601 results about "Semantic search" patented technology

The invention discloses a multi-path recall mixed retrieval method and system based on intelligent dynamic weight distribution, and aims to solve the problems that semantic comprehension and keyword matching are difficult to balance and the adaptability is poor due to the adoption of a fixed weight in the existing retrieval technology. The invention provides a multi-path recall mechanism fusing vector semantic retrieval, BM25 keyword retrieval and entity retrieval. A query feature vector containing 13-dimensional features such as semantic complexity, keyword density and entity coverage rate is constructed, a query type is recognized in combination with an SVM and a random forest integration model, a dynamic weight distribution algorithm is designed, and the final weight of each retrieval path is calculated in real time. And an adaptive multi-source enhanced reciprocal ranking fusion (AMSE-RRF) algorithm is further adopted to carry out optimization fusion on multiple paths of results, and a depth reordering model can be selected to improve the precision. According to the method, the accuracy and robustness of retrieval can be remarkably improved in multiple scenes of medical treatment, finance, government affairs and the like according to a millisecond-level self-adaptive adjustment strategy of query features.

Disclosed in the present disclosure is a rich-media document auxiliary generation apparatus. The apparatus comprises a material extraction module, a theme sorting module, a semantic retrieval module, a structured data text generation module, an illustration recommendation module and a video composition module. The present disclosure uses intelligent means to assist a user to efficiently generate a high-quality rich-media composite document, thereby quickly and accurately describing a theme event in an all-round way.

The invention relates to a government affair file information extraction and question answering method and device and a medium, and the method comprises the steps: carrying out the entity extraction of a government affair file through employing a BERT-CRF joint model, and obtaining a structured entity set; performing relation extraction on the structured entity set to generate a semantic relation set between the entities; constructing a knowledge graph according to the structured entity set and the semantic relationship set, storing entity nodes into a graph database, and storing an embedded vector of an entity text into a vector database; when a query request of a user is received, relation query of the graph database and semantic retrieval of the vector database are carried out, sub-graph structures and semantic matching vectors related to query are extracted, and a mixed retrieval result is obtained; and inputting the mixed retrieval result into a large language model, and generating a question and answer response text conforming to a preset format by applying a dynamic prompt template. According to the method, the document processing efficiency and accuracy are effectively improved, and a solid technical support is provided for intelligent management of government affair documents.

The invention relates to the technical field of intelligent questioning and answering, in particular to a domain intelligent questioning and answering method and system based on a multi-modal knowledge graph and RAG, and the method comprises the steps: constructing a concept layer knowledge graph based on a directory structure of a domain multi-modal document, and constructing an instance layer knowledge graph based on document content; obtaining a user question, pruning and positioning the user question in combination with the concept layer knowledge graph and the thinking chain, and determining a target chapter; splitting the question into sub-questions through intention analysis, and performing semantic retrieval in the instance layer knowledge graph corresponding to the target chapter to obtain a graph retrieval result; optimizing the original problem based on the atlas retrieval result, and executing semantic retrieval in a vector database to obtain a vector retrieval result; and fusing the atlas retrieval result and the vector retrieval result to generate a preliminary answer, and performing iterative optimization until a final answer is generated. According to the method, the semantic coverage, the expression accuracy and the response efficiency of the vertical domain question-answering system are remarkably improved by constructing the multi-modal knowledge graph and optimizing the retrieval process.

The invention relates to the technical field of multi-modal data processing and semantic retrieval, in particular to a multi-modal heterogeneous knowledge fusion construction and semantic enhancement retrieval system based on a large model, which comprises a data acquisition module, a semantic analysis module, a knowledge fusion module and a retrieval optimization module. Multi-modal data such as texts, images and audios are uniformly expressed and deeply analyzed by introducing a large model technology, a knowledge graph is dynamically constructed, a structure is optimized in combination with a user query intention, and meanwhile accurate sorting and screening are achieved through a semantic enhancement algorithm. According to the method, the semantic comprehension capability and the intelligent level of the system can be improved, the real-time and diversified scene requirements are met, and the accuracy and the adaptability of a retrieval result are remarkably enhanced.

