767 results about "Text retrieval" patented technology

The invention relates to the field of natural language processing, and discloses an SQL statement generation method, system and device based on a large model. Respectively carrying out vectorization processing and document processing on the metadata and the metadata description text information from the database, and storing the metadata and the metadata description text information into a vector database and a full-text retrieval library; in response to the query instruction, respectively performing query matching on the vector database and the full-text retrieval library, screening matching results which are ranked in the front and are preset ranks according to the similarity from high to low, and determining an optimal SQL statement list and optimal metadata; on the basis of the current language of the query instruction, generating a cue word of the current language in combination with the optimal SQL statement list and the optimal metadata; the large model of the preset type is determined according to the language type of the cue word, the preset large model is called to conduct reasoning on the cue word, and the SQL statement is generated. Based on the large model and the generative AI technology, the accuracy of the generated SQL statement is improved, the use threshold of non-technical personnel is lowered, and the query efficiency of the SQL statement is also improved.

The invention provides a cross-modal remote sensing image-text retrieval method based on multistage semantic collaborative matching, which comprises the following steps of: extracting a region of interest by using a semantic segmentation algorithm through an image preprocessing module, segmenting a remote sensing image into a plurality of regions and generating image blocks; respectively extracting global features, regional features and pixel-level features of the image, and carrying out fine-grained coding on key regions such as fine-grained ground feature edges and the like; the text multi-level coding module is used for carrying out three-level feature coding of documents, sentences and words on texts based on a pre-training language model to ensure multi-level understanding of the texts; in the multi-level matching and fusion module, the similarity between the remote sensing image and the text description is calculated through a cross attention mechanism, weighted fusion is carried out on features of all levels, and finally a retrieval score is output. The method not only improves the accuracy and robustness of image-text retrieval, but also can be widely applied to the fields of remote sensing monitoring, environment change recognition, geographic information systems and the like.

The invention discloses a knowledge graph-driven water conservancy intelligent question and answer interaction platform and method, and relates to the related field of data processing, and the platform comprises an entity disambiguation module which is used for constructing a water conservancy knowledge graph to carry out standardized modeling, generating structured knowledge nodes to carry out entity disambiguation on water conservancy objects, and generating entity identifiers; the full-text retrieval module is used for performing semantic analysis on a natural language query text of the user according to the entity identifier, identifying a query intention type, performing full-text retrieval and generating a multi-modal answer; and the iterative interaction module is used for performing dynamic questioning based on the multi-modal answers, generating user semantic feedback information, optimizing a query path according to the user semantic feedback information, and realizing iterative interaction of water conservancy knowledge questions and answers. The technical problem that existing water conservancy intelligent question and answer interaction is insufficient in question and answer accuracy and richness is solved, and the technical effect of improving the question and answer accuracy and richness is achieved.

The invention provides a multi-knowledge-granularity text retrieval method and device for RAG, and the method comprises the steps: sorting an original text into a JSON file, carrying out the recursive character and semantic dicing processing, generating a target JSON file, and storing the target JSON file in a BM25 database and a vector database; when a user queries, preprocessing to generate a keyword list and a query embedded vector; searching for a target text in the BM25 database, and calculating a score of correlation with the keyword to determine a first to-be-selected text; determining a second to-be-selected text according to the query embedding vector; and performing duplicate removal processing on all the first to-be-selected texts and the second to-be-selected texts, and determining and outputting a final recommended text by utilizing a sorting model. By considering the problem of different search granularities, the keyword granularity is solved by adopting a BM25 algorithm. According to the semantic retrieval strategy combining sentence granularity and segment granularity, challenges of different text information lengths and different retrieval purposes are effectively handled, and therefore the advantages of traditional retrieval and semantic retrieval are fully utilized.

