817 results about "Graph recognition" patented technology

The invention discloses a dynamic intention recognition and GraphRAG fusion method and system for open domain questions and answers, and relates to the technical field of intelligent and natural language processing. The method comprises the following steps: constructing and dynamically updating a heterogeneous knowledge graph; performing dual-stage intention recognition on user query; subtasks are disassembled based on an intention result, and cooperative execution is carried out through multiple agents; service standardization integration is realized by means of a model context protocol; and closed-loop optimization is carried out in combination with user feedback. The system comprises an image knowledge base, an intention recognition module, an agent collaboration module, an MCP service integration module and a feedback optimization module. The system is a novel open domain question-answering system integrating structured knowledge modeling, dynamic intention understanding, intelligent collaborative reasoning and standardized service interaction, and through fusion of structured knowledge modeling and intelligent collaborative reasoning, question-answering accuracy and complex intention understanding ability are improved, system adaptability and efficiency are enhanced, multi-system collaboration is promoted, and the system has a wide application prospect. The method is suitable for scenes such as knowledge services and intelligent assistants.

The invention discloses a large-model real-time voice text intention recognition method and system based on text prediction, and the method comprises the steps: obtaining the real-time voice data of a user, carrying out the real-time voice recognition processing through a streaming voice recognition interface, and obtaining a part of transcriptional text; inputting the partial transcription text into a mask language model for text prediction, and generating a plurality of high-credibility complete sentence candidates; based on the complete sentence candidates, the complete sentence candidates are input into a large language model in parallel for intention recognition, a corresponding intention result is obtained, and a mapping relation between the candidate sentences and the intention recognition result is established; and obtaining a sentence completely expressed by the user, calculating the similarity between the complete actual sentence and a plurality of high-credibility complete sentence candidates through a multi-level text similarity algorithm, selecting the candidate sentence with the highest similarity score, and directly obtaining a corresponding final intention recognition result based on the mapping relationship. The objective of the invention is to solve the technical problem of high response delay of an existing voice intention recognition system.

The invention belongs to the field of natural language processing, particularly relates to a multi-modal document generation method and device based on multi-agent collaboration, and aims to solve the problems that an existing method is low in intention recognition accuracy, limited in retrieval range and not professional enough in content generation. The method comprises the following steps: generating a structured template; analyzing the text input by the user to identify a writing intention, and determining a target template; vectorizing each candidate resource feature to obtain a corresponding sparse vector, a dense vector and a knowledge vector, and performing semantic alignment; extracting context features of the input text, respectively performing multi-path retrieval recall, evaluating and sorting recall results, and screening out target features; and constructing a thinking chain in combination with the knowledge graph, and generating a multi-modal document according to the target template. According to the method, the outline structure can be extracted, the picture / table style can be recognized, the templates adaptive to different document types can be dynamically generated, and full-process automation from user input to document output is achieved.

A computer-implemented method for operating an artificial intelligence voice agent system includes receiving voice input through communication channels; analyzing converted text through natural language processing (NLP) pipelines implementing intent recognition and sentiment analysis detecting emotional cues using a multimodal large language model (LLM); generating response content using machine learning models trained on domain-specific corpora; converting generated responses to synthetic speech through text-to-speech (TTS) engines; integrating with a customer relationship management (CRM) platforms or an enterprise resource planning (ERP) database; and implementing continuous learning by updating language understanding models using conversation logs, voice recognition parameters based on user feedback, and response generation patterns. One implementation is a computer-implemented system and method that operates a suite of intelligent interactive devices and platforms including an artificial intelligence voice agent, enhanced communication platforms, an intimacy companion system, and augmented / virtual reality eyeglasses. Further, one implementation includes AR / VR eyeglasses that project visual content onto interchangeable lenses or directly onto the user's retina via laser-based retinal projection, provide prescription adjustments, incorporate ear-mounted sensors for monitoring physiological parameters like heart rate, oxygen saturation, and blood pressure, and utilize wireless data transmission, onboard environmental sensing, and remote calibration, all designed to offer dynamically adaptive, secure, and context-aware interactions across communication, personal assistance, health monitoring, and immersive augmented or virtual reality environments.