The invention discloses an intelligent log retrieval and analysis system based on a model context protocol MCP, and relates to the technical field of log analysis. The system comprises an MCP log semantic conversion and retrieval engine, a log format irrelevant feature extraction and indexer, a dynamic log format recognition and context enhancement system, a real-time retrieval analysis and aggregation controller and a multi-level semantic retrieval and visualization engine. According to the context enhancement system, unknown formats can be identified, semantic tags can be complemented, and semantic consistency and behavior tracking capability can be improved. The retrieval analysis controller supports semantic expression analysis, strategy generation and feedback closed loop, and strategy scheduling and multi-dimensional aggregation analysis are achieved. And finally, outputting a structured semantic result by the system, and visually displaying the structured semantic result through components such as a semantic composition device and a context expander. All the modules are managed in a unified mode through a capability registration mechanism, dynamic arrangement and upstream and downstream closed-loop linkage are supported, and a log intelligent analysis framework with high semantic driving and a clear structure is formed.

The invention provides a distributed storage method based on source code semantic partitioning, and particularly relates to the technical field of cloud data distributed storage. The method comprises the steps of performing semantic partitioning on a source code, and segmenting the source code into a plurality of semantic blocks according to dimensions such as functional semantics, an abstract syntax tree structure, author information and version information; generating metadata containing information such as grammar type tags, file paths, line number ranges, author identifiers, version identifiers and access popularity for each semantic block; constructing a weighted directed acyclic graph (DAG) based on the semantic chunks and the dependency relationship thereof; superposing a metadata layer in the DAG structure, and recording information such as function call dependency, inter-block reference relationship and version evolution chain; blocks with relatively high access frequency and close semantics are aggregated into super blocks, the traversal depth is reduced, and meanwhile, hot data and cold data are differentiated for hierarchical storage by adopting a cold and hot data management strategy; and evaluating a parent block aggregation degree through a BDS algorithm, determining a block sorting priority, and optimizing super block boundary division. Compared with the prior art, the method has the advantages that the semantic retrieval efficiency, the incremental updating capability and the distributed query performance of the source code storage system are improved.

The invention discloses a listed company operation risk early warning method based on multi-source auditing and text semantic fusion, and relates to the technical field of auditing, and the method comprises the steps: S1, crawling and converging multi-source heterogeneous data of listed company financial newspapers, auditing suggestions, supervision announcements, inquiry letters, news public opinions and market transactions; according to the method, unstructured texts are subjected to cleaning, blocking and semantic vectorization processing, each text segment is embedded into a high-dimensional semantic space, a vector index is established, a bottom-layer knowledge base of an RAG framework is formed, in the stage, it is ensured that the data structure is uniform, the source is traceable, standardized input is provided for subsequent semantic retrieval and modeling, and the reliability of the system is improved. S2, a query expression is constructed based on a target company, a time window and a risk topic, dense semantic retrieval and sparse BM25 retrieval methods are comprehensively used, a time decay and source credibility weighting mechanism is introduced, and the problems that a traditional method is single in data dimension and information is split are solved.

The invention discloses a structured data retrieval system and method based on semantic matching and hierarchical indexing, and the related retrieval system comprises a first construction module which is used for extracting slice data in a preset vector library and meta-information corresponding to the slice data, and constructing a text node object containing an id; the second construction module is used for traversing a text node object to obtain meta-information subjected to hierarchical structure processing, and constructing a nested index tree; the directory decomposition module is used for receiving an input text, performing decomposition based on a hierarchical structure and generating a corresponding query vector; the retrieval module is used for performing semantic retrieval and hierarchical retrieval on the text in sequence to obtain a retrieval result; the grouping and sorting module is used for grouping the retrieval results according to the hit hierarchy, sorting the retrieval results in each group according to a descending order, and combining all groups to obtain a final retrieval result list; and the data backtracking module is used for acquiring an original text field from the vector database according to the id corresponding to the retrieval result.

The invention relates to the technical field of electric power engineering information processing, and discloses a power grid power transformation engineering knowledge graph construction and retrieval method and system, and the method comprises the steps: carrying out the dynamic adaptive partitioning of a power grid power transformation engineering related document, and obtaining semantic coherent and independent text blocks; extracting entities and relationships based on the text blocks, and complementing implicit entities and relationships through a multi-round refining mode; performing fusion and disambiguation on the extracted and complemented entities and relationships to form a unified knowledge graph; performing hierarchical clustering on the formed knowledge graph to generate a multi-granularity community structure and a corresponding community report; intention resolution and pre-judgment guidance are carried out aiming at fuzzy questions of the user, and a retrieval strategy is optimized; and executing multi-hop semantic retrieval based on the optimized retrieval strategy, recalling related knowledge and generating answers. According to the method, automation, precision and intelligentization of power grid power transformation engineering knowledge graph construction and full-link retrieval can be realized.

