39 results about "Comprehension approach" patented technology

The invention provides a semantic understanding method based on natural language processing and a science and technology operation platform system.The method comprises the steps that firstly, a target interaction data set containing a text instruction sequence, collaboration document content and resource scheduling request records in a science and technology management scene is obtained, and then cross-modal semantic alignment processing is conducted on the target interaction data set; and generating a structured semantic analysis result containing an intention decision tree and the like. Then, based on a dynamic process arrangement rule, the result is mapped to a predefined process node topological space, an initial process execution path set containing a node execution sequence chain and the like is obtained, conflict resolution is conducted on the set according to real-time system resource state data, and an optimized executable process path containing resource allocation priority and the like is generated; and finally, the optimized executable flow path is input into a science and technology management central system, automatic deployment and execution state tracking of a cross-department cooperation flow are realized, and the semantic understanding and flow processing capability of a science and technology management scene is effectively improved.

The invention relates to the technical field of voice recognition, in particular to a training method of an audio understanding model, an audio understanding method and device, a storage medium and a program product. The method comprises the following steps: obtaining a speech recognition model and a large language model; the speech recognition model comprises a coding module, a prediction module and a first fusion module; according to the coding module, the large language model main body, the first fusion module and the binary classification layer, constructing an audio text classification model; the first fusion module and the binary classification layer obtain a modal prediction result according to the acoustic features output by the coding module or the semantic features output by the large language model main body; determining a reverse gradient value of the first fusion module according to the real mode and updating parameters of the first fusion module; in response to the fact that the preset condition is met, an audio understanding model is constructed and trained according to the coding module, the large language model body and a second fusion module, and the second fusion module comprises the first fusion module. The accuracy of audio understanding can be 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.

The invention discloses a multi-agent brain signal autonomous understanding method based on large language model driving, and the method comprises the steps: constructing a hierarchical cooperation architecture comprising a central supervisor agent and a specialized sub-agent, and carrying out the autonomous understanding of a brain signal on the basis of reducing the technical threshold of brain signal analysis; the problems that a traditional normal form process is rigid and long-time-history complex tasks are difficult to process are solved. According to the method, a central supervisor agent is used for analyzing a natural language intention of a user and dynamically decomposing a task, and a specialized sub-agent is combined with a global sharing state and a context isolation mechanism to execute domain-specific full-link dynamic planning and accurate tool calling; a comprehensive analysis report with cross-domain causal logic is generated by integrating quantitative calculation results and qualitative clinical knowledge through hierarchical resource allocation and retrieval enhancement generation mechanism, then a three-layer difficulty assessment reference system is established to verify framework performance, and finally autonomy, flexibility and clinical interpretability of a brain signal understanding process are achieved.

The invention discloses a complex table semantic understanding method and device based on a large language model, and the method comprises the steps: firstly carrying out the preprocessing of a document through a table detection model and a table structure recognition model, and extracting the structure information of a table in the document; secondly, reconstructing the structure of a complex table through a large language model, and constructing two tree structures according to row and column information; and on the basis, semantic translation is performed on the reconstructed table through a preset rule, and a sentence which most conforms to logic is screened out through a large language model, so that deep understanding and accurate expression of complex table contents are realized. The invention provides a new method for processing complex table semantics, the table processing efficiency and accuracy are improved, and valuable references are provided for practical application scenes such as data mining, information retrieval and intelligent questions and answers.

The application discloses a multi-intent spoken language understanding method based on syntax analysis, which comprises the following steps: firstly, obtaining an intent feature matrix and a slot feature matrix according to a user input sentence, and constructing a multi-level intent feature from the intent feature matrix; secondly, obtaining initial intent labels and initial slot prediction labels by using an intent decoding module and a slot decoding module respectively on the intent feature matrix and the slot feature matrix; then, inputting the multi-level intent feature and the initial slot prediction labels into a slot-intent interaction module to obtain an enhanced intent feature matrix, and inputting the slot feature matrix, the multi-level intent feature and the initial intent labels into an intent-slot interaction module to obtain an enhanced slot feature matrix; finally, inputting the enhanced intent feature matrix and the slot feature matrix into the intent decoding module and the slot decoding module respectively to obtain intent labels and slot sequence labels of the spoken language understanding task. The application improves the accuracy of intent recognition and slot sequence labeling and the accuracy of multi-intent recognition.

