58 results about "Natural language semantics" patented technology

The invention discloses an unmanned aerial vehicle flight control system vulnerability detection method based on data flow analysis and LLM, and belongs to the technical field of intelligent software testing. Comprising the following steps: extracting a code function module associated with user operation in an unmanned aerial vehicle flight control system through a data flow analysis method, and establishing an operation-code mapping relation library; generating a structured natural language semantic description for each function module code by adopting a large language model LLM, and forming a multi-dimensional semantic feature vector; based on correlation analysis of multi-module semantic features, a combined test scene is constructed, and a natural language test case is generated; the natural language test case is converted into an executable test code through reverse semantic mapping, and coding reconstruction of test logic is completed; and executing a test code and capturing a runtime log in an unmanned aerial vehicle simulation environment, and performing vulnerability feature extraction and root cause positioning by using a large language model. According to the method, the efficiency is improved, and meanwhile, the deep coverage test of a complex interaction scene is supported.

The invention discloses a natural language semantic recognition method, device and equipment and a medium, and the method comprises the steps: extracting semantic features according to an input natural language, inputting the semantic features into an initial hybrid expert model, and analyzing the semantic features through a Transform model to obtain a hidden state matrix; inputting the hidden state matrix into a gating network to generate a routing weight matrix; on the basis of rank estimation of randomized singular value decomposition, generating the number K of expert networks activated by the current layer in combination with the hidden state matrix; selecting first K expert networks according to a sorting result of the routing weight matrix, generating a mask matrix, executing sparse forward calculation, and optimizing model parameters of the expert networks based on sparse gradient propagation and load balancing loss to obtain a target hybrid expert model; and the target hybrid expert model is adopted to recognize the semantic features to obtain a semantic recognition result, and the semantic recognition accuracy and efficiency are improved by adopting the semantic recognition method and device.

The invention belongs to the field of electric digital data processing, and particularly relates to a multi-source cross-modal threat intelligence processing method, device and equipment and a medium. Innovation of a threat intelligence processing normal form is realized through a technical route of'double-layer progressive fusion ': a cross-modal fusion layer focuses on heterogeneous feature deep coupling of natural language CTI and picture CTI, and mapping of natural language semantics and visual information is realized by adopting a three-stage processing mechanism of'intra-modal self-attention, cross-modal cross attention and LSTM time sequence fusion'; and the multi-source alignment layer is used for carrying out joint modeling on CTI feature vectors subjected to cross-modal fusion, malicious codes and log data, constructing a three-dimensional association network of a CTI knowledge graph, a malicious code graph and a log time sequence graph, and realizing cross-source semantic space unification through a heterogeneous graph attention network. The problems that when a traditional threat intelligence processing method faces multi-source cross-modal data, collection and integration are difficult, preprocessing is insufficient, cross-modal feature fusion is difficult, and knowledge graph construction is imperfect are solved.

The invention discloses a natural language semantic recognition model and system for linguistics, and relates to the technical field of semantic recognition, the natural language semantic recognition model comprises a multi-level context perception semantic recognition module, the multi-level context perception semantic recognition module receives pre-processing data output by a text pre-processing module, and the text pre-processing module sends the pre-processing data to the text pre-processing module; the semantic weight is adjusted under the guidance of the disambiguation optimization module, and the multi-level context perception semantic recognition module is used for extracting semantic features from a plurality of context levels. According to the method, a multi-level context perception semantic recognition module is designed, semantic features are extracted to capture the logic relation between a complex context and a long text, the problem that a traditional model is insufficient in understanding of complex sentence patterns and multi-level contexts is solved, and the accuracy and expression richness of overall semantic recognition are improved.

