234 results about "Parsing" patented technology

This application provides a method and computing device for recommending device components, relating to the field of computing device technology. This method can improve the accuracy and efficiency of device component recommendation. The method includes: acquiring input demand information; describing the features of the component to be recommended in natural language using the demand information; inputting the demand information into a parsing model to obtain the output parsing result; the parsing model is a locally deployed lightweight model obtained by model distillation of a large language model; describing the features of the component to be recommended in a structured format using the parsing result; outputting a recommendation result based on the parsing result; the recommendation result is used to indicate the recommended device component.

This invention discloses a spoken language understanding method based on multi-view expert fusion and interest lexical selection, belonging to the field of natural language understanding and semantic parsing technology. The method includes: extracting hidden state sequences from the input utterance using a shared encoder; constructing a multi-view expert fusion module containing utterance view experts, block view experts, and lexical view experts to generate multi-granularity expert features; generating intent aggregation features and slot aggregation features through a task decoupling gating mechanism; performing interest lexical selection on the intent aggregation features, calculating lexical importance scores, generating weighted intent representations, and predicting multi-intent labels; and inputting the slot aggregation features into a decoder with diagonal mask constraints to generate a position-aligned slot label sequence. This invention enhances the model's dynamic focusing ability on key intent signals and can be applied to intelligent dialogue systems, virtual assistants, and vertical domain semantic parsing scenarios.

This application relates to the field of data processing technology and discloses a method and system for Chinese word segmentation and semantic unit parsing based on rule enhancement. The method includes: constructing a multi-level domain rule base from forced matching rules, pattern template rules, and context constraint rules to generate a set of rule triples; loading the set of rule triples into an AC automaton to linearly scan the input text to obtain a set of candidate segments and trigger word position indices; constructing a candidate directed acyclic graph, and obtaining a structured word segmentation sequence and a pruned candidate pool through dynamic programming after dynamic modulation and fusion scoring; verifying the integrity of downstream slots, and locating backup candidate edges in the pruned candidate pool using gap signals when failure occurs, and obtaining a corrected word segmentation sequence through renegotiation and scoring. This application improves the completeness of professional terminology recognition in professional vertical scenarios and the self-correction capability of cross-domain word segmentation results.

The application discloses a COBOL-to-Java program conversion method and system based on a syntax tree, belongs to the technical field of computer program language conversion, and comprises the following steps: obtaining a COBOL source program file to be converted and configuration rules; performing lexical analysis and syntax analysis to generate an abstract syntax tree; converting COBOL syntax elements into corresponding Java semantic representations according to pre-defined semantic mapping rules; establishing an accurate access chain of a main program and COPYBOOK internal variables through variable path tracking; detecting and solving naming conflicts of COBOL different-level same-name variables based on a scope tree, and renaming variables by adding a parent class name prefix; and generating the converted Java semantic representations into a Java source code file. The application realizes high-fidelity and high-automation COBOL-to-Java conversion, significantly reduces the migration cost of a legacy system, and generates code with strong readability and excellent performance.

This invention discloses a method and system for extracting and analyzing key points of legal documents based on a large model, relating to the field of natural language processing technology. The invention generates a semantic parsing candidate graph based on legal semantic nodes and semantic relationships, calculates the matching scores of candidate paths in the semantic parsing candidate graph, summarizes the matching scores of all candidate paths in the semantic parsing candidate graph, and calculates the topological consistency index of the semantic parsing candidate graph. It identifies semantic conflict units and calculates initial conflict weights, and calculates the overall conflict impact of the semantic parsing candidate graph. Based on the topological consistency index, the basic semantic confidence of the semantic parsing candidate graph, and the overall conflict impact, it calculates a comprehensive score for the semantic parsing candidate graph and selects the optimal result, comprehensively optimizing and dynamically adjusting the legal semantic parsing results, significantly improving the accuracy, reliability, and intelligence level of legal text parsing.

