57 results about "Graph parsing" patented technology

The invention discloses a multi-modal visual arrangement recommendation method, belongs to the technical field of artificial intelligence and data visualization crossing, and realizes visual arrangement recommendation based on multi-modal input analysis, a dynamic mixed recommendation model and an intelligent optimization algorithm. Comprising the following steps: multi-modal intention analysis: realizing intelligent analysis of multi-modal input through combined use of a base model and a fine tuning model, realizing high-precision intention classification in combination with a pre-training language model and a domain adaptation fine tuning technology, and triggering dynamic prompt word recommendation; performing intelligent layout generation: performing global optimization of component space allocation by adopting a genetic algorithm, performing business rule adaptation by combining a constraint solver, and modeling an interaction relationship between components by utilizing a graph neural network; and dynamic mixed recommendation: constructing a three-level recommendation architecture including collaborative filtering, content matching and reinforcement learning. According to the method, a closed-loop recommendation process of user intention-intelligent recommendation-feedback optimization is realized, and the intelligent level of visual arrangement and the user experience are remarkably improved.

The invention provides an intelligent question number and index management engine and system based on dynamic reward optimization, relates to the technical field of data learning, and is used for enterprise index analysis, attribution diagnosis and decision support. The system is provided with an index governance layer, index caliber, computational logic, blood relationship, credibility score and version information are managed in a unified mode through a dynamic knowledge graph, unified semantic constraint is carried out on a multi-agent analysis process, and index consistency and traceability are guaranteed. The system also establishes a causal cognition module, based on time sequence data and in combination with expert priori, generates and corrects a business index causal directed acyclic graph, realizes root cause positioning and anti-fact simulation, and answers what change is and what intervention is. The multi-agent collaborative analysis core is responsible for natural language intention analysis, index compliance verification, automatic access, causal inference, narrative generation and chart presentation, calculates a multi-target composite reward value based on user feedback and interaction behaviors, and adaptively adjusts output; and the user corrects and writes back to form closed-loop learning.

The invention discloses a natural language spatio-temporal retrieval method and system based on a large model, and relates to the technical field of big data resource services, and the method comprises the following steps: finely adjusting a preset large language model according to a spatio-temporal retrieval problem and a preset cue word engineering template; dividing the target treatment area into geographic space grids, wherein each geographic space grid has a unique grid code; according to the business time-space database and the dynamic semantic tag, constructing an entity knowledge base classified by different data categories; performing natural language intention analysis on user input based on the fine-tuned large language model, and identifying spatial constraints, time constraints and service attribute constraints; converting the spatial constraint into a filtering condition; querying a data category of a corresponding key entity in an entity knowledge base; and outputting a space-time retrieval result based on the fine-tuned large language model according to service attribute constraints, data categories, spatial constraints and filtering conditions. The method gets rid of specialized dependence, improves the interaction experience, and is high in flexibility.

The invention discloses an intelligent NL2SQL generation and optimization system, an application method and a storage medium, and belongs to the crossing field of natural language processing and database query technology.According to the system, four core components including a dynamic SQL RAG cache module, an intention-Schema double-channel alignment module, an incremental TableSchema sensing module and a multi-table index guide JOIN optimization module are used for optimizing the NL2SQL generation and optimization system; the defects of the prior art in the aspects of high-frequency query efficiency, fuzzy intention analysis, dynamic Schema adaptation, multi-table JOIN performance and SQL credibility are overcome. The method has the beneficial effects that the query efficiency and the resource utilization rate are improved, the accuracy and the interaction efficiency of fuzzy intention analysis are enhanced, the dynamic adaptation of industrial level bins is realized, and the method is particularly suitable for large-model asset query in an enterprise-level operation scene.