The invention provides a traditional Chinese medicine knowledge question-answering system based on a fine-tuning large model and dual retrieval enhancement. The traditional Chinese medicine knowledge question-answering system comprises a large model fine-tuning module, a dual retrieval enhancement module, a prompt template module and an answer generation module. The large model fine tuning module constructs a high-quality corpus by using traditional Chinese medicine ancient books, clinical cases and the like, performs incremental pre-training and supervised fine tuning on a ChatGLM3-6B pre-training model, and adopts technologies such as low-rank adaptation (LoRA) and direct preference optimization (DPO) to improve the adaptability of the model to traditional Chinese medicine professional knowledge. The dual retrieval module enables the model to map user questions to related contents in traditional Chinese medicine classical literatures, guidelines and modern literatures through text retrieval based on a LangChain framework on one hand, and provides structured background knowledge through map retrieval on the other hand. The system effectively makes up for the knowledge blind area of a large-scale general model in the field of traditional Chinese medicine, realizes the improvement of the accuracy, continuity and speciality of question and answer results, and has wide application prospects and relatively high innovativeness.

The invention discloses a large model enhanced cross-modal retrieval method and system and related equipment. The cross-modal retrieval method comprises the following steps: acquiring an image-text pair; based on the image-text pair, obtaining large model enhancement information of the image-text pair, combining an original image, a text and the enhancement information, adopting a multi-branch encoder of a pre-training CLIP model to obtain a plurality of feature vectors, constructing a multi-stage collaborative alignment loss function, and performing collaborative alignment on an image mode and a text mode in a public semantic space; and training a model through the multi-stage collaborative alignment loss function and a pre-constructed training database, and performing retrieval through the trained model. According to the method, collaborative learning is carried out on the image-text features obtained by the encoder, auxiliary semantic enhancement information is added, and collaborative alignment is carried out on the image modality and the text modality in the public semantic space, so that a better retrieval network is trained, and the accuracy of image-text retrieval is improved.

The invention discloses an image-text retrieval method based on comparative learning and modal fusion. The method comprises the following steps: giving an original image-text pair; the method comprises the following steps of: 1, respectively carrying out local coding and global coding on an input image based on a target detection model and a deep residual network, and coding an input text based on a pre-training language model; 2, generating more matched image-text pairs (positive sample pairs) and mismatched image-text pairs (negative sample pairs) by adopting a diversified data augmentation strategy; 3, establishing cross-modal hierarchical semantic fusion of the image and the text, and bridging a semantic gap between a visual mode and a language mode; 4, measuring the semantic similarity degree between the image and the text; and 5, based on positive and negative sample pairs generated by data augmentation, carrying out model training through comparative learning. The method solves the problem that an existing image-text retrieval method is insensitive to fine granularity difference between modes.

The emergency decision support method based on cross-domain knowledge fusion comprises the steps of building an emergency semantic model, building an emergency response graph, building an emergency decision auxiliary model based on the graph and the like, a full-cycle emergency disposal knowledge graph oriented to multiple disaster types is provided, and various emergency disposal knowledge can be effectively integrated and stored. Meanwhile, an emergency decision-making auxiliary model is constructed on the downstream based on the atlas, disaster grade division, multi-hop path query analysis and decision-making recommendation can be carried out according to real-time multi-dimensional disaster data, and the cross-domain text retrieval efficiency is greatly improved; meanwhile, a plan chain recommendation model based on an event chain is provided, disaster chain prediction can be carried out based on rules, refined plan pushing can be given, and a vulnerable community is helped to make emergency risk avoiding and planning in advance in a complex scene.

According to the knowledge text retrieval method and device, the storage medium and the computer equipment, when knowledge text retrieval is carried out, the retrieval statement and the target knowledge document corresponding to the retrieval statement are obtained firstly, the document structure tree of the target knowledge document is determined, the document structure tree is of a tree structure constructed by utilizing the directory structure of the target knowledge document, and the retrieval statement is stored in the document structure tree; according to the method, a target knowledge document is taken as a component of the target knowledge document, an index structure between each index node in the component of the target knowledge document and the target knowledge document is recorded, and leaf nodes in the index nodes are connected through pointers to form a linked list structure. The corresponding index node can be dynamically retrieved based on the association relationship between the index structure and the linked list structure of the tree structure, and the context content corresponding to the retrieval statement in the target knowledge document is intercepted by adopting different modes based on the type of the index node. And omission of unrelated contents of other chapters and key contents of the same chapter is avoided, so that the retrieval precision and quality are improved.

