2678 results about "Index term" patented technology

The invention discloses a knowledge base enhancement generation method and system based on hybrid retrieval and fact verification. The method comprises the following steps: receiving an original query of a user; performing intention analysis and rewriting on the query, identifying an intention type and generating a sub-query adapted to retrieval; executing mixed retrieval of vector retrieval, keyword retrieval and selectable knowledge graph retrieval based on the sub-query, and recalling related knowledge fragments; performing deduplication clustering, fact conflict recognition processing and correlation reordering on the knowledge fragments; according to the intention type and the reordered knowledge fragment, dynamically selecting a prompt template to construct an enhanced prompt; and sending the enhanced prompt into the large language model, and generating a target response with the reference source. According to the method, knowledge recall comprehensiveness is improved through mixed retrieval, knowledge reliability is ensured through fact verification, generation logicality is enhanced in combination with dynamic prompt construction, and response accuracy and credibility are improved.

The invention discloses a multi-modal interview automatic quality analysis and evaluation method and system based on a large model, and the method comprises the steps: collecting and storing multi-modal data, such as texts, audios, videos and behavior interaction, and carrying out the preprocessing of the multi-modal data to form a standardized data set; utilizing a preset interview structure and a large model to dynamically guide the process, adjusting the topic rhythm according to real-time feedback, and recording stage conversion information to form logic trajectory data for process coherence management; automatically coding text data through a large language model, extracting features such as keywords and performing topic clustering, performing cross validation and semantic fusion in combination with data analysis results of each modal, and generating deep analysis results such as psychological states; and generating a comprehensive assessment report containing qualitative description, quantitative score and psychological abnormality or cognitive disorder risk prompts based on a deep analysis result, thereby providing a basis for psychological health assessment and cognitive competence evaluation. According to the method, automatic analysis of multi-modal data is realized, and evaluation scientificity and efficiency are improved.

The invention relates to a low-altitude intelligent question and answer construction method and system based on dynamic parameters. The method comprises the following steps: collecting low-altitude domain data, cleaning the low-altitude domain data, generating a semantic vector index, and constructing a low-altitude domain knowledge base based on the semantic vector index; receiving a natural language query of a user, analyzing a query intention, extracting keywords in the natural language query, and matching a corresponding candidate word quantity based on query types of the natural language query of the user, the query types at least comprising high-frequency phrase query and low-frequency long-tail query; and respectively carrying out fusion semantic retrieval and keyword retrieval, carrying out secondary sorting on the candidate results based on a preset resorter, preferentially sorting the candidate results related to the query intention, and outputting the corresponding candidate results. By adopting the method, a combined domain retrieval enhancement generation mechanism is provided, so that the professionality and accuracy of answers are improved; and the retrieved knowledge base content is re-screened to increase the hit probability of the knowledge base.

The invention discloses a search method and system based on computer natural language processing, and the method comprises the steps: extracting a synonym set and a context association relationship of keywords in a query text through a preset semantic knowledge graph, and generating a semantic vector representing a semantic dimension in combination with a deep learning model; extracting a historical behavior feature sequence from the query log based on the semantic vector, and analyzing a user search intention by adopting an attention mechanism model; performing similarity matching on the pre-constructed database by utilizing a semantic matching algorithm, and screening an information matching set meeting a threshold value; performing distributed processing on the matching set through a context-aware dynamic fragmentation algorithm, and constructing an index fragmentation cluster; semantic aggregation is realized by adopting a cross-fragment graph attention network, and an optimized search result set is generated through dynamic semantic projection. According to the method, through multi-modal fusion of the semantic knowledge graph and deep learning and in combination with a dynamic distributed processing architecture, the accuracy of search intention recognition and the efficiency of large-scale semantic matching are improved.

The invention provides an intelligent data query method based on a natural language, and relates to the technical field of intelligent data processing and natural language interaction.The intelligent data query method comprises the steps that firstly, enterprise original data is subjected to standard treatment, and a standardized theme database and a data directory and index definition document are constructed; key semantics are extracted based on unstructured knowledge, and a domain knowledge vector library is fused and constructed by combining document text fragments and vector representation of a mapping relation between historical questions of a user and an SQL (Structured Query Language). And after receiving a natural language question of a user, calling a large language model to identify a task type, and distinguishing knowledge questions and answers, data query and complex analysis. Executing corresponding operations according to different types: directly retrieving a vector library by knowledge questions and answers to generate answers; extracting keywords in data query and generating a query request in combination with context; and in the complex analysis, predefined workflow is judged and executed or intelligent agent processing is called, and query or analysis requirements are output.

