511 results about "Natural language understanding" patented technology

A real-time system for the multimodal generation of virtual reality scenes based on artificial intelligence for the creation of immersive three-dimensional environments from natural language narratives, consisting of: a speech capture module configured to continuously record a user's spoken narrative via one or more directional microphones, preprocesses the captured signal by noise reduction and temporal alignment, and outputs a digital speech stream; A speech-to-text processing unit that is operationally coupled to the speech capture module and configured for real-time speech recognition using a continuous neural transformer model. The unit is trained to transcribe natural language utterances into structured text data while maintaining contextual continuity throughout the evolving narrative. a semantic interpretation processing unit that is communicatively linked to the speech recognition unit and configured to perform natural language understanding techniques to extract contextual entities, spatial references, temporal relationships, and object attributes from the transcribed narrative; the engine includes a large language model that is fine-tuned for spatial reasoning tasks; a scene graph generation module configured to transform the interpreted semantic data into a structured, hierarchical representation that defines nodes for identified entities and edges for corresponding relationships, with each node associated with metadata describing geometry, position, orientation, texture, and linking attributes between objects; a multimodal image-language model processor coupled with the scene graph generation module, wherein the processor is configured to retrieve, adapt, or synthesize appropriate three-dimensional elements from a pre-trained visual-lexical embedding space and align these elements with their semantic and spatial definitions derived from the scene graph; a scene assembly and rendering controller configured to create a cohesive virtual scene from the aligned assets, perform real-time rendering using a GPU-accelerated ray tracing pipeline, and produce a stereoscopic visual output that corresponds to the evolving narrative; A head-mounted virtual reality visualization device connected to the rendering engine and configured to display the generated immersive environment to the user in real time. The device features motion sensors and inside-out tracking cameras to detect head and body movements, dynamically updating viewing angles and perspective within the rendered scene; and a bidirectional feedback module integrated into the head-mounted device and connected to the semantic interpretation processing unit; the module is configured to interpret corrective commands, gestures, or supplementary comments from the user to refine or modify specific scene elements without interrupting the real-time visualization; The system continuously updates the virtual scene as the narrative develops, ensuring temporal synchronization between speech input and rendered output below a defined latency threshold, thus enabling a natural, dialogic construction of complex three-dimensional virtual environments.

The invention relates to the technical field of artificial intelligence and Internet of Things, and discloses an AI interaction intelligent module based on a hybrid architecture, comprising a user interaction unit which supports voice, text and image multi-modal input and integrates intention recognition and context understanding algorithms; the data processing unit is used for carrying out structured processing on the electric appliance specification and the historical fault data and constructing a dynamically updated knowledge graph; the hybrid architecture core unit comprises a deep learning subunit for realizing natural language understanding and generation based on a Transform model, and a knowledge reasoning subunit; a fault diagnosis unit; and a feedback optimization unit. According to the method, seamless cooperation of deep learning and symbol logic is realized through a dynamic routing strategy, a high-confidence-coefficient scene generates a response through a Transform model, a medium-confidence-coefficient scene calls a knowledge graph rule for verification, and a low-confidence-coefficient scene supplements information through multiple rounds of interaction, so that the effect of improving balance efficiency and safety is achieved.

The invention discloses a multi-modal natural language understanding and generating system and method. The method comprises the following steps: constructing a cross-modal pre-training module, training a multi-modal encoder, and establishing a cross-modal association mapping space; mixing prompt fine tuning is carried out, and a complete blank filling template is constructed; according to the intention reasoning network, extracting multi-round dialogue intention representation of the user, and retrieving an external knowledge base for fine-grained reasoning; constructing a unified semantic representation framework, embedding the text, the image and the voice into a unified space, and generating a query vector of multi-modal intention perception; and the knowledge query module based on key value memory generates entity-level multi-modal replies and optimizes the semantic comprehension and generation capability of the dialogue model. According to the method, the multi-modal information understanding and generating capacity is improved, deep association and understanding of image and text information are achieved, downstream task adaptability is enhanced, task completion accuracy and efficiency are improved, unified semantic representation of the multi-modal information is achieved, and support is provided for information retrieval and utilization.

