161 results about "Knowledge question" patented technology

The invention discloses a knowledge question and answer processing method fusing a large model and a knowledge graph, and relates to the technical field of artificial intelligence and natural language processing. Aiming at the defects of a traditional retrieval enhancement generation technology in the aspects of complex semantic association, context consistency and dynamic knowledge updating, the scheme adopted by the invention comprises the following two stages: knowledge graph construction and mixed index generation: collecting and processing internal and external multi-source data of an enterprise, and performing cleaning preprocessing such as coding normalization and de-duplication to obtain a mixed index; entities and relations are extracted through a pre-training model to generate a triple, a knowledge graph is constructed and stored in Neo4j, then a mixed index is generated through text and graph embedding fusion, and two types of retrieval are supported; retrieval and answer generation: obtaining user query, preprocessing, vectorizing, obtaining a candidate list through low-level semantic retrieval and high-level reasoning retrieval, fusing multi-dimensional indexes, rearranging and screening top-M candidates through Cross-encoder, constructing a JSON evidence list, and generating traceable answers through small model draft, large model fine calibration and consistency verification.

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

The invention provides a knowledge question and answer library agent construction method and system. Efficient knowledge management and question and answer are achieved through cooperation of multiple agents. According to the system, firstly, a multi-modal information extraction agent is constructed, and heterogeneous data such as texts, images and tables are converted into structured vectors and stored; meanwhile, the knowledge graph is dynamically constructed and continuously optimized by the self-adaptive knowledge graph construction agent, and a new relationship is derived through combination of symbolic logic and a graph neural network, so that an evolvable knowledge network is formed. In the question and answer stage, a query analysis agent deeply analyzes the intention of a user and generates sub-queries; retrieving the vector library and the knowledge graph in parallel by the retrieval enhancement generation agent; and the reasoning and synthesizing agent integrates multi-source information and generates an accurate answer with a complete source label through a large language model. Dynamic knowledge management, precise semantic analysis and system self-evolution are achieved, and the method is particularly suitable for professional field scenes needing high-reliability questions and answers.

The invention discloses a knowledge question-answering method and system based on topic knowledge graph retrieval enhancement, and the method comprises the steps: firstly extracting a local topic represented in a triple form based on an original document through employing a large language model, carrying out the clustering, and generating a global topic triple set representing the global perspective of the whole document; secondly, on the basis of the global topic triple set, topic-guided entity and relation extraction is adopted, and a mixed knowledge graph is constructed; secondly, providing a semantic perception personalized PageRank algorithm, matching query semantics with semantics of edges in the mixed knowledge graph, and dynamically adjusting the weight of score propagation between nodes; and finally, designing a three-level progressive retrieval mechanism, retrieving multi-level information related to user query from the mixed knowledge graph, and inputting the multi-level information into the large language model to generate a final answer. According to the method, the semantic integrity and retrieval precision of the knowledge graph are remarkably improved, and the accuracy, comprehensiveness and enabling performance of generated answers are ensured.

The invention discloses a multi-modal multi-scale retrieval enhancement generation method, system and device applied to external knowledge questions and answers and a medium. The method comprises question perception, multi-modal multi-scale query fusion coding, dense recall and answer generation. Analyzing a key query phrase from the question through a fine-tuned instruction language model, and accurately positioning a region of interest corresponding to the phrase in an image by using an open set visual positioning model; multi-source information is compressed and distilled into an optimal query vector through a deep fusion network integrating multi-head self-attention and an information bottleneck theory; executing a maximum inner product search to recall related knowledge; guiding the large language model to synthesize all information to generate a final answer; the system, the equipment and the medium directly perform feature fusion in the vector space based on the method, so that challenges such as information loss and cascading errors caused by a traditional normal form can be effectively dealt with, high correlation and high accuracy of retrieval knowledge are ensured, and accurate and reliable image-text questions and answers are realized.