Implementations of semantic parsing using pre-trained language models are provided. One aspect includes a computing system for semantic parsing of natural language. The computing system comprises processing circuitry and memory containing instructions that, when executed, cause the processing circuitry to receive a request comprising a natural language utterance and generate a formal meaning representation using the natural language utterance and a language model comprising a semantic parser that has been prompted with training data generated by providing a dataset comprising a set of unlabeled programmatic scripts and a seed programmatic script, generating a set of parsed natural language descriptions by inputting the set of unlabeled programmatic scripts into an inverse semantic parser, generating a set of re-parsed programmatic scripts by inputting the set of parsed natural language descriptions into the semantic parser, and determining a set of labeled programmatic scripts by validating the set of re-parsed programmatic scripts.

The invention discloses an intelligent query method for a railway construction stage operation instruction, which comprises the following steps of: S1, sorting an operation instruction text, S2, extracting a chapter number, dividing chapter content and establishing chapter association, S3, extracting a summary of the chapter, S4, creating a knowledge graph of the railway construction stage operation instruction, S5, identifying user query semantics, generating a query semantic set, and S5, storing the query semantic set into a database, s6, converting the query semantic set into a knowledge graph query statement; and S7, visually displaying a graph query result, and outputting the query result. According to the method, a large model technology is taken as a core, the natural language semantic understanding capability of a large model and the structured knowledge management capability of a knowledge graph are highly fused for the structured characteristics of the railway construction stage operation instruction, and intelligent query of the railway construction stage operation instruction based on the natural language is realized.

The invention relates to a large model database query generation method, system and device based on semantic matching prompt and a medium, and the method comprises the following steps: constructing a database query-oriented natural language semantic representation model, and generating a semantic vector by taking a natural language query text input into a database by a user as input; based on a semantic vector similarity matching mechanism, retrieving a historical query text most similar to the semantic vector from a pre-stored training set; extracting a database query statement corresponding to the historical query text as a semantic guidance prompt, and forming a structured prompt word instruction with a natural language query text input into a database by a user; and inputting the prompt word instruction into a pre-trained large language model, calling the context reasoning capability of the large language model, and generating a target database query statement consistent with the intention of the user, thereby completing the conversion from the natural language to the SQL, and obtaining a user query result. The method can be widely applied to the crossing field of artificial intelligence and database technologies.

The invention discloses a 3D modeling calculation auxiliary system based on natural language driving, in the system, a basic information input unit is used for receiving a modeling request input by a user, and the modeling request comprises description of specific scene modeling requirements of the user in a natural language form; the semantic recognition unit performs semantic recognition on natural language input information to extract structural modeling calculation parameters, and performs standardized output; a corresponding modeling tool flow is called through a 3D modeling unit according to the semantic recognition result of the large model, and parametric modeling is carried out; the finite element calculation unit can perform data interaction with the 3D modeling unit, geometric information established by the 3D modeling unit is input into finite element calculation software, calculation parameter structures serve as other parameters to be input into the finite element calculation software, corresponding finite element models are established according to the calculation parameter structures, and solving calculation is performed. According to the system, a hybrid architecture of natural language semantic link parameterized workflow is adopted, so that the learning cost of parameterized modeling, finite element calculation and special calculation requirements can be effectively reduced, and the efficiency of modeling and calculation is improved.

The invention relates to the field of natural language semantic analysis, in particular to a natural language-driven CIM scene interaction method and system, and the method comprises the steps: receiving a natural language interaction instruction inputted by a user side in real time; analyzing the natural language interaction instruction, and extracting scene data in the natural language interaction instruction; calling a semantic mapping library based on the extracted scene data, and mapping the scene data into corresponding CIM platform functions and space elements through the semantic mapping library; according to the CIM platform function and the space element, generating an interface calling instruction of the CIM platform, sending the interface calling instruction to the CIM platform, and executing a corresponding space element operation through the CIM platform; an operation result returned by the CIM platform is received, multi-modal feedback information is generated based on the operation result, and the multi-modal feedback information comprises visual feedback carried out in the CIM scene; visually feeding back synchronous natural language explanation feedback; and outputting the multi-mode feedback information to the user side.