This application relates to the field of fintech and discloses a dynamic hybrid parsing and deterministic verification system and method for fuzzy bond instructions. The system constructs structured data through an instruction preprocessing module; a routing decision module calculates complexity scores based on structure, semantics, and business characteristics, and generates path selection instructions using a resource-aware dual-threshold strategy; a hybrid parsing module responds to instructions, employing a rule engine to handle low-complexity tasks and a large-scale model with enhanced retrieval to handle highly ambiguous tasks; a fallback verification module performs confidence-weighted integration and logical consistency checks, and repairs anomalies through issuer set operations and edit distance matching; a mapping generation module constructs standard query statements using an abstract syntax tree; and a closed-loop optimization module dynamically updates parameters based on user interaction feedback. This invention effectively balances computational efficiency and parsing accuracy, eliminates model illusion risks, and achieves adaptive evolution of the system.

This invention relates to the field of natural language processing technology, specifically to a method and system for matching the intent of intelligent NPC dialogues in multimodal interaction. The method involves real-time acquisition of multimodal data, generating multimodal semantic features through submodal preprocessing; integrating the semantic features of each modality using a cross-modal fusion module based on semantic association, generating a candidate intent set based on semantic context representation and combined with a semantic parsing module and predefined intent templates; tracking changes in user intent in real time through a continuous semantic learning mechanism and an interactive memory module, combined with a Bayesian update method, dynamically adjusting the confidence level of each intent in the candidate intent set, and filtering the final intent; constructing an NPC semantic cognition model, and performing semantic consistency analysis to perform semantic checks on user input and NPC dialogue state; combining the final intent and a decision engine to generate a dialogue strategy and output synchronized response content; this invention improves the accuracy of dynamic matching of intelligent dialogue intents.

This invention relates to the field of teaching aids technology, and more particularly to a method for adaptive generation of speech content based on a multimodal large model and a real-time question-answering system. The method includes the following steps: acquiring multimodal raw materials provided by the speaker and parsing them using a multimodal large model to extract the speech's logical structure, key entities, and content attribute tags; organizing the multimodal large model parsing results into a content tree and constructing a knowledge graph representing arguments, sub-arguments, cases, data, and conclusions, wherein the knowledge graph defines support, exemplification, and comparison relationships between nodes; learning from the speaker's historical audio / video and text data and outputting a speaker style vector; generating an initial speech suite and configuring adjustment strategy templates, priority definitions, and safety boundaries. In this invention, by organizing content into an operable knowledge graph / content tree and constructing a real-time closed loop of "perception—understanding—decision—generation," dynamic path selection and content generation based on real-time multimodal perception are achieved.

This invention discloses a method for generating intelligent shell commands in a Linux environment, comprising: acquiring input natural language in a Linux terminal; determining whether a corresponding ready-made command exists; if it exists, directly executing the corresponding ready-made command; if it does not exist, calling a cloud model to perform semantic parsing on the natural language, identifying the user's intent based on the semantic parsing, and performing knowledge retrieval in conjunction with the context; combining the user's intent and the knowledge retrieval results, calling a large model to generate a shell command, and displaying the shell command to the user; after user confirmation, performing sandbox pre-execution; if pre-execution fails, returning the pre-execution result; if pre-execution succeeds, executing the shell command, and returning the execution result to the user after execution. This invention also discloses an intelligent shell command generation system in a Linux environment. This invention uses natural language to operate the terminal, making it convenient to use.

Techniques are disclosed relating to extracting data from a document, using a large language model (LLM), to populate fields in a data structure. A computer system may receive a request to populate multiple fields of a data structure with data extracted from text of a document. The computer system parses the text using an LLM (as well as regular expressions or other parsing techniques in some embodiments). The parsing includes issuing, to the LLM, a sequence of queries targeting individual ones of the multiple fields. The computer system applies a validation algorithm to results received from the LLM in response to the sequence of queries. The validation algorithm confirms the presence of results in the text of the document and populates the data structured with the validated results. In various embodiments, the computer system performs an optical character recognition (OCR) on the document to determine the text for parsing.

