and detecting unregistered or unknown third-party connections within the network infrastructure. Further aspects include normalizing identifiers, computing string similarity metrics, assigning confidence scores, incorporating external data sources, building network association patterns, comparing current patterns to baseline patterns to detect anomalies, and updating security policies or firewall rules in response to detected anomalies. Additional aspects are provided.

The invention discloses a multi-modal data driven general report generation method and system based on a large model, and belongs to the technical field of intelligent report generation. Firstly, texts, images and sensor data related to a report theme are obtained and subjected to standardized preprocessing; analyzing the report generation instruction, and matching and querying a task modal mapping library matching modal configuration scheme according to a task demand; quantitatively evaluating the data quality of each modal, dynamically calculating the final decision weight of each modal in combination with the basic weight, and distributing the final decision weight to a corresponding processing path to form dominant, supplementary and reference data; inputting the dominant data and the supplementary data into a multi-modal model for analysis to obtain a preliminary conclusion with confidence score, performing consistency judgment, if no conflict exists, performing fusion to form a comprehensive conclusion, and if the conflict exists, combining a quality evaluation result and an arbitration rule to complete conflict judgment; and finally, inputting the comprehensive conclusion and the reference data into a large language model to generate a report text, and outputting a complete report after typesetting and proofreading.

The invention discloses a multi-path thinking chain reasoning generation method based on fine-grained knowledge retrieval, which comprises the following steps of: performing deep semantic analysis on a user question by adopting a large language model, and extracting a relationship between entities contained in a question text to generate a triple set; the triple is dynamically divided into different confidence sets by setting high and low confidence thresholds; constructing a thinking chain framework by using a predefined path to obtain an initial reasoning path set; optimizing the initial reasoning path, and sampling an optimized reasoning path set by using Top-k scoring to obtain a reasoning path set with high semantic relevancy; dividing the reasoning path set into a plurality of reasoning path groups with complementary internal path information to obtain a plurality of candidate answers; and adopting a majority voting mechanism to select a plurality of candidate answers, and finally obtaining consistent answers. According to the method, the reasoning accuracy and interpretability can be remarkably improved, and the reliability and robustness of a final conclusion are greatly improved.

The invention discloses a method for reducing a large model illusion problem based on an RAG technology, and the method comprises the steps: extracting semantic entities, relation phrases and context features in a natural language query, and constructing a multi-source heterogeneous hypergraph; fusing the graph structure and sequence context information by using a graph attention network and a sequence perception network to form unified semantic representation; evaluating the illusion risk based on the confidence score, the evidence coverage rate and the semantic deviation index, and triggering reverse retrieval and fusion reinforcement; and the content is generated through causal consistency discrimination feedback control. According to the method, the illusion phenomenon of the generation result is remarkably reduced, and the method is widely applied to the field of intelligent question answering and information retrieval.

The embodiment of the invention relates to the technical field of artificial intelligence, in particular to a waste incineration large model domain knowledge self-adaptive extraction method and system based on dynamic confidence evaluation, and the method comprises the steps: carrying out the dynamic word segmentation of preprocessed text data, and obtaining a dynamic word segmentation result; performing domain term confidence analysis according to a dynamic word segmentation result to obtain a dynamic term confidence score; generating a candidate domain term set based on the dynamic term confidence score; screening the candidate domain term set according to a confidence score threshold, and constructing a waste incineration domain knowledge dictionary according to a screening result; the waste incineration domain knowledge dictionary is merged into a preset large model bottom layer dictionary, and a merged knowledge dictionary is obtained; analyzing the target working condition document based on an AI algorithm model corresponding to the merged knowledge dictionary, and generating an operation instruction question and answer pair; and performing parameter fine adjustment on the AI algorithm model by adopting the operation instruction question and answer to obtain a target algorithm model.

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.