Interactive reading comprehension is provided. An analysis of a set of responses received from a user to a set of interactive comprehension questions related to a set of main topics in a digital book up to where the user stopped reading in the digital book in accordance with a set reading schedule is performed using a large language model of an artificial intelligence (AI)-based virtual interactive reading assistant. A level of comprehension of the main topics in the digital book is determined using the large language model of the AI-based virtual interactive reading assistant based on the analysis of the set of responses. The user is engaged in a discussion regarding the main topics in the digital book using the large language model of the AI-based virtual interactive reading assistant based on the level of comprehension of the main topics by the user.

The invention relates to a large language model-based job matching scene query understanding method. The method comprises the following steps of: receiving a job name, a job description and job requirement information input by a user; performing noise filtering and coding normalization processing on the input post information to generate a standardized text; geography and organization entities are extracted through a named entity recognition model, cue words are finely adjusted through a large language model, structural constraint conditions are formed by technical recognition educational background, working years and ages, and a condition analysis template is dynamically generated. And finally, through a large language model, verifying the accuracy of the keyword items, and allocating weight coefficients for the lexical items. Therefore, the efficiency is remarkably improved. Through automatic semantic analysis of a large language model, manual deep intervention of professional knowledge learning of posts is not needed, and core information such as post responsibilities and skill requirements can be rapidly extracted and converted into semantic retrieval features.

The invention discloses a semantic understanding method and engine based on multi-model collaborative reasoning and self-supervised learning, and belongs to the technical field of natural language processing and artificial intelligence. The method comprises the following steps: preprocessing input data to extract semantic features; at least two models are intelligently scheduled from a large language model, a task type model and a rule engine for collaborative reasoning through a dynamic routing module based on a multi-level strategy and a meta-learning network; performing hierarchical fusion and conflict resolution on the reasoning result by using a multi-model fusion module, and outputting a final semantic understanding result; and continuous optimization of the system is realized through feedback learning. Universal semantic representation is learned by using unlabeled data through a self-supervised pre-training task, so that the generalization ability of the model is enhanced. The engine comprises an input processing core module, a dynamic routing core module, a multi-model fusion core module, a feedback learning core module, a model warehouse core module, a monitoring security core module and the like so as to collaboratively realize the method. According to the method, high-precision and high-efficiency semantic understanding with self-adaptive capability is realized.

This application provides a semantic understanding method based on natural language processing and a technology operation platform system. First, a target interaction data set including a text instruction sequence, collaborative document content, and resource scheduling request records in the technology management scenario is obtained. Then, cross-modal semantic alignment processing is performed on it to generate a structured semantic parsing result including an intention decision tree, etc. Next, based on dynamic process orchestration rules, this result is mapped to a predefined process node topological space to obtain an initial process execution path set including a node execution order chain, etc. Then, conflict resolution is performed on this set according to the real-time system resource status data to generate an optimized executable process path including resource allocation priorities, etc. Finally, this optimized executable process path is input into the technology management central system to realize the automated deployment and execution status tracking of cross-departmental collaboration processes, effectively improving the semantic understanding and process handling capabilities in the technology management scenario.

The application discloses a text reading comprehension method and device based on article difference perception representation, a storage medium and an electronic equipment, belongs to the field of natural language processing and artificial intelligence, and aims to solve the technical problems of how to effectively utilize article information to improve the accuracy of answer selection and how to realize effective matching between a question and options, thereby improving the prediction accuracy of a text reading comprehension system, and adopts the technical scheme that: ① a text reading comprehension method based on article difference perception representation comprises the following modules: a pre-training embedding representation module, a feature filtering module, an article difference perception representation interaction module and a label prediction module. ② a text reading comprehension device based on article difference perception representation comprises a text reading comprehension data set acquisition unit, a text reading comprehension model construction unit and a text reading comprehension model training unit.

The embodiment of the invention relates to the technical field of natural language understanding, and discloses a semantic understanding method, device and equipment and a storage medium, the method comprises the following steps: when user input is received, transmitting the user input to a preset artificial intelligence model through a LangChain framework to perform semantic understanding and generate a semantic understanding result; if the semantic understanding result contains a function call instruction, selecting a target function call from a plurality of registered function calls through a LangChain framework according to the function call instruction so as to execute corresponding instruction operation; transmitting an execution result called by the target function to a preset artificial intelligence model through a LangChain framework so as to generate answer content input for the user; and the generated answer content is returned to the user through a LangChain framework. By applying the technical scheme provided by the invention, the problems of high development difficulty, obvious technical threshold and difficulty in non-professional personnel to participate in development due to the fact that a structured semantic framework is defined by a domain expert in the prior art can be solved.