The invention discloses an RAG performance improvement method based on process optimization. The method comprises the following steps: S1, preprocessing text data; s2, performing hierarchical text segmentation, obtaining a document, storing the text by utilizing a database after the document is segmented, converting the text into vectors, and storing the vectors into a vector knowledge base; s3, querying and rewriting to obtain a rewritten question; s4, combining parent document search with mixed retrieval, and retrieving related contexts for the rewritten questions; s5, performing rearrangement and denoising to obtain a final context; and S6, generating an answer, and sending the final context into a large language model for understanding questions and answers. According to the method, the links of text preprocessing, text partitioning, text embedding, query optimization, retrieval, retrieval post-processing, generation and the like are sequentially optimized according to the data flowing direction, the semantic retrieval precision is improved, and the performance of RAG in the aspects of text retrieval precision, answer generation quality, user interaction and the like can be remarkably improved; and the flexibility and the practicability of the system are enhanced, so that the system is more excellent in practical application.

The invention discloses an image report generation method, system and device based on multi-modal learning optimization, and the method comprises an image retrieval module which is used for carrying out the image feature extraction of an input medical image, and obtaining similar medical images and reports; the simulation generation module is used for guiding an image report generation model to generate an initial draft report by utilizing the medical image and the report; the personalized diagnosis module is used for carrying out personalized adjustment on the report generation model according to the historical report preference of the doctor or the historical medical data of the patient; the reinforcement learning optimization module is used for dynamically adjusting a text generation mode based on a reinforcement learning report optimization strategy and optimizing an image report generation model in combination with doctor scoring, automatic evaluation and clinical feedback; and the iterative refining module is used for performing text retrieval by using the initial draft report as a query, acquiring text fragments which are semantically similar to the initial draft report, and performing neural symbol reasoning optimization to generate a final report.

The invention provides a multimodal reasoning method based on a Monte Carlo tree and dynamic retrieval. The method is applied to an artificial intelligence assistant-assisted teacher paper judgment scene. Specifically, the framework comprises a unified retrieval module, wherein the retrieval module comprises a mixed modal retrieval corpus and a multi-modal retrieval module; the multi-modal retrieval module comprises two retrieval modules, namely a text retrieval module and a cross-modal retrieval module, key problem solving insights are selected by adopting knowledge concept filtering, and progressive multi-modal reasoning annotations of multi-modal reasoning are automatically obtained by utilizing Monte Carlo tree search and an active retrieval mechanism for data annotation; and gradually aligning a process reward model through course process reward modeling in two stages by utilizing the annotation data so as to realize fine-grained verification of multi-modal large model reasoning. An MCTS algorithm and an active retrieval strategy are combined to improve multi-modal reasoning. The framework can automatically obtain high-quality step-by-step reasoning annotations, so that a process reward model is aligned step by step, and finally reliable automatic multi-modal reasoning verification is realized.

The invention discloses a cross-modal image text retrieval method based on deep learning, and provides a novel cross-modal feature extraction and alignment framework, efficient cross-modal retrieval is performed by learning semantic representation of an image and a text in a common feature space, the framework comprises a plurality of modules, and in a feature extraction stage, the cross-modal feature extraction and alignment framework is used for extracting and aligning the images and the texts. BERT Tokenizer and BERT Embedding are adopted for text coding, and the image feature extraction is combined with a Faster R-CNN (Convolutional Neural Network) model and a ResNet-101 model, so that the dimensional consistency of image features and text features is ensured. In the feature alignment stage, fine-grained semantic alignment of image and text features is realized through an I2T Attention module and a T2I Attention module, and the cross-modal matching precision is remarkably improved. In the correlation scoring stage, a correlation scoring matrix is generated by calculating the similarity score between the image features and the text features, so that the accuracy of cross-modal matching is improved. And further optimizing the feature alignment effect through normalization and attention redistribution. In an optimization stage, the system innovatively adopts a shared semantic and sorting loss strategy, integrates an OpenCLIP model framework, efficiently mines a semantic relationship between an image and a text from unlabeled large-scale data through comparative learning, and shows strong transfer learning ability and inference precision.