The invention discloses a retrieval enhancement generated document screening system and method fusing a verification mechanism, and relates to the technical field of document screening, the system comprises a user input and query analysis module for extracting key information through natural language processing, and converting the key information into a high-dimensional semantic vector, a meta-tag and a keyword set; the multi-source document retrieval module is used for obtaining documents from multiple data sources through mixed retrieval and generating a candidate set through preliminary screening and sorting; the credibility evaluation and security verification module is used for generating scores and labels after multi-dimensional evaluation and screening qualified documents; the document consistency detection module is used for detecting document conflicts, processing and sequencing, and ensuring logic consistency; the document acquisition and generation module is used for inputting qualified documents into a generation model and generating answers with references; and the result output and tracing module is used for outputting answers and recording whole-process data to ensure traceability. The invention aims to ensure the accuracy and credibility of the generated content through a multi-dimensional verification mechanism.

The invention belongs to the field of question and answer generation, and provides an interactive retrieval enhancement question and answer generation method and system based on a knowledge graph, and the method comprises the steps: carrying out the document partitioning based on an original document set, generating a global block set, carrying out the entity extraction of each text block in the global block set, and obtaining an entity set; performing relation extraction on entity subsets in each text block in the entity set to obtain a global relation set; generating a plurality of sub-knowledge maps based on the global block set, the entity set and the global relationship set, and performing entity fusion and relationship fusion on the sub-knowledge maps to obtain a knowledge map; performing keyword extraction and semantic embedding on the original problem to obtain a dense vector, performing semantic embedding based on the knowledge graph to obtain an embedded vector, and generating a candidate entity set according to the dense vector and the embedded vector; and based on the candidate entity set, utilizing a large language model calling tool to carry out extended search to generate a candidate information set, and utilizing a large language model to obtain an answer to the original question based on the candidate information set.

The invention discloses a supply chain contract intelligent review system and method based on a large language model, and relates to the technical field of contract review. Aiming at the defect that the existing contract review generally depends on fixed template and keyword matching, the adopted scheme comprises the following steps: receiving a contract text through a text acquisition module; preprocessing the text through a text preprocessing module; the large language model analysis module adopts a pre-trained large language model to carry out deep semantic understanding on a text and extract key information; a supply chain management domain knowledge graph is constructed through a graph construction module, and compliance verification is assisted; the intelligent analysis module performs multi-dimensional risk identification and compliance evaluation on contract content in combination with a big language model analysis result and a knowledge graph; and the visualization module provides an interactive user interface for a user to upload a contract text, and displays an examination result, a risk prompt and a compliance suggestion of the contract text. According to the invention, the supply chain contract text can be automatically examined and risk early warning can be carried out.

The invention discloses a science and technology public text intelligent classification and service method and device based on deep learning. The method comprises the steps that multi-source science and technology public text data are acquired and preprocessed; extracting keywords by adopting a keyword extraction algorithm, and splicing the keywords with the public text title to form enhanced text features; constructing a multi-dimensional public text classification system and performing data annotation; performing feature extraction and fine adjustment by adopting a BERT pre-training model to obtain a classification model; automatically classifying the newly-added public texts and visually presenting the newly-added public texts; and generating a personalized recommendation result based on the user portrait and the public text feature index. The invention further relates to a technical scheme of multi-objective quality diversity optimization, heterogeneous resource allocation and fusion of the LPLC2 neural network and the BERT. The technical problems that a traditional method is limited in complex semantic understanding ability, single in classification dimension and lack of an integrated solution are solved, and the accuracy of science and technology public text classification and the intelligent level of service are improved.

The invention discloses an intelligent document question-answering method and device, equipment and a storage medium, and relates to the technical field of intelligent question-answering, and the method comprises the steps: obtaining a target query question of a target user; based on keyword matching and vector matching, keyword document fragments and vector document fragments related to the target query problem are retrieved from a target document knowledge base; generating recall block information according to the keyword document fragment and the vector document fragment; and generating a large model cue word according to the recall block information, and outputting target answer information for the target query question through a large model according to the large model cue word. The answering quality can be improved.

