118 results about "Query Rewriting" patented technology

The invention relates to the technical field of data optimization, and discloses a financial data warehouse intelligent SQL (Structured Query Language) optimization method based on a large model, which comprises the following steps: S1, SQL statement analysis and preprocessing: carrying out word segmentation, grammatical analysis and logic structure analysis on an SQL statement submitted by a user, and identifying keywords, table structures and query conditions in query; s2, large model semantic understanding and optimization suggestion: performing semantic understanding and logical reasoning on the analyzed SQL statements by using a large model, and automatically generating optimization suggestions, the optimization suggestions including index recommendation, query rewriting and execution plan optimization; and S3, generating and selecting a dynamic execution plan. According to the method, the advantages of a large model in the aspects of natural language processing and intelligent decision making are fully utilized and combined with the specific requirements of the financial data warehouse, and the execution efficiency of SQL query and the overall performance of the system are remarkably improved; the query response time of the financial data warehouse can be effectively shortened, and the resource utilization rate is improved.

Artificial intelligence techniques for query management are described. A method comprises generating, by a context detection module, context information for a first query comprising natural language information to request a result from one of a plurality of machine learning models, modifying, by a query modification module, the first query based the context information to form a first modified query, determining, by an intent module, an intent type for the first modified query, selecting, by a routing module, a machine learning model from the plurality of machine learning models based on the intent type, and routing, by the routing module, the first modified query to the selected machine learning model. Other embodiments are described and claimed.

The invention discloses a construction method of a traditional Chinese medicine alert question-answering system based on a large language model. The method comprises the following steps: establishing a traditional Chinese medicine knowledge base; constructing a retrieval enhancement generation model PV-RAG oriented to drug alert, and training and optimizing the PV-RAG model by taking the traditional Chinese medicine knowledge base as a training set; the PV-RAG model comprises a retrieval module, a text extraction module, a query rewriting module and a generation module; and constructing an intelligent question and answer application end, and generating a traditional Chinese medicine alert answer according to a natural language question input by a user. According to the traditional Chinese medicine alert question-answering system based on the large language model and the retrieval enhancement generation technology, deep semantic understanding of traditional Chinese medicine literatures is achieved through the text embedding model, multi-source data such as traditional Chinese medicine specifications, traditional Chinese medicine classics and clinical research literatures are effectively integrated, and the traditional Chinese medicine alert question-answering system is established. And rich knowledge support is provided for traditional Chinese medicine alert questions and answers.

The invention relates to the technical field of computer data processing, and discloses a data segmentation and query processing system under a distributed architecture. The system comprises a data segmentation module which divides data blocks based on a self-adaptive partitioning algorithm; the distributed storage module is used for distributing data blocks by using a consistent Hash algorithm and dynamically adjusting the distribution of virtual nodes; the index construction module is used for generating a global index table through a multi-layer inverted index algorithm; the query optimization module is used for converting query statements by utilizing a query rewriting algorithm; and the result aggregation module is used for processing the sub-query results by adopting a parallel aggregation algorithm. The system can dynamically process data according to data characteristics, optimizes the data storage and query process, effectively improves the data processing efficiency and query performance of a distributed system, and is suitable for scenes such as big data storage and analysis.

The invention relates to the technical field of retrieval enhancement generation, and particularly provides an RAG query rewriting method based on multi-stage retrieval feedback. The method comprises the following steps: constructing an improved RAG framework by introducing a query rewriter; training a query rewriter based on two stages of static feedback and dynamic feedback of a retrieval task; according to the method, the query is rewritten, the information alignment strategy is designed, the rewritten query is calibrated to the information range and semantics of the retrieval requirements, the query is optimized, the matching degree of the retrieval requirements is improved, and the coverage rate and accuracy rate of retrieval are improved.

The invention relates to the technical field of intelligent retrieval, in particular to an engineering knowledge base construction and deep retrieval method, which comprises the following steps of: in a knowledge base construction stage, performing knowledge level identification on an engineering knowledge document to form a multi-level tree structure taking chapter titles and corresponding contents as nodes; performing analysis processing on the heterogeneous content of each node to generate knowledge fragments; and generating embedded vectors of knowledge fragments by adopting a way of combining path embedding and content embedding, and storing association relationships among knowledge, vector data and original information to complete knowledge base construction. In the deep retrieval stage, after a user question is received, a knowledge blank question list is generated through query and rewriting, a knowledge base is retrieved through traversal of the list, the retrieval process is optimized through knowledge grouping, correlation sorting and loop termination judgment, and finally reply content subjected to traceable verification is generated and output based on existing knowledge accumulated in a circulation mode. According to the method, the reuse efficiency and the retrieval accuracy of the engineering knowledge can be improved.

