1543 results about "Query language" patented technology

The invention discloses an interactive question intelligent agent system based on a large language model, and relates to the technical field of dialogue interaction systems. Aiming at the technical defects of the traditional BI tool, the technical scheme is as follows: a heterogeneous data management engine realizes unified access and secure access of cross-source data; the NLP semantic recognition engine converts a natural language into structured semantics through multiple steps, drives the hybrid SQL generation engine and provides visual parameters; the generation engine realizes precise generation from semantics to SQL through a two-stage architecture based on metadata and authority rules; and the visual management console is combined with multi-party configuration and parameters to visually build a number-asking agent. The method is used for realizing intelligent conversion from a natural language to a structured query language (SQL) and a data service interface, and automatically generating an interactive data visualization result.

A graphical, hierarchical document stream browser and environment for semantic (e.g. framing) and performance data analysis and interactive visualization integrates three scales: entities (competitive), entity (diachronic), and document (linguistic). The document level includes annotation and computational linguistics facilities; the entity level has calendrical and time-series focus. All levels emphasize deep linkage and network (i.e. connective / relational space) view of objects, with user-configurable connectivity. Large language model (LLM) integrations provide synthetic advisories, public opinions, reports, plot insights, comparisons; traditional natural language processing techniques and neural models are also employed. A smart plot system includes a “plot cart” and interpreter with an analysis snippet library. Graph structure may arise via adjustable blending or perceptual optimization of canned attribute-related distance functions or via link-induction query language with deep “semantic stored procedure” subexpressions, or feed into graph neural network-style inference for predictions. Most non-LLM ongoing computational load is client-side, using precomputed hierarchical summary files.

The invention discloses a Text2SQL (Structured Query Language) implementation method and system, and relates to the field of data processing, and the method comprises the following steps: firstly, receiving a natural language query, and analyzing a query intention, field classification and a key entity through a planner; the searcher obtains domain knowledge, entity information, a database table structure and a historical query mode in a multi-path parallel mode based on the planning result; the generator constructs an SQL framework according to the retrieval result and generates an initial statement; the verifier carries out grammar, table field, authority and logic multi-dimensional verification on the SQL, and if the verification fails, iteration adjustment is carried out to generate logic; when the SQL is executed, the result is formatted and a natural language explanation containing query logic, a data source and a calculation method is generated if the SQL is executed successfully, and a diagnosis and error correction mechanism is started for correction and then rechecking is performed if the SQL is executed unsuccessfully. According to the method, through deep fusion of domain knowledge, whole-process verification error correction and interpretability enhancement, the accuracy, robustness and user interaction experience of SQL conversion in a professional scene are improved.

The invention relates to the field of natural language processing, and discloses an SQL statement generation method, system and device based on a large model. Respectively carrying out vectorization processing and document processing on the metadata and the metadata description text information from the database, and storing the metadata and the metadata description text information into a vector database and a full-text retrieval library; in response to the query instruction, respectively performing query matching on the vector database and the full-text retrieval library, screening matching results which are ranked in the front and are preset ranks according to the similarity from high to low, and determining an optimal SQL statement list and optimal metadata; on the basis of the current language of the query instruction, generating a cue word of the current language in combination with the optimal SQL statement list and the optimal metadata; the large model of the preset type is determined according to the language type of the cue word, the preset large model is called to conduct reasoning on the cue word, and the SQL statement is generated. Based on the large model and the generative AI technology, the accuracy of the generated SQL statement is improved, the use threshold of non-technical personnel is lowered, and the query efficiency of the SQL statement is also improved.

A user provides a question to be answered from detailed, dense or otherwise complex documents to a processing system that converts the question to a structured query language query and generates an embedding from the question, augmented by temporal data, synopses, themes, or other relevant information or data. The embedding is compared to embeddings generated from documents of a knowledge base to identify documents that are relevant to the question, and to rank such documents for their relevance. Highly ranking documents are combined with the query and provided to a language model that returns an answer to the question. A source for the answer is identified in at least one of the documents. The answer and the identified documents are presented to the user.

