49 results about "Semantic role labeling" patented technology

The invention relates to the technical field of intelligent bid evaluation, and provides an intelligent multi-dimensional bid evaluation analysis and decision-making method based on big data, which comprises the following steps: acquiring original bid evaluation data from a multi-source heterogeneous data interface, and fusing through semantic role labeling and a timestamp alignment algorithm to generate a time-space association data set. And performing multi-level cleaning to generate a high-confidence bid evaluation data set. And extracting a multi-dimensional index based on the domain knowledge graph, generating a dynamic feature tensor, and dynamically allocating a weight by adopting a coupling attenuation weight model. And constructing a bidder association network, calculating a node influence score, detecting a potential bidding behavior and generating a risk correction coefficient. And injecting the real-time data stream into the dynamic feature tensor, updating the index weight, and generating a three-dimensional scoring vector through a multi-target aggregation decision algorithm. And performing Pareto optimization by using the asymmetric game equilibrium model, and outputting an optimal bid-winning party sequence and a risk early warning report. The bid evaluation efficiency and fairness can be improved, and the bid invitation risk is reduced.

The invention relates to the technical field of text data analysis, in particular to an electronic medical record free text analysis method, system and device, which improve the efficiency of information extraction and reduce the demand of manual intervention. The method comprises the steps of receiving free text data of the electronic medical record, performing cleaning, word segmentation and medical term standardization processing, and converting an unstructured text into structured data; based on deep learning and a medical knowledge base, text features are extracted through a pre-training language model, entity boundaries are captured on an output layer in combination with a conditional random field, medical entities in a text are recognized, and the recognized entities are classified and labeled; extracting a causal relationship, a treatment relationship and an examination relationship among entities through a dependency syntactic analysis and semantic role labeling technology, and constructing an entity association network; performing dynamic correction and supplementation on entity classification and relationships in combination with medical record context information; and outputting an analysis result in a structured JSON format to generate a computable semantic map.

The embodiment of the invention provides a fraud phone real-time recognition method and device based on AI semantic understanding, and the method and device achieve the precise understanding of the dialogue content through the innovative construction of a voice analysis mechanism, the grammatical feature extraction and the semantic role marking. And designing a scene discrimination model based on verbal skill recognition, and establishing a fraud verbal skill recognition strategy for intelligent classification in combination with semantic pattern matching and hierarchical clustering algorithms. A residual fusion assessment mechanism is introduced, and accurate assessment and timely prevention and control of call risks are realized through historical case feature fusion and risk scoring. According to the method, the defects of the traditional technology in the aspects of speech understanding, verbal skill recognition, risk assessment and the like are effectively overcome, and the accuracy and reliability of fraud phone recognition are remarkably improved.

The invention provides a structured processing method and device for a contract text, equipment and a storage medium, and the method comprises the steps: carrying out the preprocessing of the contract text, generating a standardized word sequence, and enabling the standardized word sequence to comprise a plurality of word sequences and part-of-speech tagging information of each word sequence; the standardized word sequence is input into a named entity recognition model to recognize key entities in the contract text, key terms in the contract text are extracted based on a machine learning algorithm, the key entities include both parties of the contract, the amount of the contract and the name of a product, and the key terms include payment terms, delivery terms, default responsibility terms and force majeure terms; through dependency syntactic analysis and a semantic role labeling model, analyzing to obtain a semantic relationship between the key entities and the key terms; and storing the extracted key entities, key terms and semantic relationships in a target database in a structured form, and establishing a target index to support quick query. According to the invention, the error rate of manual processing is reduced.

The invention discloses a research and development platform language intelligent analysis method based on multi-system fusion, and relates to the technical field of language intelligent analysis. According to the method, various language data in a multi-system fusion research and development platform are efficiently processed, cleaned and coded to generate a standardized data set by customizing a data adaptation interface, deep lexical and syntactic analysis and semantic role labeling are performed on the standardized data set, related features are extracted, a semantic mapping network is constructed, and semantic feature vectors are generated; cross-modal feature fusion is realized, deep meanings of language data are comprehensively captured, rich feature input is provided for intelligent analysis, a constructed intelligent analysis model can perform accurate intelligent analysis and intention recognition on natural language instructions and technical documents, and the intelligent analysis model can be used for performing intelligent analysis and intention recognition on the technical documents by means of compiling environment simulation, debugging information semantic optimization and the like. The model training effect is improved, and the analysis accuracy and the hardware compatibility are improved through hardware behavior simulation, real-time data flow analysis, user feedback and other modes.

