434 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.

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 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 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 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.

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 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 belongs to the technical field of natural language processing and geographic information systems, and particularly relates to a region address standardization method based on knowledge graph enhanced retrieval. Cleaning and preprocessing the original address text input by the user; utilizing a fine-tuned large language model to identify a geographic entity and performing standardized expansion on variant expression to generate a query candidate set; entity linking and context retrieval are carried out based on the knowledge graph, and attributes, hierarchy and spatial topology information of associated entities are obtained; in combination with the original input and the map context, an enhanced retrieval query text is generated through large language model reconstruction; vectorized semantic retrieval is carried out through the fine-tuned embedding model, and a preliminary candidate address set is obtained; carrying out multi-dimensional refined sorting by adopting a resorting model; and generating a structured standard address by using a large language model, and outputting the structured standard address after multi-level verification. According to the method, the problems of ambiguity resolution, alias recognition and context understanding in address processing are solved, and the accuracy and robustness of address standardization are improved.

The invention discloses an intelligent voice question-answering system and a knowledge reasoning method for operation and maintenance of power equipment. The system comprises a knowledge base construction module and a core question and answer engine module, the knowledge base construction module is used for constructing a power equipment knowledge graph and a fault case library, and the core question and answer engine module comprises a natural language understanding unit, a multistage semantic retrieval unit and a voice interaction ambiguity resolution unit. A natural language understanding unit identifies intent categories and power entities. The multi-stage semantic retrieval unit executes the following steps: matching in an ontology layer of the knowledge graph; performing extended query to obtain detailed information; and similar case matching is carried out in the fault case library. The voice interaction ambiguity resolution unit is used for executing disambiguation processing; analyzing the confidence and clarifying the dialogue; and triggering knowledge retrieval and reasoning and generating a sorting answer. The operation and maintenance efficiency is improved, the dependence on experts is reduced, the operation and maintenance quality and safety are improved, knowledge precipitation and sharing are promoted, the field work experience is improved, and scientific decision making is assisted.

The present invention discloses a computer-implemented system and method for automated evaluation of Environmental, Social, and Governance (ESG) disclosures and detection of greenwashing. The system integrates artificial intelligence and machine learning techniques to extract, segment, and analyze ESG content from structured and unstructured sources. A retrieval and segmentation module identifies ESG-relevant sections, which are then vectorized and stored for semantic search. A semantic retrieval module fetches contextually relevant content, which is evaluated against predefined benchmarks using an analysis and validation module. The scoring module assigns ESG scores based on rule-based criteria including key strengths, specificity, and supporting evidence. A report generation module creates structured ESG reports with visual analytics, while an orchestrator module dynamically coordinates all processing steps based on ESG framework requirements.

The invention discloses a target-level three-dimensional point cloud cross-modal semantic retrieval method and device and electronic equipment. The target-level three-dimensional point cloud cross-modal semantic retrieval method comprises the steps that independent three-dimensional target point clouds are segmented from three-dimensional scene point clouds, and unique identifiers are given to the independent three-dimensional target point clouds; projecting each target point cloud to three orthogonal two-dimensional observation planes to generate a multi-view composite image; a pre-trained vision-language basic model is adopted to code and fuse the synthesized image, and a unified multi-modal feature vector is generated; a vector database in which the feature vectors are associated with their identifiers is constructed. And encoding a natural language query text into a text query vector by using the model, calculating the semantic similarity between the text query vector and the feature vector in the database, and positioning and returning the corresponding three-dimensional target point cloud. According to the method, accurate and efficient cross-modal retrieval from a natural language to a three-dimensional point cloud target is realized, the problem that a traditional method is difficult to support semantic fine-grained retrieval of the three-dimensional target point cloud is solved, and a key technical support is provided for training data management in the fields of intelligence and the like.

