146 results about "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 a pre-training language model fine tuning method, an inference service system, equipment and a medium, and the method comprises the steps: obtaining an original instruction of a target field and related fields, the original instruction comprising a language understanding task; evaluating and screening the original instruction according to a multi-dimensional index, and constructing a first high-value instruction set; extracting instructions in related fields from the first high-value instruction set, and performing filtering and mobility evaluation on the extracted instructions by using a pre-training language model to obtain a second high-value instruction set; adopting a pre-training language model to perform labeling, screening and enhancement processing on the second high-value instruction set in sequence, and generating a structured training sample; and training a pre-training language model according to the structured training sample to enable the pre-training language model to adapt to the target domain. Through the method and the device, the field annotation data quantity is reduced.

The invention discloses a document auditing method and device based on cooperation of a large model and a rule engine. The method comprises the following steps: analyzing an original document to form an intermediate representation file; extracting entities from the intermediate representation file to form an entity candidate set; inputting the thinking chain cue word into the large model to obtain a first triple, a first confidence coefficient and a first risk level, and calculating a first traceable score of the large model according to the reasoning path node; performing deterministic judgment by using the rule engine to obtain a second triple, a second confidence coefficient, a risk level and a second traceable score; calculating two weighted voting values and obtaining a conflict difference value; taking a conclusion corresponding to the high-weighted voting value as a final conclusion when the conflict difference value is smaller than a preset judgment threshold value; otherwise, starting an artificial rechecking process; and generating audit reports in various formats. According to the method, the advantages of relatively high language understanding ability of a large model and relatively high certainty of a rule engine are exerted, and the problem of missed checking or excessive marking is avoided.

System and method for using knowledge fabric based on knowledge ontology, designed for deep language understanding and mechanistic causal reasoning, and meta-knowledge repository for auditable question answering. The method includes receiving an input text from a user, building a knowledge graph that represents real world facts and associations in the form of contextually tagged and weighted knowledge propositions, in multiple knowledge domains. The knowledge graph in combination with causal path knowledge and metadata describing digital sources containing answers constitutes the knowledge fabric. The method includes resolving ambiguity and determining actual intent of the user for the input text, from a plurality of interpretations of intent for sentences using the knowledge graph in conjunction with logical inference to achieve deep natural language understanding. The method includes finding / delivering response to the input request as to why / how unknown factors resulted in known outcome, or what outcomes are likely given known causal factors.

The invention belongs to the technical field of contract review, and particularly relates to an intelligent contract review analysis method and system based on a large language model. According to the method, dynamic generation of rules and a neural symbol reasoning mechanism are mainly fused, and the core is to realize automatic and precise risk identification and evaluation of contracts by utilizing the powerful language understanding and generation capability of a large language model (LLM); the method comprises the specific steps of generating a contract review rule, extracting facts from a contract to be reviewed, performing review reasoning and generating a review report. According to the method, the inherent logic preciseness of symbol deduction and the powerful semantic understanding capability of a large language model are organically combined, so that core elements and potential risks in a contract can be more accurately identified, and contract terms which are complex in expression or have hidden agreement can be effectively processed and expressed.

The invention discloses a structured information extraction system for a mental disorder electronic medical record based on a knowledge graph and a natural language, and belongs to the technical field of medical information processing. According to the system, firstly, core concepts such as diseases, symptoms and drugs are extracted from an authoritative guide to construct a mental disorder knowledge graph, and a standardized clinical knowledge base is established; then pre-training and fine-tuning the deep learning model on a large number of biomedical texts and desensitized medical records to enable the deep learning model to have a medical language understanding ability; performing preprocessing, named entity recognition and entity linking on the electronic medical record text, and mapping spoken expressions to standard medical terms; inference is carried out by utilizing a relation extraction model and combining with a knowledge graph to complement implicit clinical information; and finally, structured data output meeting the standards of FHIR and the like is generated. According to the method, through deep fusion of knowledge driving and data driving, the problems of insufficient semantic understanding and weak generalization ability of a traditional method are effectively solved, and the accuracy and clinical value of electronic medical record structured information extraction are remarkably improved.

A public opinion analysis visualization platform construction method based on sentiment analysis belongs to the technical field of natural language processing, and specifically comprises the following steps: 1, collecting related corpora and data required by sentiment analysis; 2, preprocessing comment data required by sentiment analysis; and filtering invalid texts, and performing sentence segmentation processing. 3, firstly performing text classification on the processed data, then performing sentiment analysis, judging sentiment tendency in a comment text, and finally performing visual display; and 4, performing public opinion early warning based on an obtained sentiment analysis result and a popularity data analysis result. And 5, generating an independent public opinion evaluation report and a summary report through a related API interface of the local large language model. Through the method, the public opinion response efficiency can be remarkably improved, the risk identification capability is enhanced, the complex language understanding bottleneck is broken through, and meanwhile the manual analysis cost is reduced.