The invention discloses a large model enhanced code security detection method. The method comprises the following steps: dynamically associating CVE vulnerability features with code semantic representation through a knowledge graph construction module; extracting vulnerability features from a CVE vulnerability library by utilizing a knowledge graph construction module, and dynamically associating the vulnerability features with code semantics; based on the CodeQL standard, a query language is generated by adopting a large model and input into CodeQL for AST analysis, and code structure features are extracted; the large model generates a query language meeting the CodeQL standard, codes are analyzed through CodeQL, and key structure features are extracted; integrating a static analysis tool chain to carry out multi-dimensional credible verification on model output; integrating an SAST tool and a symbolic execution tool, and verifying the model output from different dimensions; and summarizing and fusing detection results of the enhancement layers, and determining a final detection result by adopting a decision optimization method. According to the method, through technical fusion and dynamic optimization, the problems of rule stiffness, one-sided detection and low result credibility are systematically solved.

A disclosed method facilitates translation of natural language queries into query language statements usable to retrieve data from or write data to a particular database. The method includes obtaining a pool of shots. Each shot in the pool includes a natural language query component and a corresponding database translation component. The method further provides for vectorizing the natural language query component for each of the shots into a common vector space; receiving a natural language query from a user interface; vectorizing the natural language query within the common vector space; identifying a subset of vectorized natural language query components that satisfy a similarity metric when compared to the vectorized natural language query; and generating an LLM prompt that includes shots from the pool corresponding to the subset of the vectorized natural language query.

Systems and methods are directed to incorporating large language model (LLM) prompts into graph queries using graph query language and executing these graph queries. The system receives a graph query that includes a LLM prompt in the graph query language. The LLM prompt comprises an input context and a query to be answered. Based on the graph query, the system traverses a knowledge graph to obtain context data associated with the input context. The context data may be constrained by access control policies of an enterprise providing the knowledge graph. A context table may be generated using the context data based on the input context indicated in the LLM prompt. The system then invokes an LLM to determine a result by applying the query of the LLM prompt to the context data obtained from the traversal of the knowledge graph. The result is then presented on a user interface of a client device.

The invention discloses a database query method and device, electronic equipment and a nonvolatile storage medium. The method comprises the steps that a knowledge graph corresponding to a to-be-queried database is determined, and the knowledge graph is used for representing a logic structure and an incidence relation of data in the to-be-queried database; a similarity score between the user question text and each graph node in the knowledge graph is determined, a target node is determined in each graph node of the knowledge graph according to the similarity score, and the similarity score is used for representing a correlation degree between the graph node and the user question text; and generating database mode information corresponding to the to-be-queried database according to the target node, and generating a structured query language statement corresponding to the user question text by adopting a large language model according to the database mode information. According to the method and the device, the technical problem of poor accuracy of generating the query statement of the database by utilizing the large language model due to the fact that the field information in the database is numerous and the relationship is complex is solved.

A computer-implemented for information processing based on a large language model (LLM) includes: obtaining a query request; determining, by the LLM and based on the query request, a query condition, a source of a query result, and a select field for generating a structured query language (SQL) statement; generating by the LLM, the SQL statement by combining the query condition, the source of the query result, and the select field; and obtaining the query result corresponding to the query request, by inputting the SQL statement into the LLM for execution

The invention discloses a charging station operation maintenance method based on a multi-dimensional data system, and relates to the field of intelligent optimization, and the method comprises the steps: collecting the operation, environment, user and power grid data of a charging pile, preprocessing the data into JSON, carrying out the real-time analysis and classification through Kafka-Flume, storing the data into a distributed database, building a composite index, and carrying out the retrieval through Presto; after cleaning, combining GraphQL and a graph query language to construct a space-time atlas, and extracting a multi-dimensional feature vector; a digital twinborn model is generated, multi-source data are fused through virtual-real mapping, and residual correction and reinforcement learning optimization are combined; fusing multi-modal data by using a hypergraph neural network, and optimizing topology in combination with an entropy regularization multi-target strategy and meta-learning; power is dynamically distributed, LSTM-GAN predicts and positions faults, and PID regulates and controls output; and the block chain contract automatically triggers equipment freezing and power limiting, and on-chain data feedback optimizes scheduling and load balancing. According to the invention, through multi-dimensional data fusion and a dynamic optimization mechanism, the operation and maintenance accuracy and response efficiency of the charging station are significantly improved.

The invention discloses a structured query language generation method and device based on a large model, equipment and a medium, and relates to the technical field of artificial intelligence. The method comprises the steps of performing unified index definition and dimension definition for different business scenes, and combining indexes and dimensions in the business scenes according to the index definition and the dimension definition to obtain different structured query language templates; obtaining a natural language query statement input by a user in the current service scene, and performing semantic analysis on the natural language query statement by using a preset large model to obtain a semantic analysis result; and determining a target structured query language template matched with the natural language query statement from the structured query language templates according to the semantic analysis result, and filling the target structured query language template to generate a structured query language statement result. According to the technical scheme, the natural language query of the user can be efficiently and accurately converted into the structured query language statement.