This invention discloses a method and system for labeling prompt words in a large-scale communication domain model based on knowledge graphs. Belonging to the fields of communication technology and artificial intelligence, it addresses the following technical problems: low efficiency in labeling specialized terms in communication domain prompt word annotation, low accuracy and efficiency of automatic recognition, limited prompt word dimensions, and lagging domain knowledge. The method includes: sequence labeling and entity extraction using a trained combined model to output entities; generating relation triples as candidate relations using a trained generator, and scoring and ranking the selected relation triples using a trained discriminator; semantic parsing of user input to extract key entities and intents; multi-hop reasoning from a dynamic knowledge graph to retrieve relevant entities and relations; eliminating illusory content using a trained GAN network; generating entity prompt words from three levels: basic, extended, and application dimensions; and introducing a triple quality verification mechanism.

This invention discloses a method for porting a digital signal processor (DSP) assembler based on a processor architecture description, comprising the following steps: S1. Based on the processor architecture description, a lexical analysis and syntax analysis part of the assembler is constructed to realize the parsing of special assembly instructions; S2. Taking the parsed instruction data or instruction binary code as input, dynamic encoding and decoding of instructions are implemented according to the instruction definition, thereby realizing the conversion between the object file and the assembly file. This DSP assembler porting method further improves the performance of the assembler and automates the porting process, adapting it to the digital signal processor architecture. It also provides support for single instruction multiple data, very long instruction words, and instruction validity checks. While ensuring that the program execution result meets expectations, it greatly reduces the number of clock cycles required for execution, possesses universality, and meets the needs of rapid processor architecture updates.

This invention relates to the field of computer system technology based on specific computational models, and discloses a method and system for parsing and evaluating multi-source heterogeneous data streams based on semantic understanding of large language models. The method includes: extracting a logical dependency matrix representing the logical subordination relationship between data nodes in the multi-source heterogeneous data stream; generating a mask constraint tensor based on the logical dependency matrix to guide the feature fusion path of the large language model; injecting the mask constraint tensor into the self-attention computation layer of the large language model, using the tensor to suppress the distribution of attention weights, forcing feature extraction to converge within the logical constraint subspace, and generating a semantic parsing vector; and outputting the evaluation result based on the semantic parsing vector. This invention eliminates the feature dilution of core nodes by unstructured noise through numerical truncation of irrelevant weights in the computational path, avoids the illusion of association generated by semantic fusion, and improves the logical determinism of heterogeneous data parsing.

This invention discloses a method for mining alumni information based on a large-scale model, comprising the following steps: 1) acquiring raw alumni-related data; 2) preprocessing the acquired data; 3) performing natural language processing on the acquired data; 4) semantic parsing and information extraction using a large-scale model; 5) constructing a knowledge graph; storing the extracted alumni information and relationships in a graph database; and constructing a visualized alumni knowledge graph; 6) updating the knowledge graph data; and 7) providing intelligent retrieval and question-answering services for alumni information based on the knowledge graph data. This invention uses a large-scale model to perform deep semantic understanding and information extraction from unstructured text. Compared to traditional keyword-based or small-scale model-based methods, it can more accurately identify alumni identities, professional experiences, and social relationships, while reducing the false matching rate.

This application discloses a method, device, and storage medium for global fluctuation analysis of text. The method, relating to the field of text parsing technology, includes: processing the input text using a first model to obtain a first parsing result, and processing the input text using a second model to obtain a second parsing result; determining the sentence-level raw evaluation value of each sentence in the input text; determining the paragraph-level raw evaluation value of each paragraph in the input text based on the first parsing result, the second parsing result, and the sentence-level raw evaluation value; connecting the paragraph-level raw evaluation values ​​of each paragraph into an expression intensity curve using the paragraph sequence of the input text as a time axis; and identifying and labeling four geomorphic features—peak, valley, data slope, and data plain—based on the expression intensity curve to generate a visualized scoring geomorphic map. This application achieves accurate prediction and hierarchical selection of training corpus quality before model training.