The invention relates to a voice interaction large model family health assistant dialogue method and device, equipment and a medium. The method comprises the following steps: carrying out fragmentation processing according to an original voice stream of a user to generate an audio fragment with a medical mark, and carrying out voice recognition and entity extraction on the audio fragment to generate a dynamic entity map; generating an evidence-based decision prompt based on the map, inputting the prompt into a preset medical big model for processing, and outputting a result containing an essential symptom list; and according to the symptom matching degree of the necessary symptom list and the dynamic entity map, generating a diagnosis report or a question-asking list, if the diagnosis report is output, performing medical rule chain verification operation on the diagnosis report to generate a quality control report, and based on the question-asking list or the quality control report, generating a synthetic voice stream. According to the method, through medical intention directional screening, map entity analysis, large model diagnosis, voice synthesis and the like, the voice recognition accuracy, the diagnosis suggestion reliability and the inquiry interaction efficiency of the family health assistant in the medical scene are improved.

The invention relates to the technical field of power grid operation and maintenance, and particularly provides a load transfer configuration method and device based on a power grid topological graph large model, and the method comprises the steps: enabling a fault region power grid topological graph to serve as the input of a pre-trained graph neural network model, and obtaining an adjusted power grid topological graph outputted by the pre-trained graph neural network model; and performing power load transfer configuration on the power grid in the fault area by using the adjusted power grid topological graph. According to the technical scheme provided by the invention, the power grid topological graph large model with the power grid topological graph analysis capability is used as an auxiliary tool for selecting the power load transfer point, so that the working efficiency and accuracy of power grid operation personnel can be improved, and reliable and stable operation of a power system is ensured.

The application provides a smart question and index management engine and system based on dynamic reward optimization, relates to the technical field of data learning, and is used for enterprise index analysis, attribution diagnosis and decision support. The system sets an index management layer to uniformly manage index caliber, calculation logic, blood relationship, credibility score and version information by means of a dynamic knowledge graph, uniformly implements semantic constraints on a multi-agent analysis process, and guarantees index consistency and traceability. The system also establishes a cause-effect cognition module, generates and corrects a business index cause-effect directed acyclic graph based on time series data and in combination with expert priori, realizes root cause positioning and counterfactual simulation, and answers "why change" and "what if intervention". A multi-agent collaborative analysis core is responsible for natural language intention analysis, index compliance verification, automatic data acquisition, cause-effect inference, narrative generation and chart presentation, and calculates a multi-target compound reward value based on user feedback and interaction behavior, and adaptively adjusts output; user correction write-back forms a closed-loop learning.

The invention belongs to the technical field of search engines, and particularly relates to an optimized search engine construction method and system based on feature deep learning, and the system comprises a search operation unit, a monitoring and early warning unit and a management and control terminal, the search operation unit comprises a multi-dimensional semantic feature mining module, a user implicit intention analysis module, a deep feature fusion modeling module and a dynamic retrieval strategy generation module; a multi-dimensional semantic feature set and a user intention feature set are formed through a multi-dimensional semantic feature mining module and a user implicit intention analysis module, and a deep feature fusion modeling module performs deep fusion of data features and user intention features through an attention mechanism and cross validation optimization. The dynamic retrieval strategy generation module is used for providing high-quality feature support for retrieval strategy generation, the accuracy of retrieval results is guaranteed, the dynamic retrieval strategy generation module generates dynamic strategies adaptive to different requirements and data states on the basis of reinforcement learning, and the retrieval accuracy and retrieval efficiency of a search engine are remarkably improved.

The invention discloses an edge gateway north-south communication configuration method and device and a medium, and relates to the technical field of edge gateways. The method comprises the following steps: in response to a natural language instruction of a user, analyzing the natural language instruction by adopting a natural language intention analysis model to obtain a user intention; the user intention is converted into a configuration command, and north-south communication of the edge gateway is configured based on the configuration command; and based on a configuration result obtained by completing the configuration command, generating a multi-modal feedback result by using a multi-modal generation model, and displaying the multi-modal feedback result to the user. Therefore, the north-south communication of the edge gateway can be configured.

