180 results about "Retrieval algorithm" patented technology

The invention discloses a large language model knowledge base question answering system based on a multi-path fusion recall retrieval algorithm, and relates to the technical field of artificial intelligence application, and the system comprises the steps of S1, data collection, S2, data preprocessing, S3, knowledge base construction, S4, analysis and clustering, S5, knowledge recall, S6, weight adjustment, and S7, weight fusion. According to the method, a dynamic weight distribution module is arranged, so that various paths of recall weights such as keyword matching, semantic similarity and a knowledge graph can be flexibly adjusted according to different semantic scenes such as a technical scene and a product query scene, a recall result can be effectively optimized, knowledge related to problems can be accurately screened, and the method is high in practicability and high in practicability. And irrelevant information interference is reduced, the answer quality and the system efficiency are improved, and the user satisfaction is improved.

The embodiment of the invention provides a document generation method and device based on artificial intelligence, and the method comprises the steps: extracting multi-modal data features of a historical multi-modal file through natural language processing and a computer vision algorithm, and constructing a corresponding knowledge graph according to the multi-modal data features, converting the multi-modal data subjected to feature extraction into high-dimensional vectors by using a vectorization algorithm, and storing the high-dimensional vectors to form a vector library; splitting a current document generation task into a plurality of sub-tasks by adopting a task planning algorithm, and executing the sub-tasks at the same time to obtain a first document; performing iterative optimization of document content according to the document first draft, the cue word and the language model to obtain an optimized first draft, acquiring related information from the vector library by using an attention mechanism-based retrieval algorithm, and fusing the related information and the optimized first draft through a text generation algorithm to obtain a final document; according to the invention, the accuracy and intelligence in the document generation process can be effectively improved.

The invention provides a government affair information intelligent retrieval and generation system applying an RAG technology, and relates to the technical field of government affair information intelligent retrieval and generation systems. Comprising an information collection module, a data preprocessing module, a knowledge base construction module, an RAG core engine module, an intelligent retrieval module, an information generation module, a user interaction module, a safety and authority management module and a system monitoring and maintenance module, and all the modules work cooperatively to achieve efficient retrieval and intelligent generation of government affair information. Wherein the information acquisition module can improve the information retrieval accuracy from a plurality of government affair data sources, the query intention of a user can be accurately understood by combining an RAG technology with a knowledge base and a powerful retrieval algorithm, the most relevant content can be quickly positioned from massive government affair information, and compared with a traditional retrieval system, the accuracy of a retrieval result is greatly improved, and the retrieval efficiency is greatly improved. And the information screening time and energy of the user are effectively reduced.

The invention discloses an intelligent question answering method and device based on a large model, a storage medium and a server, and relates to the field of information retrieval. The method comprises the steps of receiving a to-be-answered question input by a user; according to formats indicated by a plurality of preset retrieval algorithms, converting the question to be answered into query statements respectively corresponding to the plurality of retrieval algorithms; according to the generated multiple query statements, retrieval is performed in a knowledge base, and candidate document sets corresponding to the multiple query statements are obtained; fusing the candidate document sets according to a preset fusion rule to obtain a fused document set; extracting a target answer from the fusion document set according to a pre-trained generation large model; according to the method and the device, the candidate document sets generated by fusing different algorithms are balanced between accuracy and diversity, so that the answer is enabled to be related to the question, and rich information is provided.

The invention discloses a multi-modal data automatic processing and information extraction method, and belongs to the technical field of data processing. Comprising the steps of establishing an original knowledge base according to original training data in a business scene; preprocessing the original multi-modal data in the original knowledge base to obtain a preprocessed knowledge base; inputting the preprocessing knowledge base into a knowledge retrieval unit; a text to be queried is converted into a query vector, the distance between the query vector and a knowledge fusion vector representation vector in the knowledge retrieval unit is calculated, and a retrieval result is obtained through an approximate nearest neighbor retrieval algorithm; and performing multi-modal data fusion on a retrieval result through a cross-modal Transform model, and combining fused semantics with user query to generate an answer. According to the method, data of multiple modes such as texts, images, audios and videos can be processed, multi-mode fusion and reasoning are carried out through the visual language model, accurate extraction and structured storage of information are achieved, and the efficiency and quality of data analysis and mining are improved.