The invention relates to a multi-mode intention recognition method and system, and the method comprises the steps: carrying out the time domain and frequency domain enhancement of the features of text, video and audio modes, carrying out the splicing to obtain non-language mode fusion features, combining the features of an original text, modeling the time synchronization relation of audio-text and video-text, and carrying out the recognition of a multi-mode intention. Standardized audio features, video features and text features are obtained through context alignment processing; fusing the standardized features of the three modalities to obtain a fused feature vector, and mapping the fused feature vector back to the text modal space to be connected with the weighted residual error of the original text feature to obtain a fused semantic vector; extracting global semantic anchor points and mask positions from the fused semantic vector, and splicing the global semantic anchor points and the mask positions with the original text features and the fused semantic vector to obtain input features; and obtaining probability distribution of multiple intention categories by using the input features. Three types of heterogeneous modal input can be supported, and the accuracy and robustness of intention recognition are improved through fine-grained semantic supervision and enhancement strategies.

The invention relates to the field of computer vision, and particularly provides a table recognition reconstruction method and system, a terminal and a medium, and the method comprises the steps: firstly decomposing a large-size table image into a plurality of overlapped sub-images, and carrying out the table structure detection and OCR character recognition of each sub-image through parallel recognition; then, sub-graph recognition results are integrated through a coordinate mapping and confidence coefficient weighted fusion algorithm, and boundary errors are eliminated; then, automatically distinguishing common cells based on an area clustering algorithm, merging the cells and a header region, and reconstructing a complete table logic structure; further understanding header semantics through a natural language model and repairing identification errors; and finally, realizing intelligent splicing and standardized output of the cross-page table. According to the method, the memory limitation of the traditional OCR technology is broken through, an oversized table can be processed, the recognition accuracy of a complex structure is improved, and the digitization efficiency of professional documents such as financial statements and engineering drawings is improved.

The invention relates to the technical field of large model intention understanding, and discloses an APP dialogue type service reaching method and system based on large model intention understanding. The method comprises the steps of receiving a natural language text input by a user on an APP dialogue interface and performing large model semantic analysis to obtain service semantic data; inputting the business semantic data into an intention recognition model for business intention understanding to obtain business intention data; performing multi-agent cooperative process planning to obtain execution process data; carrying out interactive confirmation on the service parameters to obtain service execution parameters; transmitting the service execution parameters to corresponding service tool interfaces for calling execution to obtain a service tool calling result, and performing intelligent analysis and card rendering on the service tool calling result to obtain display card data. According to the method, the real business intention of the user is accurately understood, and the problems of execution efficiency and stability of a traditional single interface calling mode in a complex business scene are solved.

The invention relates to a power distribution network distributed energy bearing capacity assessment method and device. The method comprises the following steps: carrying out topology analysis on a network structure of a power distribution network to obtain an initial network topology model; obtaining a node dynamic feature data set based on the initial network topology model and the distributed energy access point data of the power distribution network; wherein the node dynamic characteristic data set comprises operation parameters of each node of the power distribution network in different load scenes; generating a parameter incidence matrix according to the node dynamic characteristic data set, and obtaining a bearing capacity reference model of the power distribution network according to the parameter incidence matrix and real-time data of the power distribution network in an operation state; wherein the parameter incidence matrix is used for quantifying the coupling degree between the operation parameters; and obtaining a risk distribution mapping graph according to the bearing capacity reference model, and identifying a potential overload area of the power distribution network based on the risk distribution mapping graph. According to the invention, power distribution network operation risk assessment can be accurately realized.

The invention discloses a land investigation quality monitoring system for remote sensing image intelligent segmentation and ground feature recognition, and relates to the technical field of remote sensing, and the system comprises an image recognition module, a label comparison module and a monitoring module, and specifically carries out the remote sensing image acquisition of a to-be-monitored land through a remote sensing sensor, and carries out the structural complexity analysis and image region division. The method comprises the steps of forming a non-uniform region set, analyzing and acquiring category probability vectors of pixel positions of all regions in the formed non-uniform region set to construct a tag map of a whole remote sensing image, comparing pixel-by-pixel categories on a current tag map and a reference tag map to form a change mask map, identifying a structural change region according to the change mask map, and identifying a structural change region through sequential analysis. And determining whether the corresponding candidate tag inconsistent region under different time phase conditions is still a structural change region, so as to obtain a judgment result, and updating the electronic map based on the judgment result.