The invention provides a natural language SQL (Structured Query Language) conversion method based on a data platform and a large language model, which relates to the technical field of data processing and comprises the following steps of: performing vectorization storage on metadata, blood relationship, indexes and historical query information, performing intention judgment and vector matching on a user query request, and determining a query condition based on a matching result. An association path is constructed according to data consanguinity, and an optimal SQL statement is generated by utilizing a historical query optimization table connection sequence and combining index matching. According to the method, intelligent conversion from the natural language to the efficient SQL can be realized, the query efficiency is improved, and the use threshold of a user is reduced.

A text-to-structured query language conversion method based on a large language model comprises the steps that database outline information is cut, and tables and columns needed by query of a non-target structured query language SQL are eliminated through correlation scoring and Steiner tree problem solving; screening context samples, predicting a similarity score from a text to a structured query language Text-to-SQL by using a cross encoder language model, and selecting a sample most related to a query problem; and injecting the cut database table and column information and the screened context sample into a cue word template, and generating an SQL query statement by using a large language model. The method can be used for optimizing the automatic conversion process from the natural language to the SQL and improving the conversion accuracy, and is used for providing a quick and convenient database retrieval mechanism for a non-SQL user and providing applications such as a data access mode in a wider form for mechanisms such as big language model retrieval enhancement generation RAG and the like.

The present disclosure includes systems and methods for a security policy framework. Various embodiments include responsive to receiving a trigger, fetching one or more policies from a policy catalog service; compiling the one or more policies into a query, wherein the one or more policies can be compiled into a plurality of different query languages; executing the query over customer data, the customer data being located in one or more data sources; and persisting results of the query.

A graphical, hierarchical document stream browser and environment for semantic (e.g. framing) and performance data analysis and interactive visualization integrates three scales: entities (competitive), entity (diachronic), and document (linguistic). The document level includes annotation and computational linguistics facilities; the entity level has calendrical and time-series focus. All levels emphasize deep linkage and network (i.e. connective / relational space) view of objects, with user-configurable connectivity. Large language model (LLM) integrations provide synthetic advisories, public opinions, reports, plot insights, comparisons; traditional natural language processing techniques and neural models are also employed. A smart plot system includes a “plot cart” and interpreter with an analysis snippet library. Graph structure may arise via adjustable blending or perceptual optimization of canned attribute-related distance functions or via link-induction query language with deep “semantic stored procedure” subexpressions, or feed into graph neural network-style inference for predictions. Most non-LLM ongoing computational load is client-side, using precomputed hierarchical summary files.

In one embodiment, a method herein comprises: inputting, by a device, an input prompt to a first large language model to generate an output; computing, by the device, a reward metric in part by using a solver to process the output; tuning, by the device and based on the reward metric, a second large language model configured to correct errors of the first large language model using reinforcement learning; and using, by the device, the second large language model to correct an error of the first large language model.

The invention relates to an intelligent power data searching method based on a resource map, which comprises the following steps of: S1, integrating power data from different systems, cleaning the data, and unifying a data format; s2, performing entity recognition by using Stanford NLP and BERT, and establishing relation mapping among entities by using a relation extraction algorithm; s3, storing a knowledge graph by using a graph database, mapping entities to nodes, mapping relationships to edges, and establishing multiple types of indexes; s4, natural language query is converted into graph database query languages such as Cypher, and query execution is accelerated by utilizing an index of a graph database to be matched with a cache strategy; s5, on the basis of the established multi-type index, using a query mode prediction model to predict a query mode and dynamically adjusting the index; and S6, adjusting a result sequence based on user history and context information, and executing semantic reasoning to expand a query result according to a semantic concept and a hierarchical structure of the knowledge graph. According to the method, the query efficiency on the large-scale power multi-source data set is effectively improved.

A communications session with a user may be automated using a language model. The language model may be instructed to select a next action to be performed where the next action may include transmitting a responsive communication to the user or performing an API call. The prompt used to query the language model may include one or more of the following: a representation of text of the communications session, a list of available API calls, instructions to select a next action, a representation of API calls performed, or a representation of API call responses received. The language model may be sequentially queried to continue the communications session by transmitting responsive communications or performing API calls. In some implementations, a prompt template may be used to generate the prompt and a prompt template may be selected using text of the communications session.