The invention discloses a PDF contract file identification method and system, a medium and a program product, and relates to the technical field of information identification, and the method comprises the steps: carrying out the image analysis of an obtained PDF contract file through employing a deep learning model, generating an editable text, and synchronously identifying the page layout of the document, outputting structured data including page numbers, text paragraphs and coordinate information; performing multi-dimensional feature matching on the text paragraphs according to an adaptive semantic analysis algorithm, a preset contract template library and a dynamic keyword library, and positioning contract core element information; performing entity relationship verification on the content of the contract core element information, correcting an extraction error through dependency syntactic analysis and semantic role labeling, and establishing a contract element data set containing a confidence coefficient weight; and performing serialized packaging on the verified contract element data set to generate a contract element list conforming to electronic signature authentication. According to the invention, the processing efficiency and recognition precision of the PDF contract file are improved.

The invention relates to the technical field of intelligent testing, and discloses a software test task management method and device based on an intrusive instruction knowledge base, equipment and a medium, and the method comprises the steps: analyzing an obtained demand card based on a large model technology, analyzing a semantic role of a vocabulary in the demand card through a semantic role labeling technology, and obtaining a semantic role of the vocabulary in the demand card; extracting test requirements and test points of semantic roles of vocabularies in the requirement cards; querying test information matched with the test requirements and the test points in a knowledge base of the software project, and determining the test information with the highest matching degree as target test information; in combination with the demand card and the target test information, automatically generating a test scheme of the current version based on a large model technology; and according to the generated test scheme. The method can be applied to the development of business systems such as financial science and technology, medical health, old-age care and the like, and the efficiency of the test work is remarkably improved by automatically analyzing the demand card, generating the test scheme and arranging the test task.

The invention discloses a flexible business process automatic configuration method and system based on semantic intention recognition, and relates to the technical field of semantic recognition, and the method comprises the steps of semantic fragment extraction, process fragment atlas construction, process structure generation, process configuration visualization and flexible business process configuration. The method comprises the following steps: carrying out word segmentation, named entity recognition, semantic role labeling and relation extraction on natural language input by adopting a hierarchical guide type semantic decomposition combined extraction model, establishing a business semantic labeling system, and realizing modeling and extraction of semantic elements such as actions, objects, roles and conditions; on the basis, a process fragment graph improved by structural semantic fusion is constructed, and through node-level splitting, semantic tag binding and logic connection abstraction, process fragment graph data with tag attributes are generated, so that semantic understanding, process matching and cross-scene multiplexing capabilities are improved, and efficient, flexible and intelligent configuration of a business process is realized.

The invention discloses a photovoltaic construction professional knowledge base construction and updating method based on an NLP technology. The method comprises the following steps: firstly, acquiring a multi-source text from multiple channels; photovoltaic domain entity recognition is completed by adopting a named entity recognition technology after preprocessing, an entity relationship is extracted through dependency syntax and semantic role labeling, and a knowledge triple is generated; and then performing unified modeling on entity category levels and relationship types based on the ontology, storing a triple into a graph database, storing detailed attributes and business process data of entities and relationships into a relational database, and realizing interconnection of the two databases by a bidirectional URI mapping mechanism. In the updating stage, minute-level knowledge updating is achieved through increment monitoring, entity alignment, conflict resolution and version control. And finally, performing quantitative evaluation on knowledge quality, and performing feedback by a visual instrument panel to form closed-loop optimization. Real-time and reliable knowledge support can be provided for planning, design, construction and operation and maintenance of a photovoltaic project through knowledge base entity recognition query constructed by the method.

The invention discloses an e-commerce platform user comment emotion tendency analysis method. The method comprises the following steps: S1, obtaining a comment corpus and preprocessing the comment corpus; s2, constructing a time sequence syntactic graph based on a time decay function weighting dependency edge, and constructing a document-sentence-aspect-word multi-level hierarchical semantic graph based on semantic role labeling; and S3, based on the time sequence graph neural network and the graph attention network, respectively encoding the time sequence syntactic graph and the hierarchical semantic graph, and outputting a corresponding feature matrix. S4, performing dynamic weighted fusion on the two types of features through an attention mechanism to form comprehensive feature representation; s5, inputting the comprehensive features into a full connection layer for emotion classification to obtain emotion polarity; according to the e-commerce platform user comment emotional tendency analysis method provided by the invention, the time sequence syntactic graph and the hierarchical semantic graph are respectively coded through the graph neural network, so that the problems of high semantic information extraction difficulty and context dependency deficiency under the condition of a complex text structure are solved, and support is provided for e-commerce product popularity analysis.

