5780results about "Other databases querying" patented technology

The invention relates to the technical field of data exchange, in particular to a data exchange system of a nested tag structure, which comprises a data carrier adaptation module, a structure analysis module, a field mapping module, a logic driving module and a script generation module. According to the method, carrier identifiers are generated through comparison of MIME types, file header features are positioned through pattern matching, the recognition accuracy and adaptability are improved, a nesting relation is calculated through depth-first traversal of file paths, node sequences are generated through analysis in combination with a DOM tree, the label analysis efficiency is optimized, and a mapping table is generated through algorithm matching of field identifiers and database codes; the method comprises the following steps: dynamically constructing a field mapping relation, reducing manual configuration, constructing a decision matrix based on a mapping table, executing logical operation to generate a status bit and triggering a threshold write-in instruction, enhancing strategy dynamic adjustment capability, reducing semantic ambiguity through multi-algorithm collaboration and a dynamic decision mechanism, improving data exchange robustness, and supporting real-time state response. And the transmission timeliness of the industrial Internet of Things is ensured.

The embodiment of the invention provides a document generation method and device based on artificial intelligence, and the method comprises the steps: extracting multi-modal data features of a historical multi-modal file through natural language processing and a computer vision algorithm, and constructing a corresponding knowledge graph according to the multi-modal data features, converting the multi-modal data subjected to feature extraction into high-dimensional vectors by using a vectorization algorithm, and storing the high-dimensional vectors to form a vector library; splitting a current document generation task into a plurality of sub-tasks by adopting a task planning algorithm, and executing the sub-tasks at the same time to obtain a first document; performing iterative optimization of document content according to the document first draft, the cue word and the language model to obtain an optimized first draft, acquiring related information from the vector library by using an attention mechanism-based retrieval algorithm, and fusing the related information and the optimized first draft through a text generation algorithm to obtain a final document; according to the invention, the accuracy and intelligence in the document generation process can be effectively improved.

The invention discloses a knowledge graph analysis and question answering method and device based on a large language model. The method comprises the steps of obtaining original data, performing data processing based on a large language model to obtain target data, constructing a knowledge graph according to the target data, and storing the knowledge graph into a graph database; acquiring an open source data set, and processing the open source data set by using the large language model to obtain a training data set; according to the graph database, constructing a dictionary which is used for reflecting a graph structure of the graph database; utilizing the training data set, the dictionary and a preset prompt instruction to finely adjust the large language model to obtain an optimized large model; generating a query statement by utilizing the graph database and the optimization large model according to a query problem of a user, and determining a query result in the graph database according to the query statement; and based on the optimization large model, carrying out integration processing on the query question and the query result to obtain a final answer. According to the method, the construction process of the knowledge graph is simplified, and the accuracy of analysis and question answering is improved.

The present invention proposes a vector database retrieval method and system, which relates to the technical field of big data processing and intelligent information retrieval. The method includes preprocessing high-dimensional multimodal data to obtain a dimension reduction feature vector; constructing a cluster center based on the dimension reduction feature vector; establishing an inverted file and an intra-cluster plane index based on the cluster center, compressing the inverted file and the intra-cluster plane index to obtain a compressed inverted file and an intra-cluster plane index; obtaining a user's query vector, using the inverted file to screen candidate clusters for the query vector, introducing a hierarchical navigable small-world graph in the intra-cluster plane index, performing an intra-cluster search on the cluster cluster, and obtaining a vector database retrieval result. The present invention effectively takes into account the efficiency and accuracy of high-dimensional data retrieval, and improves the retrieval efficiency and accuracy.

The invention provides a retrieval enhancement generation method and system based on a large language model. The method comprises the steps that input query information of a user is obtained; performing rewriting and key information extraction on the input query information based on a large language model to obtain a first query instruction and a second query instruction; according to the input query information, identifying a user intention based on a large language model and performing intention classification to obtain an intention classification result; according to the first query instruction and the second query instruction, performing multi-path mixed retrieval through a preset multi-source knowledge base to obtain an initial retrieval result; according to the intention classification result, performing result rearrangement and screening on the initial retrieval result to obtain an enhanced cue word; and inputting the input query information and the enhanced cue word into the large language model to obtain a retrieval enhanced generation result. According to the method, the query demand and intention of the user can be accurately recognized, related information is retrieved in an open domain in a high-precision manner, and the instantaneity, the accuracy, the specialty and the reply quality of information retrieval are improved.