The invention discloses a psychological state text classification method based on large model generative data enhancement, and relates to the technical field of natural language processing. According to the method, patient psychological semantic clusters are automatically found by clustering a limited number of original samples, and then a natural language semantic template of each patient psychological semantic cluster is extracted; then, under the dual control of emotional polarity and psychological themes by utilizing a large language model, according to the natural language semantic templates, psychological state texts with consistent themes and diversified expressions are generated as enhanced samples; according to the method, high-quality sample generation is carried out by utilizing a natural language semantic template obtained based on clustering through a large language model so as to expand a model training sample, and the authenticity and diversity of the generated enhanced sample can be ensured through the large model generation type data enhancement method; therefore, the classification accuracy and generalization ability of the psychological state text classification model obtained through training are improved.

The invention provides a multi-interface collaborative natural language data query method and system, and relates to the technical field of natural language processing.The method comprises the steps that text query data transmitted by a text input interface, voice query data transmitted by a voice input interface and touch instruction data transmitted by a touch selection interface are obtained; performing optimization processing on the voice query data and the touch instruction data to obtain a multi-interface fusion text set; analyzing the annotation data set based on preset natural language semantics to obtain a semantic analysis result; generating a unified query instruction through a digital information transmission technology; determining a data source corresponding to each piece of query field information in the semantic analysis result; according to the method, the initial query result is obtained according to the preset retrieval rule of each data source, so that accurate analysis and cross-interface unified execution of the natural language query intention are realized, and the accuracy, robustness and interactive experience of data query in a complex scene are improved.

This application discloses a user behavior attribution method and related products. The method constructs a behavior sequence for each user based on multimodal behavior data of multiple users within a preset time window. Based on each user's behavior sequence, corresponding natural language semantic tags are determined, and these tags are converted into corresponding semantic vectors. The semantic vectors of multiple users in the current time window and in historical time windows are clustered to obtain clustering results for the current and historical time windows. The clustering results of the two time windows are compared to determine the semantic drift trajectory of each user group. Based on the semantic drift trajectories of multiple user groups, the contribution of each user group to the fluctuation of preset business indicators is quantified, and the quantification results are generated, along with an attribution report. Compared to the low accuracy of existing user behavior attribution technologies, this application has significant advantages.

The invention provides a cross-domain shared biological information metadata integration and management platform, and belongs to the technical field of bioinformatics. Comprising a metadata acquisition module used for supporting uploading of various metadata file formats, recording data change history and providing field preview and condition prompt; the metadata standardization and semantic mapping module is used for realizing field semantic analysis, standardized mapping and user-defined mapping management through a built-in biological ontology library; the universal metadata model building module is used for providing a dual-interface definition metadata structure template and realizing model version control and field verification; the authority control and sharing mechanism module is used for setting a data visibility authority and distributing a metadata unique reference identifier; the advanced retrieval and semantic search module is used for supporting condition combination retrieval and natural language semantic association retrieval; and a database. According to the method, standardized integration, safe sharing and semantic retrieval of the multi-source heterogeneous metadata are realized, the cross-laboratory cooperation efficiency is improved, and the scientific research cost is reduced.

Technologies for machine learning-based entity understanding and resolution are disclosed. Data for training an entity resolution model is collected to learn semantic relationships associated with entity names. The entity names are provided in a domain of documents that follow the semantic conventions differently from natural language semantic conventions. The data includes entries each specifying an entity name and a label. The entity resolution model is trained using the data to learn and generalizes the semantic relationships and is deployed to serve requests for resolving an entity name from text extract from a document image.

The invention relates to the field of language control systems, and discloses a virtual reality natural language interaction control system based on big data, and the system comprises a data acquisition unit which collects the interaction original data of a virtual reality scene according to a sensor array; performing natural language semantic analysis on the interaction original data to obtain user intention semantic feature data; performing virtual scene correlation analysis according to the user intention semantic feature data to obtain scene correlation data; a data prediction unit; through natural language semantic analysis in the data acquisition unit, intention feature data of the user can be extracted, so that the system can more accurately understand the requirements of the user in a virtual reality environment, the naturalness and fluency of interaction are improved, and in addition, by combining scene correlation analysis and user behavior pattern mining, the interaction efficiency is improved. The interactive intention of the user can be dynamically predicted, so that the user demand is responded in advance, and the immersive experience is enhanced.