The invention discloses a large model-based government affair official document quotation retrieval method, device and equipment and a medium, and relates to the technical field of artificial intelligence, the method comprises the following steps: obtaining a government affair official document, determining a document slice corresponding to the government affair official document, and creating a document knowledge base and a vector knowledge base based on the document slice; identifying the terminologies in the government affair document by using a target pre-training natural language processing model to obtain a corresponding identification result; based on the document knowledge base and the vector knowledge base, performing keyword matching on the recognition result by using a target information retrieval algorithm to obtain a plurality of corresponding candidate quotation documents; and performing semantic correlation scoring on each candidate citation document and the recognition result through a Rianker model, reordering each candidate citation document according to a corresponding scoring result, and outputting a target citation document according to a corresponding reordering result. Therefore, the quotation retrieval efficiency can be improved.

The invention belongs to the technical field of virtual machine mirror image static scanning, and particularly relates to a virtual machine mirror image static scanning method and system based on a hyper-fusion platform, and the method comprises the steps: creating a to-be-scanned mirror image storage snapshot, employing an index and retrieval algorithm, obtaining a static virtual machine mirror image file, extracting and recording metadata information of the static virtual machine mirror image file, and then carrying out integrity verification; collecting all-around resource data of the hyper-fusion platform in real time, and distributing corresponding resource quotas for scanning tasks by using a preset algorithm; multi-stage deep scanning is carried out, file fingerprints and feature matching are firstly used for preliminary screening, then misjudgment is eliminated through version intelligent comparison, potential high-risk vulnerabilities are deeply excavated for key complex components by adopting static code analysis, and configuration files in mirror images are comprehensively examined through rapid screening and positioning of known malicious software; and a preset algorithm is used for carrying out deep classification arrangement, correlation analysis and summary statistics on various types of result data, so that virtual machine mirror image scanning in a large-scale hyper-fusion cluster is completed in a relatively short time.

The invention relates to the technical field of natural language processing and artificial intelligence, and discloses a silk path knowledge base intelligent question answering system based on a large language model, comprising a silk path data acquisition module used for acquiring multi-source silk path knowledge data; the silk path knowledge base construction module is used for processing the multi-source silk path knowledge data to construct a structured knowledge base and an unstructured knowledge base; the data storage system module is used for storing a structured knowledge base and an unstructured knowledge base and providing a structured retrieval interface and an unstructured retrieval interface; and the man-machine interaction module is used for identifying a user intention according to the user question and outputting an answer corresponding to the user question by adopting a corresponding answer generation mode based on the user intention. According to the method, efficient and accurate silk path knowledge questions and answers are realized by constructing the multi-modal knowledge base and optimizing a retrieval algorithm and a prompt engineering technology.

The invention discloses an automatic driving test case generation method based on a large model retrieval enhancement technology, and aims to improve the generation efficiency of an automatic driving test scene. The method comprises the following steps: firstly, cutting a preprocessed data text into blocks, and vectorizing the text through an embedded model to construct an efficient vector database; secondly, preliminarily retrieving related text blocks by using an improved hybrid retrieval algorithm, and reordering by using a BERT cross encoder to improve the relevance of retrieval results; aiming at the complex task requirement in the automatic driving test, the method is divided into a plurality of sub-tasks to be executed in parallel, so that the retrieval efficiency and accuracy are improved. And then, a LoRA strategy is adopted to finely adjust the large language model so as to adapt to an automatic driving scene generation task. And finally, jointly inputting the cue word template and the reordering result into a fine tuning model to generate a test case. According to the invention, a brand new technical scheme is provided for automatic driving test scene generation, and the method is of great significance in improving the test evaluation level of automatic driving and accelerating the landing of the automatic driving technology.

The invention relates to the technical field of operation and maintenance automation, and provides an operation and maintenance field professional question and answer and diagnosis Agent design method and system, and the method comprises the steps: receiving and structurally analyzing an original query request of a user, carrying out the parameter validity check and safety verification, and extracting the query content and a session identifier; identifying task types through an intention classification algorithm based on the pre-training language model and performing content risk assessment; performing semantic extension on the query to generate an extended query word, performing similarity matching in the operation and maintenance knowledge base by using a hybrid retrieval algorithm, and fusing related knowledge fragments; inputting the enhanced query information and the task type into an inference engine for intelligent inference to obtain a diagnosis result; the reasoning result is stored in a historical memory library, and session context state information is updated; and performing formatting processing and security check on the reasoning result, packaging the result and context information, and outputting a standard response result. According to the method, the accuracy and the intelligent level of operation and maintenance professional question answering and diagnosis are improved.