The invention discloses an emergency fire-fighting hidden danger troubleshooting method based on a multi-modal AI large model identification technology, and relates to the field of artificial intelligence. The multi-modal hidden danger knowledge base is constructed by collecting multi-modal data such as images, texts and related laws and regulations actually recorded in the hidden danger checking process, the recognition and analysis ability of hidden danger information is improved based on the deep learning and multi-modal large model technology, the multi-hop reasoning and thinking chain technology is utilized, and the hidden danger checking efficiency is improved. A complex hidden danger positioning problem can be disassembled into a series of interpretable reasoning steps, and a user is helped to understand a hidden danger judgment basis. According to the method, the hidden danger in the image is analyzed from multiple angles and levels, different hypotheses or conditions can be verified step by step, so that the judgment accuracy is improved, the information of each dimension is comprehensively synthesized for comprehensive evaluation, and the comprehensiveness and accuracy of hidden danger investigation are ensured.

The invention discloses a data import and field intelligent matching method for a low-code platform, and particularly relates to the technical field of low-code platform data processing. Constructing a field initial feature vector, extracting a standard field and historical matching features thereof from the target data model, and calculating a semantic matching score matrix by using a multi-source feature fusion model; screening the initial mapping table based on a dynamic threshold value, performing statistical deviation analysis in combination with a field value distribution difference measurement feature delta, and when delta exceeds a preset threshold value, calling a value mapping correction model to complete rematching to obtain an optimized mapping table; if it is detected that user history adjustment exists in the same source file type, re-correction is carried out based on a user behavior log, and a final field mapping table MP3 is output; finally, the MP3 is applied to data import, and automatic matching and binding are achieved. The method improves the accuracy and automation level of field matching, and is suitable for a multi-source heterogeneous data integration scene.

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.

The invention relates to the technical field of cloud archive management, and discloses an archive management system based on a cloud archive library, which comprises a data acquisition module, a data preprocessing module, a cross-format semantic retrieval module, an intelligent rule generation module, a distributed authority control module and a dynamic resource optimization module. According to the method, through construction of the multi-modal semantic vector space, unified retrieval of heterogeneous archive data such as texts, images and audios is realized, and the problem of low retrieval efficiency caused by format differences in the prior art is solved; an archive life cycle rule is dynamically generated in combination with a reinforcement learning algorithm, so that the accuracy and suitability of resource management are effectively improved; authority control is realized based on a block chain technology, and the security and consistency of data access are enhanced; through load prediction and resource scheduling optimization, the system energy consumption is obviously reduced, and the response capability of a high-concurrency scene is improved. The file security and the data consistency are enhanced, and the problem of low authority control efficiency in a multi-terminal access environment in the prior art is solved.

The invention relates to a method for generating steel field TEXT2SQL based on LLM enhanced by RAG, which comprises the following steps: firstly, establishing connection with a steel database, and defining user semantic information and a database mode; then, obtaining user input and carrying out natural language processing; thirdly, guiding a large language model to generate a more accurate SQL query by utilizing the generated group of guiding words prompt; then, natural language query is converted into SQL query in combination with a large language model and an RAG technology; when a new user query is received, searching a historical query most similar to the new user query and a corresponding SQL query from the vector database; and finally, performing grammar correctness and logic rationality verification on the generated SQL statement, and outputting the SQL statement. According to the method, the problem that table names and field names are difficult to obtain when a large language model generates accurate SQL statements according to user description is solved. According to the method, the high-quality SQL query statement can be effectively generated, and the accuracy and the use efficiency of steel database query are improved.

Methods, systems, and non-transitory computer readable storage media are disclosed for controlling access to artificial intelligence systems based on determined intent of queries. The disclosed system utilizes one or more digital content analysis models to determine an intent of one or more queries to an artificial intelligence system. The disclosed system utilizes the one or more digital content analysis models to determine an intended use of the artificial intelligence system. Additionally, the disclosed system determines whether the intent of the one or more queries aligns with the intended use of the artificial intelligence system by generating a similarity score and comparing the similarity score to a similarity threshold. Based on whether the intent aligns with the intended use, the disclosed system executes computing instructions to enable or block the one or more queries from being processed by the artificial intelligence system.