The invention relates to a patient follow-up visit management method and system, and solves the problems that generation of follow-up visit content by means of a fixed template is lack of personalized consideration, and actual situations such as special requirements, living changes and current disease treatment stages of patients cannot be fully combined. The method comprises the following steps: performing feature coding on a first draft of follow-up content and personalized adjustment information, identifying semantic association features of sentence components through a semantic role labeling technology, calculating statement similarity of to-be-fused content by applying a semantic matching technology based on a cosine similarity algorithm and a word vector model, and optimizing a content logic structure so as to eliminate redundant information; and finally, the follow-up visit content of this time is formed. And based on a preset follow-up plan, the follow-up content of this time is combined with the features extracted from the health data of the patient, and a voice notification strategy is generated by adopting a reinforcement learning algorithm. The follow-up visit management method has the following effect that the accuracy and efficiency of follow-up visit management of the patient are improved.

The invention provides a technical and economic risk event extraction method and system based on monitoring entities, and relates to the technical field of entity extraction, and the method comprises the steps: carrying out the entity recognition of a multi-source science and technology text, carrying out the entity comparison and screening of technical and economic monitoring entities, and outputting a candidate monitoring entity list; performing semantic fragment extraction by taking the candidate monitoring entity list as an anchor point, and performing event type judgment based on a trigger word matching rule; performing dependency syntactic analysis and semantic role labeling on the trigger word set, constructing a standardized event structure, extracting a semantic relationship, and outputting a risk event candidate structure set; identifying chapter-level master events, and aggregating paragraph-level associated events to form a master-slave event structure; and assembling the event chain according to the master-slave event structure, and performing standardized output. By means of the method and device, the technical problem that in the prior art, the reliability of extraction of economic risk events is poor can be solved, and the technical effect of improving the reliability of extraction is achieved.

The invention provides an intelligent work order automatic classification system, and relates to the technical field of work order management. According to the system, work order texts are analyzed through an LLM technology, core business phenomena are identified, auxiliary descriptions are eliminated, and an initial phenomenon mark set is generated. And further establishing a cross-sentence association analysis mechanism, dynamically inserting context associators with directivity between discrete phenomena based on syntactic dependency and semantic role labeling, and implementing dynamic weight assignment based on context proximity. The system generates a causal rule set with version identification, and a multi-decision trigger unit processes weighted phenomenon marks in parallel to generate a differentiated candidate root cause set. And the decision conflict quantization unit calculates rule matching degree distribution, and activates rule backtracking verification to ensure decision stability. And finally outputting a root cause classification work order entity with a rule version traceability identifier, thereby realizing automatic work order classification with high accuracy and stability.

The invention discloses a voice real-time question and answer processing method based on a large model and a domain knowledge base, which belongs to the technical field of computer data processing, and comprises the following steps: acquiring a voice input stream of a user, carrying out intelligent sound wave deconstruction on the voice input stream, generating a text stream, and carrying out dependency syntactic analysis and semantic role labeling; generating intention information and key information, dynamically accessing a domain knowledge base, executing predictive loading, generating a preloaded data subset, performing fusion processing by combining the intention information, the key information and the preloaded data subset, generating a fusion result, performing accuracy verification and correction, generating a natural language answer, and converting the natural language answer into voice output. The technical scheme of combining knowledge predictive loading driven by intention analysis, context fusion and answer traceability correction is adopted, and low-delay response, high-precision intention understanding and high-factuality answer of voice questions and answers can be achieved.

The invention relates to the technical field of intelligent question answering, and discloses an enterprise regulation intelligent question answering system and method based on semantic understanding, and the system comprises a data collection layer which is used for obtaining a multi-level complex regulation query statement input by a user; the semantic understanding layer is used for performing word segmentation, dependency syntax analysis and semantic role labeling on a query statement; and the knowledge reasoning layer is used for carrying out multi-step evidence fusion and answer verification through a logical reasoning engine. The method comprises the following steps: S1, acquiring a multi-level complex regulation query statement input by a user; s2, performing word segmentation, dependency syntax analysis and semantic role labeling on the query statement; and S3, analyzing the nested structure statement by using a hierarchical recurrent neural network. By introducing a multi-level semantic understanding mechanism and combining dependency syntactic analysis, semantic role labeling and a level recurrent neural network, deep structure analysis of the composite query statement is achieved, and the real intention which is not shown by a user can be accurately recognized.