The invention discloses an intelligent self-adaptive time sequence diagram analysis and structuring method. The method comprises the following steps: preprocessing an input time sequence diagram; identifying and extracting basic structure elements in the time sequence diagram; extracting text information in the time sequence diagram by using an optical character recognition technology; the recognized signal lines are analyzed, and signal state changes and key event points are extracted through a neural network; detecting arrows representing time sequence constraints, and performing arrow detection and classification by using a target detection network; establishing an association relationship between the graphic elements and the text; the association relationship and the identified elements are verified and corrected by using grammar rules and global layout information of the time sequence diagram, and unreasonable results are filtered; converting the time sequence relation model into a standardized structured data format; and the overall recognition performance is continuously optimized based on interactive correction and feedback of confidence. According to the method, the workload of manually converting the time sequence diagrams by engineers is greatly reduced, the accuracy of time sequence constraint extraction is improved, and various time sequence diagram formats and styles are supported.

The invention discloses a big data matching recommendation system and method based on a technology transfer platform, and relates to the technical field of artificial intelligence, and the system comprises a data processing module, a knowledge graph construction module, an intention analysis module, a similarity calculation module and a recommendation sorting module. Wherein the data processing module adopts a field adaptive encoder to realize heterogeneous data standardization; the knowledge graph construction module extracts technical entities and relationships based on a pre-training language model; the intention analysis module extracts core features of a supply party and a demand party through a double-decoder mechanism; the similarity calculation module fuses graph structure analysis and differentiation weight distribution and realizes dynamic compensation; and the recommendation sorting module generates a personalized recommendation result in combination with the market potential evaluation. According to the invention, the intelligent matching precision of the technology transfer platform is obviously improved, the precise docking of cross-field technology supply and demand is realized, and the method has important practical value.

The application provides a smart home layered intention analysis and safe execution method and system and a storage medium, and relates to the technical field of smart home control. The method analyzes natural language into structured intention by constructing control context and home capability graph; adopts a layered mechanism to constrain retrieval candidate entities and calculate relevance score; performs risk scoring on control plan based on five dimensions of device risk level, control range, remote access state, time period and instruction conflict state, and adopts a hierarchical confirmation strategy; generates an execution graph and performs state checking, automatically reverts when a strong consistency scene fails; stores the correction result as personalized preference and sets a confidence decay rule. The application can significantly reduce the range of candidate devices, support contextual dialogue, control high-risk devices in stages, reduce the risk of miscontrol, ensure the consistency of complex scene execution, continuously improve the accuracy of alias recognition, and thus improve the efficiency, safety and user experience of smart home control.

The invention relates to a chip time sequence diagram labeling method and device based on a multi-mode large language model, and relates to the field of chip time sequence diagram analysis and automatic labeling, and the method comprises the steps: firstly, carrying out the line and column line recognition of a chip time sequence diagram, and obtaining a signal line block and a time line block; then, detecting an intersection point area of the signal line block and the time line block, and further obtaining an image slice; then, detecting to obtain an annotation state of the image slice; then connecting the continuous annotation states in series to obtain an event, and further obtaining a natural language conforming to the understanding of the large language model; and finally, constructing according to the cue word to obtain a second text description, inputting the second text description into the first large language model to obtain a text response returned by the first large language model, and constructing based on the text response to obtain a sample for training a second large language model. Compared with the prior art, the method has the advantages that the accuracy of label state recognition is improved, the efficiency of training sample generation is improved, and the degree of manual intervention is reduced.

The present invention discloses an event extraction method and system based on graph parsing. By treating multiple events included in an input sentence as a whole and linking the multiple events to form an event graph, the problem of extracting events from the input sentence is transformed into a graph parsing method for analyzing and generating an event graph from the input sentence. This method no longer relies on event trigger words, explicitly models the correlation between multiple events, solves the argument sharing phenomenon, and alleviates the long-tail problem. At the same time, an effective decoding algorithm is designed based on the Transformer-based generation model to improve the performance of event extraction. In addition, a pre-trained sequence-to-sequence model is adopted to improve the data sparsity problem. In the generation model based on the event graph, dependency syntactic information is utilized, and a graph attention neural network is used to encode the dependency information, and the dual attention mechanisms of the dependency graph encoding layer and the sentence encoding layer are fused to improve the performance of event extraction.