Aiming at the problems of insufficient language understanding depth, weak personalized dialogue generation ability, lack of continuous learning and long-term user state modeling and the like in the current emotion recognition and psychological intervention technology, the invention provides a user emotion recognition and psychological intervention method combined with a large language model (LLM). According to the method, the potential emotional state is identified by analyzing free text information input by a user by utilizing the powerful capabilities of a large language model in the aspects of natural language understanding, emotional modeling and text generation; constructing a multi-round dialogue context, and reasoning a psychological change trend of the user; in combination with a psychological knowledge base, personalized and mild psychological intervention dialogue content with a dredging effect is generated. The system supports recognition and classification of various emotional states such as depression, anxiety and alonity, is suitable for various interaction scenes (such as APPs, webpages and social robots), and can greatly improve the precision of emotion recognition and the timeliness and effectiveness of psychological intervention. The emotion recognition and psychological intervention method based on the large language model provides solid technical support for constructing an intelligent, continuous and personalized psychological health management system, and has wide application prospects and profound social significance.

A system for improving employee engagement and automating the integration of business processes. The system includes: a user interaction module configured to receive multimodal inputs, including natural language text and voice requests from employees via enterprise portals, mobile applications, voice-activated devices, and collaboration platforms, and to generate real-time responses via conversational output channels; a context processor that is operationally coupled with the user interaction module, wherein the context processor stores the interaction history, employee preferences, organizational role metadata, and task results in both short-term and long-term memory and dynamically derives context for controlling responses and initiating workflows; A natural language and intent processor that is communicatively linked to the context processor. The intent engine consists of large language models trained on company-specific lexicons to perform intent detection, entity extraction, ambiguity resolution, and sentiment or urgency classification from employee queries; a workflow orchestration layer in communication with the intent engine and the context processor, wherein the workflow orchestration layer includes a rule-based and AI-powered process execution engine configured to automatically initiate, route, and complete cross-functional business tasks, including approvals, escalations, and compliance checks, with workflows defined using modular templates that include conditional logic and time-based triggers; Webhooks and authentication protocols provide secure interoperability between the workflow orchestration layer and external enterprise platforms; a feedback and learning module that is operationally coupled with the workflow orchestration layer and the natural language understanding engine, wherein the feedback and learning module is configured to analyze task completion rates, response accuracy, latency metrics, and user feedback signals, and to retrain underlying language and workflow models for adaptive improvement in real time; and an administration console with role-based access controls, compliance dashboards, audit trails and interfaces for workflow configuration, whereby the administration console enables authorized personnel to monitor system operations, adjust interaction rules and enforce data protection restrictions across departments.

The invention relates to the technical field of artificial intelligence large language models, and discloses a data attribution analysis task processing method, system and device based on a large language model and a storage medium. The data attribution analysis task processing method is applied to data attribution equipment and specifically comprises the following steps that S101, user input is received through a multi-mode input interface, and the user input comprises natural language problems, structured data files or API data streams; by means of the natural language understanding ability of the large language model, the system can directly analyze service problems put forward by a user in a daily term, professional data query languages are not needed, non-technical personnel can conveniently use the system, the data retrieval time is shortened to be within 3 minutes from 30 minutes on average through the automatic SQL query generation technology, the efficiency is improved by 10 times, and the method is suitable for large-scale popularization and application. The system can intelligently identify the database fields corresponding to the business indexes and generate optimized query statements.

Techniques are described for identifying functionalities (i.e., user experiences) that are requested by users but are not supported by natural understanding (NU) processing. Some embodiments may involve identifying functionalities by transforming user inputs to functionality-based representations. The functionality-based representations may be grouped into individual functionalities. The user inputs associated with an individual functionality may be evaluated using an NU component to determine whether the functionality is supported. These techniques may enable discovery at a functionality level, rather than at a user input level, an intent level, or an entity level. These techniques may also be used to group user inputs to determine trending functionalities.

Embodiments of the present invention provide computer-implemented methods, computer program product, and computer systems. One or more processors analyze user prompts using one or more natural language understanding techniques. One or more processors then enrich the user prompts by integrating contextual data from user interaction history and adapt the enriched user prompts to align with characteristics of Large Language Models (LLMs) and Application Programming Interfaces (API) requirements of the LLMs.