The invention relates to the technical field of wind power operation and maintenance, and discloses a wind power blade crack diagnosis method and system based on knowledge graph large model enhancement, and the method comprises the steps: S1, edge end image collection and crack semantic recognition: an edge end carries out the crack detection and semantic feature extraction of a collected wind power blade image sequence through an ECL-Net lightweight network, generating structured semantic information and transmitting the structured semantic information to a cloud; s2, cloud knowledge graph retrieval and semantic reasoning: the cloud performs semantic retrieval and causal reasoning on the structured semantic information through a KFR-Net knowledge graph reasoning network based on a pre-constructed wind power blade operation and maintenance knowledge graph, and outputs a knowledge retrieval result; and S3, multi-modal information is fused through an MMR-Cogntive multi-modal memory retrieval-cognitive generation network, and a structured maintenance report including crack detection summarization, cause analysis, maintenance measures and risk assessment is generated. The method has the advantage that intelligent closed-loop management of wind power blade cracks from detection to maintenance suggestions is realized.

Disclosed herein are system, method, and computer program product aspects for semantic search in a model-based prompt builder system. A system generates a search retriever object based on a search index comprising unstructured data. The search retriever object includes metadata specifying one or more details of a vector search operation to be performed on the search index. The system obtains search results by performing the vector search on the search index based on the one or more details of the vector search operation provided by the search retriever object and a search query. The system provides the search results to a prompt generator configured to use a model to generate a reply to a prompt request requiring the search results.

The invention provides a product scheme PPT automatic generation method, system and device and a medium, and belongs to the technical field of artificial intelligence. The method comprises the steps that product demand information is collected, an NLP tool is called for entity recognition and relation extraction, and a demand feature vector is generated; based on a MySQL database, retrieval is performed according to the demand feature vector, a structured record set is returned, and an associated document ID is obtained; based on a Milvus vector database, retrieval is carried out according to the demand feature vectors, and an unstructured document fragment set is returned; filtering the unstructured document fragment set according to the document ID, retrieving the unstructured document fragment set by adopting a mixed strategy of a BM25 algorithm and semantic retrieval, comprehensively sequencing retrieval results through a weighted scoring mechanism, and generating a final content fragment set; and calling a PPT template according to user requirements, and filling the final content fragment set into the PPT template to generate a PPT draft file.

The invention provides a life cycle evaluation automatic modeling method based on a large language model, and relates to the technical field of life cycle evaluation, and the method comprises the steps: extracting the multi-modal information of texts, tables, images and the like from the multi-source data of academic literatures, reports and the like, constructing an instruction data set in combination with LCA process knowledge, carrying out the instruction fine tuning of a base large model, and carrying out the automatic modeling of the life cycle evaluation. And obtaining the LCA field large language model. And generating a standardized prompt by utilizing a prompt word optimizer, driving a model to generate a product LCA model framework, filling list data, and perfecting process data in combination with semantic search and a correction mechanism. And intelligent connection recommendation among unit processes is realized by calculating the semantic similarity of input and output streams. And finally, the verified structured data is output to LCA modeling software, an automatic modeling process is completed, and the modeling efficiency and normalization are improved.

Systems or methods of the present disclosure may provide a design tool for adjusting designs implemented on programmable logic devices. The present disclosure includes receiving documentation and receiving a full text search. The documentation may include user guides, technical specifications, and design files such as HDL code, constraints, timing reports, and / or design assistant / rule violation (DRC) reports. The present disclosure also includes determining semantic search for embedding vectors based on the documentation and the full text search. Furthermore, the present disclosure includes providing the semantic search to a large language model (LLM).