The invention discloses an advertisement generation evaluation system and method based on industrial big data, and belongs to the field of advertisement evaluation.The method comprises the steps that an advertisement information understanding model is constructed, advertisement data are imported into the advertisement information understanding model to extract advertisement semantic and visual features to recognize advertisement core focuses, and a product feature analysis model is constructed; product function parameters and selling point features are extracted through product data, product keywords are recognized, an audience cognition analysis model is constructed, audience understanding ability, information processing ability and attention focus features are extracted through user data, the language understanding and cognition level of target audiences is evaluated, and an advertisement product matching model is constructed; the matching condition of advertisement content, audiences and products is evaluated through an advertisement multi-mode semantic vector, an audience cognition vector, an advertisement focus vector and a product feature vector, a matching effect evaluation model is constructed, the defects of advertisement expression complexity, focus coverage and product adaptation degree are recognized, and the advertisement creation and delivery effect is improved.

The invention discloses a story-driven role and scene image generation method. The method comprises the steps that a natural language story text input by a user is received and preprocessed; through predefined role description structure constraints, enabling the language understanding and generation model to output a structured role description information structure under template constraints; generating a role image according to the structured role description information text, and extracting image features for consistency control; establishing a mapping table of structured role description information and image feature representation, and realizing the consistency of the appearance of roles in multiple scenes; automatically disassembling the complete story text into a plurality of scene nodes, and generating structured scene description information for each scene; and generating a complete story picture in combination with the scene description information and the role reference diagram. The invention provides a story-driven role and scene image generation method, which is used for automatically generating a story text to a role image and a scene image through semantic understanding, information description structured generation and image consistency management.

The invention belongs to the technical field of automobile testing, and particularly discloses a digital twinning-based automobile instrument testing method, which comprises the following steps of: automatically generating a structured test case through a large language model, constructing a double-digital twinning architecture by relying on a high-fidelity rendering engine and a real-time simulation engine, and realizing synchronization of a virtual model and a physical instrument; multi-modal data are collected through a multi-sensor array, and defect intelligent analysis and grade judgment are completed in combination with a large language model; and test strategy self-optimization is realized through reinforcement learning based on historical test data. According to the invention, a double-engine architecture in which a high-fidelity rendering engine and a real-time simulation engine cooperatively work is adopted, and the requirements of large-scale scene and refined rendering are met at the same time. And seamless switching and data fusion between the double engines are realized through the scene transformation matrix, so that the consistency of a virtual environment and a physical entity is ensured. Meanwhile, a large language model is introduced into a test case generation and result analysis link, and natural language understanding level test script generation and anomaly analysis are achieved.

The invention discloses an Internet of Things industry intelligent customer service supervision and control system based on artificial intelligence, and belongs to the technical field of customer service supervision. Comprising an omni-channel intelligent access and intention understanding module, an AI intelligent center and complex decision module, an intelligent supervision and ethical regulation and control module, a man-machine cooperation and humanistic care module, a data-driven optimization and edge intelligent module and a security privacy and controllable treatment module, and the omni-channel intelligent access and intention understanding module is used for integrating multiple channels. Unified request distribution is achieved, data input by a user are analyzed through voice recognition, NLU natural language understanding and image recognition technologies, composite intentions are accurately captured, interaction strategies are dynamically adjusted in combination with device state data, user historical behaviors and real-time positions, and pacified talking skills or manual intervention are triggered through voiceprint / text emotion analysis. On the basis of realizing customer service supervision and regulation, all-channel fusion and intention accurate analysis can be realized, and ethical safety integrated design can be realized.

The invention provides a method and system for pre-training a sign language understanding framework based on semantic enhancement of skeletons, and relates to the technical field of sign language recognizing.The method comprises the steps that sign language video data and skeleton sequences and text data matched with the sign language video data are obtained; extracting a skeleton key point sequence from the sign language video data, modeling to form skeleton features, and performing word segmentation processing on a text; in a pre-training stage, skeleton features and word segmentation texts are input into a fusion network to generate bidirectional enhanced features, and global and local similarities are obtained through double-layer semantic alignment; calculating the comparison loss based on the similarity, and coordinating the weight through the balance parameter to obtain the hierarchical loss; executing the matching task and the language modeling task to obtain corresponding loss, weighting and combining the three types of loss into pre-training total loss, and adjusting parameters to complete training; and finally, part of parameters are optimized in combination with specific task types in a fine tuning stage, and enhanced understanding of sign language semantics is realized. The sign language understanding accuracy is improved.