The invention discloses a text retrieval enhancement generation method and device, a medium and equipment, and relates to the technical field of retrieval enhancement generation. Comprising the following steps: establishing a database through vectorized corpora, and screening and labeling key information to generate a golden section vector library; extracting an adversarial sample from an external database by using a training problem, and fusing the adversarial sample with related corpora in a golden section vector library to obtain a training set; and adding a noise classification layer to improve the language large model, and training the improved language large model by using the fusion training set. When a user question is processed, relevant corpora are recalled, noise is recognized through the classification layer, context representation is generated through the attention fusion layer, and the output layer dynamically adjusts a decoding strategy and generates an answer. According to the method, a large language model added with a noise classification task is trained through the fusion training set, so that the model can identify and distinguish different types of noise, the adaptability of the model to different types of noise is enhanced, the model is helped to learn how to distinguish related and unrelated information, and thus the method is more robust when an actual problem is processed.

The invention provides a medical AI question and answer method based on retrieval enhancement, which comprises the following steps: acquiring a medical professional knowledge base, and constructing an entity recognition model and a medical knowledge graph; the method comprises the following steps: splitting a medical professional knowledge base, and creating a vector index and a full-text retrieval reverse index; intention classification is carried out, and initial processing is completed; performing multi-path mixed retrieval on the medical professional knowledge base to obtain a user question related text block; a filtering rule is preset, and the user question related text blocks are filtered; answering the user question according to a preset second prompt word, and answering the user question according to a preset third prompt word when the user question exceeds the range of the medical professional knowledge base or the multi-path mixed retrieval has no result. According to the method, related context information can be accurately searched, reliable reference information is provided for a generative large model to answer professional questions, the interactive experience of a medical question answering system is improved, and the accuracy and specialty of answer generation of the system are remarkably improved.

The invention discloses an intelligent construction and retrieval method for a medical knowledge graph based on GraphRAG and LLM. The intelligent construction method of the medical knowledge graph comprises the steps of data collection and processing, text segmentation, entity and relation extraction, entity analysis, weak connected component identification, word distance filtering, LLM evaluation, element abstract generation, graph community generation and community abstract generation. The intelligent retrieval method comprises the steps of knowledge graph vector library construction, text vector library construction, user question entity extraction and vectorization processing, multi-layer entity and relation retrieval, text retrieval, LLM summarization, result output and user feedback collection. According to the method, the GraphRAG and the LLM large model technology are combined, and efficient retrieval and accurate presentation of the medical information are achieved. According to the system, the accuracy and efficiency of medical literature retrieval are remarkably improved through deep integration of graph structured data and natural language processing capacity.

The invention provides a retrieval method and device based on document segmentation and a document retrieval system. The method comprises the following steps: acquiring a to-be-segmented document; based on an NLP algorithm, calculating the semantic similarity between the partial texts of the to-be-segmented document to obtain a first semantic relevancy; according to the first semantic relevancy of all the partial texts, the document to be segmented is segmented, a plurality of semantic text blocks are obtained, and each semantic text block comprises at least one partial text; under the condition that a query request is received, calculating semantic similarity between a query text corresponding to the query request and each semantic text block based on an NLP algorithm to obtain a plurality of second semantic relevancy, and determining the semantic text block with the highest second semantic relevancy of the query text corresponding to the query request as a target semantic text block, and displaying the target semantic text block in a display interface. According to the scheme, the problem that in the prior art, the accuracy rate is low during text retrieval is solved.

The invention discloses a legal supervision clue mining method and system based on full-text retrieval and a large model, and belongs to the field of data collection and data retrieval and large model application. The method comprises the steps that S1, supervision rules and retrieval keywords are sorted; s2, full-text retrieval: carrying out data retrieval by utilizing keywords for supervising thematic sorting and a full-text retrieval system, and collecting all related image-text data in a specified time period from various data sources; s3, information distillation and information filtering; s4, constructing a knowledge base of thematic analysis; s5, searching and sorting the knowledge base; and S6, carrying out intelligent analysis and clue mining on the large model. According to the legal supervision clue mining method based on the image-text electronic data, basic data are collected through automatic keyword full-text retrieval, and valuable legal supervision clues can be mined from massive data through automatic element analysis and dialogue reasoning analysis of a large model, so that the legal supervision clue mining efficiency based on the image-text electronic data is improved.