The invention provides a three-dimensional object collision detection parcel grid generation method and system, a storage medium and a program product, and the method comprises the steps: extracting all vertex data of a first object according to a sub-Mesh data set after serialization of a three-dimensional model, and determining an initial center point; each vertex of each piece of sub Mesh data is converted from a local coordinate system to a global world coordinate system, and a point cloud data set is generated; constructing an initial convex hull by adopting a matrix hierarchical extremum retrieval algorithm, and generating a final convex hull by adopting a conflict graph and incremental convex hull algorithm; initializing a radius coverage model by taking the geometric center of the model as a sphere center; performing subdivision according to longitude and latitude to generate a hierarchical ball grid; emitting rays, correcting vertex positions layer by layer, approaching the surface of the model, and outputting a collider network. Through the overall point cloud set, the incremental convex hull algorithm and the spherical grid contraction technology, unified topological wrapping of the multiple three-dimensional objects is achieved, the visual fidelity and the collision precision are ensured, and resource consumption is reduced.

The invention discloses a method and system for generating a grade protection evaluation report based on RAG, and the method comprises the steps: carrying out the text segmentation of an input evaluation related file, and forming a plurality of text blocks; converting the text block into a vector form through a vector embedding model, and storing the text block into a semantic vector database; generating a corresponding user question according to terms in a preset evaluation template, and retrieving a target text block related to the user question from the semantic vector database by using a retrieval algorithm; and inputting the target text block into a pre-trained large language model, and generating evaluation contents corresponding to terms in combination with the keywords and terms in the evaluation template. The method does not depend on specific data formats or contents of specific companies, can flexibly cope with different conditions of different companies through the semantic vector database, the retrieval algorithm and the powerful natural language understanding and generation capability of the large model, automatically matches related terms and generates corresponding evaluation reports.

The invention relates to the technical field of artificial intelligence, and discloses an enterprise-level large-model agent application system supporting multi-modal collaboration, and the system comprises a user interaction terminal, an agent engine server, a knowledge engine server, a plug-in integration center, and a distributed storage unit. The agent engine server is responsible for intention recognition and task arrangement of a multi-modal input signal, and dynamically loads a differential reasoning strategy based on an environment isolation mechanism. And the knowledge engine server constructs a cross-modal semantic anchor point, analyzes an unstructured document into a tetrad knowledge unit, and realizes accurate recall of images and texts by using a hybrid retrieval algorithm. And the plug-in integration center executes outbound replacement and inbound restoration of the sensitive data through the context-aware dynamic desensitization gateway. According to the method, through a multi-modal semantic association and closed-loop verification mechanism, the problems of low complex document retrieval precision and leakage of external calling data are solved, and the service processing capacity and safety of the system are improved.

The invention discloses an AI (artificial intelligence) agent construction system based on hybrid retrieval and father-child segmentation, which comprises the following steps of: dividing a subclass knowledge base according to domain knowledge, performing father-child segmentation processing, and constructing a hierarchical semantic network; vectorization embedding and deep semantic reconstruction are carried out on the user question text; retrieving the reconstructed problem by adopting a mixed retrieval algorithm combining sparse retrieval and dense retrieval, and forming a high-score sub-segment set according to a comprehensive score obtained by dynamic weight distribution; mapping the sub-segments to the parent segment through a hierarchical backtracking algorithm, aggregating brother nodes to form an extended candidate set, and generating an associated sub-segment set after duplicate removal and re-retrieval; and finally inputting a large language model to generate a complete answer. According to the method, the problems of context segmentation, low retrieval accuracy and complicated knowledge base maintenance of traditional document segments are solved, the answer coverage and accuracy of an intelligent question-answering system are remarkably improved, and the method is suitable for knowledge question-answering scenes in the complicated technical fields such as intelligent network connection automobiles and the like.

The invention relates to a knowledge base content recommendation method and system based on large model and subdivision field matching. The method comprises the steps that key content feature words are automatically extracted from original content currently read by a user based on a feature word weighted extraction algorithm; forming cue words based on the feature words and the names of the subdivided fields, and determining professional subdivided fields according to the cue words; aiming at each determined subdivision field, searching contents related to the feature words in a database or a knowledge base by adopting a semantic similarity retrieval algorithm, and extracting first M most related results; on the basis of the feature words and the search results of the subdivision fields, prompt words are formed, the first L most relevant results are calculated from the M search results to serve as recommendation content, and corresponding recommendation reasons are generated; summarizing the recommended contents determined in each subdivided field, and storing the summarized recommended contents in a database; and calling the recommended content of each subdivided field from the database. According to the method, automatic and low-cost accurate recommendation can be realized, and a large amount of manual data annotation is not needed.