The invention discloses a consultation method and system based on natural language processing and a legal knowledge graph, and relates to the field of data processing, and the method comprises the steps: receiving a multi-format legal consultation demand of a user, converting the multi-format legal consultation demand into a text, inputting the text into a BERT law NLP model, and analyzing key information through word segmentation, intention recognition and entity extraction; based on a pre-constructed multi-level legal knowledge graph, carrying out accurate and fuzzy retrieval and domain filtering in combination with an analysis result, and obtaining an associated law article, a case and a legal relationship; screening conflict law articles and similar cases, and inputting the conflict law articles and the similar cases into a graph neural network reasoning model to generate a preliminary conclusion; the conclusion is converted into a spoken consultation report through a natural language generation module, and output is customized according to a user scene; and if the user feedback satisfaction degree is less than the threshold value, iteratively optimizing the storage data to the historical library. The method has the advantages that accurate retrieval is realized based on the BERT model and the multi-level knowledge graph in the legal field, the oral personalized conclusion combined with the user scene is generated through GNN reasoning, and iterative optimization is performed through user feedback.

The invention relates to a multi-mode intention recognition method and system based on consistency and difference decoupling, and the method comprises the steps: carrying out the consistency modeling and difference modeling of the features of text, video and audio modes, and enabling the consistency modeling to be used for extracting common information expressing similar meanings in each mode; the difference modeling is used for retaining information which is unique in each mode but possibly has important supplementary value; by constructing a shared-private feature space, carrying out explicit modeling on common information in the consistency features and specific information in the difference features, and fusing the consistency features and the difference features; and based on the fused feature representation, judging the real intention of the user through a classifier, and outputting a result. Through consistency and difference collaborative modeling, in combination with a shared-private feature space, semantic consistency and difference among all modalities are explicitly modeled, and the accuracy and robustness of intention recognition are fundamentally improved.

The invention discloses a micro-grid dynamic collaborative scheduling method based on multi-modal reinforcement learning, and relates to the technical field of micro-grid control, and the method comprises the steps: constructing a multi-modal state space of a micro-grid, designing a layered reward function, and dynamically adjusting the reward weight of each layer of the layered reward function through employing a self-adaptive weight algorithm; dynamically identifying a node connection relationship by using a graph neural network, constructing a microgrid node connection graph to identify an operation mode of the microgrid, updating the node connection relationship in real time, and optimizing a distributed power supply output distribution strategy of the microgrid based on an attention mechanism of the graph neural network; and updating the overall model of the micro-grid by using a cloud edge coordination mechanism. According to the invention, the capability of coping with uncertainty of the micro-grid can be enhanced, and the intelligent operation level of the micro-grid is improved.

The invention provides an engineering drawing intelligent processing system based on a ComfyUI, and the system comprises an algorithm service module which integrates a plurality of drawing processing algorithm assemblies, such as drawing layout analysis, OCR recognition, drawing direction detection, semantic understanding, drawing frame disassembly, and axis net recognition, and provides services for the outside through a standardized interface; the workflow arrangement module is used for packaging the algorithm components into parameterized drawing processing nodes based on a visual node configuration framework of a ComfyUI, and supporting flexible combination, real-time preview and batch execution of drawing processing flows; and the workflow management module is used for importing, analyzing and publishing the workflow configuration file in the ComfyUI format, and realizing metadata management, publishing verification, API document generation, interface registration and call authority control of the workflow. The method supports multi-type input of PDF and CAD drawings, is suitable for engineering drawing processing tasks such as drawing label extraction, sub-drawing recognition, drawing frame segmentation and drawing filing, and is high in intelligent degree, flexible in process configuration, easy to integrate and high in expansibility.

The invention discloses a behavior-driven twinborn prediction method, and relates to the technical field of intelligent information processing and prediction modeling, and the method comprises the following steps: building a unified event time baseline, collecting nanosecond clock offset information of each data source, building a cross time sequence suspicion chart, recognizing time synchronization abnormal nodes, and forming a credible time anchor point set; and based on the trusted time anchor point set, executing anti-fact playback, reconstructing a historical evolution process of behavior data, generating a time offset vector set, and constructing a corresponding time sequence offset spectrum. According to the method, through construction of a unified time baseline, trusted anchor points, anti-fact replay, causal topology and time reversal control, time sequence dislocation identification, calibration and false trajectory elimination of multi-source behavior data are realized, a dynamic self-healing closed-loop prediction mechanism is established, and the twin system prediction accuracy and stability are improved.