The invention discloses a railway standard specification digital processing method based on a large model and a knowledge graph. The railway standard specification digital processing method comprises the steps of S1, railway standard specification preprocessing, S2, railway standard specification term knowledge graph construction, S3, semantic splitting combination and semantic extraction of railway standard specification articles, and S4, railway standard specification structured output. According to the method, a large model technology is taken as a core, the natural language semantic comprehension ability of a large model and the industry knowledge management ability of the knowledge graph are highly fused, and the railway standard specification term knowledge graph is established through intelligent term extraction in the specification, semantic disassembly of term paraphrasing and intelligent calculation of term similarity. The method is used for replacing the step of building a dictionary and a synonym list in traditional digital processing, standard specification provisions are intelligently split based on a large model, a keyword set is preliminarily extracted, the keyword set is expanded based on a term knowledge graph, a synonym and associated word set is automatically constructed, and finally, an lxml library of Python is used for conducting structured output on an analysis result. And high-efficiency digital processing of railway standard specifications is realized.

The application provides a natural language semantic understanding method and device based on a vertical field knowledge graph, which comprises the following steps: performing word segmentation processing on input text to obtain at least one candidate word segmentation result; determining a relationship set corresponding to each candidate word segmentation result in the at least one candidate word segmentation result based on a knowledge graph, wherein each element in the relationship set represents a relationship corresponding to a word segmentation entity pair of the candidate word segmentation result corresponding to the relationship set, and the type of the relationship is related to two ontologies corresponding to the word segmentation entity pair and the word segmentation entity pair; and determining a target word segmentation result from the candidate word segmentation result according to the relationship set corresponding to each candidate word segmentation result in the at least one candidate word segmentation result. The optimal target candidate word segmentation result can be confirmed, the candidate word segmentation result with ambiguity is eliminated, and the user satisfaction is improved.

The application provides a multi-interface cooperative natural language data query method and system, relates to the technical field of natural language processing, and obtains text query data transmitted by a character input interface, voice query data transmitted by a voice input interface and touch instruction data transmitted by a touch selection interface; the voice query data and the touch instruction data are respectively optimized to obtain a multi-interface fusion text set; based on a preset natural language semantic analysis annotation data set, a semantic analysis result is obtained; a unified query instruction is generated through digital information transmission technology; data sources corresponding to each query field information in the semantic analysis result are determined; and an initial query result is obtained according to preset retrieval rules of each data source, so that accurate analysis and cross-interface unified execution of a natural language query intention are realized, and the accuracy, robustness and interactive experience of data query in a complex scene are improved.

The invention discloses a hybrid multi-modal document retrieval enhancement method, system and device and a storage medium. The method comprises the following steps: performing format analysis on an unstructured document; generating a text vector, a visual vector and a structured table vector based on an analysis result, and constructing three index libraries for storing the text vector, the visual vector and the structured table vector respectively; in response to the natural language queried by the user, recalling candidate text paragraphs, candidate pictures and candidate tables related to the semantics of the natural language queried by the user; merging at least two types of candidate elements in adjacent candidate text paragraphs, candidate pictures and candidate tables in the same page into a mixed fragment; assembling a plurality of mixed fragments to form a multi-modal context; and inputting the multi-modal context into the large language model to obtain an answer. According to the method, adjacent candidate elements of the same page are merged, spatial position association of elements in a document is considered, and cross-modal information is automatically integrated, so that the obtained answers pay more attention to context association.