The invention relates to the technical field of natural language processing, in particular to an intelligent search engine system and method based on NLP and vector hybrid retrieval, and the system comprises a query analysis module which is used for receiving a query statement input by a user and obtaining structured query information based on the query statement; the symbiotic index module comprises a sparse extension index unit which is used for constructing a sparse inverted index table based on keywords in the structured query information; the vectorization hypergraph index unit is used for forming a hypergraph index based on the business data; the recall arrangement module is used for acquiring a candidate object set according to the structured query information; the constraint rearrangement module is used for calculating a joint priority score between query and candidate objects based on the candidate object set, and obtaining a sorting result under constraint conditions of meeting a supplier proportion, a category proportion and a price interval; and the evidence generation module is used for generating evidence information based on the sorting result and outputting the evidence information to the user interface.

The invention discloses an electronic archive intelligent retrieval method and system based on a block chain, and relates to the technical field of archive retrieval, and the method comprises the steps: extracting text features of an electronic archive, and generating metadata; generating a content hash value from the electronic file original text; writing the metadata, the content hash value and the ABE access strategy into the block chain smart contract; constructing a reverse index based on the metadata semantic tag, wherein an index entry is associated with a block chain storage address; calculating a root hash and anchoring the root hash to the block chain; analyzing a keyword and a digital identity certificate in the user retrieval request; calling an intelligent contract to verify whether the user attribute accords with the ABE access strategy of the target file; retrieving an encrypted hash list matched with the file in the distributed index; acquiring the encrypted file fragments from the distributed storage system; verifying data integrity; and combining the fragments to generate a final retrieval result. The method has the advantages that through deep coupling of the block chain and attribute encryption, an electronic archive management system considering security and intelligent retrieval is constructed.

The invention discloses an RAG intelligent retrieval question-answering system and method based on enhanced metadata, and relates to the technical field of information processing and intelligent retrieval, multi-source heterogeneous knowledge data is preprocessed to obtain unified knowledge data, and structured metadata is extracted from the unified knowledge data based on different text forms; vectorizing a document text in the structured metadata by combining with embedding of the knowledge graph to obtain document representation, and outputting the document representation, the structured metadata and the enhanced keyword set as an enhanced metadata object; labeling a display relationship between different enhanced metadata objects, and constructing to obtain a knowledge database; according to the intelligent knowledge service system and method, restrictive conditions and question intentions are extracted from user questions, mixed retrieval is performed from a knowledge database based on the restrictive conditions and the question intentions, a candidate literature semantic set is output, then structured statistical visualization reports and structured answers are output, and accurate, explainable and multifunctional intelligent knowledge services are achieved.

The invention discloses a contract filing method, system and device based on automatic recognition and a medium, and the method specifically comprises the steps: taking a contract document uploaded by a user as input, and extracting contract key data; inputting the signature area coordinate, the signature date metadata and the clause keyword into a space-time correlation model to generate a context enhanced candidate contract number set; inputting the candidate contract number set into a preset knowledge graph, and outputting a target contract number; inputting the distribution characteristics of the clause keywords into a bidirectional long-short-term memory network classifier for processing, and constructing a multi-dimensional metadata matrix in combination with the target contract number; and inputting the desensitized contract text content and the multi-dimensional metadata matrix into a file DNA atlas generator, and generating a unique feature code by fusing a semantic embedding vector and a document structure fingerprint. The efficiency bottleneck and accuracy problems of a traditional archiving mode are solved, and the efficiency, accuracy and compliance of contract archiving are remarkably improved.

The invention provides a knowledge graph-based government policy question and answer method and related equipment, which realize intelligent processing of government policy question and answer, contribute to improving the intelligent level of government policy service and meet the actual question and answer requirements of actual government policies. The method comprises the steps of obtaining multi-modal government affair policy data, wherein the multi-modal government affair policy data comprises structured policy data, an unstructured policy text, an OCR text, layout features and a policy document; the multi-modal government affair policy data are fused through a Transform hybrid architecture, a knowledge graph is constructed, and the knowledge graph comprises five elements including entities, relationships, attributes, time and space; constructing a time sequence diagram structure of policy conditions based on the dynamic graph neural network; receiving user query information, and extracting a geographic position keyword based on the query information; and carrying out semantic extension on the keyword by utilizing a Geo-BERT model, and obtaining a target keyword.

