261 results about "Database schema" patented technology

The present disclosure relates to systems, non-transitory computer-readable media, and methods for linking a database schema to a natural language query. In particular, in some embodiments, the disclosed systems determine, from tables in a database schema, a subset of tables relevant to a natural language query by comparing embeddings for the tables in the database schema and embeddings for the natural language query. Additionally, in some implementations, the disclosed systems select, from a schema graph comprising nodes that represent the tables in the database schema, an additional table along a path between a pair of nodes representing a pair of tables from the subset of tables. Moreover, in some embodiments, the disclosed systems determine a set of relevant tables by appending the additional table to the subset of tables. Furthermore, in some implementations, the disclosed systems generate, from the set of relevant tables, a response for the natural language query.

Provided herein are systems, methods, and computer-readable media for generating one or more database queries based on a natural language input data. An example method comprises configuring, using a conversational artificial intelligence (AI) editing module, information for a task. Moreover, the method may further comprise parsing the configured information based on a database schema to obtain a parsed database schema. Further, the method may further comprise generating, using a natural language question-answering system, one or more database queries based on the parsed database schema and natural language input data.

An LLM is adapted to generate database queries that are compatible with a proprietary database of a security provider. Adapting the LLM includes evaluating performance of the LLM after initial prompt engineering / fine-tuning to ensure that generated database queries are valid (i.e., comport to the database schema and can be executed to return results). When the LLM performance is satisfactory, a dialogue system uses the LLM to generate database queries from user queries. The dialogue system determines intent of each user query, which informs whether the query is supported. Supported user queries are converted to database queries using the LLM and submitted to the database. The dialogue system leverages another language model to generate a summarized, natural language representation of the database query results and constructs a response from the summary. The dialogue system also checks for XSS and prompt injection before database queries are ultimately submitted to the database.

Systems and methods described herein relate to automatic index recommendations for improved database query performance. Candidate indexes are identified. The candidate indexes are associated with a database query that is classified as a slow query. A feature vector is generated for each candidate index to represent statement features and statistical features associated with the candidate index. The feature vectors are provided to one or more machine learning models to obtain an index recommendation value for each candidate index. An index recommendation is presented at a user device. The index recommendation identifies a first index of the candidate indexes based at least partially on the index recommendation value obtained for the first index. User input indicative of a user selection of the first index is received. A database schema is updated to include the first index in response to the user input.

The invention discloses an ICL large language model data query generation method and system based on diversity SQL enhancement, and the method comprises the steps: S1, determining a target query database, and obtaining a database Schema; s2, vectorizing a database Schema, and storing the vectorized database Schema into a database meta-information vector library; s3, vectorizing SQL statements in the SQL sample set, and storing the vectorized SQL statements in an SQL sample vector library; s4, performing clustering diversity sample recall on the information stored in the SQL sample vector library; s5, according to the database summary and the natural language question of the user, combining the recalled sample question and the corresponding SQL query statement as model reference information, constructing comprehensive prompt information, and guiding the large language model to generate SQL query conforming to semantics and grammar; and S6, inputting the large language model, and generating SQL statements by the large language model. According to the method, the Prompt is formed by recalling the reasonable related information, the model is guided to correctly generate the SQL, and the accuracy of the SQL statement generated by the large language model can be effectively improved.

The present application discloses a database query method and apparatus, an electronic device, and a non-volatile storage medium. The method comprises: determining a knowledge graph corresponding to a database to be queried, wherein the knowledge graph is used for representing a logical structure and an association relationship of data in said database; determining similarity scores between user question text and graph nodes in the knowledge graph, and determining a target node from among the graph nodes of the knowledge graph on the basis of the similarity scores, wherein the similarity scores are used for representing the degree of association between the graph nodes and the user question text; and on the basis of the target node, generating database schema information corresponding to said database, and using a large language model to generate, on the basis of the database schema information, a structured query language statement corresponding to the user question text.