The invention discloses a science and technology fast message intelligence perception system based on a large language model, and belongs to the field of intelligence perception, the system comprises an information collection module, a data standardization module and a database, the information collection module obtains multi-mode science and technology fast message data; the data standardization module is used for receiving the multi-modal data output by the information collection module and executing data cleaning, structured processing and semantic standardization operation; after standardization processing, storing the data into a database; the system further comprises an intelligence value screening module, an evaluation system module and a visualization module. And the intelligence value screening module is combined with the evaluation system to identify the intelligence value, and multi-dimensional visual presentation is realized through the visualization module. The method improves the efficiency and accuracy of information recognition and perception, and has significant advantages in the aspects of processing mass information and enhancing the information perception ability.

The invention discloses a spacecraft intelligent design method and system capable of autonomously learning, and belongs to the technical field of spacecraft design and simulation. The problems that in spacecraft design, natural language requirements are fuzzy and difficult to process, instruction generation is prone to ambiguity, linkage between simulation and design is not smooth, a design scheme lacks an effective iterative optimization mechanism, and traditional design is low in efficiency are solved. The method comprises the following steps: firstly, receiving a natural language demand, extracting key parameters to generate prompt words, inputting the prompt words into Design.AI, and generating a simulation instruction sequence; simulation is started through MCP Server conversion, if the result does not reach the standard, feedback correction is carried out, and iterative optimization is carried out. And repeating the steps until a design target is met, and generating a design report containing multiple items of content. Through natural language processing, real-time simulation, iterative optimization, knowledge accumulation and other technologies, the spacecraft design efficiency is greatly improved, the accuracy is enhanced, the threshold is lowered, and the flexibility is improved.

The invention discloses an AI-based conference record data searching method and system, and the method comprises the steps: carrying out the feature extraction and alignment through a multi-mode fusion neural network according to the voice, text, image and video data collected in a conference process, and obtaining a semantic representation vector; according to the semantic representation vector, combining context information of the conference scene, and utilizing a pre-trained context perception model to perform semantic enhancement processing to generate an enhanced semantic vector with context association; according to the enhanced semantic vector, combining with an external knowledge base, and utilizing a dynamic knowledge graph construction algorithm to generate a knowledge graph related to the conference theme in real time; and according to the knowledge graph, intelligent retrieval and recommendation of conference record data are carried out by using a graph neural network. By utilizing the embodiment of the invention, the intelligent retrieval efficiency and accuracy of the conference record can be improved.

The invention relates to the technical field of intelligent operation and maintenance, in particular to an execution method of a large model graph retrieval enhancement system oriented to software and hardware monitoring operation and maintenance, which comprises the following steps: S1, inputting fault information to the graph retrieval enhancement system; s2, a graph construction and updating module receives and processes the fault information, generates a triple, and writes the triple into an operation and maintenance / fault knowledge graph; s3, the fault information is input into a graph retrieval enhancement module for two-stage filtering retrieval, and sub-graph information is screened out; s4, the prompt word construction module converts the fault information and the screened sub-graph information into structured natural language prompt segments; and S5, a reasoning generation module performs natural language question and answer to generate a fault analysis result. Based on the above scheme, the execution method enhances the adaptive capacity of knowledge reasoning and fault positioning, gives play to the generalization reasoning capacity of a large language model while ensuring the accuracy, and enhances the practical value.