The invention relates to a power field Text2SQL (Structured Query Language) data analysis method based on LLM (Logical Language Model) and RAG (Random Access Gateway), and solves the defects that a retrieval result contains noise and redundancy and a large model still has a large number of illusion phenomena due to the absence of a vectorization model in a specific field and the singleness of knowledge base types and dimensions in the RAG technology compared with the prior art. The method comprises the following steps: constructing a data set of a Text2SQL data analysis method in the power field; constructing a multi-dimensional text knowledge base of the Text2SQL data analysis method in the power field; fine adjustment of an LLM base of a Text2SQL data analysis method in the electric power field; constructing an RAG retrieval module of the Text2SQL data analysis method in the power field; and constructing an Agent data analysis module of the Text2SQL data analysis method in the power field, and performing data analysis processing. According to the method, related information required by Text2SQL data analysis in the electric power field can be obtained by a large language model through retrieval on the basis of an RAG technology, meanwhile, the privacy and timely updating of the data are ensured by field data stored in a knowledge base form, and the model training cost is also greatly reduced by the LLM-based Text2SQL data analysis method taking a prompt project as a main part; and by setting the mixed retrieval parameters, the retrieval result has relatively high accuracy, and the effect of Text2SQL data analysis is ensured.

Systems, methods, devices, and computer readable storage media described herein provide techniques for generating and / or repairing query language (QL) queries. In an aspect, an embedding is determined based on a request to generate a QL query. The embedding is compared to a layer embedding(s) of a deep data map to determine a similarity between a layer embedding and the embedding satisfies similarity criteria. A prompt is provided to a large language (LLM) to cause the LLM to generate the QL query, the prompt comprising a description of an item associated with the layer embedding. In another aspect, an alert indicating an undefined variable of the QL query is received. A query embedding associated with the QL query is compared to the layer embedding(s) to determine a candidate variable. The candidate variable is substituted in for the undefined variable, and a response comprising the repaired QL query is generated.

The invention provides an SQL (structured query language) statement generation method based on large-model multi-stage iteration, which is used for database structure understanding and natural language SQL query generation, constructing multi-level semantic embedding of a database structure through advanced semantic modeling, and deeply analyzing a natural language query request of a user by utilizing an intention recognition model; a query intention frame is extracted in combination with a pre-trained large model, the query intention frame and database semantics are embedded and fused by adopting a calibration correction model and in combination with a multi-stage feedback mechanism, and a query intention and model parameters are optimized step by step; an optimal practice SQL statement is generated through deep optimization and a retrieval strategy model, model parameters and retrieval strategies are continuously optimized through self-adaptive evolution and user preference feedback, and a knowledge base is updated. According to the method, the problems of much manual intervention, inaccurate intention understanding, insufficient structure understanding and lack of a feedback mechanism are effectively solved, and efficient and accurate SQL query generation is realized.

The invention provides an intelligent data query method based on a natural language, and relates to the technical field of intelligent data processing and natural language interaction.The intelligent data query method comprises the steps that firstly, enterprise original data is subjected to standard treatment, and a standardized theme database and a data directory and index definition document are constructed; key semantics are extracted based on unstructured knowledge, and a domain knowledge vector library is fused and constructed by combining document text fragments and vector representation of a mapping relation between historical questions of a user and an SQL (Structured Query Language). And after receiving a natural language question of a user, calling a large language model to identify a task type, and distinguishing knowledge questions and answers, data query and complex analysis. Executing corresponding operations according to different types: directly retrieving a vector library by knowledge questions and answers to generate answers; extracting keywords in data query and generating a query request in combination with context; and in the complex analysis, predefined workflow is judged and executed or intelligent agent processing is called, and query or analysis requirements are output.

A natural language to database query converter (converter) receives a natural language query from a user (i.e., a user utterance) and identifies a cybersecurity domain related to intent of the natural language query. The converter then generates a database query for a query language of the cybersecurity domain corresponding to the natural language query with a large language model (LLM). An initial prompt to the LLM generated by the converter specifies a grammar of the query language and instructs the LLM to generate an initial database query that functions like the natural language query and satisfies the grammar. If a lint program determines that the initial database query is not valid for the query language, the converter generates a follow-up prompt to the LLM that indicates valid database queries from which to generate a follow-up database query. A query parser retrieves data that satisfy the initial or follow-up database query and a visualization / summarization module generates graph visualizations and summaries of the retrieved data.