The invention provides a Text2SQL generation method and system driven by a large language model, and the method comprises the steps: recognizing key entities and relationships in a natural language question through the large language model, and carrying out the construction to obtain a query graph; constructing a hierarchical graph representation model based on the database mode of the target database; searching candidate sub-image sets which have the same structure as the query graph and are in semantic association with the query graph from the constructed graph representation model; and constructing a structured Prompt template based on the candidate sub-image set and the user question, generating an initial SQL statement, and outputting a final query result after grammar and semantic detection correction. According to the method, a traditional database is converted into the graph knowledge base, so that the SQL generation accuracy and performance are improved; guiding the large model to generate an SQL (Structured Query Language) meeting business requirements through knowledge graph storage and retrieval table and column information; and the accuracy of the SQL is continuously optimized by utilizing a self-adaptive feedback mechanism, so that the method is particularly suitable for a large-scale complex query scene, and self-improvement and customization of the model are realized.

The invention relates to a Text-to-SQL (Structured Query Language) complex query statement generation method and system based on a pre-trained large model. The method comprises the following steps: acquiring an input sequence comprising a user question and dictionary interpretation of table names and column names in a database; respectively inputting the user question and the dictionary explanation into a Sension-BERT model, obtaining Top-K explanations most related to the user question, and obtaining an enhanced input sequence according to the Top-K explanations most related to the user question; encoding the enhanced input sequence to generate an enhanced semantic vector, and constructing a hierarchical database mode pattern according to the enhanced semantic vector; inputting the hierarchical database mode graph into a hypergraph neural network model to update node features, and obtaining optimized node features; and obtaining a structured query statement according to the optimized node features. According to the method, complex association and multi-level query logic among multiple tables in a complex query scene can be better processed, and the performance in the complex query scene is improved.

Here is multitask finetuning of natural language (NL) interaction (NLI) to increase semantic accuracy of database statement generation. A computer associates a first natural language request with a correct database statement for a database schema. The correct database statement contains multiple distinct or repeated identifiers. A large language model (LLM) predicts, from the first natural language request and a strict subset of the database schema, multiple predicted identifiers. Finetuning the LLM entails neural backpropagation, into the LLM, of a loss that is based on a comparison of: a) identifiers in the correct database statement to b) the predicted identifiers. After finetuning, the LLM inferentially generates an inferred database statement from a second natural language request, and this statement is accurate even if a new (i.e. previously unseen) database schema is involved.

The invention relates to the technical field of computers, in particular to a dynamic configuration initialization and version synchronization method and system for multi-agent service, and the method comprises the following steps: obtaining a database update lock, constructing a database migration script dependency relationship, determining a current version of a database mode, upgrading and deploying the database mode, and verifying agent versions. The method has the beneficial effects that a rigorous database updating lock control mechanism, perfect migration script dependency chain verification, agent version management, port availability detection, idempotence and transaction safeguard measures are introduced, so that the processes of database structure upgrading and agent version initialization in a distributed deployment environment can be effectively supported; and the data consistency, the operation stability and the service continuity of the system are ensured.

Techniques are disclosed herein for generating dynamic vocabularies for conditioning a language model. A dynamic vocabulary is constructed from an input prompt, database schema information for a database to be queried, and programming language information for a programming language to be used for querying the database to condition the language model to predict an output statement in the programming language. The dynamic vocabulary can be included in prompt information that is provided to the language model. The number of tokens in the dynamic vocabulary can be different than a number of tokens included in a vocabulary of the language model. By utilizing a dynamic vocabulary, the language model can be conditioned to predict tokens for the output statement that are contextually consistent with the tokens included the dynamic vocabulary.

The invention discloses a method and a system for generating an SQL (Structured Query Language) query based on a natural language question. The method comprises the following steps: converting mode information of a target database and the natural language question into semantic vector representation; based on the semantic vector representation, a simplified database mode set related to SQL query is screened out through an attention mechanism; based on the natural language problem, the simplified database mode set and preset database constraint information, generating an SQL structural skeleton, and filling specific elements of the SQL structural skeleton to form a preliminary SQL query; and performing dynamic correction and verification on the initial SQL query by utilizing a large language model, and outputting a final SQL query. According to the method, association mining between user query and a database mode is effectively enhanced by utilizing a context-aware cross-encoder mechanism, and an implicit corresponding relation between a natural language problem and a database table / column can be more accurately identified and utilized.