The invention relates to the technical field of electric digital data processing, in particular to a traditional Chinese medicine data management system and method for data retrieval. The method comprises the following steps: acquiring morphology data of a traditional Chinese medicinal material sample; performing grade evaluation based on the traditional Chinese medicinal material morphology data to generate traditional Chinese medicinal material grade label data; acquiring a to-be-detected traditional Chinese medicinal material image; preprocessing the to-be-detected traditional Chinese medicinal material image, and performing entity recognition and relation extraction to obtain traditional Chinese medicinal material semantic annotation data; and fusing the traditional Chinese medicinal material grade label data and the traditional Chinese medicinal material semantic annotation data to obtain traditional Chinese medicinal material semantic annotation enhanced data. According to the method, the information of the traditional Chinese medicinal materials is expressed through structured processing and semantic enhancement, the knowledge graph containing dominant and implicit semantic relationships is constructed, and the retrieval depth, flexibility and intelligent application of knowledge of the traditional Chinese medicinal materials are improved.

The invention provides a multimodal reasoning method based on a Monte Carlo tree and dynamic retrieval. The method is applied to an artificial intelligence assistant-assisted teacher paper judgment scene. Specifically, the framework comprises a unified retrieval module, wherein the retrieval module comprises a mixed modal retrieval corpus and a multi-modal retrieval module; the multi-modal retrieval module comprises two retrieval modules, namely a text retrieval module and a cross-modal retrieval module, key problem solving insights are selected by adopting knowledge concept filtering, and progressive multi-modal reasoning annotations of multi-modal reasoning are automatically obtained by utilizing Monte Carlo tree search and an active retrieval mechanism for data annotation; and gradually aligning a process reward model through course process reward modeling in two stages by utilizing the annotation data so as to realize fine-grained verification of multi-modal large model reasoning. An MCTS algorithm and an active retrieval strategy are combined to improve multi-modal reasoning. The framework can automatically obtain high-quality step-by-step reasoning annotations, so that a process reward model is aligned step by step, and finally reliable automatic multi-modal reasoning verification is realized.

The invention relates to the technical field of saline-alkali soil improvement, in particular to an intelligent irrigation and soil conditioning system for saline-alkali soil improvement, which comprises a climate prediction module, a soil detection module, an electrochemical salt migration prediction module, a data analysis module, an irrigation execution module and a data feedback module, the climate prediction module predicts future climate conditions; the soil detection module monitors soil parameters of the saline-alkali land in real time; the electrochemical salt migration prediction module is used for predicting the migration behavior of salt in soil; the data analysis module formulates irrigation and soil conditioning strategies; the irrigation execution module controls operation of irrigation equipment; and the data feedback module feeds back the irrigation execution result and the actual soil improvement effect, and continuously optimizes irrigation and soil conditioning strategies. According to the method, efficient utilization of resources is achieved, and the accuracy and scientificity of saline-alkali soil improvement are ensured.

The invention discloses a method for reducing a large model illusion problem based on an RAG technology, and the method comprises the steps: extracting semantic entities, relation phrases and context features in a natural language query, and constructing a multi-source heterogeneous hypergraph; fusing the graph structure and sequence context information by using a graph attention network and a sequence perception network to form unified semantic representation; evaluating the illusion risk based on the confidence score, the evidence coverage rate and the semantic deviation index, and triggering reverse retrieval and fusion reinforcement; and the content is generated through causal consistency discrimination feedback control. According to the method, the illusion phenomenon of the generation result is remarkably reduced, and the method is widely applied to the field of intelligent question answering and information retrieval.

The embodiment of the invention provides a multi-modal knowledge graph construction method in cross-media retrieval. The method comprises the steps that extracted multi-modal features are mapped to a multi-modal feature space through a linear transformation layer; in the multi-modal feature space, the intra-modal attention weight of each modal feature is calculated according to a self-attention mechanism, the cross-modal attention weight of different modal features is calculated according to a cross attention mechanism, the two weights are fused to obtain a final fusion weight, each modal feature is weighted and input into a graph attention network, and the multi-modal feature is obtained. Obtaining a multi-modal fusion graph structure; performing semantic analysis on each modal feature, matching with a preset multi-modal semantic knowledge base, determining potential semantic association, performing semantic alignment on the multi-modal fusion graph structure according to a preset graph matching algorithm and the potential semantic association to obtain a multi-modal knowledge graph, performing cross-modal data retrieval according to the multi-modal knowledge graph, and performing cross-modal data retrieval according to the multi-modal knowledge graph. The multi-modal data cross-media retrieval method and device can improve the efficiency and accuracy of multi-modal data cross-media retrieval.