The invention relates to a multi-class archive knowledge question and answer agent based on a large language model, and belongs to the technical field of artificial intelligence and archive information management. The intelligent agent comprises a data preparation module, a semantic knowledge base construction module, a perception and analysis module, a decision and matching module, an execution and retrieval module, a cognition and reasoning module and an interaction and generation module. According to the method, the complex query intention of the user can be accurately understood, automatic association and semantic reasoning across archive categories are achieved, and the semantic splitting problem of a traditional retrieval mode in cross-category and multi-level query is effectively solved.

The invention discloses a knowledge question-answering method and system based on a large language model and a semantic abstract. The system comprises a tree structure abstract generation subsystem which comprises a knowledge base configuration module, a file management module, a document analysis module and a knowledge block management module and is used for automatically generating tree structure hierarchical knowledge blocks for large manual documents or multi-chapter manual documents; the dual-channel retrieval engine subsystem comprises a question rewriting module, a semantic abstract retrieval module, a detail knowledge block retrieval module, a father-son retrieval module and a prompt word construction module, and all the modules work cooperatively to ensure that semantic abstract knowledge blocks and detail knowledge blocks related to the question of the user are retrieved. According to the method, by introducing the semantic abstract based on the tree structure and the two-channel retrieval, perception of global knowledge and accurate extraction of local fine-grained knowledge can be achieved at the same time, and then the ability of a knowledge base question-answering system in processing the general and inductive problems is improved.

The invention relates to the technical field of knowledge questions and answers, in particular to a large language model knowledge question and answer method and system fused with a multi-modal knowledge graph. The method comprises the following steps: acquiring structured and semi-structured data and unstructured multi-modal data in an enterprise business scene; capturing data change through a real-time synchronization technology and executing targeted preprocessing to ensure the consistency of data quality and modal characteristics; constructing a dynamically updated multi-modal knowledge graph based on the preprocessed data, and integrating a multi-modal embedded model, a reordering model and a fine-tuned generative large model to obtain a knowledge storage-feature matching-semantic generation integrated architecture; according to the method, the defect of knowledge lag of a traditional system is overcome, and seamless fusion of the AI capability and the enterprise core business process is realized.

The invention discloses a question answering method and device for credit review knowledge based on a large model and a medium, and the method comprises the steps: obtaining a to-be-processed credit review question, extracting a core keyword from the question through a natural language processing algorithm, and converting the question into a deep semantic vector through a semantic vector model; inputting the questions into an intention classification model, generating filtering labels, inputting the questions into a distributed full-text search engine, screening a target knowledge base according to the filtering labels, and performing retrieval in the target knowledge base based on the core keywords and the deep semantic vectors to obtain a preliminary retrieval result set; calculating the score of each preliminary retrieval result in the result set according to the core keyword, the deep semantic vector and the weight factor, and screening out final reference content in a descending order; and on the basis of credit and loan business compliance requirements, risk control rules and question and answer output specifications, the credit and loan prompt words are constructed, and the final reference content is input into the large model to obtain structured credit and loan review answers, so that the question and answer efficiency and accuracy are improved.

The invention discloses an RAG question and answer optimization method and system based on fusion retrieval, and relates to the technical field of large model knowledge question and answer. The method comprises the steps of obtaining user query, executing keyword retrieval and semantic vector retrieval in parallel, and obtaining a keyword retrieval result list and a semantic vector retrieval result list respectively; and calculating the quality score of each text unit in each retrieval result list based on multi-dimensional quality evaluation, and filtering out the text units with the quality scores lower than a preset quality threshold value. And sorting the text units in all the filtered retrieval result lists by adopting a quality weighted reciprocal sorting fusion algorithm. And based on the length of each text unit and the document format to which the text unit belongs, performing context content enhancement and combination on each text unit after sorting, and generating an enhanced context block list. And constructing structured prompt information based on the enhanced context block list and user query, inputting structured prompt words into the large language model, and generating and outputting a final answer.

The invention provides a knowledge question-answering method and device based on a large model and a medium, and relates to the technical field of knowledge questions.The method comprises the steps that a data query period corresponding to a question text is obtained through a first large language model; if the duration of the data query time period is smaller than the preset duration, determining a target operation and maintenance tool from a plurality of preset operation and maintenance tools through a second large language model; controlling the target operation and maintenance tool to perform data acquisition, and taking the acquired data as intermediate data corresponding to the target operation and maintenance tool; performing data compression on the intermediate data based on the character number of the intermediate data to obtain target data; merging the target data into the context information, and obtaining an answer text according to the context information and a specified large language model after merging is completed; according to the method, input overflow, model reasoning failure or response delay caused by too large data volume or exceeding of the context length limit of the large language model can be avoided, the stability of answer generation is ensured, and the user experience is improved.