Embodiments of the invention disclose a query rewriting method and apparatus, which can search for synonyms of keywords in a specified field according to field information, so that a semantic drift phenomenon can be reduced, and contents of other fields in a query result can be reduced. The method comprises the steps that after a query rewriting device obtains a keyword from a query statement from a user, field information of the keyword is determined, then synonyms of the keyword are obtained from an inter-word relation ontology associated with the field information, and the query statement is rewritten into a target query statement comprising the synonyms.

The invention discloses an information retrieval method and system based on an RAG and a large language model, and belongs to the technical field of intelligent office. The method comprises the following steps: analyzing different types of documents by adopting a long and short mixed granularity method and a preset splitting strategy to obtain text fragments of long and short granularities aiming at the different types of documents, and constructing a long and short mixed granularity knowledge base on the basis of the text fragments of the long and short granularities; when a user question is received, adjusting the user question into a specific query statement by using a multi-round query rewriting mechanism based on a large language model; and taking the specific query statement as a retrieval statement, performing retrieval in the long and short mixed granularity knowledge base by using a retrieval enhancement generation technology (RAG) to obtain retrieval results, sorting the retrieval results according to release dates of knowledge in the retrieval results, and preferentially displaying the retrieval results sorted in the front. The application of the method improves the accuracy of question and answer retrieval query.

The invention belongs to the technical field of artificial intelligence, and particularly relates to a commercial real estate question and answer content generation system based on a retrieval enhancement technology. The system comprises an original data processing module, a text content slicing module, a knowledge base construction module, a query rewriting module, a problem planning and disassembling module, an intention routing module, a mixed retrieval module and a content generation module. The method has the characteristics that the efficiency is higher, the accuracy is higher, and meanwhile, the use experience of a user is also greatly improved.

The invention relates to a query optimization method and device based on agent planning, electronic equipment and a medium. The method comprises the following steps: pre-retrieving a target tree structure index based on a user query request to obtain a pre-retrieval result set; generating a retrieval-reasoning double-stage directed acyclic graph task chain comprising a task type, a retrieval / reasoning target and a dependency relationship; executing each task according to a topological sequence, and obtaining a target text fragment through query rewriting and expansion; and performing multi-hop logical reasoning in combination with the task chain and the target text fragment, and outputting a final answer. Therefore, dynamic task planning of environment perception is carried out by constructing a retrieval-reasoning dual-stage directed acyclic graph task chain and combining a knowledge base tree structure index; the problems that when an existing retrieval enhancement generation system processes a multi-hop question and answer task, logic association understanding ability among retrieval fragments is insufficient, semantic matching precision is low, and a reasoning path is prone to deviation are solved, and the retrieval recall rate and the answer accuracy under a multi-hop question and answer scene are improved.

The invention discloses an intelligent questioning and answering method and system for a knowledge graph in the field of power marketing based on a large model Agent, and the method comprises the steps: obtaining a to-be-queried question and the large model Agent, enabling a question rewriting tool of the large model Agent to complete and rewrite the question Q based on a constructed prompt word module and a pre-trained templated processing model, and carrying out the quality verification of a rewritten new question Q '; inputting the new question Q'passing the quality auditing into a large model Agent, and converting the new question Q'into at least one query statement q; the query statement q is processed through a result generation tool, a result R returned by processing is received, and the result R contains data requested by the query statement q; the large model Agent evaluates the result R, if the result R is correct, the result R is output, if not, the iteration process is started, and in the iteration process, the large model Agent judges whether to rewrite the generated new question Q'and generate a new query statement.By means of the question query rewriting method and device, the question query rewriting capacity can be enhanced, the query result accuracy can be improved, and the query efficiency can be optimized.

Aspects of the disclosure include methods and systems for an intelligent chat powered by a large language model that leverages both public and private data to answer user questions. An exemplary method includes receiving a user query including natural language input from a user and executing the user query against at least one public data source and at least one private data source. Queries executed against a public source are retrieved using public search indices and queries executed against a private data source are retrieved using user credentials. A query rewrite and a query context including the user query and retrieved information from the public and private data sources are input to a large language model. A response is received from the large language model that includes a natural language answer to the user query and a link to the retrieved information.