The application discloses a kind of based on ecological environmental protection supervision big language model address resolution and geographic coding acquisition method and system.For the fuzzy, non-standard and positioning difficult problems of environmental supervision letter and visit complaint address description, the method first uses big language model to parse the original text into structured address, and cooperates multi-level fault tolerance mechanism to ensure the reliability of parsing result.In the matching stage, the system adopts local priority strategy, and preferentially searches the environmental special position database containing key polluting units and other information;If the initial matching is not hit, the self-defined part-of-speech tag segmentation technology is used to accurately extract the core environmental entities such as pollution outlet and water source protection area for secondary matching.To ensure accurate positioning, the system verifies by semantic similarity and geographical distance, to prevent errors caused by the same name in different places.When local matching fails, the system automatically accesses the network query, and uses big language model to simplify the redundant description and retry, forming a closed-loop error correction mechanism.The application significantly improves the accuracy and efficiency of pollution source positioning, protects data privacy, and provides strong technical support for environmental law enforcement personnel to achieve accurate positioning, rapid verification and scientific division of responsibility area.

This application discloses a dynamic decision-making method and system for flash floods and debris flows based on multi-agent and LLM (Limited Language Model), belonging to the field of emergency management and intelligent decision-making technology. This method constructs an intelligent decision-making architecture based on a large model and multi-agent collaboration. It solves the execution challenges of complex disaster tasks through the division of labor and cooperation among multiple agents, and overcomes the decision-making limitations of traditional systems by leveraging the deep reasoning capabilities of a large language model. Specifically, the multi-agent collaborative framework decomposes disaster prevention and control decisions into sub-tasks such as intent parsing, contingency plan retrieval, spatial analysis, data acquisition, and analysis and prediction. Each functional agent focuses on its area of ​​expertise, improving the efficiency and accuracy of task execution. The agent communication protocol ensures efficient information interaction and collaborative scheduling between modules, realizing fully automated processing from task input to data output.

The application discloses an AI driving-based structured data migration method and system, belongs to the technical field of big data migration, and aims to solve the technical problem of how to improve the efficiency of large-scale data migration and reduce resource waste. The method comprises the following steps: forming a private large language model with field adaptation capability; performing lexical analysis and syntax analysis on non-standard structured data in a source database based on an AST analysis method, generating an abstract syntax tree AST, traversing and optimizing AST nodes, and converting the AST nodes into standard structured data supported by a target database; calling the large language model, and converting unstructured data into structured data supported by the target database through instruction fine-tuning, thought chain reasoning and step-by-step analysis; generating a migration script by the large language model; monitoring the migration process in real time, recording abnormal events, automatically retrying or repairing the abnormal events by the large model, and optimizing the large language model configuration strategy and data conversion rules in combination with feedback data.

This application discloses a text sentiment analysis method, apparatus, device, and medium based on a large language model (LLM), relating to the field of natural language processing technology. The method includes: acquiring financial text to be analyzed; performing multi-granularity sentiment analysis on the financial text based on preset prompts and a large language model (LLM), outputting multiple independent preliminary sentiment analysis results; wherein the preliminary sentiment analysis results at least include sentiment tendency and sentiment intensity scores; and integrating the multiple preliminary sentiment analysis results based on semantic consistency and logical conflict resolution using the LLM to generate a final sentiment analysis result. This application, by combining a multi-agent architecture, deeply customized multi-granularity parsing logic for financial text, and advanced integration strategies, eliminates the dependence on large-scale labeled data and significantly improves the accuracy of sentiment analysis by introducing semantic consistency analysis and logical conflict resolution reasoning.