The invention provides a bridge operation and maintenance knowledge management and question answering method based on a knowledge graph and a large language model. The method comprises the following steps: performing semantic dicing and dynamic cue word generation on texts such as a design report and an overhaul report through a large language model, automatically extracting an entity-relationship-attribute triple, completing entity co-reference resolution and relationship combination, and constructing an initial knowledge graph; further utilizing a curiosity algorithm to continuously merge low-similarity new knowledge in a subsequent detection report to realize iterative growth of the atlas along with an operation and maintenance life cycle; forming a multi-level community by adopting Leiden clustering, generating an abstract pyramid, and enhancing macroscopic semantic expression; and finally, through a semantic embedding model and a GraphRAG technology, precise matching and traceable answering from natural language questions to graph knowledge points are realized. According to the method, the problems of knowledge fragmentation, update lag and illusion in the bridge operation and maintenance field are solved, and the accuracy and robustness of operation and maintenance knowledge questions and answers are improved.

The invention provides an electricity-carbon knowledge question-answering method and related equipment for the power industry, and the method comprises the steps: responding to a received question text inputted by a user, carrying out the retrieval in a pre-constructed electricity-carbon knowledge database based on the question text, and obtaining a plurality of pieces of associated data; acquiring identity information of the user; based on the question text, the multiple pieces of associated data and the identity information, a target answer text is generated through a pre-constructed electricity-carbon question and answer model, the technical problem that in the prior art, the efficiency of querying the electricity-carbon field knowledge by a user is low is solved, and the purpose of accurately and efficiently querying the electricity-carbon field knowledge is achieved.

The invention relates to an electricity marketing knowledge question-answering system and method based on multi-modal retrieval enhancement generation in the technical field of artificial intelligence and electricity marketing crossing. A three-layer framework of retrieval enhancement, generation enhancement and feedback optimization is adopted. A multi-modal retrieval engine is adopted, a large amount of related data is extracted from multi-source heterogeneous data, deep association, unstructured text fragments and structured data are fused and converted into a plurality of associated knowledge chains through a feature alignment technology, and therefore fragmented data are converted into data with high association. Therefore, comprehensive retrieval and deep association of the multi-modal data are realized; generating a unified knowledge representation through the plurality of associated knowledge chains, and analyzing the unified knowledge representation through a generative large model to generate a preliminary answer; the technical problems that a traditional power marketing knowledge question-answering system cannot effectively fuse and directly output answers by associating various data, so that the retrieval efficiency is low, and the accuracy of obtained answer data is poor are solved.

The invention provides a knowledge question-answering method and device, a processor and a storage medium, and belongs to the field of information retrieval, and the method comprises the following steps: constructing a professional knowledge base for a specific field; wherein the professional knowledge base at least comprises a full-text database and a vector database; receiving a user query, and preprocessing the user query to obtain a standardized query; executing multi-path knowledge recall from the plurality of heterogeneous data sources in parallel based on the standardized query to generate a fusion recall result; wherein the plurality of heterogeneous data sources comprise but are not limited to a full-text database, a vector database, an internal retrieval API (Application Program Interface) plug-in and an internet retrieval interface; the historical interaction information, the fusion recall result and the standardized query are assembled into cue words through the instruction template; and inputting the cue word into the large language model to generate a reply text, and outputting the reply text in multiple modes. Through the method provided by the invention, the accuracy and coverage rate of knowledge recall can be improved, the answer is closer to real consultation, and the user experience is improved.