The invention discloses a multi-hop reading understanding method based on a paragraph pair loss and replication mechanism, and the method comprises the steps: respectively splicing a preset question with a plurality of paragraphs, and obtaining a spliced paragraph; screening the plurality of spliced paragraphs to obtain high-score paragraphs; splicing the high-score paragraph with a preset question again to obtain a high-score spliced paragraph; generating word list distribution and replication distribution based on cross attention scores for the high-score spliced paragraphs through a preset decoder, and dynamically fusing the two types of distribution to generate a prediction distribution probability; and determining a maximum value in the prediction distribution probability, and determining a corresponding prediction token in a preset word list according to an index corresponding to the maximum value so as to obtain a prediction text.

A machine reading comprehension method includes obtaining a question text and an article text associated with the question text, generating a first knowledge text corresponding to the question text and a second knowledge text corresponding to the article text based on a knowledge set, encoding the question text and the article text to generate an original target text encoding, encoding the first knowledge text and the second knowledge text to generate a knowledge text encoding, performing a fusion operation on the original target text encoding and the knowledge text encoding, importing part of the knowledge in the knowledge set into the original target text encoding to generate a reinforced target text encoding, and obtaining an answer corresponding to the question text based on the reinforced target text encoding, and outputting the answer.

The invention discloses a content understanding method and device, a readable medium, electronic equipment and a program product. The content understanding method comprises the following steps: acquiring first content associated with a first object; the first content is processed through a large language model, a target attribute word used for describing the first object is obtained, and the large language model is used for obtaining the target attribute word through the following processing steps that semantic understanding is conducted on the first content according to a preset attribute definition associated with the first object, and the target attribute word is obtained; obtaining a first attribute word conforming to the preset attribute definition; and performing semantic summarization based on the first attribute word to obtain the target attribute word. The content is subjected to semantic understanding in combination with the preset attribute definition, the comprehensiveness and accuracy of content understanding can be improved, it is guaranteed that the extracted first attribute word can accurately represent the attribute information of the first object, then semantic summarization is conducted on the attribute word, the complexity of the attribute word can be reduced, and the accuracy of attribute word extraction is improved.

The application provides a generative reading comprehension method based on multi-task learning, and the method comprises the following steps: obtaining a target question and a target paragraph, obtaining corresponding feature vectors of the target question and the target paragraph, inputting the feature vectors into a target reading comprehension model, and obtaining a target answer, so that the accuracy and reliability of the target answer are improved.

This invention discloses a semantic understanding method and engine based on multi-model collaborative reasoning and self-supervised learning, belonging to the fields of natural language processing and artificial intelligence. The method includes preprocessing input data to extract semantic features; intelligently scheduling at least two models from a large language model, task-oriented model, and rule engine for collaborative reasoning through a dynamic routing module based on multi-level policies and meta-learning networks; using a multi-model fusion module to perform hierarchical fusion and conflict resolution of the reasoning results, outputting the final semantic understanding result; and continuously optimizing the system through feedback learning. A self-supervised pre-training task is used to learn a general semantic representation from unlabeled data to enhance the model's generalization ability. The engine includes core modules such as input processing, dynamic routing, multi-model fusion, feedback learning, model repository, and monitoring and security, which work together to implement the above method. This invention achieves high-precision, high-efficiency, and adaptive semantic understanding.

The invention provides a multi-scene semantic understanding method and device, electronic equipment and a storage medium, and belongs to the technical field of natural language process.The method comprises the steps that a current user instruction is obtained; classifying the current user instruction based on a text classification model to obtain an instruction type to which the current user instruction belongs; if the instruction type to which the current user instruction belongs is an equipment control type instruction or a system setting type instruction, extracting a first keyword from the current user instruction; searching a second keyword matched with the first keyword from a mapping dictionary to obtain a search result; and if the search result shows that the second keyword matched with the first keyword exists in the mapping dictionary, taking a standard instruction corresponding to the second keyword as a semantic understanding result of the current user instruction. According to the multi-scene semantic understanding method and device, the electronic equipment and the storage medium provided by the invention, the semantic understanding precision of the user instruction under multiple scenes can be improved.