The invention discloses a medical data storage method based on semantic recognition, and belongs to the technical field of data processing, and the method comprises the steps: receiving medical data, carrying out the parallel processing of an unstructured medical text in the medical data through a large language model, and generating a structured semantic triple and a semantic vector representing the overall semantics; constructing a semantic graph index and a vector index to form a mixed index structure; the method comprises the following steps: receiving a natural language query, analyzing the query into a structured query condition and a query vector, forming an executable multi-modal query instruction, executing atlas query and a vector similarity search process in parallel, and mapping the structured query condition to a semantic atlas execution path for matching. In the implementation process of the technical scheme, natural language processing and a large language model are introduced, entity recognition, relation extraction and semantic role labeling are conducted on medical unstructured texts, and structured conversion of key information such as illness state description, diagnosis conclusions and treatment schemes is achieved.

The invention discloses a large model reasoning question and answer method for enhancing a multi-modal knowledge graph based on image retrieval, and belongs to the technical field of artificial intelligence and knowledge graph crossing. Firstly, keywords are screened through multi-stage text analysis, and images are accurately retrieved in combination with a cross-modal semantic matching model CLIP. Analyzing the image to generate text description, constructing a triple through dependency syntactic analysis and semantic role annotation (SRL), and fusing the triple into a knowledge graph by adopting multi-dimensional entity alignment; and designing a two-way reasoning architecture of a drawing neural network GNN and a large language model LLM, and generating answers through subgraph construction, hierarchical reasoning and result fusion. According to the method, multi-mode information such as texts and images can be effectively fused for question answering, the defect that a single-mode knowledge graph lacks image information is overcome, meanwhile, the problems of visual information lag and high computing power consumption in an existing multi-mode knowledge graph question answering method are solved, and the method has the characteristics of plug-and-play and light weight; and a new solution is provided for the field of multi-modal knowledge graph questions and answers.

The present invention discloses a method for constructing a complete knowledge graph based on multi-source vulnerability data, which mainly solves the problems of complex vulnerability data sources and missing relationships in the vulnerability database. The method includes: 1) collecting multi-source vulnerability data, where the data comes from unstructured vulnerability data recorded in CVE, CWE, CAPEC, and the security community; 2) normalizing sentences describing unstructured vulnerability information, performing sentence boundary detection and noun phrase normalization; 3) labeling the processed sentences with semantic roles, extracting sentence role construction data triples, and generating a vulnerability knowledge graph; 4) using node2vec to represent the nodes and relationships in the vulnerability knowledge graph into a low-dimensional dense vector space, and performing similarity calculation on the graph embedding results; 6) completing missing relationships through link prediction to obtain a complete knowledge graph. The present invention can establish a complete vulnerability database and effectively improve vulnerability retrieval efficiency.

The invention relates to the technical field of tea leaf processing intelligent monitoring, and discloses a tea leaf sorting process monitoring method and system. The method comprises the following steps: collecting multi-source asynchronous data in a tea sorting process, carrying out semantic role labeling and dependency analysis on an operation log to generate a process feature vector, and carrying out wavelet packet transformation and singular value decomposition on an equipment vibration temperature signal to extract equipment features. A tensor fusion technology is utilized to construct a three-dimensional feature cube, a deep belief network is adopted to perform hierarchical feature abstraction to obtain causal association of a process and a quality defect, an abnormal propagation chain is identified through a random walk algorithm, a root process node is positioned, and an optimization strategy is generated according to the abnormal propagation chain and pushed to an actuator in real time. According to the method, the deep semantic understanding of the sorting process and the high-order correlation analysis of the multi-source data are realized, the root procedure of the quality problem can be accurately positioned, and the control precision of the sorting quality and the production efficiency are improved.