The invention provides a big language model user query rewriting method and system based on historical context, and belongs to the technical field of artificial intelligence. The method comprises the following steps: firstly, collecting a data set containing user query and historical dialogues, redesigning a new instruction, taking a DeepSeek model as a query revisor, and further optimizing the preliminarily rewritten query to obtain a final query version; the method comprises the following steps: calling a DeepSeek model through an API (Application Program Interface), rewriting a query by utilizing the DeepSeek model under the guidance assistance of a designed instruction, optimizing an original query, generating a plurality of improved candidate queries, storing the improved candidate queries in a query pool, and then scoring all queries in the query pool by adopting a candidate query-context alignment scoring mechanism, and selecting the candidate query with the highest score as a preliminary optimization result. According to the method, the query rewriting frame based on the open source large model is constructed, so that the rewriting quality of user query is effectively improved, and the performance of information retrieval is improved.

The invention discloses a document retrieval query rewriting method and system based on a large language model, and the method comprises the steps: collecting a query rewriting data set, carrying out the correlation filtering and retrieval increment, and retaining a data sample highly related to a query rewriting task; an auxiliary task data set highly related to the query rewriting task is collected, and a multi-task SFT data set is constructed; constructing a self-supervised fine tuning model based on GPT-2, taking query as input, taking query rewriting as output, and training the self-supervised fine tuning model by using a multi-task SFT data set; a self-supervised fine tuning model is regarded as an intelligent agent, and target alignment is carried out based on reinforcement learning, so that the self-supervised fine tuning model better conforms to the user intention when generating query rewriting; a plurality of candidate rewrites are generated for each query using a beam search algorithm, a self-supervised trim model of target alignment is entered, and a set of related documents is retrieved. According to the method, the retrieval relevance is improved, and the user satisfaction is improved.

The invention relates to a retrieval problem optimization method, medium and system based on a multi-layer knowledge base, and the method comprises the steps: carrying out the level-to-level management of knowledge data, and constructing the multi-layer knowledge base; according to user query, retrieving the multi-layer knowledge base to generate an initial vector block set; performing first query rewriting on the query, and retrieving the multi-layer knowledge base again to generate an update vector block set; according to the source statistical result of the initial vector block set and the updated vector block set in the multi-layer data block, determining the strength direction of retrieval; and according to the strength direction of the retrieval, carrying out second query rewriting on the query, and outputting a query problem. Therefore, the intensity direction of the retrieval is positioned, and a query problem with both professionality and comprehensiveness can be generated. According to the method, through two rounds of optimization, the ambiguity of query is remarkably reduced, the accuracy and diversity of the generated content are enhanced, and a more efficient and more accurate solution is provided for application of the RAG system in complex tasks.

The invention relates to the technical field of natural language processing, can be applied to business system platforms of financial science and technology, medical health and the like, and discloses a document retrieval method, system, equipment and medium. Extracting semantic features of the text data and visual features of the image data, extracting time sequence features of the interaction log, carrying out cross-modal fusion on the semantic features, the visual features and the time sequence features to obtain fusion features, carrying out query rewriting on the text data according to the fusion features to obtain a query text, and sending the query text to the server. The method comprises the steps of obtaining a query text, performing document retrieval according to the query text to obtain a retrieval result set, determining the correlation between each retrieval result in the retrieval result set and the query text to obtain a correlation score set, and sorting the retrieval result set according to the correlation score set to obtain a final retrieval result. And the document retrieval accuracy is improved.

The embodiment of the invention discloses a database query optimization method and device based on a large model and a medium, and relates to the technical field of databases. The method comprises the steps that under triggering of a current query request, a query SQL text of the current query request is collected in real time, and real-time environment data of a current execution engine is obtained; vectorizing the query SQL text and the real-time environment data to determine a query reference vector; the query reference vector is input into a pre-trained space-time attention model, performance bottleneck positioning data for the current query is determined, a query optimization strategy is determined based on the performance bottleneck positioning data, and the query optimization strategy comprises an index optimization strategy and a query rewriting strategy; and optimizing the current query request according to the query optimization strategy, determining optimized query information, performing rewriting security verification on the optimized query information in a preset database copy environment, and executing database query based on the optimized query information after the rewriting security verification is passed.