The application discloses a hierarchical cognitive video understanding method and system based on a multi-modal large language model, and a medium, relates to the cross technical field of artificial intelligence, computer vision and natural language processing, and comprises the following steps: acquiring a long video stream and user query information, adaptively performing time sequence segmentation on the long video stream to obtain sparse key frames and time anchor points, constructing a global semantic mapping based on a lightweight visual language model, combining the user query information and short-term constraint memory, using a large language model to obtain a set of saliency scores, and performing time sequence local center extraction and high-frame-rate dense sampling on the set to determine a dense frame sequence; then, using a multi-modal large model to determine a binary reliability flag and a video understanding result; if the video understanding result is relevant, outputting the video understanding result; if the video understanding result is not relevant, performing a self-reflection mechanism based on the multi-modal large model to determine an updated internal state. The application can realize efficient and accurate analysis of a long video, and improve the accuracy and efficiency of video analysis.

The application belongs to the technical field of artificial intelligence, and discloses a human action understanding method based on a large language model and adaptive contrast decoding, proposes a FLARE framework, introduces a pre-trained frozen large language model LLM and a frozen action encoder, aligns the action and language semantics, and uses an adaptive contrast decoding AdaCD method to reduce excessive dependence on language prior, thereby improving the model's understanding ability of the action, enabling the method to handle various action understanding tasks, improving the generalization ability of the human action understanding method, and reducing the task specificity and computing resource consumption problems in the prior art.

The application discloses a text understanding method and system based on parallel multi-dimensional semantic signal output, and belongs to the technical field of natural language processing. The method simultaneously performs parallel analysis on literal dimension, intention dimension and emotion dimension of input text, and fuses signals of the three dimensions into comprehensive cognitive signal output. The intention dimension adopts sentence structure recognition and does not need to depend on a large-scale language model. The method simulates the instantaneous understanding process of the human brain through a parallel multi-dimensional architecture, and outputs cognitive signals that can be directly used by the brain, rather than fragmented labels.

The application discloses an AI robot dialogue understanding method based on causal reasoning, comprising the following steps: obtaining user dialogue text, and splitting semantic roles, event elements, emotional expressions and key sentences into semantic microparticles; establishing a semantic charge conservation constraint in a semantic microparticle set, and adaptively adjusting microparticle charges; generating causal bias change information for the semantic microparticles, and updating the moving trend of the microparticles in the semantic space; constructing a semantic microparticle density field, identifying a semantic area with a density exceeding a threshold, and determining the semantic meaning corresponding to the area as the user intent of the current dialogue; and generating a robot action instruction or a natural language reply matched with the user intent and the moving trend of the semantic microparticles in the area. The application realizes fine-grained semantic tracking and stable robot response generation in multi-round dialogue by splitting dialogue text into semantic microparticles and applying a semantic charge conservation and causal bias driving mechanism.

The present invention discloses a method and system for understanding referential expressions for computer vision language alignment, including: analyzing a language expression input by a computer through a language parser to generate text features; using a selective filtering module guided by an expression to adaptively select visual features related to the language expression from a feature map of a visual object; constructing a multimodal attention map based on the text features and the visual features; and executing a noun-oriented multi-step reasoning strategy to achieve graph reasoning and target object matching. The present invention selects relevant visual features of individual objects through an expression-guided selective filtering module, and uses them together with expression representation for graph construction. The negative impact of functional words in the expression is effectively reduced through a noun-oriented reasoning strategy, thereby improving the accuracy of text-to-object matching.

This invention discloses a sentiment cause pair extraction method based on multi-turn machine reading comprehension, belonging to the fields of natural language processing and machine learning. This invention decomposes the sentiment cause pair extraction task using a multi-turn structure, mitigating the label sparsity problem at the clause level rather than the clause pair level by processing the task at the clause level, thus improving the efficiency of document sentiment cause pair extraction. Furthermore, by utilizing question design and the interaction between questions and clauses in machine reading comprehension methods, the relationship between sentiment clauses and cause clauses is fully established. This established relationship enables the extraction of sentiment cause pairs under various complex relationships, broadening its applicability. The extracted candidate document sentiment cause pairs are verified using a multi-turn machine reading comprehension method with a reflective mechanism, and explicit causal semantic information is used to improve the F1 score of the sentiment cause pair extraction task. This invention is applied to the fields of natural language processing and machine learning, solving related technical problems.