This application discloses a graph-based natural language control method, apparatus, device, and medium for accelerators, relating to the field of particle accelerator control technology. Through deep integration of a natural language semantic scheduling module and an accelerator domain knowledge graph, it achieves precise conversion from unstructured natural language instructions to standardized device control commands. The method includes: receiving first natural language text input by a user; parsing the first natural language text into control intentions and parameter slots based on a pre-trained natural language semantic scheduling module; mapping the control intentions and parameter slots to accelerator devices based on a pre-constructed accelerator domain knowledge graph, utilizing the device topology and operational dependencies within the accelerator domain knowledge graph, and inferring and generating a control command sequence; and distributing the control command sequence to the target accelerator device to control the target accelerator device to perform corresponding operations.

The invention provides a code snapshot management method and device and related equipment. The method comprises the following steps: monitoring a change event of a code file; obtaining multiple pieces of evaluation dimension information corresponding to the change event, and fusing the multiple pieces of evaluation dimension information to obtain a semantic importance score corresponding to the change event; when it is determined that the score is larger than a preset score threshold value, semantic analysis is conducted on codes in the change file, corresponding code semantic information is obtained, and according to the code semantic information, a code snapshot is generated and stored. According to the method, an automatic triggering mechanism based on semantic importance evaluation is adopted for code change evaluation, whether snapshots are generated or not is intelligently decided on the basis of an automatic snapshot triggering mechanism, problem positioning is converted into semantic retrieval through natural language semantic matching, the analysis period is greatly shortened, the uncertainty of manual judgment is eliminated, and the analysis efficiency is improved. According to the generated code snapshots, the storage cost is reduced on the premise of ensuring that any historical snapshots can be completely reconstructed.

The application discloses a railway construction stage operation instruction book intelligent query method, including S1. Operation instruction book text arrangement, S2. Extract chapter number, divide chapter content, and establish chapter association, S3. Extract the summary of the chapter, S4. Create a railway construction stage operation instruction book knowledge graph, S5. Identify user query semantics, generate a query semantic set, S6. Query semantic set is converted into a knowledge graph query statement, S7. The graph query result is visualized and displayed, and the query result is output. The application takes large model technology as the core, faces the structured characteristics of the railway construction stage operation instruction book, highly integrates the natural language semantic understanding ability of the large model and the structured knowledge management ability of the knowledge graph, and realizes the intelligent query of the railway construction stage operation instruction book based on the natural language.

The present invention relates to a natural language semantic extraction method and system, wherein the method comprises: performing word segmentation on a target document in units of sentences to obtain word segmentation units; analyzing whether multiple word segmentation units in a sentence constitute keywords; in response to multiple word segmentation units in a sentence constituting one or more keywords, extracting the sentences containing the keywords; performing grammatical analysis on the sentences containing the keywords to obtain a syntax tree; and extracting effective keywords and corresponding semantic tags from the syntax tree. The method and system provided by the present invention extract keywords that meet the requirements of information recommendation from the relevant target document content, and obtain effective keywords through grammatical analysis of the sentences containing the keywords, splitting and reconstructing the syntax tree, so as to obtain the true intention of the target document and improve the understanding of the user's target requirements.

This invention discloses a high-performance semantic recognition method, belonging to the field of natural language semantic recognition. The method first converts a sentence into a corresponding word vector sequence according to word order, and then inputs the word vectors into a semantic recognition network to obtain the recognition result. The semantic recognition network includes several sequentially arranged semantic recognition units; each semantic recognition unit includes hidden neurons, a value prediction network, an output neuron, and a classifier. During computation, the value prediction value determines whether each unit is retained. After all word vectors have been processed, the classification result output by the classifier in the last semantic recognition unit marked as "retained" is taken as the semantic recognition result of the sentence. This invention can reduce the computational load while ensuring that semantic features are not lost, significantly improving the performance of semantic recognition.

The application provides an agent identity verification method based on a trust mechanism, belongs to the technical field of artificial intelligence and network security, and is used for solving the problems that in related technologies, external credentials cannot distinguish real agents from fake requests and are vulnerable to prompt injection attacks. In the application, a natural language semantic task is issued by a verification direction request party as a verification task, the request party generates a high-cost natural language response meeting a preset quality constraint, the verification party performs lightweight verification with a lower computing resource than the generation cost, and if the verification is passed, the request party is determined to be an agent with a legal semantic generation capability. The application realizes identity verification based on the endogenous semantic capability of the agent as the trust basis, naturally resists fake and flooding attacks through a cost asymmetry mechanism, and is immune to prompt injection at the protocol level through an output locking mechanism, and can be widely applied to trusted communication scenarios of an agent network.