The present application provides a query processing method and apparatus based on multi-table join. The method relates to a user end, an optimization end, an execution end, and a database. The method comprises: when the optimization end receives a query request sent by the user end, the optimization end invokes corresponding metadata from the database on the basis of the query request; the optimization end generates a first access constraint on the basis of a data table set and preset cross-table semantics; the optimization end generates a query plan on the basis of the first access constraint and preset query rewriting types, wherein the query rewriting types comprise projection matching rewriting and Join rewriting; the optimization end sends the query plan to the execution end; the execution end is used for feeding back a query result, which is generated by executing the query plan, to the user end. The present application improves a cross-table data dependency capability, reduces the read-write overhead and calculation amount of scanning during query, reduces the maintenance cost, and supports real-time updating of data.

In some embodiments, a system transforms an initial user query into a first rewritten query using a first query rewriting algorithm, executes a search of a data repository using the first rewritten query to generate a set of results, executes a chunking process on the set of results to generate chunks of data, transforms the initial user query into a second rewritten query using a second query rewriting algorithm, generates corresponding embeddings for the second rewritten query and the chunks of data using a reranking model, selects a subset of the chunks of data based on a comparison of the embeddings for the chunks of data and the embedding for the initial user query, generates a prompt based on the initial user query and the subset of the chunks of data, submits the prompt to a Large Language Model (LLM) to generate a response to the initial user query.

The invention discloses an autonomous controllable heterogeneous data driven agent collaborative optimization system and method, and the method comprises the steps: constructing a private domain knowledge database containing knowledge information of an interested field through deploying an inference engine and a functional component; the intelligent agent development and management collaborative platform deployment is used for developing a multi-task intelligent agent based on cooperation of a functional component and an inference engine, and the multi-task intelligent agent is sequentially subjected to iterative questions and answers of intention recognition, query rewriting, dynamic planning, retrieval recall coarse screening and secondary fine arrangement of coarse screening results on the basis of a private domain knowledge database. Therefore, collaborative optimization of the multi-task agent based on autonomous controllable heterogeneous data driving is realized. According to the method, an agent development and management collaboration platform is constructed based on a private domain knowledge database, full-link autonomous controllability of a multi-task agent is achieved, domain knowledge and user feedback pairs are introduced to conduct multi-round iterative problem retrieval, retrieval results are collaboratively optimized, and the problem retrieval efficiency and retrieval precision are remarkably improved.

Aspects of the disclosure include methods and systems for an intelligent chat powered by a large language model that leverages both public and private data to answer user questions. An exemplary method includes receiving a user query including natural language input from a user and executing the user query against at least one public data source and at least one private data source. Queries executed against a public source are retrieved using public search indices and queries executed against a private data source are retrieved using user credentials. A query rewrite and a query context including the user query and retrieved information from the public and private data sources are input to a large language model. A response is received from the large language model that includes a natural language answer to the user query and a link to the retrieved information.

The embodiment of the invention discloses a search query information complementing method and device, equipment, a medium and a program product. A specific embodiment of the method comprises the following steps: generating a candidate complementation information set corresponding to search and query information according to the input search and query information; determining whether candidate completion information meeting a preset query rewriting condition exists in the candidate completion information set or not; in response to determining that the candidate completion information meeting the preset query rewriting condition exists in the candidate completion information set, performing rewriting processing on the candidate completion information meeting the preset query rewriting condition in the candidate completion information set so as to update the candidate completion information set; and generating a complementation information set corresponding to the search query information based on the updated candidate complementation information set. According to the embodiment, the accuracy and the conversion rate of the complemented search query information can be improved, so that the difficulty of detecting the required article can be reduced, and the conversion rate of the searched article can be improved.

Artificial intelligence techniques for query management are described. A method comprises generating, by a context detection module, context information for a first query comprising natural language information to request a result from one of a plurality of machine learning models, modifying, by a query modification module, the first query based the context information to form a first modified query, determining, by an intent module, an intent type for the first modified query, selecting, by a routing module, a machine learning model from the plurality of machine learning models based on the intent type, and routing, by the routing module, the first modified query to the selected machine learning model. Other embodiments are described and claimed.