The application provides a multi-scene semantic understanding method and device, electronic equipment and storage medium, and belongs to the technical field of natural language processing. The method comprises the following steps: obtaining a current user instruction; classifying the current user instruction based on a text classification model to obtain an instruction type to which the current user instruction belongs; if the instruction type to which the current user instruction belongs is a device control type instruction or a system setting type instruction, extracting a first keyword from the current user instruction; searching for a second keyword matched with the first keyword from a mapping dictionary to obtain a search result; and if the search result shows that the mapping dictionary contains the second keyword matched with the first keyword, taking a standard instruction corresponding to the second keyword as a semantic understanding result of the current user instruction. The multi-scene semantic understanding method and device, electronic equipment and storage medium provided by the application can improve the semantic understanding accuracy of user instructions in multiple scenes.

This invention discloses a selection-based reading comprehension method, apparatus, storage medium, and electronic device based on the Dot Triple-Attention mechanism, belonging to the fields of natural language processing and artificial intelligence. The technical problem this invention aims to solve is how to more efficiently utilize text information to promote interaction between questions and options, and how to achieve direct interaction between the three sequences, thereby improving the prediction accuracy of the selection-based reading comprehension system. The technical solutions adopted are: ① A selection-based reading comprehension method based on the Dot Triple-Attention mechanism, comprising the following modules: a pre-trained embedding representation module, a feature filtering module, a Dot Triple-Attention interaction module, a feature aggregation module, and a label prediction module. ② A selection-based reading comprehension apparatus based on the Dot Triple-Attention mechanism, comprising: a pre-trained embedding representation module unit, a feature filtering module unit, a Dot Triple-Attention interaction module unit, a feature aggregation module unit, and a label prediction module unit.

The present invention belongs to the field of natural language processing, and specifically relates to an attention-based multiple-choice machine reading comprehension method, comprising: incrementally training a Chinese pre-trained model BERT-wwm-ext using a sentence selection dataset S to obtain a continued pre-trained model D; introducing a multi-head attention mechanism to fuse option information, question and article information, and enhance the accuracy of the model's answers; and optimizing the model parameters using a weighted moving average. By continuing to pre-train the pre-trained model BERT-wwm-ext, the present invention makes the model more adaptable to horizontal fields. At the same time, the introduction of the multi-head attention mechanism can fully utilize the information between articles, questions and options, and then optimize the model parameters through weighted moving average, so that the model can more accurately answer reading comprehension questions.

This invention relates to a selection-based reading comprehension method based on multi-view graph encoding within a joint learning framework. First, this invention uses a multi-view graph encoding network to jointly encode documents, questions, and candidate answers from multiple different perspectives. It captures the relationships between sentences in the document and between document sentences and questions from three perspectives: statistical characteristics, relative distance, and deep semantics, fully mining potential evidence information to obtain document encodings for question-answer pair perception. Then, a binary classifier is used to determine whether each sentence in the document is an evidence sentence, thus implementing the function of the evidence extraction module. Finally, an answer prediction module is constructed, using the probability of document sentences obtained from the evidence extraction module as evidence to weight and selectively fuse the document encodings obtained from the multi-view graph encoding network. Both modules are trained simultaneously within the joint learning framework, thereby achieving the goal of answer prediction. This invention has achieved good results on selection-based reading comprehension tasks.

The invention provides a spoken language understanding method and device, electronic equipment and a storage medium, and the method comprises the steps: inputting a voice feature map into a feature extraction module in a spoken language understanding model, and obtaining a shared representation matrix; inputting the shared representation matrix into a modal conversion module in a spoken language understanding model to obtain initial text representation; inputting the initial text representation into a text enhancement module in a spoken language understanding model to obtain an enhanced text representation; and inputting the enhanced text representation into a structured information generation module in the spoken language understanding model to obtain structured information corresponding to the speech to be recognized. Through the method, semantic logic coherence and text element relevance can be effectively enhanced, the semantic consistency learning ability of spoken language understanding is remarkably improved, the accuracy of structured information output and the model generalization ability are greatly improved, and the semantic understanding and intelligent response level of a machine to natural spoken languages is enhanced.