The application provides a kind of track traffic emergency dispatching method and intelligent agent system based on subgraph retrieval and scene perception, belongs to the field of track traffic emergency dispatching.The application first converts unstructured event description and knowledge text into semi-structured scene parameter set through large language model, and then automatically maps the semi-structured scene parameters into the binary activation state of the corresponding constraint in the mixed integer linear programming model through the scene perception constraint activation function, thereby realizing reliable bridging between natural language semantic understanding and strict mathematical constraint modeling, avoiding the illusion risk of directly processing mathematical constraints by large language model and the limitations of traditional optimization methods that cannot understand unstructured text, and solving to generate train working diagram adjustment scheme, through multi-dimensional credibility evaluation framework and intelligent agent iterative dispatching closed loop to guarantee the reliability of dispatching decision.

The automated generation of a natural language explanation of what code does. The code is structured to perform tasks because the code itself semantically specifies that those tasks are to be performed. A task-centric representation of the code is automatically generated that includes a task representation of each of some or all of the tasks to be performed as specified by the code. Natural language utterances are then automatically generated by generating a corresponding natural language utterance that semantically describes in natural language the corresponding task represented by the corresponding task representation. Controls are rendered for each natural language utterance that each permit a user to edit the corresponding natural language utterance. After editing, the code itself may be automatically modified or regenerated to reflect the changed natural language utterances.

The application discloses an intelligent question answering implementation method and device based on an analysis model, and a medium, and belongs to the technical field of large models. The technical problem to be solved by the application is how to improve the accuracy of natural language semantic analysis, improve the practicability of intelligent question answering, and overcome the defects of deviation between the expression habits of natural language of users and the API of a business intelligent system. The technical scheme is as follows: an analysis model metadata vector library is constructed; a custom dictionary is added; semantic analysis: after user input information is segmented by a segmenter, a segmented result meeting industry characteristics is obtained, and the original text is preliminarily analyzed according to the segmented result to obtain a structured original text analysis result; the structured original text analysis result is used to match index names and role playing dimension names; dimensions are inversely searched through physical dimension names, dimensions are inversely searched through dimension attribute names, and dimensions are inversely searched through constraint values to obtain constraint detailed information; and a business intelligent system API is called.

The application discloses a kind of based on natural language semantic conversion's graph database query statement construction method, comprising the following steps: 1) according to node label, graph database node is classified, entity extraction is carried out to classification result, and abstract entity set E is established;2) abstract entity is established corpus entity set C by synonym mining and is materialized as corpus entity;3) define basic graph database query statement template;With the aid of knowledge base, natural semantics is selected, and natural semantics is converted into formal semantics;4) semantic entity set Q is traversed in order, and query clause pql is constructed;The application proposes a kind of based on natural language semantic conversion's graph database retrieval service construction method, can be suitable for multiple different types of graph database, and good universality.

The invention discloses a high-performance semantic recognition method, and belongs to the field of natural language semantic recognition. The method comprises the following steps: firstly, converting a statement into a corresponding word vector sequence according to a word order, and then inputting word vectors into a semantic recognition network to obtain a recognition result. The semantic recognition network comprises a plurality of semantic recognition units which are arranged in sequence; the semantic recognition unit comprises a hidden layer neuron, a value prediction network, an output neuron and a classifier. And during calculation, determining whether each unit is reserved or not according to the predicted value. And after all word vectors are processed, taking a classification result output by the classifier in the last semantic recognition unit marked as'retention 'as a semantic recognition result of the statement. According to the method, the operand can be reduced under the condition that the semantic features are not lost, and the semantic recognition performance is remarkably improved.