The invention discloses a knowledge question-answering method and device fusing data completion and space-time anomaly perception, and belongs to the field of intelligent question-answering and credible generation in artificial intelligence, and the method comprises knowledge anomaly detection, retrieval enhancement generation, and question-answering based on artificial intelligence. According to the method, under the complex conditions that grammar errors, information loss, space-time dislocation or sensitive expression exist in user input, a space-time consistency constraint mechanism penetrating through the whole process of input-retrieval-generation-verification is constructed, so that a system actively recognizes and corrects multi-dimensional anomalies, wrong intention analysis and fact distortion propagation are avoided, and the user experience is improved. And the end-to-end question and answer service with high robustness and high credibility is realized. Meanwhile, prompt words and generated contents can be intelligently complemented according to context reasoning and domain knowledge under the condition of lacking a complete user instruction, and meanwhile it is ensured that output is strictly aligned with a real scene in the aspects of time, space and logic. Furthermore, in order to improve the factual accuracy and safety of the generated content, a'detection-correction-verification 'dual-stage closed-loop governance architecture is realized by utilizing an anomaly detection model (NN1 / NN3) and a correction generation model (NN2 / NN4) which are jointly trained, and landing application of a credible intelligent question-answering system in high-risk professional scenes such as medical treatment, law and industrial maintenance is effectively supported.

The invention relates to the field of big language model reasoning, in particular to an intelligent reasoning method based on big language model chain reasoning and a self-verification mechanism. The scheme comprises the steps of performing semantic analysis on a text input by a user, and extracting a problem structure and a reasoning intention; the problem is disassembled into a plurality of sub-problems, and a reasoning chain is constructed for reasoning; verification is performed after reasoning is completed; the verification result is judged, if verification passes, the reasoning result is reserved, and if verification of the reasoning result fails, the reasoning path is automatically optimized. Through a chain structure and a self-verification mechanism, the inference error rate is remarkably reduced, an inference path, a verification score and a logic basis are provided, and the user trust is improved. And multi-mode and multi-field tasks, such as knowledge questions and answers, logical reasoning and task decomposition, are supported. When verification fails, a reasoning path is automatically optimized, reasoning efficiency is improved, various large language models, knowledge bases and logic rule bases can be accessed, collaborative reasoning is achieved, and the method is suitable for multi-modal and multi-field intelligent reasoning tasks.

This invention relates to the field of natural language processing technology, and more particularly to a method, apparatus, terminal, and storage medium for question answering related to power finance knowledge. The method first performs word segmentation and entity linking on the question text, identifying multiple candidate word sets corresponding to multiple keywords in the power finance knowledge graph. The power finance knowledge graph includes multiple entities and multiple relationships. Then, relationship path matching is performed based on the multiple candidate word sets to obtain multiple candidate relationship paths. Finally, the final relationship path is selected from the multiple candidate relationship paths, and the final answer is determined based on the final relationship path. This invention utilizes a link reasoning model based on the intersection of candidate word sets for power finance knowledge graph question answering tasks, which can reduce the scope of relationship matching, improve the accuracy of relationship path matching, and thus enhance the accuracy of the question answering task.

The application relates to the technical field of artificial intelligence, in particular to a knowledge intelligent question-answering system based on knowledge graph driving, which comprises a knowledge graph construction module, an information point extraction module, an information analysis module, a correlation coefficient calculation module and a heuristic sorting module. The knowledge graph construction module extracts entities and the relationship between entities from a domain knowledge graph data set, traverses neighbor nodes of each entity node in a breadth-first manner, integrates remote nodes with a question distance value of 2 hops and above into a core knowledge graph, and obtains a domain knowledge graph containing extended correlation nodes. The information point extraction module performs double filtering and judgment of associated sentences and extended sentences on the first answer of the evaluated model, counts the number of effective associated information points and records the corresponding node total set. The application realizes quantitative evaluation and model optimization of the heuristic ability of the knowledge question-answering model, and effectively solves the problems of single heuristic evaluation dimension and the lack of horizontal comparison between models in the prior art.

Embodiments of the present application provide an enterprise knowledge question answering method and device, electronic equipment and computer readable storage medium, relating to the technical field of computer. The method actively detects the current configuration information of the target vectorization model before processing the user request, and compares it with the expected configuration information required by the corresponding target set in the vector database in real time, realizing the differentiated response to the write request and the query request. When the configuration does not match, the write operation is directly blocked to prevent data pollution of the vector library caused by error embedding. The query request is automatically degraded to text retrieval to ensure service availability. This read-write asymmetric control strategy avoids the data consistency risk caused by the asynchronization of the vectorization model and the database, ensures that the user can still obtain basic replies in abnormal state, and clearly feedbacks the blocking reason, thereby improving the user experience.