The invention discloses a customer service robot system integrating knowledge base question and answer retrieval and work order processing, which comprises a natural language understanding and generating module, a knowledge retrieval module, a business system integration module, a dialogue management and decision module and a cue word management module, and relates to the technical field of artificial intelligence. Through cooperation of a large language model and a dialogue management module, the system realizes multiple rounds of deep understanding of a natural language, and can actively guide a user to clarify a demand, such as gradually inquiring an equipment model and fault details during repair, memorizing a dialogue context and avoiding information omission. Compared with traditional regular customer service, the method has the advantages that the accuracy of understanding complex problems is remarkably improved, open dialogue scenes such as technical consultation and fault diagnosis are supported, user interaction experience is closer to manual service seats, and the problems that multi-round dialogue understanding is limited, progress data cannot be obtained in real time, multiple knowledge bases are fused, and the automation degree of the business process is low are solved.

Techniques for processing with respect to a user input as contextual information is available are described. A system generates a first task prediction using first context data that is available when a user input is received. The system generates a second task prediction (e.g., updated first task prediction) when second context data is received, and then further generates a third task prediction when third context data is received. Example first context data may include device type information, time information, location, etc. Example second context data may include automatic speech recognition (ASR) data. Example third context data may include natural language understanding (NLU) data. Using the third task prediction, the system generates an output responsive to the user input.

The invention discloses a root cause analysis method and device based on a large language model, equipment and a medium. The method comprises the steps that a target entity and a topological relation are extracted in response to a root cause analysis request; searching matched historical root cause cases in a vector database, inputting the topological relation, the historical root cause cases and cue words into a large language model to generate a doubtful point list, and extracting downstream entities in the doubtful point list; calling a detection tool to collect entity diagnosis data and identify abnormal downstream entities; returning to execute the operation of retrieving the historical root cause case until a preset iteration ending condition is met; and inputting the final doubtful point list, the abnormal diagnosis data, the topological relation and the historical root cause case into the large language model again to obtain a root cause reasoning result and generate a root cause report. According to the embodiment of the invention, through the full-chain design of natural language understanding, topological constraint, historical cases, dynamic detection and iterative reasoning, the fault positioning efficiency and the root cause accuracy are improved, and the operation and maintenance labor cost and the service fault time consumption are remarkably reduced.

In some embodiments, a natural language understanding (NLU) hypothesis may be determined for a natural language input to a device and a first component may be used to obtain first visual content corresponding to a first skill associated with the first NLU hypothesis. A second component may also be used to obtain second visual content corresponding to a second skill. The device may be caused to output a first graphical user interface (GUI) element including the first visual content and a second GUI element including the second visual content. In response to a subsequent input to the device corresponding to the second GUI element, the device may be caused to output content corresponding to the second skill.

The invention provides an operation and maintenance method and device based on a large language model, electronic equipment, a storage medium and a computer program product, relates to the technical field of computers, in particular to the technical field of artificial intelligence large models, natural language understanding and operation and maintenance, and can be applied to operation and maintenance scenes. The specific implementation scheme is as follows: iteratively executing the following operations through an intelligent agent: determining a link operation and maintenance result corresponding to a completed link in an operation and maintenance task; through a large language model, according to the link operation and maintenance result corresponding to the completed link, determining a target tool for continuing to execute the operation and maintenance task from the tool set; and calling the target tool, and generating a link operation and maintenance result corresponding to the next link in the operation and maintenance task. According to the method and the device, the Agent Loop (agent loop) mode is adopted, the target tool of the next link in the operation and maintenance task is determined according to the link operation and maintenance result corresponding to the completed link in the operation and maintenance task, and the applicability of the operation and maintenance scheme in each operation and maintenance scene and the accuracy of the operation and maintenance result are improved.

The invention discloses a multi-knowledge-base scheduling routing method based on intention recognition and feedback optimization, and the method comprises the steps: S1, receiving multi-modal input from a user, carrying out the deep semantic analysis of the input content through natural language understanding and multi-modal analysis, and outputting a standardized intention label; s2, constructing a capability portrait for each knowledge base, and then generating a route matching score matrix according to a similarity relationship between the user intention tag and the capability portrait of each knowledge base; s3, screening out one or more most relevant candidate knowledge bases according to the scoring matrix and a set matching threshold value, and selecting a retrieval combination strategy to realize information recall; s4, information retrieval is executed based on the selected knowledge base, recall results and original user input are submitted to a large language model for content generation, and answers or suggestions are formed and output; and S5, user feedback collection and strategy optimization are carried out. According to the method, a more accurate, efficient and self-evolutionary knowledge base scheduling mechanism can be realized.