The invention discloses a storage system software defect analysis method and system based on a large model. The method comprises the following steps: firstly, collecting public and internal historical defect data and multi-source logs, training a lightweight log extraction model after cleaning, and coarsely screening original logs of newly added defects; and inputting a coarse screening result into a large language model, and further studying and judging to output a real key log. And fusing and vectorizing the key log and the Bug description, and writing the fused and vectorized key log and Bug description into Elasticsearch to construct a historical case knowledge base capable of semantic retrieval. When a new defect enters the system, quickly extracting a key log by utilizing the trained model, and executing dual-channel retrieval in the knowledge base to recall similar cases; and the big language model is combined with similar cases to automatically generate responsible person recommendation, root cause analysis and executable troubleshooting and avoiding suggestions. According to the method, the problem that historical cases are difficult to retrieve can be effectively solved, similar cases can be quickly and effectively found from massive historical data under the double-control of Bug description and key logs, and study and judgment assistance is provided.

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 data retrieval, and discloses a time dimension semantic retrieval method based on a large model, which comprises the following steps of: acquiring multi-source original text data by utilizing a distributed crawler system, sequentially executing text cleaning operation, word segmentation processing operation, stop word removal operation and stem extraction operation, and performing identification and extraction to obtain multi-source original text data; obtaining a key time label; receiving and analyzing a natural language query instruction input by a user to obtain structured query information; based on the retrieval model, the absolute key time tag, the structured query information and a preset mixed index structure, executing retrieval operation to obtain a preliminary retrieval result; and performing online fine adjustment on the retrieval model by utilizing the optimized data to obtain a target retrieval result. By implementing the method and the device, the problems that related technologies excessively depend on predefined keywords or templates, the efficiency is low when large-scale data is processed, and individual requirements of different users are difficult to flexibly adapt are solved.

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.

The invention relates to the technical field of artificial intelligence, and discloses a semantic search method based on a legal knowledge graph, and the method comprises the steps: carrying out legal semantic element deconstruction on a natural language query of a user, and generating a query element sub-graph; in the pre-constructed legal knowledge graph, executing structured alignment retrieval in a mode of combining core node semantic pre-screening and graph structure isomorphism test; and performing weighted aggregation on the multi-dimensional element matching scores based on a legal element weight model to generate comprehensive correlation measurement, and sorting and returning a result according to the comprehensive correlation measurement. The system comprises a legal knowledge graph construction module, a query deconstruction module, a structured retrieval module and an interpretable abstract generation module. According to the method, through structured legal element alignment and weighted correlation evaluation, the accuracy, logicality and interpretability of class case retrieval are remarkably improved.

The invention provides a semantic search method and system for blood disease medical record big data, and relates to the technical field of medical information processing.The method comprises the steps that firstly, a blood disease medical record semantic association network is constructed, medical record text units serve as nodes, semantic association relationships serve as edges, and related information of the nodes and the edges is marked; analyzing a user search intention to generate a search semantic vector, calling semantic association network information to perform dynamic semantic matching to obtain a matched medical record text unit set, generating a hierarchical search result according to a matching result, dividing and sorting according to a matching dimension, and generating semantic association interpretation; and finally, based on the access behavior feedback of the user to the hierarchical search result, optimizing the semantic association network, recording user clicking, staying and secondary search triggering conditions, and adjusting the node association priority, edge association strength and weight to improve the accuracy and practicability of blood disease medical record search.

The invention discloses a report generation agent method, system and device driven by a large language model and a medium, and the method comprises the steps: constructing an agent execution framework independent of a native interface, outputting a decision through a cue word constraint model in a JSON structure, and scheduling a local tool function; analyzing the reference data and constructing a local vector knowledge base supporting semantic retrieval; the intelligent agent autonomously plans and generates a report directory structure based on a local vector knowledge base, stores the report directory structure as a structured intermediate file as a persistent intermediate representation, generates chapter content in parallel by utilizing a concurrent flow control and exponential backoff retry mechanism and combining a mixed retrieval strategy, and serializes and updates the chapter content to the intermediate file in real time; and finally, converting the intermediate file into a target format report according to a mapping rule. The system, the equipment and the medium are used for implementing the method. According to the method, the efficiency and the accuracy of complex report generation are remarkably improved through agent whole-process autonomous driving and combination of persistent intermediate representation, retrieval enhancement and concurrency control technologies.