The invention relates to a multi-layer nested service visual scheduling engine and method based on a graph structure, and belongs to the technical field of visual programming. The engine comprises a visual design module, a graph analysis module and a logic judgment module which are in communication connection with one another; the visual design module is used for constructing a business flow chart by dragging nodes, drawing edges and setting nested nodes, and the chart analysis module is used for converting the business flow chart into a task execution plan. And the logic judgment module is used for determining a concurrent and serial execution sequence of a plurality of tasks and an execution path of a conditional branch according to the task execution plan, and generating a logic judgment result.

This invention discloses an intelligent adaptive time series graph parsing and structuring method. The method preprocesses the input time series graph; identifies and extracts basic structural elements from the graph; extracts text information using optical character recognition (OCR); analyzes the identified signal lines, employing a neural network to extract signal state changes and key event points; detects arrows representing time series constraints, using an object detection network for arrow detection and classification; establishes associations between graphical elements and text; verifies and corrects the associations and identified elements using the time series graph's syntax rules and global layout information, filtering out unreasonable results; converts the time series relationship model into a standardized structured data format; and continuously optimizes overall recognition performance through interactive correction and feedback based on confidence levels. This invention significantly reduces the workload of engineers manually converting time series graphs, improves the accuracy of time series constraint extraction, and supports multiple time series graph formats and styles.

The application discloses a literature processing method and device based on multi-agent cooperation, a storage medium and a computer device. The method comprises the following steps: in response to a natural language instruction input by a user, performing intention analysis on the natural language instruction through a semantic analysis agent to generate an intention analysis result and an identification code, wherein the identification code is used to represent a literature processing task type to which the natural language instruction belongs; based on a responsibility chain mode, generating an agent calling sequence according to the identification code and a preset agent scheduling rule, wherein the agent calling sequence comprises a plurality of agents arranged in sequence and an execution logic relationship; sequentially activating the agents according to the agent calling sequence, and delivering a processing result of a previous agent to a next agent, wherein the processing result received by the first agent in the agent calling sequence is the intention analysis result; and generating a literature processing result according to an output result of the last agent in the agent calling sequence.

The application relates to the technical field of agent permission security risk control, and discloses an agent minimum permission pre-checking method based on layered intention analysis and permission reachable graph deduction, which adopts a double-layer coupled multi-branch condition perception layered Transformer model, draws a task global permission baseline through a main intention coding layer, completes multi-execution branch splitting through a branch condition time series coding layer, and predicts a minimum permission set of each branch in fine granularity. The application constructs a permission reachable topology graph for single-branch permission, identifies an implicit over-authorization link through link traversal and risk quantification, and completes secondary convergence of permission by adaptively cutting redundant permission. After being checked according to a compliance baseline, dynamic on-demand authorization is realized according to a task real-time execution branch, and temporary permission is automatically recovered after the task is completed. The method can realize branch-level accurate empowerment and link-level deep risk control, effectively suppresses the risk of over-authorization and implicit over-authorization of an agent across systems, and improves the permission security and compliance of an automatic task of the agent.

The invention provides a multi-modal chart analysis model based on an auxiliary Token mechanism, a reasoning method and equipment. The multi-modal chart analysis model comprises a visual encoder used for extracting multi-level visual feature representation from a chart image; the large language model is used for forming a Token sequence based on multi-level visual feature representation and text prompt, dynamically generating an auxiliary Token, and inserting the auxiliary Token into the front end of the Token sequence; the auxiliary decoder is used for enhancing the expression ability of the numerical features of the auxiliary Token and constraining numerical prediction by adopting a loss optimization mechanism; the original decoder is used for outputting structured chart data according to a preset format; and the reliability verification module is used for performing evaluation based on the numerical prediction results of the original decoder and the auxiliary decoder, generating a confidence score, and screening out numerical prediction data with a high confidence score. Compared with the prior art, automatic analysis, numerical value prediction optimization and structured output of the complex chart are realized.