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 provides a code generation and evaluation method and system based on RAG and a multilevel decision tree, and the method comprises the steps: integrating project related design documents, and constructing a knowledge base capable of semantic retrieval through a vectorization technology; associating business demand description with related documents in the knowledge base based on an RAG technology, and performing demand semantic enhancement to generate a technology demand cue word; receiving the technical requirement cue word by adopting a large language model so as to generate a complete code conforming to business logic; constructing a four-level decision tree evaluation system, and sequentially executing code quality scanning, deployability verification, dynamic test verification and demand satisfaction verification through an evaluation assembly line to generate an evaluation result; and generating an optimization suggestion according to the evaluation result so as to trigger an iteration generation process when the code does not pass the verification, thereby solving the problems of disjunction between code generation and business requirements, low verification efficiency and insufficient iteration optimization.

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.

Computer-implemented systems and methods implement semantic search in high-dimensional vector spaces, specifically tailored for use with large language models (LLMs). In particular, clustering is combined with Euclidean distance measurements to facilitate real-time vector searches. By implementing clustering, the invention reduces the computational complexity and costs associated with Euclidean distance calculations, which are typically more resource-intensive than other methods such as cosine similarity. This reduction is achieved by limiting the scope of distance calculations to within clusters, thereby avoiding the inefficiencies and diminished accuracy otherwise encountered by existing systems when using Euclidean distance in high-dimensional spaces. As a result, the invention retains the benefits of Euclidean distance, such as its superior granularity and precision in measuring semantic relevance, without succumbing to the usual drawbacks of high computational demands and poor scalability.

A method for managing user queries applied to a large language model (LLM) includes obtaining a user query and in response to obtaining the user query: identifying a state of the user query, wherein the state is based on whether the user query is associated with a previous user query, making a determination, based on the state, that the user query indicates an enhanced context generation, in response to the determination, performing a semantic search on a vectorized database to obtain a set of relevant documents, performing an enhanced search on the set of relevant documents using a knowledge graph to obtain enhanced context, embedding the enhanced context to the user query to obtain a finalized prompt, and applying the finalized prompt to a large language model (LLM) of the data system to obtain a finalized result, and providing the finalized result to the client device.

A system and method for executing computer readable code instructions for an on-the-box (OTB) artificial intelligence (AI) productivity tool comprising a hardware processor accessing capabilities associated with each of a plurality of AI productivity tool-enablable software applications, a natural language capabilities database memory to store natural language descriptions of the capabilities and capability intent values generated from the natural language descriptions in a capabilities decision tree with each capability node grouped under a branch of the capabilities decision tree according to logical topics in hierarchical parent-child relationships, the hardware processor generating a query input intent value from a user query input and performing a cosine semantic similarity search comparing the capability intent values of the capability nodes along the branch of the capabilities decision tree for identifying a best match capability node having a highest cosine semantic similarity search score, and the hardware processor executing the best match capability.

Techniques for multimodal document retrieval are disclosed herein. Multimodal documents that include both textual and graphical components are retrieved from a knowledge base by a multimodal retrieval augmented generation (RAG) agent in response to a query. The documents and / or components or chunks thereof are retrievable by the RAG agent from the knowledge base using the semantic summaries and / or vector search of embeddings in the knowledge base that are generated from text extracted from processing non-textual components of the data. The RAG agent classifies the query type to determine whether to use a semantic match for text or image summaries, full text semantic search, vector cosine similarity search, and / or other multimodal vector search. The RAG agent performs types of searches selected based on the modality used to generate the response to the query.

Methods and systems for retrieving relevant information in response to an input question. The method includes obtaining text content related to the input question and partitioning the content into one or more paragraphs based on predefined rules. The method further involves extracting one or more evidence spans that are relevant to the input question by inputting the text content and the question into a trained language model. A semantic search is then performed on both the paragraphs and the extracted evidence spans, ranking the candidate passages based on their relevance to the input question. Each candidate passage may comprise either a paragraph or an evidence span that addresses the question. The disclosed methods and systems improve the quality and relevance of retrieved information by combining heuristic-based content partitioning with machine learning-based evidence extraction.

The invention provides an abnormity early warning security system and method based on cross-modal semantic retrieval, and relates to the technical field of public security, and the system comprises a video collection and frame sampling module which is used for extracting key frame images from a real-time monitoring video stream according to a preset frame interval and storing the key frame images to an object storage system; the target detection module adopts a YOLO model to execute instance-level target detection on the extraction frame, and generates a structured detection result containing a target position, a category and confidence; the semantic vector storage and structured warehousing module packages the standardized metadata of the image frame and the semantic vector generated by the CLIP into structured data, and stores the structured data into a high-performance vector database; and the semantic retrieval and reverse query module receives a natural language query instruction to generate a semantic vector, and realizes cross-modal retrieval of historical monitoring images through vector similarity matching. According to the invention, a set of exception security system with real-time perception capability, semantic understanding capability and cross-modal retrieval capability is constructed.