This application discloses an automatic code generation method and system for SOME / IP data types, relating to the field of vehicle system development. The method includes: S1, data dictionary reading: obtaining the data dictionary for SOME / IP protocol communication; S2, data type classification, identification, and processing: opening the Excel file from step S1, classifying each row of data in the worksheet, and performing specific parsing processing for different types; S3, multi-round iterative dependency resolution: using a multi-round scanning strategy to resolve nested dependencies between various data types; S4, naming standardization processing: standardizing the names of each parsed data type according to preset naming rules; S5, standard code generation and output: converting all data types that have undergone naming standardization processing into type definition code conforming to C language specifications; simultaneously converting the value range, precision, unit, and Chinese description metadata in the data dictionary of the Excel file into code comments, generating a C language header file that can be included in the compilation project.

This invention discloses a temporally enhanced knowledge graph-driven dialogue agent and its implementation method, belonging to the fields of artificial intelligence and natural language processing technology. The dialogue agent includes a dialogue interface, natural language understanding, a temporal knowledge graph, a temporal reasoning engine, dynamic update and failure management, and a natural language generation module. It includes designing the basic representation unit of the knowledge graph as a temporal quintuple; designing a temporal reasoning engine and a dynamic update and failure management method; designing a method for matching, verifying, and performing multi-hop reasoning of temporal information in natural language problems with temporal facts in the knowledge graph; achieving accurate parsing of temporal constraints in dialogue, real-time adaptation of dynamic knowledge, rigorous temporal logic reasoning, and continuous maintenance of contextual temporal consistency; and outputting a temporally accurate, knowledge-reliable, and logically coherent intelligent response, capable of meeting the needs of complex scenarios such as vertical industry decision support and high-reliability intelligent interaction.

This invention discloses an AI interaction system and method with multi-window task splitting and real-time task response. By designing multiple independent AI dialogue input windows, each pre-bound with specific functional instructions (such as analysis or memorization), the system can directly trigger the corresponding function after the user inputs task content, achieving synchronous execution of input and instructions, eliminating the redundant steps of the traditional "input-select instruction-execution" process. The multiple AI dialogue input windows are functionally independent and support parallel operation, avoiding task conflicts and significantly improving multi-task processing efficiency. Clear window function binding reduces the risk of errors in semantic ambiguity parsing, ensuring the accuracy of task execution. This invention overcomes the limitations of existing single-window multi-instruction interaction modes, achieving significant improvements in operational efficiency, interactive experience, task accuracy, and flexibility.

Techniques are disclosed relating to extracting data from a document, using a large language model (LLM), to populate fields in a data structure. A computer system may receive a request to populate multiple fields of a data structure with data extracted from text of a document. The computer system parses the text using an LLM (as well as regular expressions or other parsing techniques in some embodiments). The parsing includes issuing, to the LLM, a sequence of queries targeting individual ones of the multiple fields. The computer system applies a validation algorithm to results received from the LLM in response to the sequence of queries. The validation algorithm confirms the presence of results in the text of the document and populates the data structured with the validated results. In various embodiments, the computer system performs an optical character recognition (OCR) on the document to determine the text for parsing.

An audio generation method, apparatus, device, and storage medium are disclosed. The method includes: parsing the input text in response to receiving it; determining the target character object and turn included in the input text based on the parsing result; determining the mapping relationship between the target character object and the timbre based on preset mapping rules and the target character object; segmenting the input text based on the turn to obtain multiple text segments; processing the multiple text segments based on the mapping relationship through an asynchronous concurrency mechanism to obtain audio segments corresponding to each of the multiple text segments; and determining the audio information corresponding to the input text based on the audio segments. The technical solution disclosed herein achieves text-to-audio conversion through an asynchronous concurrency mechanism and the mapping relationship between the target character object and the timbre; thus, it not only ensures the speech consistency of multi-character dialogues but also reduces conversion time and significantly improves audio generation efficiency.