The invention discloses a time sequence database architecture, a data writing method and electronic equipment, and the time sequence database architecture comprises a distributed storage module which enables data of the same equipment to be continuously distributed in a physical storage layer based on an equipment dimension fragmentation strategy; the independent index layer is decoupled from the data storage module and maintains a mapping relationship between the equipment identifier and the corresponding physical fragment through a metadata structure; the migration module is used for performing rolling updating on the hot data layer; and the query engine module is used for positioning the target physical fragment according to the equipment identifier and executing predicate push-down calculation on the compressed data. The data writing method comprises the following steps: receiving a data writing request, and analyzing a device identifier in the request; positioning a target physical fragment according to the equipment identifier in cooperation with a Hash algorithm; and adding the data to the column type storage file in the corresponding physical fragment according to a timestamp sequence, and synchronously updating the metadata mapping relationship of the independent index layer. According to the method, the data query performance and query efficiency can be improved, and the data storage cost is reduced.

Techniques for natural language processing include accessing an input string comprising a natural language utterance and a database schema representation for a database; providing the natural language utterance to a first encoder to generate one or more embeddings of the natural language utterance; providing the database schema representation to the first encoder to generate one or more embeddings of the database schema representation; encoding, by a second encoder, relations between elements in the database schema representation and words in the natural language utterance based on the one or more embeddings of the natural language utterance and the one or more embeddings of the database schema representation; and generating a logical form for the natural language utterance based on the encoded relations, the one or more embeddings of the natural language utterance, and the one or more embeddings of the database schema representation.

A computer-implemented method for improved schema matching of two databases is disclosed. The method can receive a schema of a source table from a first database and a schema of a plurality of target tables from a second database, identify one or more matching tables among the plurality of target tables based on comparison of the schema of the source table and the schema of the plurality of target tables using a large language model, obtain first sample attribute data from the source table and second sample attribute data from a selected matching table, and identify one or more pairs of matching attributes between the source table and the selected matching table based on comparison of the first sample attribute data and the second sample attribute data using the large language model. Related systems and software for implementing the method are also disclosed.

The embodiment of the invention provides a continuous breath sound monitoring application system, which is oriented to double versions of a medical professional version and a civil public version, can continuously collect and analyze breath sound, adopts a multi-level label system to carry out classified labeling, and combines expert labeling and machine learning to improve the recognition accuracy. And meanwhile, a perfect database architecture and a local / cloud mixed storage strategy are provided to ensure reliable management of data, and data security compliance is ensured through encryption and access control. The system is also integrated with an interactive teaching module to meet the requirements of professional training and popular science popularization, and is equipped with a multi-parameter linkage grading alarm mechanism to provide real-time early warning. In addition, the system has good expandability and can be integrated with a hospital information system (HIS) and a remote medical platform through standard interfaces.

The invention relates to the technical field of large-scale language models, and discloses a method for converting a natural language to an SQL (Structured Query Language) task by combining fine tuning and Prompt. According to the method, the database mode knowledge learning module is constructed, so that the database mode can be efficiently understood and memorized, the length of input tokens is remarkably reduced, and the token efficiency is improved. Meanwhile, the module utilizes a LoRA model to carry out fine adjustment on a large language model, the performance of the model on text-to-SQL tasks is optimized, and the model can generate SQL statements more accurately; besides, an example selection module is also constructed, and the most similar example is selected as a prompt by calculating the similarity between the problem and the candidate example, so that the accuracy of generating the SQL statement by the model is further improved. According to the method, the generalization ability of the model is improved, and the model can more flexibly cope with natural language queries in different fields.

The invention relates to a database Schema version management method and device, computer equipment and a storage medium. The method comprises the following steps: responding to received target Schema tree structures sent by each user terminal, generating a combined target Schema tree structure according to each target Schema tree structure, and performing format conversion on the combined target Schema tree structure to obtain a modified Schema file; performing tree node traversal comparison according to the combined target Schema tree structure and the to-be-modified Schema tree structure to obtain corresponding distinguishing tree nodes; the distinguishing tree nodes are tree nodes on the combined target Schema tree structure which are different from the Schema tree structure to be modified; and determining a version modification type of the modified Schema file according to each distinguishing tree node, generating a semantic version identity identification number of the modified Schema file according to the version modification type, and storing the modified Schema file into a database according to the semantic version identity identification number. By adopting the method, the efficiency can be improved and version management chaos can be avoided.