The invention discloses a text retrieval method and device, equipment, a storage medium and a product. The method comprises the steps of obtaining a question input by a user and at least one candidate text; for each candidate text, determining semantic similarity and keyword similarity between the question and the candidate text; sentence features of the questions and document features of the candidate texts are extracted respectively, and the weight of semantic similarity and the weight of keyword similarity are determined according to the sentence features and the document features; based on the weight of the semantic similarity and the weight of the keyword similarity, according to the semantic similarity and the keyword similarity of the question and each candidate text, calculating the comprehensive similarity of the question and each candidate text; at least one candidate text with the maximum comprehensive similarity is screened out, and an answer candidate set is obtained; and inputting the answer candidate set and the question into a preset large language model, and outputting a retrieval result. According to the method, the accuracy and efficiency of long text retrieval can be improved.

The invention discloses a water conservancy design archive retrieval system and method based on a local lightweight large model, and the method comprises the steps: S1, constructing a Python automatic preprocessing assembly line, extracting texts for PDF and Word multi-format archives, correcting metadata, and outputting standardized data; s2, constructing a full-text retrieval and semantic retrieval dual-mode cross-document retrieval service by relying on a Weavi ate local vector database and a lightweight text embedding model; s3, analyzing a user query intention through a local large model, synchronously triggering metadata accurate retrieval and content semantic retrieval, and generating a structured result; and S4, integrating the core module into a local area network Web platform, adopting Docker containerization deployment, and combining an RBAC permission model and JWT authentication to guarantee security. The system comprises a preprocessing module, a cross-document retrieval module, an intelligent agent module and a background management module, and collaboration is achieved through a standardized API. According to the method, the problem of archive fragmentation is solved, multi-mode retrieval breaks through keyword limitation, an intelligent agent reduces manual intervention, a localized architecture prevents secret-related leakage, background management adapts to an existing I T environment, and full-process intelligent archive service is provided for water conservancy design.

The invention discloses a document knowledge base LLM intelligent question and answer method, device and equipment and a storage medium. The method comprises the steps that dynamic partitioning is conducted on a to-be-processed document, and vectorization and index storage are conducted on knowledge blocks; vector retrieval and keyword retrieval are carried out according to the natural language question, a vector retrieval result and a keyword retrieval result are fused, an answer is obtained through LLM, and the answer is fed back to a user after being safely filtered; when it is detected that the to-be-processed document is updated, the vector library and the index are synchronously updated, and the cue word template and the partitioning strategy are periodically optimized, so that the problem of form picture information loss can be solved, the integrity of document information analysis is guaranteed, the situation that the partitioning strategy is single is avoided, the multi-hop recall rate is increased, and the problem of semantic missing is avoided; a partitioning mechanism is reasonable, retrieval precision is improved, updating cost is reduced, data security is improved, implementation is convenient, universality is good, and the speed and efficiency of LLM intelligent question answering of the document knowledge base are improved.

The invention belongs to the technical field of text processing, and particularly relates to a method and system for retrieving DOCX document content based on keywords, which comprises the following steps: analyzing an Office Open XML structure of a DOCX document, combining with multi-dimensional features such as style names, and utilizing a title classification score model to accurately distinguish a title and a text, so that a semantic hierarchical structure of the document is effectively reserved; and secondly, a multi-level semantic extension mechanism is introduced, and a Sension-BERT, a HowNet knowledge base and a Word2Vec model are fused, so that intelligent extension of synonyms and synonyms of keywords is realized, and the recall rate and semantic understanding ability of retrieval are remarkably improved. And in addition, a BM25 model is combined with paragraph length normalization and structure position weight to calculate a correlation score, so that retrieval results are sorted more accurately and reasonably. The construction of the reverse index is combined with the position coding and compression optimization strategy, and the retrieval efficiency and the storage performance are both considered.

The invention discloses an AI intelligent marketing content publishing subject matching recommendation method, and relates to the technical field of marketing content publishing subject matching recommendation, and the method comprises the following steps: carrying out keyword density mutation detection, brand semantic coincidence detection and content publishing period anomaly detection on the basis of a behavior content fusion graph; determining whether the content publishing main body has a condition that cooperation information is lost and behavior characteristics show that cooperation history exists or not; and on the basis of a determination result, performing semantic co-occurrence path construction, propagation pattern similarity analysis and behavior residual discrimination operation, and obtaining a cooperation frequency recessive signal under the condition that the cooperation information of the content publishing subject is lost but the behavior characteristic shows that the cooperation history exists. According to the method, the problem that the real cooperation frequency cannot be identified and the exposure risk cannot be accurately judged under the condition that the cooperation information of the content publishing main body is lost but the behavior characteristic display has the cooperation history is solved, and the implicit cooperation frequency extraction and the risk level dynamic regulation and control based on the multi-source behavior characteristics are realized.