An executable in a user-readable format that corresponds to a workflow function is received. The workflow function can be a stepwise process within a workflow. The executable is converted using one of natural language processing or a graph parsing algorithm and then an executable file is accessed. The executable file corresponds to the executable where the workflow function is associated with a task library function created by a machine-level language and stored at the executable file. The executable file is converted using the other of the natural language processing and the graph parsing algorithm. The converted executable file is then linked to a second user interface that is configured to present the workflow function in the user-readable format according to the stepwise process within the workflow.

The application relates to a code generation method, device and equipment based on a chip clock tree prototype graph. The method comprises the following steps: obtaining a clock tree prototype graph of to-be-generated code, analyzing the clock tree prototype graph, obtaining the type of components in the clock tree prototype graph and the connection relationship of the components, and generating the code corresponding to the clock tree prototype graph according to the type of the components and the connection relationship of the components. According to the type of the components and the connection relationship of the components, the code corresponding to the clock tree prototype graph can be directly and accurately generated. Chip design engineers do not need to design the corresponding code while designing the clock tree prototype graph. The code corresponding to the clock tree prototype graph can be automatically generated by only maintaining or modifying the clock tree prototype graph.

The present invention belongs to the field of document-level event extraction and provides a document-level event extraction method and system based on a hypergraph neural network. The method comprises obtaining document text data; extracting document-level events using a trained document-level joint extraction model based on the document text data; and designing an improved affine graph parser to enable the model to more fully capture grammatical dependency information and longer-range dependency grammatical information for local feature extraction. Furthermore, a hypergraph convolutional network is introduced for global feature extraction, while sentence and word association matrices are constructed. An effective fusion mechanism for local features and the association matrix is ​​designed to enhance the feature extraction capabilities of the hypergraph convolutional network.

The present application relates to the technical field of electronic chart, and provides an S-101 electronic chart parsing and drawing method, system, device and medium, the method comprises loading electronic chart basic information and drawing resource library, generating chart drawing parameters according to the drawing resource library;Parsing the object definition file to obtain the type, attribute, association and symbolization rule of the element in the electronic chart;Parsing the object drawing parameter file to obtain the symbolization rule and style of the map element in the electronic chart;Parsing the S-101 corresponding object space data file to obtain the spatial element record of the electronic chart, generating drawing instructions through Lua language and main program, and drawing S-101 electronic chart according to chart drawing parameters.The present application solves the pain points such as lack of self-controllability, lack of parsing depth, poor adaptation flexibility and lack of compatibility in the current S-101 electronic chart parsing and drawing field.

This invention discloses an intelligent NL2SQL generation and optimization system, application method, and storage medium, located at the intersection of natural language processing and database query technologies. Through four core components: a dynamic SQL RAG caching module, an intent-Schema dual-channel alignment module, an incremental Table-Schema perception module, and a multi-table index-guided JOIN optimization module, this system addresses shortcomings of existing technologies in high-frequency query efficiency, fuzzy intent parsing, dynamic schema adaptation, multi-table JOIN performance, and SQL reliability. This invention achieves beneficial effects such as improved query efficiency and resource utilization, enhanced fuzzy intent parsing accuracy and interaction efficiency, and dynamic adaptation of industrial-grade data warehouses. It is particularly suitable for large-model asset queries in enterprise-level operational scenarios.

The application discloses a semantic enhancement type chemical structure diagram automatic analysis system and method. The system comprises: an image recognition and structure analysis module, which utilizes an OCSR model to analyze a chemical structure image and outputs a machine-readable molecular representation, and combines a chemical common sense rule base to automatically correct errors; a text semantic analysis module, which extracts associated text and determines a chemical structure semantic role; a professional knowledge base comparison module, which compares a Tanimoto structure similarity and a name alias double-channel comparison to calculate a consistency score; a consistency verification and review module, which triggers a hierarchical review mechanism for low-confidence results and feeds back the confirmed results into the database; and a structured result output module, which outputs JSON / XML structured data containing a molecular structure, a semantic role and a confidence score, and provides a picture-text link interactive display. The application realizes a leap from image recognition to semantic understanding, greatly improves the accuracy and practical value of chemical literature structure diagram analysis.