The invention discloses a knowledge graph generation method and system based on a large model, and the method comprises the steps: carrying out the preprocessing of data, obtaining a data set, and determining a target mode of a knowledge graph; extracting a triple conforming to the type of the target mode from the data set to obtain a candidate knowledge triple; carrying out multi-dimensional verification on the candidate knowledge triad to generate a confidence score; performing consistency verification and conflict resolution on the candidate triad set with the confidence score higher than a preset threshold value to obtain a verification candidate knowledge triad; performing entity linking and relationship standardization processing on the verification candidate knowledge triples, and mapping the verification candidate knowledge triples to a knowledge graph of a corresponding target mode to obtain standard candidate knowledge triples; and fusing the standard candidate knowledge triples into the knowledge graph database, and updating the knowledge graph database. According to the method, the powerful natural language understanding and knowledge reasoning potential of the LLM can be utilized to the maximum extent, and the inherent defects of the LLM are actively and systematically overcome by introducing an innovative mechanism.

The invention relates to the technical field of software development tools, and discloses a micro-application generation system and method based on natural language interaction, and the system comprises four core components: a natural language understanding module, a demand modeling module, a code generation engine and a deployment and integration platform. The natural language understanding module generates structured semantic representation through intention recognition, entity extraction and context analysis; the demand modeling module constructs a data model, a process logic and an interface prototype based on the semantic representation, and optimizes model parameters by utilizing reinforcement learning; the code generation engine generates a cross-platform code of the micro-service architecture through template matching and modularization assembly; and the deployment and integration platform realizes seamless integration of the external system and the Internet of Things equipment through a standardized interface. According to the method, the problems that a traditional low-code platform depends on visual dragging operation, demand analysis is rough and cross-domain adaptation is insufficient can be solved.

In one embodiment, a method includes receiving training utterances associated with a domain, receiving ontology labels for the domain, wherein the ontology labels comprise one or more of an intent or a slot, generating an inventory for the domain, wherein the inventory comprises at least a respective index and respective span for each intent or slot, wherein the respective span comprises a respective descriptive label associated with the intent or slot, and wherein the respective descriptive label comprises a natural-language description of the intent or slot, generating frames for training utterances based on the training utterances and the inventory by a natural-language understanding (NLU) model, wherein each frame comprises a structural representation of the respective training utterance, wherein the structural representation is generated based on a comparison between the corresponding training utterance and the inventory, and updating the NLU model based on the frames.

An AI-powered dispute triage and classification system (100) that includes: (a) a dispute input module configured to receive dispute inputs from multiple communication channels, including text, voice, email and chatbot interfaces; b) a Natural Language Understanding (NLU) module that uses machine learning models to extract intent, sentiment and contextual metadata from the dispute content; (c) a classification and prioritization module configured to categorize disputes into predefined taxonomies and assign priority levels based on predefined rules and AI-based predictions; (d) an intelligent routing module that routes disputes to specific human agents, automated systems or escalation paths based on classification results and organizational policies; (e) a solution assistance module configured to suggest or autonomously execute solution actions using AI-generated answers or predefined templates; and (f) a continuous learning module configured to retrain AI models using feedback data from dispute outcomes, user interactions and resolution performance, enabling automatic triage and classification of disputes in real time to optimise resolution time, accuracy and resource utilisation.

The invention relates to the field of artificial intelligence medical application, and discloses a lightweight intelligent traditional Chinese medicine inquiry system and a construction method thereof, and the system comprises a multi-dialect adaptive speech recognition module, a traditional Chinese medicine intelligent dialogue large language model module, a natural speech synthesis module, and a continuous learning mechanism module. The multi-dialect adaptive speech recognition module is used for converting dialect speech input of a patient into a standard text; the traditional Chinese medicine intelligent dialogue big language model module is the core of the system and is used for carrying out natural language understanding, dialectical reasoning and inquiry dialogue generation, and the natural speech synthesis module is used for converting a text response generated by the system into speech output; and the continuous learning mechanism module realizes continuous optimization of the large language model through incremental learning architecture and clinical feedback integration. According to the method, while the professional traditional Chinese medicine diagnosis capability is maintained, the calculation complexity is remarkably reduced, and the universality and sustainable development capability of system application are improved.