The invention relates to a geology vertical field large language model construction method and system fused with a knowledge graph, and the method comprises the steps: obtaining multi-source geology data, and carrying out the standardization processing, and obtaining a structured geological corpus; constructing a first knowledge graph and a vector index database supporting semantic retrieval based on the structured geological corpus; extracting first path information and constructing a first cue word, and performing fine tuning training on a pre-trained large language model according to the first cue word; and receiving an original text input by a user, and performing normalization processing to obtain first prompt information. And constructing a second cue word in the vector index database and the first knowledge graph based on the first cue information, and inputting the second cue word into a large language model subjected to fine tuning training to obtain a geoscience domain question and answer with a controlled structure. Compared with the prior art, the technical problem of semantic deviation and uncontrollability of question and answer generation content can be solved.

Disclosed herein, is a method and system for selecting a LLM for response generation to user queries. The method includes receiving a user query from a user device. The method includes determining, for the user query, a query type from a set of query types through a fine-tuned text classification model. The method includes retrieving a plurality of document embeddings based on the user query and the query type from a vector database through a semantic search technique. The method includes preparing a prompt using the user query and the plurality of document embeddings. The method includes inputting the prompt to an LLM selected from a set of LLMs based on the query type. The method includes generating, via the selected LLM, a response to the user query based on the prompt.

The invention discloses a retrieval enhancement generation method and system based on hybrid retrieval and adaptive sorting, and relates to the technical field of artificial intelligence and natural language processing. Comprising the following steps: 1, analyzing a query language and providing multi-path retrieval: receiving a natural language query input by a user, and performing semantic analysis and structured processing; starting dense vector retrieval and sparse semantic retrieval in parallel, and respectively obtaining candidate document sets from the knowledge base; 2, candidate mixed result fusion is carried out, wherein duplicate removal and preliminary fusion are carried out on candidate documents obtained through dense retrieval and sparse retrieval, and a unified candidate document pool is formed; all the candidate documents are evaluated according to the query semantic matching degree, document authority and quality, context coherence and generation task type factors, sorting weights are dynamically generated based on all the factors, and a candidate document pool is resorted; and constructing a structured context prompt prompt, inputting the structured context prompt prompt into a pre-trained large model, and generating final response content.

The invention relates to a knowledge graph enhanced multi-modal file retrieval method, and belongs to the field of artificial intelligence and multi-modal information retrieval. The invention aims to solve the problems of multi-modal information semantic segmentation, weak semantic reasoning ability and low semantic matching precision in the existing multi-modal archive resource retrieval process. Through four stages of archive multi-modal data preprocessing and feature extraction, knowledge graph construction and enhancement, semantic retrieval request analysis and intention modeling, and multi-modal semantic matching and sorting, a semantic relationship is enhanced by utilizing a knowledge graph, so that the semantic relevancy and context consistency of a retrieval result are remarkably improved; a user is allowed to input and inquire in various forms such as texts, images and voices, and semantic extension retrieval is supported. According to the method, more efficient and accurate archive resource retrieval can be realized, and the user retrieval experience and archive knowledge utilization are improved.

The invention provides a transformer area line loss intelligent algorithm decision-making method based on a knowledge graph and a large model agent, semantic retrieval in the algorithm calling process is supported, dominant and implicit knowledge such as expert experience, technical standards and historical cases is coded in a unified mode, a mapping relation is established between algorithm nodes and process nodes in the knowledge graph, and the algorithm is optimized. An integrated reasoning path is formed, so that the intelligent agent can automatically combine and call an algorithm according to a task target, a large model is embedded into a transformer area line loss analysis process, and a hierarchical structure of'task analysis intelligent agent-algorithm decision intelligent agent-result analysis intelligent agent 'is formed; the task analysis agent is responsible for converting a problem input by a user into a structured task; the algorithm decision agent is responsible for algorithm selection and adaptive parameter adjustment; the result analysis agent is responsible for report generation and decision recommendation based on the knowledge base; according to the method, organized association can be carried out on scattered algorithm tools, expert experience and business rules, and a unified transformer area line loss agent tool integration framework is constructed.