The invention relates to a dynamic adaptive Text2SQL (Structured Query Language) generation method and system for the power field. The method comprises the following steps: S1, analyzing a power database Schema and automatically generating a diversified natural language-SQL pair data set; s2, performing cleaning, optimization and format standardization on the data, and constructing a high-quality training set and a high-quality test set; s3, querying a prediction database Schema based on a natural language, and generating an SQL statement with accurate pattern matching; s4, a logic disassembly optimization mechanism is introduced, and it is ensured that SQL query conforms to database rules and meets the requirements of the power industry; s5, finely adjusting the large language model to improve the accuracy and the performability of SQL generation; s6, performing compression optimization on the trained model to improve reasoning performance, stability and query accuracy; and S7, efficiently deploying the optimized electric power large language model, and guaranteeing the stability, response speed and model performance of the system through real-time monitoring. According to the method, the accuracy and applicability of converting the natural language query into the SQL statement in the power industry can be effectively improved.

The present disclosure relates to manufacturing training and testing data by leveraging data augmentation techniques to generate examples of long context database schemas. Aspects are directed towards accessing a training dataset comprising training examples where each training example may include i) a prompt including a natural language utterance and a database schema having one or more tables, and ii) a gold logical form corresponding to the natural language utterance, combining the tables from the database schemas in the training examples may generate a combined database schema set, generating a set of long context training examples based on the training dataset and the combined database schema set, and incorporating the long context database schema into the selected training example to generate a long context training example to train a generative artificial intelligence model with at least the set of long context training examples to generate a trained generative artificial intelligence model.

A system and method that allows privacy-enhanced querying to occur, where re-identification risk is reduced to a user-configured level are described. The system and method include a query federation agent that analyses and augments user-submitted queries to include results that contain metadata relating to the privacy characteristics. The system and method ensure results that contain privacy risks above defined thresholds are suppressed or altered so that re-identification cannot occur. The system and method add noise to results that contain privacy risks above defined thresholds so that re-identification cannot occur. The system and method utilize a data profile that defines the sources of potential re-identification risk in a database schema. The system and method apply privacy rules that are configurable for different database tables and configurable thresholds for different types of privacy risks.

The invention relates to the technical field of data processing, and particularly provides a double-engine-based SQL (Structured Query Language) generation method, system and device and a medium, and the method comprises the following steps: receiving a natural language query input by a user; analyzing the natural language query by using an intention understanding engine in combination with a dialogue context and a business knowledge graph to generate a structured query intention representation; utilizing an SQL generation and optimization engine to generate at least one candidate SQL statement based on the structured query intention representation and a vectorization database Schema library; performing execution plan analysis on the at least one candidate SQL statement, and performing performance evaluation and optimization rewriting based on an analysis result to generate a final high-performance SQL statement; and executing the final high-performance SQL statement and returning a query result. According to the method, the query success rate and the user experience in a complex scene are greatly improved.

Embodiments of the present application relate to the technical field of computers. Disclosed are a conversational Text-to-SQL pre-training method and apparatus based on fine-grained link information. The method comprises: obtaining text statements of a conversation and a database schema, wherein the text statements comprise the current statement and a historical statement of the conversation; obtaining a statement link relationship between the statements in the conversation on the basis of the text statements of the conversation and the database schema, and obtaining a first loss function; obtaining a schema link relationship between the conversation and a database on the basis of the current statement of the conversation and the database schema, and obtaining a second loss function; and pre-training a neural network model on the basis of the first loss function and the second loss function to obtain a pre-trained Text-to-SQL model. The present application solves the problems in the prior art of low accuracy, cross-domain failure, and conversation context forgetting.