The invention provides a settlement monitoring method and system based on data traceability, and the method comprises the steps: firstly obtaining the time sequence settlement observation data of each monitoring point in a settlement monitoring region in a continuous observation period, including the settlement amount and the environment interference information of a corresponding observation moment, and then constructing a settlement data traceability association network, the method comprises the following steps: associating time sequence settlement observation data with geological base information of a monitoring point, an observation equipment traceability identifier and data processing node information, then tracing a generation link of settlement data of each monitoring point, extracting an equipment calibration record and the like, generating traceability link characteristics, then carrying out coupling analysis on the traceability link characteristics and the settlement amount, determining a traceability reliability index, and finally determining a traceability result. And finally, data are screened according to indexes, a dynamic settlement trend model and a settlement monitoring analysis report containing traceability link characteristics are generated in combination with the spatial distribution characteristics of the monitoring points, and the accuracy and reliability of settlement monitoring are improved.

The invention relates to the technical field of financial large models, and provides an RAG method and system for compliance analysis of a multi-modal financial document, and the method comprises the steps: carrying out the preprocessing of an input multi-modal financial document, generating a corresponding text block through the multi-modal data in the multi-modal financial document, and constructing a corresponding vector database; responding to the target query request; according to the target query statement, entering a multi-path retrieval process to generate a binding packet for responding to the sub-query statements; based on the binding packages generated by the multi-path retrieval module, the semantic alignment degree of each binding package and a sub-query statement is calculated, a corresponding time reward score is calculated in combination with a time reward mechanism to obtain a matching score, ranking optimization is conducted on the matching score through a direct preference optimization mechanism, and a preference text block set is obtained to respond and generate a corresponding answer; by integrating the preprocessing module, the retrieval module and the reordering module of the financial document, the defects of the traditional method in the aspects of processing heterogeneous financial data and improving the retrieval recall rate and correlation are effectively overcome.

The invention provides a data query method and system for converting a natural language into a database query language, and the method comprises the steps: analyzing the natural language input of a user through a multi-modal understanding agent on the basis of constructing a dynamic knowledge graph based on metadata, combining a historical session with a business term table, eliminating ambiguity, and generating a standardized Query, a retrieval routing agent selects a query strategy according to Query complexity, simple query directly matches a cache template, complex query traverses a knowledge graph, and related tables, fields and service constraints are returned; then, an expert committee agent generates an SQL (Structured Query Language) by adopting multi-stage collaboration, executes plan pre-evaluation, and selects a version with the highest comprehensive score; the test agent simulates and executes the SQL in the isolation environment, and verifies the grammar legality and the field permission; and finally, executing the detected SQL, and processing a result. According to the method, the accuracy of converting the natural language into the SQL (NL2SQL) in a complex database scene can be effectively improved.

The invention discloses a system and a method for extracting project information based on a multi-modal large model, and the system comprises a file preprocessing module which is used for receiving and recognizing an input project document file, and extracting the metadata information of the file; the file type identification module is used for selecting different processing modes according to file types; the information extraction module is used for extracting text elements, labels, layer information and geometric elements from the document according to the file type and embedding the text elements, the labels, the layer information and the geometric elements into a vector space; the multi-modal model processing module is used for generating semantic description according to the text content, the picture description and the element metadata; the clustering module is used for clustering elements in the DWG drawing based on the coordinates; the knowledge graph construction module is used for constructing a knowledge graph based on the description, the text content and the element metadata; the vector database is used for storing embedded text content, description and related context information; the question analysis module is used for receiving user questions, extracting keywords, and retrieving in the vector database and the knowledge graph construction module to obtain related contexts; and the answer generation module is used for generating answers based on the retrieved context information in combination with a multi-modal large model and providing original text reference.