The invention discloses a network card data local preprocessing system fused with edge computing, and relates to the technical field of edge computing and artificial intelligence collaborative optimization. Comprising an edge computing unit, a hierarchical collaborative architecture, a model hot switching and generative fragmentation module, an intention recognition and adaptive scheduling module, a delay energy consumption optimization scheduling module, a CXL zero-copy sharing module, an edge computing unit integrated processor, an FPGA or ASIC and a neuromorphic computing unit. According to the method, an FPGA, an ASIC and a neuromorphic computing unit are integrated in an intelligent network card, microsecond-level dynamic connection reconfiguration and adaptive generative model fragmentation execution are realized through a reconfigurable Mesh interconnection matrix, an attention layer and a feed-forward layer of a Transform class model are fragmented and allocated to different computing units for parallel execution, and cross-card streamlined processing is realized in cooperation with a zero-copy shared memory. And the intention recognition module is deeply coupled with the model hot switching module, so that dynamic model switching and fragmentation strategy optimization based on service priorities and system loads are realized.

The invention provides a context-based intelligent voice semantic understanding analysis method and system, and relates to the technical field of voice interaction, and the method comprises the steps: obtaining an input voice signal, extracting an acoustic feature, and decoding the acoustic feature to obtain a candidate text; constructing context semantic representation to carry out disambiguation processing; establishing a semantic dependency graph and carrying out multi-level correlation analysis; spreading context constraint information to perform multi-hop reasoning; and finally generating intention recognition and slot filling results and updating the session state. The semantic comprehension accuracy and the intelligent degree of the voice interaction system are improved by introducing the context information and the multi-level semantic dependency relationship.

A method for implementing data loss prevention (DLP) includes: generating an asset lineage map from file system metadata; identifying, based on the asset lineage map, an input feature linked to the asset, a type of the asset, and a plurality of activities linked to the asset; obtaining a sensitivity score for the asset based on the input feature and the type of the asset; obtaining, based on the plurality of activities, a malicious score and a data loss score for the asset; determining a user level of a user; and initiating implementation of a first DLP policy for the user based on the user level, the malicious score, the data loss score, and the sensitivity score.

The invention belongs to the field of traffic control, and relates to a high-risk scene-oriented risk, dynamics and intention collaborative trajectory prediction method, which comprehensively utilizes an outward risk clue, vehicle dynamics characteristics and driving intention information (historical trajectory characteristics), and constructs a priori enhanced risk attention mechanism and a three-body interaction micrograph module to predict the risk, dynamics and intention collaborative trajectory of a high-risk scene. Early perception of potential risks is realized; meanwhile, a multi-scale dynamic time sequence encoder is adopted to capture the dynamic change of the vehicle from short-term disturbance to long-term behavior trend; an explicit intention recognition auxiliary task is introduced, and semantic constraint and optimization are carried out on the multi-modal trajectory; through collaborative modeling of the modules, the trajectory prediction precision and robustness of the automatic driving system under complex high-risk situations such as sudden cut-in and sudden brake can be remarkably improved, more reliable prior support is provided for a subsequent decision and control module, and therefore the driving safety of a vehicle in a complex traffic environment is effectively improved.

The invention relates to the technical field of artificial intelligence, can be applied to business scenes such as financial science and technology and medical health, and discloses a root cause analysis method and device based on a space-time dependency graph, equipment and a medium. Comprising the steps of constructing a space-time dependency graph, generating a diagnosis path blueprint, identifying a fault source and a root cause entity type, generating a graph query statement, executing query and performing cause and effect verification, and outputting a root cause analysis report. And the causal reasoning and root cause positioning of the system state change are realized by fusing the graph structure information and the natural language processing capability. Through cooperative processing of a language model and a graph data structure, fault symptom information and system structured state data are deeply fused, a path is generated in the graph structure, and a causal relationship is verified, so that the ability of understanding a complex system state evolution chain is improved, and accurate identification and diagnosis of root causes are realized. And the accuracy and the automation level of root cause analysis are obviously enhanced.

The invention discloses a mine earthquake intelligent identification method based on multi-mode deep learning and signal processing, and belongs to the technical field of mine earthquake identification. Aiming at the problems that a traditional mine earthquake signal processing method cannot fully utilize spatial relevance and frequency domain characteristics of signals in a sensor network, the automation level is relatively low, the response speed is slow, and the emergency processing effect is influenced, seismic waveform data and multi-modal characteristic input are adopted, so that the emergency processing effect is influenced. Based on text semantic features generated by a large language model (LLMs), frequency domain features extracted by Fourier transform and time sequence features after obspy processing, a dynamic graph recognition model of a fusion graph neural network (GNN) and Transform is constructed; graph structure edge weights are dynamically updated through cross correlation between signals, and the structure change of complex environments such as mine roadways is self-adapted.