The invention provides an intelligent generation method for Text2SQL (Structured Query Language) in the power field based on prompt enhancement and progressive optimization, which focuses on improving the conversion efficiency and accuracy of natural language query to a power grid SQL instruction. The method comprises the following steps: firstly, constructing a prompt guide SQL synthesizer, and generating a high-quality training data set by fusing Schema information of a power grid database and a large language model; secondly, a semantic mapping SQL generator is designed, accurate conversion from a multi-stage natural language to an SQL is achieved through a semantic mapping mechanism, a feedback-driven optimization system is constructed, and grammar correctness and business compliance of SQL statements are guaranteed; meanwhile, the adversarial training and the automatic parameter adjustment strategy are combined, the large language model in the power field is optimized, and the model performance and generalization ability are remarkably improved. Finally, efficient deployment and stable operation of the model in a real power grid system are realized, and the intelligent level and response capability of a power dispatching system are comprehensively improved.

The invention provides a text-to-structured query statement method based on a large language model and reinforcement learning, and relates to the technical field of information, the method comprises the following steps: integrating a natural language problem and a database mode into a unified prompt template to obtain a candidate structured query, and generating a reference structured query by a reference model; constructing a multi-dimensional reward framework, and performing weighted aggregation on multi-dimensional rewards to obtain corresponding final reward scores; calculating a KL penalty value between the output of the strategy model and the output of the reference model based on the candidate structured query and the reference structured query to obtain a constraint of stable strategy update; updating the strategy model parameters through back propagation iteration to obtain an updated strategy model; and analyzing the prompt template by using the updated strategy model to obtain a text-to-structured query statement processing result, and completing the process from the text to the structured query statement. The problems that existing structured query generation is low in accuracy and semantic consistency is difficult to guarantee are solved.

Systems and methods for secure database schema migration are described. In an illustrative, non-limiting embodiment, an Information Handling System (IHS) may include: a processor and a memory, the memory having program instructions that cause the processor to: calculate a first hash of schema objects for a database; compare the calculated first hash of the schema objects with an expected second hash of the schema objects for the database; determine that the schema objects comprise a previous version of the database; and execute scripts to upgrade the schema objects for the database. The program instructions can also cause the processor to: determine that the calculated first hash of the schema objects does not compare with the expected second hash of the schema objects, and determine that the calculated first hash of the schema objects compares with a third hash of the schema objects corresponding to the previous version of the database.

Here is an innovative way to generate a finetuning corpus that maximizes the accuracy of a target large language model (LLM) that generates a database statement. From a natural language request, the target LLM infers an incorrect database statement that, based on a first database schema, could not satisfy a technical requirement. Based on the natural language request, a correct database statement is generated that, based on a second database schema, could satisfy the technical requirement. For the second database schema, a restatement of the natural language request is generated. In inputs during finetuning, the target LLM accepts: the correct database statement, the incorrect database statement, and the restatement of the natural language request.

Embodiments of the present disclosure provide large language models (LLMs) and large multimodal models (LMMs) for managing imaging data. An example method includes extracting a database schema and a data dictionary associated with a medical imaging database that maintains medical images and non-image data associated with a plurality of clinical studies; extracting object attributes associated with the medical images that are descriptive of the medical images and corresponding studies; and training an LLM to generate search queries from natural language requests based on a training dataset that includes: the database schema, the data dictionary, the object attributes, a prompt template including partial instructions for the LLM, and a plurality of example natural language requests and corresponding expected search queries. The trained LLM can then be used to generate a first search query from a first natural language request.

A healthcare shopping and management system is disclosed herein which assists users in searching for medical providers based on insurer-negotiated pricing, directly scheduling appointments, making payments, aggregating personal health records, and utilizing analytics to suggest preventative health screenings. The system architecture includes interfaces for searching, scheduling, paying, health records access, geolocation of providers, cost ratings, and an analytics engine leveraging clinical guidelines. Database schema and data models as well as example user interfaces are also disclosed.

A system for grouping architectural information within a plurality of layers for common formatting in a database. The system may include at least one processor; and at least one memory configured to execute the instructions to perform operations. The operations may include group according to the meta-model, architectural datasets together to structure database architectural information into a common format; establish an architectural domain for grouping the database architectural information in a plurality of layers; organize the meta-model to establish possession of information in the plurality of layers; and provide architectural data corresponding to each data domain for each of the plurality of layers from one or more data sources.