1337results about "Database querying" patented technology

The invention relates to the technical field of data analysis, can be applied to business scenes of medical health, financial science and technology, culture research and the like, and discloses a multi-source knowledge processing and querying method, which comprises the following steps: data acquisition, cleaning and standardization processing, and standardized database construction; extracting core concepts and association relationships, and generating knowledge elements; constructing a multi-dimensional knowledge graph based on knowledge elements, and establishing a semantic index to realize data semantic annotation and bidirectional mapping; and analyzing the query intention, extracting a query constraint condition, and executing association reasoning based on the multi-dimensional knowledge graph to generate a query result. According to the method, the standardized database of the multi-source heterogeneous data is constructed, so that the data consistency is improved; through multi-dimensional knowledge graph construction and semantic index establishment, the relevance and structural expression of data are enhanced, so that the relationship between knowledge elements is clear and traceable; and through association reasoning based on query constraint conditions, the query accuracy and efficiency are improved.

The invention provides a standard document automatic generation and multi-dimensional auditing method and system based on a large model, and relates to the technical field of artificial intelligence, and the method comprises the steps: 1, building a distributed database of a multi-source document, and analyzing a heterogeneous text through natural language processing to obtain a standardized knowledge network; step 2, extracting index elements based on the standardized knowledge network, and forming a structured parameter library through verification and verification; and step 3, based on the structured parameter library, constructing a template library, analyzing user demands in combination with semantic matching, and automatically generating a standard document outline. The document generation efficiency and quality are improved, the manual auditing cost is reduced, and the auditing comprehensiveness and accuracy are enhanced.

Certain aspects of the present disclosure provide techniques for preprocessing data prior to generating vector representations. The data is preprocessed to generate one or more natural language texts describing entities and relationships included in the data. Vector representations of the natural language format texts are stored in a vector database. The embeddings may be retrieved to augment a prompt for a generative model. The embeddings may be selected by performing a search of the vector database using an embedding for the prompt to determine relevant or similar embeddings. The augmented prompt can be input into a large language model. Although the model may be unaware of the data from which the embeddings of the embedding database were generated, the augmented prompt may enable the model to use the data to improve breadth and depth of responses. The preprocessing of the data improves response results of the model.

An intelligent search agent that can accept search request input in various ways to initiate a search of databases, websites, documents, PDF files, photos, and other digital data. Search requests can be initiated manually, through automated scheduling, and other ways and can be initiated in multiple ways including voice input, text input, form filling, large language model (LLM) processes, AI agents, selecting from dashboard menus, computer instructions and other methods. Applications of machine learning (ML) and natural language processing (NLP) and others are used to enhance the search agent's capabilities while minimizing user effort requirements. The Search Agent works in conjunction with a knowledge base function to dynamically form and manage one or more knowledge bases using search results and to automatically integrate search results into workflow processes.

Techniques for generating AI-powered responses tailored to a specific entity's communication style. The techniques involve selecting a particular AI agent associated with an entity, receiving a user query, and generating an embedding from it. This embedding is used to retrieve relevant content from the entity's knowledge database. The entity's communication type is then determined. A large language model (LLM) prompt is created, combining the retrieved content and instructions to apply the entity's communication style. This prompt is submitted to an LLM service, which generates an output. A response based on this output is returned to the user. The techniques enable the creation of AI-generated responses that are both informative and aligned with the entity's preferred communication style, enhancing the consistency and effectiveness of AI-powered customer interactions or information dissemination for the entity.

A system and method for chatbot and search engine integration comprising traversing a conversational flow of a chatbot, generating a data structure based on the conversational flow, embedding the data structure in a webpage, and directing a search engine to the webpage for the search engine to assign a webpage rank to the data structure. In some embodiments, this integration may allow search engine users to be redirected to a non-public website hosting the chatbot when that chatbot would not otherwise be identified by the search engine.

An exemplary machine-learning-based method for generating a response to a natural-language query from an entity associated with an organization comprises: obtaining a sub-query from the natural-language query; determining if a cache associated with the organization stores a matching historical sub-query: if the cache stores the matching historical sub-query, retrieving a historical sub-response associated with the historical sub-query from the cache as a sub-query response; if the cache does not store any matching historical sub-query: inputting the sub-query into a cache-based enhancement machine-learning model to enhance the sub-query, wherein the cache-based enhancement machine-learning model is trained based on historical query data stored in the cache associated with the organization; and inputting the enhanced sub-query into a language model to generate the sub-query response; and generating the response to the natural-language query based on the sub-query response.