The invention relates to the technical field of intelligent outbound calling, in particular to an intelligent outbound calling interaction method and system based on voice recognition and language understanding, and the method comprises the steps: obtaining a target outbound calling task and a verbal skill template set based on a task distribution instruction, and obtaining an initial voice signal of a user through a target number after confirming that the initial voice signal is obtained through the target number; noise reduction and feature extraction are carried out on the initial voice signal to obtain a noise reduction voice signal feature set, an automatic voice recognition unit is used for recognizing the noise reduction voice signal feature set to obtain a user voice text, and the user voice text is analyzed to obtain a user voice intention text; and matching the verbal skill template set by using the user voice intention text to obtain a target verbal skill template, performing voice synthesis on the target verbal skill template by using a voice synthesis method to obtain target verbal skill voice, obtaining user feedback voice based on the target verbal skill voice, and realizing intelligent outbound interaction based on the user feedback voice. According to the invention, intelligent interaction of the outbound task can be realized.

The invention relates to an interactive intelligent test analysis system based on a natural language. The system comprises a natural language processing and dialogue management module used for receiving and presenting natural language information, analyzing user input, identifying operation intention and extracting key parameters, an intelligent parameter recommendation and execution module used for connecting and controlling the physical test instrument according to a language understanding result, and an intelligent parameter recommendation and execution module used for importing from the instrument or a file, the working area and management module is used for storing and managing test data; the data processing and analysis engine module is used for automatically selecting and executing a data analysis algorithm according to user intention and context; the natural language processing and dialogue management module analyzes and generates a structured intention based on a pre-trained large language model and a domain knowledge base; and the intelligent parameter recommendation and execution module automatically recommends and sets optimal instrument parameters according to the structured intention based on a pre-trained large language model and a domain knowledge base. According to the invention, complex signal processing is simplified into natural dialogue interaction with experts.

The invention discloses a crop planting scheme generation method and device based on a large language model, equipment and a storage medium, and relates to the technical field of artificial intelligence, and the method comprises the steps: carrying out the natural language understanding of to-be-processed agricultural information, obtaining language understanding information, and converting the language understanding information into an information vector; constructing an agricultural knowledge graph based on the to-be-processed agricultural information; fusing the information vector and the agricultural knowledge graph to obtain a fusion result, and determining a retrieval result which corresponds to the agricultural knowledge graph and comprises a target entity and entity relationship path in the agricultural knowledge graph by utilizing a knowledge retrieval enhancement technology and based on the fusion result; determining a target context based on the retrieval result and an initial context corresponding to the large language model, and generating a crop planting scheme for the target context by using the large language model to obtain a target crop planting scheme; the target crop planting scheme comprises the explanation information corresponding to the planting suggestions, so that the efficiency of generating the crop planting scheme is improved.

The invention discloses a semantic perception kernel fuzzy test method and device based on a large language model, and the method achieves the structural and context-related semantic analysis of a system call sequence in a variation stage through the introduction of the large language model with the language understanding and code modeling capabilities. And a variation strategy with logic consistency and attack potential is dynamically generated, so that the effectiveness and diversity of fuzzy test input are greatly improved. Specifically, semantic modeling and structured understanding are performed on a system call sequence by using a large language model, a variation strategy instruction with context relevance and execution reasonability is generated, and fuzzy test path exploration is continuously optimized through a dynamic feedback mechanism. The defects of a traditional fuzzy test method in variation efficiency, coverage depth and complex state adaptation are effectively overcome, and a more intelligent, self-adaptive and efficient vulnerability detection and security guarantee solution is provided for an operating system kernel.

The invention discloses a geospatial data geometric topological relation evaluation method and system based on a large language model, and belongs to the technical field of spatio-temporal information processing, and the method comprises the following steps: S1, data preprocessing and model construction: processing a training data set containing geospatial data and a corresponding geometric topological relation thereof, and constructing a model; the geometric topological relation of the geographic space data is coded into text or vector representation which can be understood by a large language model; the coded training data is utilized to finely adjust a pre-trained large language model, so that the pre-trained large language model can evaluate a topological relation according to input geographic space data description; s2, geographic space data input and feature extraction; and S3, large language model reasoning and topological relation evaluation. According to the method, by combining the language understanding ability of the large model and the spatial topology calculation technology, intelligent and high-precision evaluation of the geographic spatial data geometrical relationship is achieved, and a brand-new and self-adaptive evaluation technology is provided for the field of geographic spatial data processing.