The invention relates to the technical field of artificial intelligence, and discloses an intelligent question and answer method and device. The method comprises the following steps: processing multi-modal problem data by utilizing an intention recognition model to obtain a user intention vector; determining a task complexity level based on the intention vector; determining a target agent based on the task complexity level and the capability scores of the plurality of agents; processing the problem data of each mode by using the plurality of special intelligent agents and the target intelligent agent to obtain a processing result; determining a target fusion mode according to each processing result by using a fusion mode judgment model; and fusing the processing results by using a target fusion mode to obtain final reply data. The intelligent agents are screened based on the task complexity level, and the target intelligent agent with the capacity matched with the current task complexity is selected; and meanwhile, the target fusion mode is dynamically determined according to the processing results of the multiple agents by utilizing the fusion mode judgment model, so that the question answering efficiency and the answering accuracy can be well balanced.

The invention provides a multi-mode interaction mobile terminal intelligent office system and method, and the method comprises the steps: collecting and converting a voice signal through a voice input module, so as to obtain standardized audio data; the speech recognition and transcription module converts and preliminarily processes the standardized audio data to obtain text data; the intention recognition module analyzes a user intention and a key entity in the text data based on a natural language processing technology to obtain an intention recognition result; the cue word template module matches the intention recognition result to a cue word template to generate a structured instruction; the dialogue module sends the structured instruction to the large language model and analyzes structured response data returned by the large language model; the system docking and function execution module calls a target office system interface according to the structured response data so as to execute mail sending, schedule management, document processing or leave application operation; and the output and function implementation module converts the text of the operation result into a voice signal or directly outputs the voice signal, so that the problem of low office efficiency of the mobile terminal is solved.

This disclosure describes systems, methods, and devices related to object detection in images. A device may input an image, representing an object, to a manual labeling learner system; identify, using the system, first coordinates of an upper left corner of a bounding box representing the object based on a heatmap indicative of a probability of the first coordinates representing the upper left corner; identify, using the system, second coordinates of a bottom right corner of the bounding box based on the first coordinates and a first distance regression map indicative of coordinate differences between the second coordinates and ground truth coordinates input to the machine learning model as training data; generate, using the system, adjustments to the first coordinates and the second coordinates based on a second regression map; and generate, using the system, the adjusted first and second coordinates, the bounding box.

The invention provides a social robot intention recognition system and method based on heterogeneous graph analysis, and the method comprises the steps: carrying out the unified modeling of multi-type nodes and multiple relation edges based on a heterogeneous graph structure, and systematically capturing the complex multi-dimensional behavior association in a social platform; according to the method, technologies such as a large language model and a knowledge graph are fused, fine recognition and classification of multiple types of behavior modes are supported, and meanwhile, hierarchical evaluation for different organized risks is realized by combining account behavior aggregation and emotional polarity analysis, so that a decision basis is provided for supervision and governance; according to the method, automatic collection and preprocessing of multi-source heterogeneous data and heterogeneous graph construction processes are integrated, manual intervention and repeated work are reduced to the maximum extent, the overall data processing efficiency and response speed are improved, and the real-time analysis requirement in a complex dynamic social environment is met; transparent analysis of robot control sites and behavior strategies is supported, and the interpretability of the system, the user credibility and the executive force of policy supervision are greatly improved.

The invention provides an enterprise tax declaration data automatic verification and intelligent error correction method and system, and relates to the technical field of tax information processing, and the method comprises the steps: receiving original voucher data, constructing a voucher association diagram, recognizing an abnormal transaction chain, and generating financial accounting data; comparing the financial accounting data with the tax payment rules, identifying violation data items and distributing risk weights; and constructing a data balance constraint matrix based on the risk weight, forming a data correction cluster, and executing grouping iteration correction. According to the invention, declaration data errors can be automatically identified, intelligent correction is provided, declaration accuracy is improved, and manual intervention is reduced.