The invention relates to an enhanced LLM-RAG multi-hop question and answer method based on logic tree reasoning, and belongs to the technical field of new-generation information, and the method comprises the following steps: inputting a multi-hop question and answer question into a computer system; the computer system calls a pre-training large language model LLM, the multi-hop question-answer question is decomposed into a hierarchical logic tree in a recursive mode, and each node of the logic tree comprises a sub-question and a corresponding hypothesis answer; performing image retrieval from a structured knowledge source Wikidata and performing text retrieval from an unstructured knowledge source Wikipedia on the basis of each node sub-question and the hypothesis answer to obtain corresponding evidence; traversing the logic tree, verifying the consistency between the hypothetical answer of each node and the evidence through LLM, if the contradiction exists, reconstructing the corresponding sub-tree, and dynamically correcting the reasoning path; and integrating the verified logic tree node information, and outputting an accurate answer to the multi-hop question and answer question.

The invention discloses a multi-mode fusion product document and source code association retrieval method based on a knowledge graph, and relates to the technical field of software engineering and artificial intelligence. The method comprises the steps that source codes are preprocessed, and code structure information and business semantics are mapped in combination with a predefined business term dictionary; performing controlled induction on a code file and a product document by utilizing a large model, extracting business terms, logic intentions and a subject relationship, fusing with original codes, and establishing a vector retrieval index system; further analyzing a code structure by using an abstract syntax tree, and extracting an entity and a calling relationship; semantic enhancement and relation normalization are performed in combination with the large model, entities and relations are stored in a graph database, and a knowledge graph is formed; and performing parallel processing on user query based on a full-text retrieval index, a vector retrieval index system and a knowledge graph, and finally generating a product concept. According to the method, the retrieval speed, the semantic depth and the logical reasoning ability can be considered at the same time, and the retrieval accuracy is improved.

The invention provides a cross-modal retrieval model training method and a remote sensing image text retrieval method, and is applied to the technical field of remote sensing cross-modal retrieval. The remote sensing image text retrieval method comprises the following steps: performing feature extraction on a preprocessed remote sensing image by utilizing a trained cross-modal retrieval model to obtain image global features and image local features, and performing feature extraction on a preprocessed target text to obtain text global features and phrase global features; calculating the global similarity between the image global features and the text global features by using the trained cross-modal retrieval model, and calculating the local similarity between the image local features and the word group global features; and carrying out weighted calculation on the global similarity and the local similarity by utilizing the trained cross-modal retrieval model, and screening a matching result between the remote sensing image and the target text based on the weighted similarity to obtain a retrieval result between the remote sensing image and the target text.

The invention relates to the technical field of data processing, and discloses a multi-modal data alignment method and system based on an iterative Riemannian manifold, a terminal and a medium, and the method comprises the steps: obtaining a multi-modal data sample set for cross-modal image text retrieval, and creating a multi-modal data alignment network training model; performing iterative Riemannian manifold training on the multi-modal data alignment network model according to the multi-modal data sample set to obtain a multi-modal data alignment model; and obtaining to-be-aligned multi-modal data, inputting the to-be-aligned multi-modal data into the multi-modal data alignment model, and outputting a multi-modal data alignment result. According to the method, different modal data are embedded into the same Riemannian manifold, and the geometrical characteristics of the Riemannian manifold are kept by utilizing the Riemannian curvature regularization, so that the embedded representation can better reflect the internal structure of the data, cross-modal alignment is carried out based on the optimal transmission of the manifold geodesic distance, more accurate and deeper semantic correspondence is realized, and the accuracy and the reliability of the data are improved. Therefore, the multi-modal data alignment effect is obviously improved.

The invention provides an intelligent text retrieval method and system, a storage medium and a program product, and relates to the field of intelligent text retrieval, the method comprises the following steps: segmenting each original document into a plurality of semantic segments according to semantic similarity; extracting a text feature of each semantic fragment to generate a text fragment vector; selecting a related fragment from each text fragment vector, wherein the first similarity between the related fragment and the retrieval vector is greater than a preset first threshold value; calculating a second similarity between each related fragment and the adjacent fragment; combining the adjacent segments with the second similarity greater than a preset second threshold value with the corresponding related segments to obtain stitching segments; based on a retrieval result corresponding to a historical retrieval request of a user, determining a retrieval granularity which is firstly displayed; and according to the retrieval granularity, adjusting the display content of the stitching fragment, and returning a text retrieval result. By implementing the method, the semantic integrity and the result relevancy of the text retrieval result can be improved.