The invention discloses an insurance clause accurate retrieval method and system based on large model incremental training, and relates to the technical field of natural language processing, the method comprises the following steps: constructing an insurance clause database, and establishing a perception hierarchy through perception analysis; a semantic label is established through named entity recognition and semantic role labeling under the constraint of the perception level; constructing a secondary retrieval vector by using the two; receiving user input, and calling an intention recognition channel to establish a structured query vector; retrieving the matching and obtaining a result; and after recording feedback, regularly extracting query feedback history and newly-added clause data increment to update a secondary retrieval vector and retrieval matching. According to the method, the technical problems that a retrieval result is one-sided, the matching degree is low and accurate retrieval requirements are difficult to meet due to the fact that semantic association and a hierarchical structure cannot be accurately captured when a traditional data processing mode is used for coping with insurance terms with complex structures and various contents are solved, accurate retrieval of the insurance terms is achieved, and the retrieval efficiency is improved. And the comprehensiveness and the matching degree of retrieval results are improved.

The invention relates to the technical field of semantic analysis, in particular to a personalized art therapy healing task generation method based on a large language model, which comprises the following steps: firstly, analyzing visual image data input by a user, extracting metaphor visual symbols and source domain semantic description, and performing semantic space alignment with a psychological model; a three-stage thinking chain technology is adopted to execute semantic reasoning reconstruction from a source domain to a target domain, a structured semantic descriptor is generated, in the process, a dynamic metaphor semantic topology network is constructed, a graph neural network is applied to aggregate global features to generate a language context bias vector, and the attention weight of a large language model is dynamically corrected; then deconstructing the descriptors into space and behavior semantic features by applying a semantic dependency syntactic analysis algorithm; the environment channel executes cross-modal semantic mapping from a text to a space; and the task channel accurately translates the natural language instruction into a cognitive interaction script by utilizing semantic role labeling and a syntactic constraint mechanism based on a finite state automaton.

The invention discloses a multi-modal retrieval method combining image features and semantic understanding, and relates to the technical field of information retrieval. Through the multi-modal retrieval method combining the image features and the semantic understanding, the design of combining an image segmentation technology and semantic role annotation is adopted; according to the design, semantic information in image and text data is fully mined, and deep fusion of the image and the text is realized by generating a semantic anchoring visual codebook and a cross-modal anchoring index. According to the method, the visual information and the semantic information in the image and the text can be more accurately corresponding and aligned, the problems of information loss and low retrieval precision caused by independent processing of image and text data in the prior art are solved, and the accuracy and the efficiency of multi-modal retrieval are remarkably improved. And meanwhile, indexing is performed by using anchoring vectors of an image side and a text side, visual code words and semantic role slots are closely combined, and more accurate cross-modal matching is established for matching and indexing among different modals.

The application embodiment provides a fraud call real-time identification method and device based on AI semantic understanding, innovatively constructs a voice analysis mechanism, realizes accurate understanding of conversation content through grammar feature extraction and semantic role labeling, designs a scene discrimination model based on dialogue identification, combines semantic pattern matching and hierarchical clustering algorithm, establishes a fraud dialogue identification strategy for intelligent classification, introduces a residual fusion evaluation mechanism, realizes accurate evaluation and timely prevention and control of call risk through historical case feature fusion and risk scoring. The method effectively solves the shortcomings of traditional technologies in voice understanding, dialogue identification and risk assessment, and significantly improves the accuracy and reliability of fraud call identification.

The invention discloses a thinking training system and method based on semantic unit cross-language conversion, and belongs to the field of intelligent education technology and natural language processing cross technology. The system includes a semantic chunk divider, a conversion processor, and a cognitive adapter. The semantic chunk divider adopts a dual verification mechanism of dependency syntactic analysis and semantic role labeling, and a predicate verb is taken as a core to divide a complete semantic unit; the conversion processor constructs a semantic intermediate representation based on a graph structure, and maintains a logic relationship between semantic units in cross-language conversion; and the cognitive adapter monitors the cognitive load of the user in real time and dynamically adjusts the complexity of the semantic unit. Through triple technical means of semantic unit division, graph structure conversion and cognitive dynamic adaptation, visualization of the cross-language thinking conversion process and personalized adaptation of training content are achieved, and the black box problem and the language training rigidity problem of an existing machine translation system are effectively solved.

The application provides a sports intangible cultural heritage analysis and tracing method based on a knowledge graph, which comprises the following steps: according to an expert rule base, constructing entity metadata and cultural feature codes containing representative inheritors, typical actions and regional schools, combining with a historical influence index to quantify the initial weight of the entity, forming a structured semantic anchor point, embedding the semantic anchor point in the knowledge graph through an improved graph neural network, and performing multi-hop path tracking by fusing path semantic features; adopting a main and auxiliary dual-channel embedding optimization mechanism to enhance the traceability and semantic consistency of the path, introducing a multi-objective loss function in model training to improve the embedding quality and optimize the semantic alignment degree of path prediction and expert rules; based on the credibility evaluation of multi-hop semantic tracing and reasoning results of user queries, finally generating a visualized graph with semantic role labeling and branch interaction functions, and the application improves the structured expression, path interpretability and reasoning transparency of the knowledge graph.