Disclosed are a system and a method of generating an image based on speech recognition. The system of generating an image based on speech recognition includes: a speech recognition apparatus configured to acquire speech information of a user, and convert the acquired speech information into text type user requirement information; a language understanding apparatus electrically connected to the speech recognition apparatus, and configured to analyze the text type user requirement information and extract semantic information of the user; a cloud image generation apparatus connected to be communicable with the language understanding apparatus, and configured to generate image data based on the extracted semantic information of the user by using a stability diffusion algorithm; and a display apparatus connected to be communicable with the cloud image generation apparatus, and configured to receive an image generated from the cloud image generation apparatus, and decode and display the received image.

The invention discloses a multi-modal clinical scientific research data processing method and system based on neural symbol hybrid reasoning, and belongs to the field of medical informatization and artificial intelligence. The method comprises the steps of receiving a natural language analysis instruction; analyzing the instruction into a structured formal problem description data object through a language understanding unit by utilizing a nerve-symbol hybrid inference engine, and selecting a data analysis algorithm according to an expert rule base through a symbol inference unit; then, generating a directed acyclic graph analysis flow based on the selected algorithm; and finally, according to the directed acyclic graph analysis flow, processing the multi-modal clinical scientific research data stored in the database, and generating an analysis report containing quantitative indexes. The technical problems that in the prior art, a clinical scientific research data analysis process is split, efficiency is low, and a semantic gap exists in man-machine interaction are solved, automation and intelligence of scientific research analysis are achieved, and the efficiency, depth and scientificity of data processing are remarkably improved.

The invention provides a question reply method and device and electronic equipment, and relates to the technical field of artificial intelligence such as human-computer interaction, natural language understanding, large models and light weight. The method comprises the steps of obtaining a to-be-processed question input by a user in a current session; a plurality of alternative models associated with the to-be-processed problem are utilized to process the to-be-processed problem in parallel to obtain a plurality of candidate replies, the alternative models comprise at least one first-class model and at least one second-class model, and the parameter scale and / or single call cost of the first-class model are / is lower than that of the second-class model; determining a target model in the plurality of alternative models according to behavior information of the user for the plurality of candidate replies; and during the duration of the current session, generating corresponding reply contents for the input subsequent questions by using the target model. According to the method, the target model conforming to user preferences can be rapidly and clearly determined by simultaneously presenting the behavior information of the multiple candidate replies to the multiple alternative models by the user, and the interaction turns and the clarification cost are reduced.

Systems and methods for using agents are provided. A first message is received from a user to engage with a corresponding session of an automated content logic. The automated content logic is configured to facilitate electronic communication between with the user and a plurality of agents associated with the automated content logic. The first message is applied as an input to a first set of agents to receive a corresponding output for each respective agent in the first set of agents. Each corresponding output identifies an action performed by the automated content logic responsive to the first message that best matches with the first message. The corresponding output for each respective agent in the first set of agents is used to identify a first action. A process is performed in accordance with the first action to generate a second message to engage with the corresponding session.

The invention provides a large language model staged pre-training method and system. The method comprises the following steps: training a Transform model by using a basic data set, optimizing a negative logarithm likelihood target, and adopting an AdamW optimizer and a cosine attenuation learning rate; continuing training by using the universal knowledge data set based on the first-stage parameters; and weighting the professional data in the training field by adopting an oversampling strategy. By structuring a training target and a data type, the model can efficiently learn language basis, general knowledge and professional skills in stages. Experiments show that according to the method, the training efficiency of the model in the basic stage is improved by 40%, the overall training time is shortened by 30%, and meanwhile the accuracy rate of tasks in the professional field is 15%-20% higher than that of traditional end-to-end training. Finally, model parameters are evaluated through professional ability, and both universal language understanding and domain specialty are achieved.