The invention discloses an automatic data modeling and optimizing system and method fusing a knowledge graph and ChatBI, and relates to the technical field of data analysis. In order to solve the problems of high interaction threshold and insufficient analysis depth of a traditional BI tool, the scheme adopted by the invention comprises a data layer which has the capabilities of multi-source data access, domain knowledge graph construction, intelligent mapping recommendation, federal calculation and data mild governance, and realizes data integration and semantic unification; the analysis layer realizes accurate conversion from a natural language to an SQL and semantic reasoning of a knowledge graph through graph vectorization, multi-model cooperation, natural language understanding, intelligent SQL generation and graph dynamic updating, and supports efficient data query and analysis; and the application layer has the functions of natural language interaction, visual recommendation and generation, root cause analysis and intelligent early warning, and provides a visual interaction interface and data display service for a user. According to the invention, intelligent data analysis and visualization based on natural language interaction can be realized.

The invention provides a battlefield environment information generation method and system based on natural language understanding, electronic equipment and a storage medium, and relates to the technical field of data processing. Enemy force deployment information and communication characteristic parameters are extracted from historical battlefield data and reconnaissance data, an association model is constructed to generate a behavior pattern library, and the behavior pattern library is used for generating battlefield environment information. Extracting communication protocol characteristic parameters from battlefield electromagnetic data, matching the communication protocol characteristic parameters with a behavior pattern library to form a communication characteristic mapping relationship, generating associated data in combination with a military strength deployment rule and the communication characteristic mapping relationship, and inputting the associated data into a strategy deduction framework to construct a strategy space of multilevel decision nodes of an enemy; a node interaction behavior is calculated in a strategy space topological structure, a decision tree is generated, decision tree semantics are reconstructed through battlefield environment feedback data, a natural language understanding model is converted into a tactical logic chain, an intelligence report is generated, and intelligent conversion from multi-source battlefield data to understandable tactical intelligence can be achieved.

The invention discloses an unauthorized vulnerability detection method, device and equipment and a readable storage medium, and is applied to the field of security detection, and the method comprises the steps: carrying out the semantic recognition of real business flow data through a large language model, and determining a to-be-detected interface; performing semantic analysis on the parameters of the to-be-detected interface by using a large language model to determine target parameters; extracting a parameter value with an unauthorized vulnerability risk in the target parameter from the historical real service flow data; generating a test effective load of the to-be-detected interface based on the target parameter and the parameter value by utilizing a large language model and a preset rule base; and performing unauthorized vulnerability detection on the to-be-detected interface by using the test payload, and determining a detection result. According to the method, the natural language understanding capability of a large language model is utilized, the limitation of traditional regularization preprocessing and effective load generation is broken through, and the method is adaptive to diversified scenes of a complex system.

The invention provides a code agent construction system, a construction method thereof and a code generation method, and relates to the technical field of computers, in particular to the technical field of artificial intelligence such as large models. According to the specific implementation scheme, the code agent construction system comprises an intelligent cooperation engine, a layered template library, a semantic understanding and layered retrieval system, a T-RAG generation and optimization system and a closed loop verification system; wherein the layered template library comprises a project-level template, a function-level template and an API-level template; the semantic understanding and hierarchical retrieval system is configured as follows: analyzing user requirements through a natural language understanding module to generate an intention vector, and sequentially executing project-level, function-level and API-level three-level progressive template retrieval; and the T-RAG generation and optimization system is configured to inject the hierarchical retrieval result into the cue word of the large language model to generate deployable codes containing front-end and rear-end logics.

The invention discloses a software process arrangement system and method based on a large model, and particularly relates to the technical field of software process arrangement. The intelligent process design module is used for realizing intelligent and low-threshold process design and optimization through natural language understanding and a visualization technology; the Agent collaborative execution module is used for dynamically distributing tasks, monitoring states and coordinating a plurality of Agents to efficiently complete process execution; and the knowledge learning enhancement module is used for constructing a domain knowledge system and providing intelligent support for process decision and optimization. According to the method, the demand described by a natural language of a user is converted into a structured process definition through the intelligent process design module, rapid design is carried out by utilizing a process pattern library and a visual editing tool, and meanwhile, compliance check and optimization suggestion are carried out, so that compliance and high efficiency of process design are ensured, and the process design efficiency is improved. And the Agent collaborative execution module dynamically allocates tasks to appropriate Agents according to process requirements, monitors the execution state in real time, and performs coordinated processing in case of abnormality to ensure efficient execution of the process.