The invention relates to the technical field of social event detection, and discloses an unsupervised social event detection and evolution system and method. The system is based on a closed-loop knowledge base evolution mechanism of double LLM intelligent agent collaboration and RAG, a self-driven closed-loop system is built based on a detection intelligent agent and an evolution intelligent agent which are clear in labor division, the detection intelligent agent applies a mixed retrieval strategy, namely keyword matching and semantic similarity calculation, real-time and high-precision event classification is carried out on an input text, and the event classification result is obtained. And the evolution intelligent agent performs deep semantic analysis on the detection result, and dynamically updates the event knowledge base through incremental keyword extraction and semantic role labeling. And under the driving of a retrieval improvement generation technology, an automatic process of'detection-refining-updating-re-detection 'is formed, so that the knowledge base is continuously evolved along with the development of events, the problem that a static system is difficult to deal with dynamic evolution is fundamentally solved, and no manual intervention is needed.

The invention provides an NLP-based text core information rapid extraction method and system, and the method comprises the following steps: S1, carrying out data preprocessing operation, collecting case file texts, and carrying out cleaning, word segmentation and named entity recognition; s2, extracting time information, and extracting case occurrence time and duration through a time expression recognition and standardization algorithm; s3, extracting site information, and extracting and sequencing case accurate sites in combination with a geographic knowledge base and an importance rule judgment algorithm; s4, event types are extracted, and the event types and core elements are recognized through text classification and semantic role labeling technologies; and S5, verifying the consistency and rationality of the extracted information through co-reference resolution and domain knowledge constraint.

The application discloses an insurance clause accurate retrieval method and system based on large model incremental training, relates to the technical field of natural language processing, and comprises the following steps: constructing an insurance clause database, and establishing a perception level through perception analysis; under the constraint of the perception level, establishing semantic tags through named entity recognition and semantic role labeling; using the two to construct a two-level retrieval vector; receiving user input, calling an intent recognition channel to establish a structured query vector; retrieving and matching to obtain results; recording feedback, periodically extracting query feedback history and newly added clause data, and incrementally updating the two-level retrieval vector and retrieval matching. The application solves the technical problem that the traditional data processing method cannot accurately capture semantic association and hierarchical structure when dealing with complex structure and numerous content insurance clauses, resulting in one-sided retrieval results, low matching degree, and difficulty in meeting the accurate retrieval requirements, and achieves the technical effects of accurate insurance clause retrieval and improved comprehensiveness and matching degree of retrieval results.

The present application discloses a method, apparatus, device and storage medium for extracting attack behaviors in threat reports, including: obtaining a threat report to be extracted, and preprocessing the threat report to be extracted by means of natural language processing to obtain target sentences related to attack behaviors in the threat report to be extracted; using a semantic role labeling tool to perform semantic analysis on the target sentences to obtain various entities with semantic labels corresponding to the target sentences, the causal relationships between the entities, and the information flow direction; generating an attack traceability graph representing the attack behaviors corresponding to the threat report to be extracted according to the entities, the causal relationships between the entities, and the information flow direction. The present application can effectively remove redundant information in the threat report and simply and quickly extract attack behaviors by automatically extracting entities and the causal relationships and information flow direction between them from the target sentences through semantic annotation and generating a traceability graph.

This application provides a method and system for extracting technical and economic risk events based on monitored entities, belonging to the field of entity extraction technology. The method includes: performing entity recognition on multi-source scientific and technological texts, comparing and filtering technical and economic monitoring entities, and outputting a candidate monitoring entity list; extracting semantic segments using the candidate monitoring entity list as anchors, and determining event types based on trigger word matching rules; performing dependency parsing and semantic role labeling on the trigger word set, constructing a standardized event structure, extracting semantic relationships, and outputting a risk event candidate structure set; identifying chapter-level main events, aggregating paragraph-level related events to form a master-slave event structure; assembling event chains based on the master-slave event structure, and performing standardized output. This application can solve the technical problem of poor reliability in the extraction of economic risk events in the prior art, achieving the technical effect of improving the reliability of extraction.