The invention relates to the field of artificial intelligence, in particular to an intelligent standard knowledge retrieval system based on an AI large model, which comprises a standard knowledge management database, a multi-source acquisition preprocessing module, a semantic understanding and indexing module, an intelligent retrieval engine module, a knowledge enhancement module, a user interaction feedback module, a security control module and a deployment expansion module. The standard knowledge management database is used for storing standard knowledge design data, real-time retrieval data and feedback data and constructing a dynamically updated standard knowledge resource pool; through the multi-source standard knowledge acquisition and preprocessing module, multi-channel objective standard data can be integrated and dynamically updated, and the problem of knowledge fragmentation is solved; and through the semantic understanding and indexing module, industry professional semantic accurate matching is realized, the limitation of traditional keyword retrieval is broken through, and the accuracy and efficiency of standard knowledge retrieval are remarkably improved.

Systems and methods disclosed herein are enabled to dynamically generate structured documents using one or more artificial intelligence models. A computing device receives an output generation request and uses a first AI model to retrieve data chunks from source documents and applicable templates. A second AI model ranks the retrieved chunks based on one or more metrics, such as vector similarity, keyword density, and temporal relevance. A third AI model subsequently generates a response using the ranked chunks, templates, and predefined operational boundaries for each chunk. The generated response is tagged with source identifiers to enable the traceability of the response back to corresponding chunks. The system transmits, via the computing device, the response, the retrieved chunks, and / or the source identifiers.

The invention provides a household appliance knowledge question-answering method and system based on retrieval enhancement generation. The method comprises the following steps: acquiring household appliance field multi-modal data from a multi-format document library; extracting text information, table information and chart information in the multi-modal data; performing domain term injection processing on the extracted information, and constructing a packet domain enhancement index; receiving a natural language question input by a user; the natural language problem is analyzed through a query optimizer, and semantic retrieval and keyword retrieval are executed in parallel; carrying out fusion processing on the semantic retrieval result and the keyword retrieval result; selecting matched document fragments by adopting a relevancy sorting algorithm; inputting the matched document fragments into a large language model to generate candidate answers; verifying the compliance and traceability of the candidate answers through a credibility evaluation module; outputting a final answer with a reference source; and storing the high-frequency questions and the final answers into a cache library to solve the problems that the answer accuracy of a knowledge question-answering system is reduced and the response efficiency is limited.

The invention relates to the technical field of artificial intelligence and information processing, and particularly discloses a multi-modal file intelligent classification and label generation method and system. The method comprises the steps of obtaining text paragraphs, image segments and video key frame data in a file, performing format recognition and region separation, and generating multi-modal content structure data; semantic features are extracted based on the data, and fused semantic representation is constructed; generating a main label, a sub-label and a keyword set by using the fused semantic vector, and constructing a multi-level label structure; and further performing label redundancy elimination and structure optimization to generate a label atlas, and performing consistency analysis and feedback optimization through the label atlas and the semantic representation structure. Compared with the prior art, the method has the advantages that various modal information can be effectively fused, the accuracy, hierarchical structure and semantic consistency of archive label generation are improved, and the method has high intelligence, self-adaption and sustainable optimization capabilities and is suitable for various scenes such as archive management, content auditing and semantic archiving.

The present disclosure relates to techniques for automatically generating new data objects from user input. The system receives user input comprising a plurality of words and executes a first query on a vector store to identify schema elements similar to keywords in the user input. The vector store provides a response with similarity scores for identified elements. A second query is executed on a knowledge graph to identify association paths between data objects that include the identified elements. The knowledge graph response includes association information linking source and target data objects through selected elements. Full association paths are constructed from this information, and a command is generated to instantiate a new data object with elements corresponding to the user input. This approach leverages the strengths of large language models, vector stores, and knowledge graphs to efficiently and accurately create new data objects, ensuring data integrity and relevance.