The invention relates to a multi-robot cooperative task planning method based on a large language model, and the method comprises the steps: converting a high-level task instruction into a multi-robot executable task plan through a large language model LLM, and sequentially carrying out the task decomposition: firstly receiving the high-level task instruction through a natural language understanding module, the task is then decomposed into a plurality of sub-tasks. And skill matching: after task decomposition, the system selects appropriate robots to form a robot team according to task requirements and robot skills. And task allocation: then, the system reasonably allocates robots to each sub-task according to a task decomposition result through a task allocation processing flow. And the system executes the result through the task generation and instruction execution module. The problem of how to effectively plan and coordinate multiple robots to complete diversified tasks in a complex and dynamically changing environment is solved, accurate decomposition and efficient execution of complex tasks are achieved, and the task execution flexibility and efficiency can be remarkably improved.

The invention provides a business rule automatic processing method and system based on natural language understanding. The method comprises the following steps: extracting text content from an original document containing business rules and preprocessing the text content; utilizing a BERT-based metadata extraction model to extract structured metadata from the preprocessed text content; confirming and perfecting the structured metadata; on the basis of the confirmed metadata, a rule execution flow chart and / or a test case are / is automatically generated and used for verifying the correctness of rule logic; and according to the target format, converting the verified rule into a corresponding symbolic representation through a template engine to obtain a defined rule. According to the invention, the automatic conversion of the business rule from the natural language description to the symbolized executable form is realized, so that business personnel can directly use the natural language to define and maintain the business rule, the manual conversion cost is reduced, and the accuracy and efficiency of rule processing are improved.

Dialogue state tracking for voice assistants involves correctly tracking intent and entities of a task that a user is performing. A dialogue state, having a tracked intent and one or more tracked entities, can then be used to perform the task. Building a dialogue state tracking system within a voice assistant is not trivial. In some embodiments, a dialogue state tracking system involving one or more large language models can be implemented downstream of a natural language understanding system to produce the tracked intent and the one or more tracked entities. In some embodiments, a dialogue state tracking system involving one or more large language models can be implemented upstream of a natural language understanding system to produce rephrased natural language text, which is in turn processed by the natural language understanding system to produce the tracked intent and the one or more tracked entities.

The invention provides a method and system for constructing a Neo4j knowledge graph based on an LLM natural language, and belongs to the technical field of smart tourism and knowledge graphs. The method comprises the steps that S1, text entities are recognized, and semantics are understood; s2, analyzing an entity relationship and generating a Cypher statement; s3, extracting entity attributes and performing constraint verification; s4, constructing a Neo4j knowledge graph; and S5, performing dynamic updating and quality control. According to the method, the natural language understanding ability of the large language model and the relation modeling advantage of the Neo4j graph database are fused, so that automatic construction, dynamic updating and culture compliance verification of the tourism knowledge graph are realized.

The invention discloses an elevator intelligent operation and maintenance question-answering system based on edge computing and computing network integration. The system obtains running state data in real time through an edge data acquisition module, and performs preprocessing and dynamic sampling optimization on an edge side; the computing network fusion analysis module performs multi-dimensional comprehensive analysis on the operation state data by utilizing computing power cooperation of the edge node and the cloud node to generate an elevator health state result and a fault risk result; the knowledge graph reasoning module executes semantic association and logical reasoning in the elevator knowledge graph according to the analysis result to obtain a fault diagnosis result and a fault reason speculation result; the intelligent question and answer interaction module analyzes questions input by a user based on a natural language understanding technology, and generates question and answer responses containing running state instructions, potential risk prompts and maintenance suggestions. According to the system, a complete closed loop from data acquisition, intelligent analysis and knowledge reasoning to semantic interaction is realized, and the intelligence, real-time performance and interpretability of elevator operation and maintenance diagnosis can be remarkably improved.

The invention discloses a multi-context semantic recognition and understanding method based on a large language model. The method comprises the following steps: S1, generating a semantic unit sequence; s2, constructing a context nested vector sequence; s3, constructing context priori representation, and generating a semantic representation sequence; s4, outputting a state vector of the semantic path by adopting a gating loop unit, obtaining a matching degree score according to a feedforward neural network, and determining a deliberate map tag and an alternative intention tag; s5, slot field extraction and semantic filling are completed, and a structured semantic task unit is generated; and S6, completing semantic recognition and service response closed loop. According to the method, by introducing a prefix regulation and control mechanism and a multi-context semantic modeling structure, the accuracy of intention recognition in multiple rounds of dialogues and the consistency of the context generated in response are remarkably improved, and the method is suitable for natural language understanding scenes of multi-language intelligent customer service, cross-context man-machine interaction and complex task driving.