The invention relates to the technical field of intelligent document generation, and discloses an intelligent document generation system combining adaptive user interaction and natural language processing, which comprises an information acquisition module, an intention analysis module, a dynamic question and answer module, a content generation module and an optimization adjustment module. The system realizes multi-round dialogue management, context tracking and flexible question generation through a dynamic question and answer mechanism and a natural language processing technology, ensures comprehensiveness and accuracy of information collection, and improves document quality through grammar, style and logic optimization. According to the method, the problems that a traditional document generation tool is insufficient in flexibility, limited in semantic understanding and poor in interaction experience can be solved, personalized, high-precision and high-efficiency document generation is achieved, diversified requirements of users are met, and the user experience is improved.

The invention relates to the field of thermal power plant intelligent control, and provides a thermal power generating unit depth peak regulation coordination method and system, and the method comprises the steps: collecting a video data stream and a broadband sound wave signal, and generating a high-dimensional time sequence data frame sequence through the alignment of acoustic atom dictionary timestamps; extracting visual and acoustic feature embedding vectors, constructing a heterogeneous dynamic graph, and analyzing spatio-temporal evolution to generate a future combustion instability index; an unstable mode code and a future risk index are generated based on an expert rule base, an enhanced state vector is constructed by fusing real-time macroscopic state parameters, and an optimal control instruction set is generated by an intelligent agent through optimization under dynamic constraint; the instruction set is decoded into a control signal sequence through multiple safety verification, a risk index difference value before and after intervention is compared to generate a validity evaluation index, and the validity evaluation index is packaged into an experience playback tuple to update agent parameters. According to the method, multi-mode space-time prediction and self-adaptive control are fused, a combustion instability precursor prediction and look-ahead control closed loop is constructed, and the method is suitable for intelligent monitoring and advanced process control of a thermal power plant.

This application discloses a corpus processing method, apparatus, storage medium, and program product, relating to the field of artificial intelligence technology. The method includes: identifying a file to be identified to obtain identification results, and performing clustering processing on the identification results to determine an aggregation result; constructing a full node graph based on the aggregation result, and determining a tree structure graph corresponding to the aggregation result according to the semantic relationships between nodes in the full node graph; classifying and identifying nodes in the tree structure graph, determining tree structure data, and constructing question-answer pairs to represent the semantic relationships corresponding to the file to be identified. The solution of this application solves the problems of neglecting tree graph parsing, difficulty in identifying text structure associations in OCR, insufficient feature utilization, and low extraction accuracy in existing corpus processing solutions.

The application relates to the technical field of artificial intelligence, and discloses a resource recommendation method, equipment, a medium and a product. The method comprises the following steps: obtaining a resource recommendation request; performing intention analysis on the resource recommendation request according to a first large language model to determine corresponding target intention information; determining at least one target recommendation tool from a plurality of preset recommendation tools according to the target intention information; determining a plurality of candidate resources corresponding to each target recommendation tool; rearranging the plurality of candidate resources to determine at least one target resource; and outputting the at least one target resource. The application decouples intention understanding and data retrieval, uses the powerful reasoning capability of a large language model to understand the deep intention of a user, can accurately realize intention analysis, assigns appropriate and professional recommendation tools for data retrieval based on the deep intention, and can accurately meet the recommendation requirements of the user while deeply understanding the requirements of the user.

The application discloses a natural language spatiotemporal retrieval method and system based on a large model, relates to the technical field of big data resource services, and comprises the following steps: fine-tuning a preset large language model according to a spatiotemporal retrieval problem and a preset prompt word engineering template; dividing a target management area into geographical space grids, each of which has a unique grid code; constructing an entity knowledge base classified according to different data categories based on a business spatiotemporal database and dynamic semantic labels; performing natural language intention analysis on user input based on the fine-tuned large language model, identifying spatial constraints, time constraints and business attribute constraints; converting the spatial constraints into filtering conditions; querying the data categories of corresponding key entities in the entity knowledge base; and outputting spatiotemporal retrieval results based on the fine-tuned large language model according to the business attribute constraints, the data categories, the spatial constraints and the filtering conditions. The application is free from professional dependence, improves the interactive experience and is highly flexible.