The invention discloses a thinking chain enhanced psychological knowledge question and answer data set construction method, device and equipment and a storage medium, and the method comprises the steps that psychological question and answer questions are sampled from an industry data source, an original question and answer data set is obtained, and the original question and answer data set comprises a plurality of psychological question and answer questions and corresponding standard answers; performing question stem splitting on each psychological question and answer question, and determining associated psychological knowledge corresponding to each sub-question stem obtained by splitting based on a psychological knowledge base; constructing a corresponding reasoning thinking chain according to the standard answer, each sub-question stem and the corresponding associated psychological knowledge; and adding the inference thinking chain to the original question and answer data set to obtain a target psychological knowledge question and answer data set. According to the method, detailed question stem splitting can be performed on the collected psychological question and answer questions, and the reasoning thinking chain is constructed in combination with the standard answers and the associated psychological knowledge, so that the data set not only comprises the questions and the answers, but also comprises a detailed reasoning process, and high-quality training data is provided for model training.

The application provides a kind of knowledge question and answer optimal solution selection method based on multi-objective semantic score, including obtaining question and splitting to form keyword set, and finding the attribute of each keyword;Determine the standard answer entry in knowledge base and match with keyword set and question respectively, and based on the same standard answer entry, splice two matching results into two-dimensional target score space;According to two-dimensional target score space, construct multi-objective optimal Pareto solution set and form hierarchical structure;According to keyword attribute, calculate dynamic keyword proportion, if greater than preset threshold, select corresponding solution from Pareto layer to merge to Pareto front;Calculate the score of each solution after merging Pareto front, and output the highest score solution as the optimal solution. By implementing the application, static and dynamic keywords in the question can be automatically identified, semantic retrieval path is constructed hierarchically, combined with Pareto optimal mechanism and hybrid scoring strategy, and finally the answer with the optimal comprehensive quality is output.

The present disclosure relates to the technical field of natural language processing, and particularly provides a knowledge question answering method, device, medium and product. The method comprises: in response to receiving a query request sent by a user terminal, obtaining a target question text to be processed, and determining a target text vector corresponding to the target question text; based on a document block vector filtering condition, starting from a leaf node at the bottom layer of a document block vector tree in a knowledge vector database, determining a target node according to a comparison result between the target text vector and a document block vector of the node, wherein the document block corresponding to the document block vector of the parent node in the document block vector tree contains text content in the document block corresponding to the document block vector of each child node under the parent node; based on a large language model, processing the target question text and the target text vector of the target node in the document block vector tree to obtain a question answering result, and sending the question answering result to the user terminal; and the present disclosure improves the accuracy, comprehensiveness and reliability of the determined question answering result.

The application relates to the technical field of knowledge question answering, in particular to a knowledge question answering high-relevance recommendation method based on large model semantic enhancement. The method obtains a query question proposed by a user, converts the query question into a query semantic vector by using a large language model; an index graph construction process of a question vector library by using an HNSW algorithm is optimized to obtain an optimized HNSW graph, the question vector library is composed of all questions in a knowledge base converted into question vectors by the large language model; ANN search is performed in the optimized HNSW graph to obtain questions with high relevance to the query semantic vector, which are used for recommendation and feedback to the user. By optimizing the construction of the HNSW graph, the generated graph structure can better reflect the internal correlation of domain knowledge, and the overall quality and user experience of relevant question recommendation in the knowledge question answering system are improved.

The application relates to the technical field of knowledge question answering, in particular to a knowledge question answering method based on a multi-modal document understanding large model of a graph structure, which comprises the following steps: obtaining a target task and a target document graph corresponding to the target task; generating a target heterogeneous document graph corresponding to the target document graph according to the target document graph; inputting the target task and the target heterogeneous document graph into a preset large model to obtain a target question and answer text corresponding to the target task; the method can achieve higher accuracy and robustness on multiple public benchmark tasks (such as document question answering, graph table question answering and table understanding); the method has excellent generalization ability for novel and complex document layouts; and the method realizes more simple and efficient system deployment and application through an end-to-end unified architecture.