The invention relates to a diabetes mellitus question-answering method, system and device based on a knowledge graph and a medium, and belongs to the technical field of medical intelligent question-answering. The diabetes mellitus question-answering method based on the knowledge graph analyzes a question sentence of a user based on a pre-trained intention classification model so as to identify a user intention; analyzing the user question based on a pre-trained named entity recognition model to recognize a question entity; performing dynamic query on the constructed diabetes knowledge graph based on the user intention and the question entity to obtain a knowledge graph query result; encoding the user question by adopting a retrieval enhancement generation model, and performing semantic retrieval on the constructed diabetes semantic retrieval library based on the encoded user question to obtain related knowledge corresponding to the user question; and the knowledge graph query result and related knowledge are input into the constructed large language model to obtain the diabetes mellitus question and answer, so that the accuracy and specialty of the answer are improved.

The invention relates to the technical field of artificial intelligence and judicial informatization, and particularly discloses a multi-format document intelligent retrieval and semantic association system driven by a large model. Comprising a multi-modal document intelligent analysis module, an intention-driven semantic retrieval module, a knowledge graph enhanced association recommendation module, a retrieval result visualization and interaction module, a reinforcement learning-driven system optimization module and a multi-format document data storage module. According to the method, the multi-format judicial document is intelligently analyzed through a large model technology; the query intention of the user is accurately understood by means of a semantic retrieval technology Semantic association among the documents is deeply mined through the knowledge graph technology; a retrieval result is visually displayed through a visualization and interaction interface; and the retrieval strategy and model performance are continuously optimized according to user feedback by relying on a reinforcement learning algorithm, so that the retrieval efficiency and semantic association capability of the multi-format document in the judicial field are effectively improved, and the development of judicial informatization is promoted.

The invention discloses a data security risk assessment method and system based on a large model, and relates to the field of artificial intelligence large models. The method comprises the following steps: firstly, preprocessing a benchmarking and checking material, and then encoding the preprocessed benchmarking and checking material and a standard specification into a unified semantic space by utilizing a pre-training language model to form a benchmarking and checking vector database; then, on the basis of standard specifications, a data security risk assessment vertical large model is utilized to construct a compliance and security risk analysis assessment item prompt, and a structured assessment problem library is formed after manual verification; and then respectively calling each evaluation item prompt in the structured evaluation problem library, carrying out semantic retrieval in the benchmarking check vector database to generate an enhanced prompt, and then carrying out multi-stage reasoning to obtain a data security risk evaluation result. Through the pre-training language model and the data security risk assessment vertical large model, automatic and intelligent data security risk assessment is realized.

The invention discloses a processing method and system for presenting double intelligent agents based on business disassembly and visualization. The processing method comprises the following steps: receiving a natural language request of a power system by a service disassembling agent, carrying out semantic analysis on the natural language request through a small language model, and executing semantic retrieval based on a power system knowledge graph to realize intent recognition and task disassembling of knowledge enhancement. Generating a corresponding task instruction chain by using a directed acyclic graph structure; the task instruction chain is sent to an instruction registration center, the instruction registration center dispatches a visual presentation agent, and an interactive instrument panel and a natural language abstract are generated through a large language model. According to the technical scheme, automatic understanding and efficient decomposition of power system services are achieved, the intelligence and automation level of data processing and visualization is improved, the task scheduling and management capacity of the system is enhanced, manual intervention is effectively reduced, and the operation and maintenance efficiency and the data display accuracy are improved.

Systems and methods are provided to improve data retrieval from a cache memory by using semantic matching to retrieve data from the cache memory. The system includes a two-tiered cache system, with a first tier implementing “key-value” pairs, and a second tier that includes a table that is configured as an artificial intelligence (AI) search indexed source. When a new input does not have a matching “key” at the first tier, the system performs a semantic search at the second tier of the cache to determine if relevant data is stored in the cache. The current systems and methods increase the likelihood of obtaining data for queries from the cache memory, reduce the response time to the queries, improve search consistency, reduce computing resource utilization, improve system performance, and reduce costs.

The invention relates to an intelligent document information real-time retrieval method and system based on the RAG technology, and the method comprises the steps: analyzing documents of various formats, extracting a text, maintaining the content continuity through adaptive semantic partitioning processing, and building a character-level position index at the same time; after vectorizing the text blocks, generating a plurality of rewriting queries for the original query; respectively carrying out mixed retrieval (combining keywords and semantic retrieval) for each rewriting query, and fusing and reordering results to obtain candidate text blocks; after correlation filtering, inputting a large language model according to correlation to generate an answer, and if the result is negative, triggering secondary retrieval and reordering; and finally, outputting a structured answer containing position information and supporting front-end visualization. According to the method, the semantic integrity maintenance, the multi-format document processing efficiency and the key information retrieval accuracy are effectively improved.