The invention relates to the field of medical teaching, and particularly discloses a clinical examination content generation method and system based on a multi-modal technology, and the method comprises a multi-modal data collection module which is used for collecting clinical medicine related information from a plurality of data sources; the data processing and classifying module is used for processing the clinical medicine related information acquired by the multi-modal data acquisition module and extracting effective medical knowledge and clinical situation data; the data embedding module is used for embedding the extracted data into the text embedding model and converting different types of data in the extracted data into uniform vector representation convenient for processing and training of the text embedding model; the retrieval content generation module is used for performing retrieval in the storage unit embedded into the text model by utilizing a vector retrieval algorithm according to examination requirements to obtain question setting reference data, and generating examination questions in combination with a cue word project; and the content optimization and verification module is used for constructing a real-time feedback mechanism for constructing the text embedding model.

The invention is suitable for the technical field of natural language processing, relates to a hierarchical memory and context awareness retrieval method of a large role model and a related product, and aims to solve the problems of limited model memory duration, insufficient retrieval correlation and insufficient personality consistency in a long dialogue. According to the invention, a short-term-middle-term-long-term three-level memory architecture is adopted, and a memory attenuation and migration mechanism is combined, so that dynamic metabolism of memory is realized; related memories are recalled accurately through a context semantics and role personality double-sensitive double-stage retrieval algorithm; relying on a personality-linked memory fusion and response generation strategy, the reply is ensured to fit personality setting; and a closed-loop adaptive learning mechanism of dialogue-memory-retrieval-generation-feedback is constructed, and the memory quality is continuously optimized. According to the method, the role large model can have the human-like continuous memory ability, the continuity, retrieval accuracy and personality consistency of long dialogues are remarkably improved, and the long-term personalized interaction requirements of scenes such as digital personality assistants and dialogue agents are met.

The present invention relates to the technical field of data retrieval. Disclosed are a data retrieval method and a network-attached storage device. The method comprises: acquiring data to be retrieved, wherein said data comprises at least one piece of sub-data to be retrieved, and each piece of said sub-data comprises one of text data, image data, and video data; on the basis of a feature extraction model, performing a feature extraction fusion operation on the preprocessed data to be retrieved to obtain a fusion feature vector corresponding to the data to be retrieved; on the basis of a target index structure corresponding to a vector database, determining a vector index corresponding to the fusion feature vector; and on the basis of a determined retrieval algorithm, performing a retrieval operation on the vector index in the vector database to obtain a retrieval result corresponding to the data to be retrieved. Therefore, by implementing the present invention, the data retrieval flexibility can be improved, so that more efficient retrieval services can be provided for users.

The invention relates to the technical field of computers, and provides an educational resource personalized recommendation method and device, equipment and a medium. The method comprises the steps of collecting learning historical data, interest preference data and knowledge mastery degree data of students in real time, and constructing a multi-dimensional student portrait through a machine learning algorithm; based on the multi-dimensional student portraits, matched data are retrieved from various kinds of data of an education resource library through a multi-modal retrieval algorithm, and learning content is generated through fusion and provided for students; and collecting feedback scores of the students on the learning content, taking the feedback scores as rewards, adjusting weight parameters of the multi-modal retrieval algorithm on retrieval of various types of data through a reinforcement learning algorithm, returning to the step of retrieving the matched data until the feedback scores meet a threshold condition, and generating personalized learning content based on the final weight parameters. According to the scheme, the disjunction rate of the recommended learning content and the student portrait is reduced, and the adaptability of the recommended learning content and the student individual is improved.

The embodiment of the invention discloses a contract review method and a related product, which are used for improving the efficiency and accuracy of contract review. According to the embodiment of the invention, the to-be-examined contract is fragmented, and at least one first feature tag is allocated to each fragment, so that the content of the whole to-be-examined contract can be split into smaller structured units, and the precision and speed of subsequent retrieval can be improved through the first feature tags. By determining the target review scheme corresponding to the contract to be reviewed, the review items can be flexibly adjusted according to different contract types, and the applicability is improved. And the to-be-reviewed data set is extracted in combination with multiple retrieval algorithms of different dimensions, so that missing detection of key to-be-reviewed data can be avoided, and the contract content matching accuracy is improved. As the data set input into the contract review model is screened and only contains the to-be-reviewed data set related to the review item, the misjudgment rate of the contract review model can be effectively reduced finally, and the accuracy of the review result is improved.