This invention provides a code sequence compression method, apparatus, and device that combines semantic analysis and attention, relating to the field of large language model processing technology. The method includes: performing lexical and syntactic analysis on a source code sequence to generate a syntax tree corresponding to the source code sequence; generating an original syntax topology distribution network based on the dependencies between nodes in the syntax tree; determining the comprehensive maintenance value of each node in the original syntax topology distribution network; and removing redundant nodes from the original syntax topology distribution network based on a comprehensive maintenance value threshold and the comprehensive maintenance value of each node in the original syntax topology distribution network, resulting in an updated syntax topology distribution network and a compressed code sequence. The method of this application avoids the problems of traditional compression methods such as accidentally deleting key nodes, disrupting program connectivity, and causing semantic understanding bias in the model, providing high-quality input with standardized structure, semantic coherence, and reliable reasoning for large language models.

This invention provides a human-machine collaborative method and system for short- and medium-term hydrological forecasting enhanced by a large language model, relating to the fields of hydrological forecasting and artificial intelligence. The method includes the following steps: constructing a hydrological forecasting knowledge base for the target watershed; obtaining natural language forecasting requirements and generating structured forecasting task descriptions; recommending solutions and completing parameters based on the knowledge base; executing business rule constraints and verifying solutions; calling the short- and medium-term hydrological forecasting system to perform forecast calculations; and intelligently interpreting forecast results and accumulating experience. The system includes six modules: user interaction, large language model interaction, hydrological forecasting knowledge base, business rule engine, system interface calls, data storage, and logs. Without changing the core architecture of existing short- and medium-term hydrological forecasting systems, this invention introduces a large language model to achieve semantic parsing of forecasting tasks, intelligent construction of forecasting solutions, and intelligent interpretation of forecast results, lowering the system's usage threshold and improving the interpretability of forecast results and the structured reusability of forecasting experience.

This application provides a method and system for optimizing user input information based on a large language model, belonging to the fields of artificial intelligence and regional management technology. The method receives initial user information and extracts key semantic features such as entities and actions through deep learning algorithms. An expanded semantic set is generated based on a dynamically updated semantic association rule base, and a precisely targeted subset is obtained through a specially trained large language model. The initial information and the subset are fused according to relevance weights, and optimized information is output after verification and correction through syntactic analysis and logical reasoning. Parameters can be dynamically adjusted based on user feedback. This invention solves the problems of low accuracy and insufficient standardization in existing technologies, improves information completeness and adaptability, and enhances the usability of user input information.

This invention discloses a language-conditional generalization learning method for deformable robot operations. Addressing the challenges of high-dimensional state space, dynamic complexity, and difficulties in cross-task transfer in deformable robot operations, it constructs a generalization framework integrating language understanding, skill decomposition, and cross-modal learning. The method collects multimodal demonstration data such as image sequences and natural language commands. It utilizes a large language model to perform semantic parsing and hierarchical decomposition of tasks, forming reusable basic skill units. Then, through a Transformer-based cross-modal skill learning model, it combines images and skill descriptions to predict operation target points and execution parameters, establishing a general skill library. When faced with a new task, the large language model generates skill sequences and calls upon the skill library for step-by-step execution, thereby achieving generalized operation of unseen tasks in both simulation and real robots, significantly improving the system's generalization, stability, and scalability.

This invention discloses a method and system for automatic extraction and knowledge construction of data quality rules for power equipment, belonging to the fields of artificial intelligence and power data governance technology. To address the problems of low parsing accuracy of complex tables in power technology standard documents, lack of physical constraint verification of extraction results, and catastrophic forgetting of models due to standard updates, this invention utilizes a multimodal large language model to parse documents. A structured document object model is obtained through hierarchical table structure encoding, cross-page context preservation, and semantic binding of table annotations. The large language model, fine-tuned with domain knowledge, extracts entity relationships and performs consistency verification in conjunction with a physical constraint knowledge base in the power domain. The verified entity relationships are assembled into structured quality rule records and stored in a graph database. A differential-adaptive elastic weight consolidation strategy is employed for continuous learning, combined with a human-machine collaborative quality inspection optimization model, achieving high-precision complex table parsing, physical consistency verification, and anti-forgetting continuous learning.