The invention belongs to the technical field of SQL (Structured Query Language) conversion, and relates to an intelligent analysis and SQL dynamic conversion method for natural language query of a large-scale database, which is used for segmenting the natural language query input by a user, extracting key information and forming a keyword list by utilizing a word segmentation technology, thereby laying a foundation for subsequent analysis. Secondly, in combination with grammar and semantic analysis of deep learning, a natural language query analysis model is constructed, training is carried out through a labeling data set, and it is ensured that the model can deeply understand semantic and structural information of query; then, the keyword list is input into the trained model, the corresponding SQL statement is successfully analyzed, and the query accuracy and efficiency are improved; after the SQL statement is generated, the system further optimizes the query plan, and the high efficiency of dynamic execution in the database is ensured through the technical means of index selection, query rewriting and the like. And finally, the query result is returned to the user in a structured form, so that the user experience and the data acquisition convenience are improved.

The invention relates to the technical field of natural language processing and artificial intelligence, and particularly discloses a generation and retrieval collaborative optimization method and system for a ReGenSearch task. The system comprises a reflection module, a query rewriting module, a retrieval and generation collaborative optimization module, a reinforcement learning and reward mechanism module and an answer optimization and generation module. The method comprises the following steps: analyzing problems and expanding backgrounds through a reflection module, generating an optimized retrieval query through a query rewriting module, dynamically selecting a generation or retrieval strategy by a retrieval and generation collaborative optimization module, and judging whether iteration is carried out by combining a self-commenting mechanism; a joint strategy is optimized through a DAPO algorithm, and feedback is evaluated through a layered reward mechanism; and finally, comparing the candidate answers by using a DPO algorithm, and selecting an optimal reasoning path for outputting. The method does not need cold start or fine tuning in the specific field, can directly run based on the pre-trained large language model, adapts to multi-step reasoning and long thinking chain tasks, realizes deep fusion of generation and retrieval, and remarkably improves the accuracy, stability and generalization ability of complex questions and answers.

This disclosure describes a workload reduction system that reduces the complexity of workloads sent to a database system. For instance, the workload reduction system pre-processes workloads sent to a database system by generating reduced workloads that include less complex queries that reference fewer tables or columns than the original workloads. In various implementations, the workload reduction system uses table reduction functions and query re-writing functions to generate the reduced workloads. As a result, the workload reduction system improves computational efficiency by rewriting complex queries from workloads into simpler ones that speed up index tuning and decrease individual what-if call times.

The invention discloses a method for constructing an intelligent search engine based on a large language model, comprising: step 1: original query; step 2: manual setting of filters; step 3: based on the original query and filter setting input by the user, the retrieval rewriting module is responsible for converting it into a professional retrieval statement, and the modules involved in the retrieval rewriting process include: dynamic few-shot examples based on NER, professional terminology recommendation, retrieval main sentence rewriting based on LLM, retrieval main sentence verification, filter automatic planning module, retrieval sentence conversion module and retrieval main sentence merge filter clause; step 4: using a retrieval engine to retrieve relevant documents; step 5: document reordering; step 6: document summary and indexing. The invention optimizes the query rewriting module and the reordering module, and the accuracy of retrieval rewriting and the rationality of recall document reordering are significantly improved.

The present disclosure provides a training method and device of a query rewriting large model, equipment and medium. The method comprises: performing preliminary optimization on the query rewriting large model based on a fine-tuning dataset to obtain a reference model; and performing re-optimization on the reference model based on a reinforcement learning method to obtain a target model, wherein a reward signal in the reinforcement learning process is generated based on a deviation between a question and answer result of the reference model and a standard answer. Thus, the model can be quickly learned to the basic query rewriting mode by using the fine-tuning dataset for preliminary optimization. Then, the reinforcement learning is introduced, and the deviation between the question and answer result of the reference model and the standard answer is used as the reward signal for fine adjustment, which can effectively correct the generation deviation that may exist in the preliminary model, so that the final target model can generate a rewriting result closer to the real intention of the user in a complex query scenario, thereby improving the overall performance of the downstream question and answer system.

The invention discloses a medical information retrieval method and system based on multi-modal vectorization and a storage medium, and relates to the field of intelligent retrieval. The method comprises the following steps: constructing a corpus and performing field self-adaptive fine tuning to obtain a field optimization recall model; generating a mixed modal vector through a cross-modal attention mechanism and a gating fusion mechanism according to the domain optimization recall model; carrying out slicing processing on the retrieval original text; and after to-be-retrieved information is rewritten and vectorized, retrieval is performed according to the mixed modal vector and the father-child node slice structure. According to the retrieval method, professional corpus semantic optimization, multi-modal information fusion, intelligent document slicing and query rewriting can be combined, and the problem of semantic fracture caused by insufficient multi-modal information fusion and document slicing in a medical RAG system is solved.