The application provides a noise identification method and device, electronic equipment and a readable storage medium. In the process of broadcasting the first reply content of the first consultation dialogue proposed by a user, the first consultation dialogue is identified as noise according to a noise identification model. In the case that the first consultation dialogue is not noise, in response to a second consultation dialogue proposed by the user, a natural language understanding model is used to determine the dialogue intention of the second consultation dialogue, the possibility score of the second consultation dialogue having the dialogue intention and / or the second entity information carried by the second consultation dialogue. Whether the second consultation dialogue is a noise dialogue is determined according to the possibility score, the intention type of the dialogue intention and / or the second entity information. If yes, the second consultation dialogue is ignored, and the first reply content is continued to be broadcast. In this way, the voice interaction process between the user and the artificial intelligence dialogue robot can be avoided from being interrupted by the noise dialogue, the business handling efficiency is improved, and the business handling time is reduced.

This invention belongs to the technical field of natural language processing and dialogue systems. It discloses a multi-target dialogue recommendation method based on hierarchical prompt optimization, including hierarchical target label modeling, learnable prompt embedding initialization, graph attention enhancement mechanism, multi-task learning framework, and response generation model. Hierarchical target label modeling encodes the hierarchical relationships between target labels into a graph structure. Learnable prompt embedding initialization integrates label semantics and deep hierarchical information into the encoder input space. The graph attention enhancement mechanism enhances the label vector structure perception ability through information transmission and aggregation between label prompts. The multi-task learning framework jointly optimizes masked language modeling and hierarchical multi-label classification. The response generation model uses the predicted target as a control signal to guide generation. This method effectively models the hierarchical dependency relationship between target types and target entities, enhances the structure perception ability of label vectors, maintains the model's language understanding ability, and improves the accuracy of target prediction.

A system and method for an artificially intelligent (AI) platform comprising a Knowledge Net (KN) Platform for automatically creating accessible, transparent knowledge stores which reflect a complete spectrum of semantic relationships between concepts. The system comprises a knowledge discovery engine that creates a machine representation of the semantic knowledge graph of a concept, namely a Concept Semantic Knowledge Graph (CSKG), for explainable, human-analogous understanding of natural language data for the full range of automated natural language understanding tasks—wherein the knowledge discovery engine, in discovering the related concepts, uses a variety of linguistic learning methods.

The application discloses a consumer complaint response method and system based on AI assistance and language understanding, which splits the complaint response process into two core sub-problems of multi-modal consumer complaint data processing and feature fusion and demand attribution and response generation. In multi-modal consumer complaint data processing and feature fusion, first, regular expressions are used to denoise text, spectral subtraction is used to denoise voice, and Gaussian filtering and adaptive histogram equalization are used to denoise images; then, modal features are extracted, text is used as the core of cross-modal fusion, and entity and relationship are extracted to construct a multi-modal semantic knowledge graph. In demand attribution and response generation, Graph Transformer is used in combination with the graph and domain prior knowledge to output primary and secondary demands; a static complaint graph is constructed, an attribution path is mined through BFS and is verified through multi-modal verification; and an "emotion-demand-attribution-prevention" structure is used to optimize text and adjust the format by using LLM, and an individualized complaint response is output.

The invention discloses an NL2SQL-based power intrinsic safety question-answering system construction method, system and device and a medium, and belongs to the technical field of power safety. The method comprises the following steps: collecting fine tuning data and constructing a fine tuning data set; performing low-rank adaptive fine tuning on a pre-trained large language model through the fine tuning data set to obtain a fine tuning large language model, and triggering an annealing strategy for optimization; building prompts through the fine-tuning large language model in combination with user questions and database structure information; and generating a structured query language statement based on the prompt, querying a database to obtain a query result, and adjusting the prompt according to the query result to process an error. According to the method, low-rank fine tuning in the field of electric power intrinsic safety is carried out on a general pre-training large model by introducing the LoRA technology, so that the model has general language understanding ability and industry exclusive knowledge at the same time, and the problem that a traditional model is high in universality but low in specialty is solved.

The invention discloses an autism spectrum disorder language rehabilitation training device with interaction ability, which comprises a data processor, loudspeaker modules symmetrically distributed on two sides of an image display screen arranged on the outer wall of the data processor and used for playing audios, and microphone modules arranged below the loudspeaker modules and used for collecting external voice information; a storage box is arranged below the microphone module and used for installing keys. A monitoring probe, a liquid storage tank and a snack box are arranged at the top of the data processor. According to the device, the language understanding and language expression ability of children can be improved through voice, picture and video communication strategies of different levels, forms and scenes, man-machine back-and-forth dialogue training and a way for providing guardians or doctors to remotely observe the states of the children and interactively communicate with the children; and on the basis of language training, the capabilities of concentration, hand-eye coordination, music perception and execution and the like of the children can be further improved, the mood of the children is relaxed, and the learning interest of the children is improved by performing real-time positive feedback on training items of the children.