The invention belongs to the technical field of artificial intelligence and multi-modal large model reasoning enhancement, and discloses a multi-modal retrieval enhancement generation method based on gradual group relative strategy optimization. A step-by-step reasoning track construction mechanism is introduced, an original problem is disassembled into a plurality of sub-problems, and in each step, a new retrieval query is autonomously generated in combination with reasoning history and current information requirements, and a most appropriate knowledge source is selected for evidence retrieval; and in the reasoning process, each step of decision and answer obtains a fine-grained reward signal. According to the method, a group relative strategy optimization method is adopted, the query quality of each reasoning step, the knowledge base routing accuracy, the answer content format compliance and the final answer accuracy are used as step-by-step rewards for joint modeling, and model parameters are optimized through global and local multiple feedback signals. The method is remarkably superior to the existing similar technology in tasks such as multi-class multi-modal open domain question answering and complex reasoning, and has excellent answer accuracy, retrieval efficiency and multi-modal adaptive capacity.

The invention discloses an SQL statement structure verification system based on large model and knowledge graph fusion enhancement. The SQL statement structure verification system comprises a knowledge graph construction module, an input design module, a verifier design module and an output design module. According to the method, a knowledge graph is introduced as a structured semantic support, and a closed-loop enhancement processing flow of SQL statements from generation, verification to optimization is realized in combination with a structure perception cue word design, a rule verification mechanism and a Function Call feedback interface; the defects that an existing Text2SQL method is insufficient in structural understanding, lack of semantic reasoning, weak in generalization ability, dependent on computing power and the like are overcome. According to the method, triple guarantee of semantic perception, rule driving and model assistance is realized, the accuracy, robustness and interpretability of SQL generation are remarkably improved, and the cognitive load and operation risk of non-professional users in database interaction are effectively reduced.

The invention discloses an apoplexy patient management method and system based on a multi-mode RAG and LLM model, and the method comprises the steps: obtaining the standardized electronic medical record data of a patient based on an FHIR standard electronic medical record; performing feature extraction on the electronic medical record data to obtain multi-modal data; integrating and representing a time-space relationship among the multi-modal data, and obtaining a dynamically updated dynamic knowledge graph; analyzing and integrating the electronic medical record data to obtain integrated information; constructing a stroke risk causal network based on an LLM model in combination with a causal reasoning mechanism; obtaining a personalized health report based on the dynamic knowledge graph and a stroke risk causal network; and based on a personalized report result and feedback data of the patient, a treatment scheme and a management strategy of the patient are optimized in real time. According to the application, the causal reasoning mechanism is embedded into the Transform architecture of the LLM, so that the modeling and prediction capabilities of the stroke risk causal relationship are enhanced.

The invention relates to a cross-modal encryption retrieval method based on semantic perception, and belongs to the field of information retrieval and data encryption. Deep learning is introduced, the semantic feature mining capability oriented to multi-modal data is enhanced, and semantic feature retrieval is used for replacing a traditional keyword retrieval mode; a low-overhead multi-modal data encryption retrieval method is introduced, a parallel retrieval tree structure is designed based on a partitioning thought, and low-overhead and privacy-protected semantic similarity rapid retrieval is realized; the reasonability of the scheme is analyzed from the precision ratio, the search time, the storage overhead and the like. The method comprises the following steps: performing feature extraction on a query request to obtain a multi-modal feature; generating an encrypted query trap door for the multi-modal query features by using a similarity hidden encryption retrieval algorithm; according to the cross-modal data encryption retrieval, multi-modal data security retrieval in the medical internet of things is realized, the characteristics of strong edge computing capability and quick response are integrated, and the problems of insufficient computing resources and key leakage of terminal users in a traditional scene are solved.

The invention discloses a multi-modal data retrieval method and device, a storage medium and computer equipment. The method comprises the following steps: collecting multi-modal original data; on the basis of description information of metadata of original data, all metadata belonging to the same associated items and logic relations among all the metadata are obtained, a metadata chain is constructed, a distributed graph database is constructed on the basis of the metadata chain, the metadata chain is expressed in the distributed graph database in the form of a graph, the graph comprises nodes and edges, the nodes represent the metadata, and the edges represent the metadata. The edge represents a logical relationship between the metadata; and when a data retrieval instruction is received, traversing each node in the metadata chain along the logical relationship of the metadata chain in the distributed graph database, obtaining a target node matched with a data retrieval requirement corresponding to the data retrieval instruction, and returning original data corresponding to metadata represented by the target node. Multi-modal data dynamic association retrieval can be realized, and cross-modal information mining efficiency and accuracy are improved.