The invention relates to a PCB component type selection method and system based on a knowledge graph and intelligent retrieval. Relates to the technical field of PCB design, and the method integrates knowledge in multiple aspects of performance parameters, packaging forms, supplier information and the like of components by constructing a PCB component knowledge graph, and establishes semantic association among the knowledge. And performing intelligent retrieval in the knowledge graph by using an information retrieval algorithm based on design requirements and constraint conditions input by a user, and quickly and accurately screening out components meeting requirements. Meanwhile, the multi-mode large model is combined to carry out comprehensive evaluation on the components, factors such as cost and supply stability are considered, optimal component type selection suggestions are provided for users, the efficiency and accuracy of component type selection in PCB design are improved, the cost is reduced, and intelligent development in the field of PCB design of electronic products is promoted.

The invention discloses an unmanned aerial vehicle frequency hopping signal sorting and identification method based on spectrum characteristics, and the method comprises the following steps: carrying out the short-time Fourier transform of a signal received by a receiver, and obtaining a time-frequency matrix; eliminating fixed-frequency signal interference by adopting an energy cancellation method to obtain a time-frequency matrix; partial background noise is processed and eliminated through a threshold value method, and a binary matrix is obtained; removing interference by adopting a morphological filtering method to obtain a binary matrix; estimating parameters of the unmanned aerial vehicle by adopting a time-frequency analysis method to obtain a frequency hopping signal parameter set; matching the frequency hopping signal parameter set with features in an unmanned aerial vehicle signal feature library to obtain a pre-classification cluster; performing frequency hopping period estimation on the frequency hopping moment sequence in the pre-classification clusters by adopting a repetition period transformation method to obtain the frequency hopping period of each pre-classification cluster; adopting a sequence signal retrieval algorithm to screen out a frequency hopping sequence conforming to a frequency hopping period estimation value in the pre-classification cluster to obtain a main classification cluster; and matching the parameter set of the main classification cluster with the features in the unmanned aerial vehicle feature library and a frequency hopping signal number threshold, and if matching succeeds, identifying a specific unmanned aerial vehicle model. The method can solve the problems that interference cannot be effectively eliminated and multi-unmanned aerial vehicle frequency hopping signals cannot be sorted in a limited technology.

The invention discloses a Cuckoo search algorithm-based grid-connected inverter multi-objective optimization control method, which comprises the following steps of: constructing a three-level grid-connected inverter mathematical model, and calculating to obtain an inverter side current reference value; constructing a current prediction model of the inverter side; constructing a value function control item of the inverter side current by adopting a value function in a square error form; constructing a cost function by taking the neutral-point potential balance and the switching frequency as control items; and iteratively calculating a weight factor by adopting an improved self-adaptive cuckoo retrieval algorithm to realize multi-objective optimization control of the grid-connected inverter. According to the multi-objective optimization control method for the grid-connected inverter based on the cuckoo search algorithm, the problem that the control performance is limited due to the fact that weight factors are difficult to set in multi-objective optimization of the grid-connected inverter in the prior art is solved.

The invention relates to a rail transit large model retrieval enhancement generation method and system, an application and a medium, and the method comprises the steps: receiving a user query text, converting the user query text into a triad sequence through a large language model, and sorting triads based on a semantic relationship; the method comprises the following steps: obtaining embedding vectors of entities and relationships in a sequence through an embedding model, and retrieving candidate entities and relationship sets from a knowledge graph according to the embedding vectors; and calculating a triple sequence semantic distance between the sequenced sequence and the candidate sequences by adopting a triple sequence retrieval algorithm, and selecting the first K candidate sequences meeting the structural constraint. And finally, inputting the user query and the first K candidate sequences into the large language model to generate an answer, thereby avoiding knowledge fragmentation and structure mismatch, and realizing reliable and accurate response to complex multi-hop query in the urban rail transit field.

The invention discloses a verifiable retrieval method and device, equipment, a medium and a product, and relates to the technical field of block chains. Obtaining a query request; performing data positioning from a retrieval algorithm tree based on the query request to obtain at least one target leaf node and a data index set corresponding to the target leaf node; generating a target node proof and a path proof based on the retrieval algorithm tree, the target leaf node and the data index set; and verifying the target node proof and the path proof based on the retrieval algorithm tree. By the adoption of the technical scheme, under-chain retrieval and verification are carried out through the retrieval algorithm tree, on-chain and off-chain cooperation of query verification is achieved, it is ensured that the certification size is small, verification calculation complexity is lowered, on-chain storage overhead is reduced, and the problems that at present, request query certification is large in size and low in verification efficiency are solved.