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 provides a multi-stage mixed retrieval method and system. The method comprises the following steps: acquiring an original database; obtaining retrieval content; rewriting the retrieval content by using the large model to obtain N query questions; performing full-text retrieval on the original database by utilizing the N query questions to obtain a first retrieval result; performing vector retrieval on the original database by using the N query questions to obtain a second retrieval result; performing weighted sorting on the first retrieval result and the second retrieval result, screening the sorted retrieval results according to a length threshold value, and defining M retrieval results after screening as final retrieval results; and taking the final retrieval result and the N query questions as cue words, transmitting the cue words to the large model, and outputting an answer result by the large model. According to the method, the advantages of full-text retrieval and natural language retrieval are combined, and the retrieval efficiency and the retrieval accuracy are 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 belongs to the field of image retrieval, and particularly relates to a multi-scale cross-modal-based satellite remote sensing image text retrieval method and system, a terminal and a medium, and the method comprises the following steps: constructing a multi-source multi-scale cross-modal remote sensing image semantic understanding model; processing a plurality of source satellite remote sensing images by using a multi-source multi-scale cross-modal remote sensing image semantic understanding model to obtain source feature vectors of the source satellite remote sensing images; storing the source feature vectors in a vector library; processing the input image retrieval information or text retrieval information by using the multi-source multi-scale cross-modal remote sensing image semantic understanding model to obtain an image retrieval feature vector or a text retrieval feature vector; and performing similarity comparison on the image retrieval feature vector or the text retrieval feature vector and a source feature vector in a vector library, and screening out a target source satellite remote sensing image. According to the method, the robustness of text and image features is improved, a unified storage and management carrier for multi-source data features is constructed, and the management efficiency and the retrieval precision and efficiency are improved.

The invention relates to a retrieval method and device based on static word embedding, computer equipment, a computer readable storage medium and a computer program product. The method comprises the steps of performing word segmentation on an original text to obtain a first word segmentation result, training a static word embedding model by utilizing the first word segmentation result to obtain word vectors, and generating a synonym word library; the method comprises the following steps: establishing a full-text inverted index by utilizing an original text, and expanding query words by utilizing a synonym library in a retrieval stage; encoding the original text into a semantic vector by using a semantic generation model, and constructing a vector index based on the semantic vector; based on a to-be-queried text in a user query request, performing retrieval by using the full-text inverted index to obtain a first candidate document, and performing retrieval by using the vector index to obtain a second candidate document; performing fusion processing on the first candidate document and the second candidate document to obtain a target candidate document; and inputting the target candidate document into the text generation model to obtain a retrieval result. By adopting the method, the accuracy of text retrieval can be improved.

The invention discloses a file retrieval method, device and equipment based on multi-modal AI and a storage medium, relates to the technical field of data retrieval, and aims to solve the problem that traditional file retrieval is low in efficiency and precision. The method comprises the following steps: performing content analysis on a multi-modal file including a picture file, a video file and a document file of text and / or visual information, and extracting a text semantic feature, a picture visual feature and a video time sequence feature; mapping the text semantic feature, the picture visual feature and the video time sequence feature to a cross-modal semantic space used for representing a high-dimensional vector associated with different modal features, and generating a cross-modal association vector; according to the modal type of the retrieval information, a corresponding retrieval module in a mixed retrieval engine is called to conduct retrieval in a cross-modal semantic space, an initial retrieval result is obtained, and the mixed retrieval engine comprises a text retrieval module, a visual retrieval module and a cross-modal fusion module; and performing dynamic weight distribution sorting on the initial retrieval result, and outputting a target matching result.

The invention discloses a remote sensing cross-modal retrieval method and system based on large model fine tuning. The method comprises the following steps: S1, inputting an obtained remote sensing image and / or description text into a trained remote sensing image text retrieval network for processing to obtain image features and / or text features after cross-modal fusion; s2, acquiring a text and / or an image matched with the remote sensing image and / or the description text based on the image features and / or the text features, and outputting the text and / or the image; the step S1 comprises: extracting initial image features and / or initial text features from the remote sensing image and / or the description text through an image text encoder; performing cross-modal fusion processing on the initial image features and / or the initial text features through a cross-modal asymmetric adapter to obtain image features and / or text features after cross-modal fusion; and carrying out optimization processing on the image features and / or the text features through a dual-task consistency loss function.