The invention relates to the technical field of user intention analysis, in particular to a user intention analysis system and method based on artificial intelligence, and the method comprises the steps: generating a single-point intention recognition result representing the current instantaneous operation of a user through multi-modal behavior data at the current moment; generating a time sequence intention chain representing continuous operation of the user according to the multi-modal behavior data at the historical moment; when an intention conflict is detected, calculating an optimal transfer path for transferring a current conflict intention node in the time sequence intention chain to a candidate target intention node according to a transfer probability weight in a pre-constructed intention transfer probability graph; and determining a resource demand corresponding to the candidate target intention node of the optimal transfer path, dynamically allocating resources to the candidate target intention node according to the current available resource state and the resource demand, and performing intention analysis. Resource allocation is dynamically optimized after intention conflicts are effectively detected and solved, and accurate understanding and efficient execution of user intentions are achieved.

The invention discloses a cross-cloud task arrangement optimization method based on multi-cloud resource scheduling, and the method comprises the steps: constructing a task topological weighted graph, and recognizing a parallelizable node set; constructing a task node preliminary scheduling feasibility table according to task topological weighted hierarchy information; constructing a granularity feature vector, and updating the task structure matrix; identifying granularity collaborative attenuation abnormal nodes, and performing cross-cloud task path repair and structure update; generating a cross-cloud scheduling time matrix based on each cloud platform resource supply capability index; predicting resource competition conflicts in combination with task execution index historical data, and generating a conflict prediction table; identifying granularity strategy deviation, and determining a repair trigger point; and generating a cross-cloud task granularity adaptive arrangement configuration file based on the repair trigger point information. According to the method, high reliability, high flexibility and high adaptability of task scheduling can be realized in a complex multi-cloud heterogeneous environment, and the stability, the resource utilization rate and the overall cooperation efficiency of cross-cloud task execution are remarkably improved.

The invention discloses an interaction control method and system for an intelligent agent and a front-end and back-end system, and the method achieves the automatic control of the intelligent agent on the front-end and back-end system through the integration of a large language model. The method comprises the following steps: an intelligent agent performs natural language intention recognition through a large language model, automatically selects a proper tool, extracts parameters required by the tool, converts the intention into a target task, generates a structured control instruction, maintains a complete session history and supports multiple rounds of dialogue interaction; the back end receives a user request, calls an intelligent agent to generate a structured instruction, transmits the structured instruction to the front end, and dynamically adjusts a subsequent instruction according to the received front end feedback; and the front end receives the instruction transmitted by the rear end, automatically identifies an instruction format through a regular expression, performs corresponding operation after parameter verification and feeds back a result. According to the method, unified control of the agent on the front-end UI and the back-end business logic is realized, complex multi-round dialogue and multi-step operation are supported, and the method has a wide application prospect.

The invention provides a system abnormity intelligent diagnosis and recovery method and system fusing time sequence logs, and relates to the field of distributed system operation and maintaining.The method comprises the steps that operation logs are collected from a plurality of service nodes of a distributed system, time sequence alignment is conducted, and calling relation and performance measurement data are extracted; time sequence change features are calculated in the sliding time window, dynamic feature vectors are generated through fusion coding, and a cross-service time sequence association graph is constructed; identifying an abnormal service node and matching the abnormal service node with historical fault data to obtain a historical propagation path and a feature vector; calculating a propagation convergence coefficient and a characteristic deviation degree based on a historical propagation path to obtain a causal intensity score; and identifying a fault influence degree according to the score, and adaptively adjusting a resource isolation and flow scheduling strategy. According to the invention, accurate diagnosis and efficient recovery of distributed system faults are realized.

The invention discloses an energy robot-oriented model training method, and relates to the technical field of energy digitization, and the method comprises the steps: synchronizing a business database to a local metadata knowledge base, and carrying out the business feature labeling of a metadata table in the metadata knowledge base according to the business logic; establishing a business problem knowledge base based on the business requirements; constructing a semantic map model of the robot based on the metadata knowledge base; generating mixed data features based on the labeled metadata knowledge base and the business problem knowledge base, and performing multi-model cooperative training of robot intention recognition, intelligent dialogue and intelligent table splicing according to the mixed data features in combination with a semantic map model; performing distributed incremental training on each model of the robot in response to the user session log, and performing model migration according to containerization to complete deployment of the robot; the intention recognition ability and data retrieval and query efficiency of the robot on the text input by the user are improved, then the question-answer response efficiency of the robot is improved, and efficient business question-answer is achieved.