The invention discloses a multi-table combined natural language query SQL (structured query language) generation method, which comprises the following steps of: 1, constructing a database meta-knowledge graph, and establishing a triple storage comprising a table structure, a primary and foreign key relationship and business description for each data table; 2, receiving a natural language query request, and calculating the topic relevancy between query semantics and each database table through a pre-trained topic matching model; 3, dynamically constructing a view, and logically associating the database tables of which the theme relevancy exceeds a threshold value to form a temporary view; 4, generating a context enhancement prompt, and combining the temporary view structure, the field semantic description of the view and the view content sample to form a structured prompt; 5, inputting the natural language query and the structured prompt into the large language model to generate candidate SQL statements; and step 6, executing verification and iterative optimization on the candidate SQL statements, verifying logic correctness through SQL execution plan analysis and result sampling, and triggering and prompting a reconstruction mechanism when detection is abnormal.

The invention relates to the technical field of database optimization, in particular to a slow SQL (Structured Query Language) statement optimization method and system, electronic equipment and a storage medium, the slow SQL statement optimization method comprises the following steps: preprocessing a collected target slow SQL statement to obtain multi-modal data of the target slow SQL statement; inputting the multi-modal data of the target slow SQL statement into the multi-modal large model, and performing feature extraction and fusion to generate comprehensive semantic representation; generating an optimization suggestion of the target slow SQL statement according to the comprehensive semantic representation; the optimization suggestions are verified, and then the optimization suggestions which are verified to be qualified are executed in a database. Through multi-dimensional data acquisition, large-model deep analysis and automatic strategy execution, full-life-cycle quality detection and optimization of the slow SQL statement are realized.

According to the artificial intelligence-based data analysis system and method provided by the invention, a set of novel data analysis system architecture is designed, and key technical components such as natural language processing, a large language model, database query optimization, multi-modal visualization and a semantic knowledge graph are fused; data transmission between modules is realized through unified intermediate data objects such as a structured query intention, an analytic tree and a structured query language template object, and asynchronous collaboration is realized through event driving and a message queue mechanism, so that a non-professional user can input an analysis request through a natural language; semantic analysis, structured query language query statement generation, data query and result visualization presentation are automatically completed, the method can be widely applied to data analysis scenes in the industries of government affairs, traffic, finance, education and the like, the data use efficiency is improved, the technical threshold is reduced, and the digital decision-making ability is enhanced.

The invention discloses an automatic tagging method and system for a fine tuning instruction set of a large language model, and the method comprises the steps: obtaining to-be-tagged original corpus data; performing desensitization and cleaning preprocessing on the to-be-labeled original corpus data; based on the scene of the original corpus data, matching a corresponding pre-trained large language model to label the corpus data, and generating a labeled label field; verifying the labeled label field through a regular statement, wherein verification comprises verification of the data content and the data format of the label field; and according to the scene of the original corpus data, assembling the generated label fields on the basis of an SQL (Structured Query Language) to form a fine tuning training set of a matched large language model. According to the method, a systematic judicial data analysis and labeling process is formed by processing judicial corpus data, so that rapid analysis and labeling of judicial data in the judicial vertical field are realized, and enabling of a text processing task in the judicial field is realized by a large language model.

The invention provides a method and a device for converting a natural language statement into an SQL (Structured Query Language) and a storage medium, relates to the technical field of data processing, and is used for improving the accuracy of converting the natural language statement into the SQL statement. The method comprises the steps that semantic analysis is conducted on a data query text, a target entity and at least one query field are obtained through extraction, and the target entity indicates a query intention corresponding to the data query text; determining a comprehensive similarity between each query field and each first candidate node according to a semantic similarity and a structural similarity between each query field in the at least one query field and each first candidate node in a pre-stored knowledge graph; determining a target node corresponding to each query field according to the comprehensive similarity between each query field and each first candidate node; according to the information, the data query text can be converted into the structured query statement.

The invention discloses a memory recall method based on a large language model and a related device. The method comprises the steps that short-term memories are divided into inactive short-term memories and active short-term memories; performing semantic content analysis on the inactive short-term memory through a large language model, and converting the obtained entity information and entity relationship triad into a long-term memory graph; entity extraction and multi-level reasoning are carried out on the active short-term memory according to entities in the long-term memory map through a large language model, and the extracted entities and reasoning levels are combined to generate a query language; and querying from the long-term memory map through a query language, performing textualization processing on the obtained long-term memory triple information, and generating a reply according to the textualized long-term memory triple information and the short-term memory through a large language model. The technical problems that an existing memory recall mode based on vector indexes has limitation of memory association ability and recalled entity memory information is incomplete are solved.