The invention belongs to the technical field of artificial intelligence and information retrieval, and provides a multi-modal retrieval method and system based on a lightweight knowledge graph and an index table, and the method comprises the steps: obtaining multi-modal source data, and extracting a structured semantic tag set; constructing a lightweight knowledge graph and a metadata index table; analyzing a natural language query input by a user to obtain a semantic query vector and a keyword set, executing semantic retrieval in the knowledge graph to obtain a text candidate result, and executing keyword matching in the metadata index table to obtain a non-text candidate result; for each non-text meta record, fusing the cross-modal similarity between the non-text meta record and the text candidate result, performing index matching on an original score and a graph semantic evidence score, calculating a comprehensive correlation score, and performing reordering; and generating a natural language answer containing a non-text record link according to a reordering result. The method is suitable for efficient cross-modal knowledge retrieval in a high-security and low-resource scene.

The invention belongs to the field of natural language processing and artificial intelligence, and particularly relates to a long text writing generation method and system based on multi-agent cooperation. The method comprises the following steps: receiving a text theme input by a user, completing complex theme decoupling, and outputting an outline directory; the method comprises the following steps: collecting keywords according to a text topic and an outline catalog, obtaining a retrieval result by retrieving the Internet, a domain database and network resources, and preprocessing to obtain a reference with a uniform format; performing systematic evaluation on the reference literature from the field integrating degree and the logic relevance, and performing grading processing on the reference literature to obtain a high-quality reference literature; based on the text theme and the high-quality reference, long text content is generated according to a set logic structure and writing specifications. According to the method, the fragmented expression problem is effectively avoided, the academic value and reading experience of the text are remarkably improved, the inherent defects of a traditional long text generation technology are practically overcome, and a high-efficiency solution is provided for text creation in the professional field.

Systems and methods are disclosed herein for compressing a prompt. In an example system, an importance score listing is obtained that includes a score indicative of an importance of a plurality of dataset keywords. From the importance score listing, a keyword importance score is identified for a plurality of keywords in a current text fragment, such as a text fragment to be compressed. A set of placeholders in an abstract prompt template is populated based on the current text fragment. The current text fragment is compressed based on the importance of the plurality of keywords in the current text fragment to generate a compressed text fragment. In an example, the compressed text fragment is included in the prompt for transmission to a computing entity, such as a large language model of a generative question-answering system.

The invention relates to the technical field of information retrieval, and provides a multi-dimensional heterogeneous knowledge recall enhanced hybrid retrieval method and system.The method comprises the steps that texts recalled through keyword retrieval, sparse vector retrieval and dense vector retrieval are screened through a reciprocal sorting fusion algorithm, and a text type candidate knowledge list is obtained; based on user query, generating and checking a query statement through a large language model, and retrieving an entity-relationship-attribute triple from the knowledge graph library; based on user query, generating enhanced knowledge through a knowledge graph enhanced retrieval method fusing keyword retrieval, vector retrieval and community retrieval; and carrying out format alignment and duplicate removal on the text type candidate knowledge list, the triple result and the enhanced knowledge to form a multi-modal candidate pool, and carrying out reordering score calculation and ordering on each piece of recall knowledge in the multi-modal candidate pool through a reordering model and a business rule to obtain a final retrieval result. And the coverage blind area of single retrieval on heterogeneous knowledge is solved.

The invention relates to an intelligent marketing content generation and optimization system, and belongs to the technical field of artificial intelligence and digital marketing. According to the system, through cooperative operation of the data acquisition module, the intelligent text generation module, the multi-modal synthesis module, the risk management and control module and the dynamic optimization module, whole-process closed-loop management of marketing content is realized. The data acquisition module captures unstructured data from a multi-source platform based on a user authorization protocol, semantic cleaning and structured processing are performed through a large model interface, and the problems of data dispersion and fragmentation are solved. The intelligent text generation module receives user parameters through an interactive interface, matches a preset prompt word bank, calls a large model interface to generate multi-version copywriting in batches, and supports concurrent processing of single-choice or multi-choice product lists. The multi-modal synthesis module extracts keywords according to copywriting semantics, matches pre-annotated visual materials and generates multilingual speech paraphrases, so as to ensure the consistency of graphic and text information. The risk management and control module intercepts sensitive content in real time based on an industry rule base, and guarantees output compliance. And the dynamic optimization module integrates the user behavior data to generate a delivery strategy, updates a prompt word bank and a generation model through a closed-loop feedback mechanism, and realizes dynamic adaptation of contents and market demands. Compared with a traditional method, the system has the advantages that the content generation efficiency, the cross-modal matching precision and the compliance control level are remarkably improved, and the system is suitable for the global digital marketing requirements of multiple industry scenes such as e-commerce, industrial equipment and cross-border trade.