The invention relates to the technical field of data processing, and discloses an energy knowledge question and answer dialogue management method and system based on regular matching. The method comprises the following steps: constructing a regular rule base and a knowledge database in the field of energy operation and maintenance, preprocessing a user input statement to obtain a standard input statement, and performing regular matching on the standard input statement to obtain a slot value list, a data table name and a query intention tag of the standard input statement; based on the slot value list of the standard input statement, the data table name and the query intention label, performing retrieval in the knowledge database to obtain a candidate answer set corresponding to the standard input statement, scoring each candidate answer in the candidate answer set to obtain a keyword score and a slot value score of each candidate answer, and obtaining the keyword score and the slot value score of each candidate answer; based on the keyword scores and the slot position value scores, comprehensive scores of the candidate answers are obtained, the candidate answer with the highest comprehensive score is selected as a reply answer to be replied to the user, the user scores the reply answer, and a reminding instruction is obtained based on scores.

The present disclosure relates to a knowledge question-answering method, an apparatus, a readable medium, an electronic device, and a program product. The method includes: acquiring a target question input by a user in a natural language; retrieving, through a machine learning model, in a knowledge base according to the target question to obtain a target knowledge document for answering the target question, and determining, based on the target knowledge document, a target answer for the target question, wherein the knowledge base is used to store a business knowledge document; and displaying the target answer to the user.

This disclosure relates to a model training method, a knowledge question answering method, an apparatus, device, medium, and product. The model training method includes: acquiring n training datasets; determining a target training dataset and a corresponding target validation dataset; validating an initial model using training data from the target validation dataset to obtain a first loss for the i-th validation operation; and validating the initial model using training data from the target training dataset to obtain a second loss for the i-th validation operation. Based on the first loss, the second loss, and a first sampling ratio corresponding to the target training dataset, a target sampling ratio is determined for the target training dataset. Target training data is acquired from the target training dataset according to the target sampling ratio, and an initial model is trained using the target training data to obtain the target model. Through this disclosure, adaptive adjustment of multi-domain training data acquisition is achieved during model training.

The invention provides a knowledge question and answer method and device, electronic equipment and a storage medium, and the method comprises the steps: receiving a question input by a user, generating a question vector corresponding to the question according to the question, determining a target corpus vector matched with the question vector from a preset first database according to the question vector, and sending the target corpus vector to the user; determining a target corpus vector, determining an identifier of the target corpus vector as a target corpus identifier, determining a knowledge type corresponding to the target corpus identifier from a corpus data table in a preset second database according to the target corpus identifier, and according to the knowledge type corresponding to the target corpus identifier and a target corpus, determining a knowledge type corresponding to the target corpus identifier from a knowledge data table corresponding to the knowledge type in the second database, and obtaining query knowledge information, generating reply information corresponding to the question according to the query knowledge information, and pushing the reply information to the user. Therefore, interactive personalized question and answer service can be provided for the user, and the question and answer efficiency and accuracy are improved.

The invention discloses an intelligent question answering and examination integration method, system and device based on retrieval enhancement generation. According to the method, two major functions of question answering and examination are deeply fused under the same technical framework, and accurate knowledge question answering and automatic examination evaluation are synchronously realized through a shared vectorization knowledge base by utilizing a large language model and a retrieval enhancement technology. According to the intelligent examination process, a question type planning algorithm, knowledge point diversity control, a question type professional scoring engine and a streaming output interaction mechanism are creatively integrated, examination paper with balanced questions and wide knowledge point coverage can be automatically generated according to preset distribution, and high-accuracy automatic scoring is achieved for complex question types such as multi-choice questions and simple answers. According to the method, the problems of information lag and answer non-traceability of a traditional large model and one-sided question setting, rough score, low efficiency and the like of an existing examination system are effectively solved, and the scientificity, efficiency and user experience of evaluation are remarkably improved.