The invention provides an intelligent retrieval and question-answering system for knowledge base context awareness and traceability enhancement, and the system obtains an analysis result, an optical character recognition result and a semantic analysis result through the analysis of PDF physical layout, Word / Excel paragraphs, titles, tables and style attributes thereof, and the optical character recognition. Structured knowledge blocks, positions and levels of path images and vector representation are generated and stored in a vector database, and related results of user query requests are extracted by executing a mixed retrieval algorithm with keyword retrieval and vector semantic retrieval. Performing intelligent reordering by considering semantic similarity, keyword matching, knowledge block type weight, source knowledge base weight and page position weight to obtain a candidate knowledge block list, constructing cue words according to an intelligent reordering result, and calling an external large language model to generate answers; source labels in answers are managed to be associated with metadata of corresponding numbers in a candidate knowledge block list, and the problem that text blocks and traceability are not accurate is solved.

The invention relates to the technical field of artificial intelligence, and provides a domain relation extraction method and system based on a large language model. The method comprises the following steps: identifying entity information in a field text set, and obtaining a labeled entity set with type labels; on the basis of entity pairs in the labeled entity set and predefined relation types, a question set is constructed by utilizing a judgment question generation algorithm, and a domain relation judgment question set is obtained; reconstructing the structured domain data into training data through a dialogue format conversion algorithm, and training a large language model based on the training data by adopting a QLoRA quantization fine tuning algorithm to obtain a domain fine tuning model; a double-layer retrieval algorithm is applied to retrieve and obtain related information from the knowledge graph, the domain relation judgment question set and the related information are combined and input into the domain fine tuning model for reasoning, and a domain relation triple is obtained. According to the method, high-precision and interpretable domain relation extraction is realized, and the accuracy and robustness of the model in the vertical domain are improved.

The invention provides a domain knowledge supplement and SQL generation optimization method and device based on a large model, and belongs to the technical field of large language models. The method comprises the following steps: integrating multi-source heterogeneous knowledge, and carrying out information input and parameter configuration on the multi-source heterogeneous knowledge; based on a semantic segmentation model and a knowledge extraction agent, automatically analyzing unstructured document content and converting the unstructured document content into structured knowledge; performing word segmentation processing on the basis of the question input by the user, and calling a retrieval algorithm to recall related knowledge from the knowledge base so as to supplement information required by answering; and on the basis of the recalled structured knowledge, designing corresponding application paths according to different types of knowledge and generating an SQL (Structured Query Language). According to the domain knowledge supplement and SQL generation optimization method based on the large model, flexible, accurate and efficient SQL generation is realized through efficient integration of multi-source heterogeneous knowledge, intelligent analysis of unstructured documents, accurate recall of related knowledge, high-quality SQL generation and optimization and dynamic update of knowledge management.

The invention discloses a sentiment analysis method and system based on a multi-modal enhanced retrieval generation technology, and belongs to the field of sentiment analysis and natural language processing. The method comprises the following steps: constructing an external multi-modal vector database oriented to an emotion analysis task; converting the user input data to obtain a query vector; aiming at a query vector corresponding to user input data, using a vector retrieval algorithm to retrieve a target feature vector from the external multi-modal vector database; constructing an emotion analysis prompt word template; according to the target feature vector, extracting other field data corresponding to the target feature vector from the external multi-modal vector database as a retrieval result; and embedding user input data and an external multi-modal vector database retrieval result into a prompt word template, calling a large language model, and generating an emotion analysis result. The invention provides an efficient and reliable multi-modal solution for the field of sentiment analysis.

The invention discloses an intelligent question and answer method and device and a storage medium. The method comprises the following steps: in response to an information inquiry request, obtaining first inquiry information input at a target terminal, analyzing the first inquiry information to obtain second inquiry information, and performing retrieval in a data cache layer based on the second inquiry information and a preset retrieval algorithm; under the condition that the first question data matched with the second inquiry information is retrieved, displaying answer data corresponding to the first inquiry information on the target terminal; wherein the data caching layer is used for caching the first question data of which the historical question query frequency is greater than the preset query frequency and the first answer data corresponding to the first question data. The problems that the query efficiency is low and the computing power consumption is too high are solved, and the beneficial effects of remarkably improving the query efficiency and reducing the computing power consumption are achieved.