A computing system configured to perform artificial intelligence-powered search and evaluation functionalities is disclosed. The computer system can receive a natural language search input entered through a user interface, request a search engine to perform a search based on the natural language search input, receive search results returned by the search engine, and submit, in runtime, structured data contained in the search results to a large language model. The structured data includes a table including one or more records and a plurality of fields. The computing system can prompt, in runtime, the large language model to generate scores for the one or more records and present the structured data and the scores on the user interface.

The invention provides a fault root cause analysis method and device, electronic equipment and a storage medium, and can be applied to the technical field of computers. The method comprises the following steps: converting a fault description text input by a user into vector representation to obtain a query vector; performing query search in a preset operation and maintenance knowledge vector library according to the query vector, and obtaining an operation and maintenance knowledge vector meeting a similarity condition with the query vector in the operation and maintenance knowledge vector library; wherein the operation and maintenance knowledge vector is a vector representation of the operation and maintenance knowledge text; based on the operation and maintenance knowledge text corresponding to the operation and maintenance knowledge vector and the fault description text, obtaining fault prompt information; and inputting the fault prompt information into the large language model to obtain a fault root cause analysis result. According to the method, by integrating the large language model and the retrieval enhancement technology, fault root cause analysis can be automatically carried out, and the analysis efficiency of fault root causes is effectively improved.

Techniques for handling natural language query processing are described. In some examples, entities are recognized during an entity recognition phase and then relations between those entities are determined. Those relations are fed to an entity linker to help the linker link candidate to columns and / or a intent representation generator to help parse multiple values and column pairs of a natural language query.

A search assistant engine is described that integrates with a data intake and query system and provides an intuitive user interface to assist a user in searching and evaluating indexed event data. Additionally, the search assistant engine provides logic to intelligently provide data to the user through the user interface such as determining fields of events likely to be of interest based on determining a mutual information score for each field and determining groups of related fields based on determining a mutual information score for each field grouping. Some implementations utilize machine learning techniques in certain analyses such as when clustering events and determining an event templates for each cluster. Additionally, the search assistant engine may import terms or characters from user interaction into predetermined search query templates to generate tailored search query for the user.

In some embodiments, a multimodal computing system receives a query and identifies, from source documents, text passages and images that are relevant to the query. The multimodal computing system accesses a multimodal question-answering model that includes a textual stream of language models and a visual stream of language models. Each of the textual stream and the visual stream contains a set of transformer-based models and each transformer-based model includes a cross-attention layer using data generated by both the textual stream and visual stream of language models as an input. The multimodal computing system identifies text relevant to the query by applying the textual stream to the text passages and computes, using the visual stream, relevance scores of the images to the query, respectively. The multimodal computing system further generates a response to the query by including the text and / or an image according to the relevance scores.

Systems, methods, and devices that relate to intelligent query decomposition and parallel routing for specialized model processing are disclosed. In one example aspect, the system receives a query from a user comprising a request relating to a particular domain. The system determines, using a decomposition model, a set of sub-queries based on semantic boundaries, syntactics, tasks, relationships, and rules relating to particular domains. The system inputs the set of sub-queries into a routing model to determine a set of specialized models. For each sub-query, the system routes the sub-query to a respective specialized model, generates an output, and assigns a confidence score. The system detects conflicts among outputs using a conflict detection model configured to identify discrepancies. The system generates an aggregated output by combining outputs according to a weighted aggregation algorithm prioritizing higher confidence scores and conflict resolution rules, then displays the aggregated output.

A computing system including one or more processing devices configured to receive prompt generation instructions that specify an initial prompt and a prompt evaluation criterion. In each of a plurality of iterations of a prompt generation loop, the one or more processing devices are further configured to generate candidate prompts at least in part at a machine learning model. The candidate prompts are generated based on a current-iteration prompt that is initialized as the initial prompt in a first iteration. As specified by the prompt evaluation criterion, the one or more processing devices are further configured to compute respective evaluation scores associated with the candidate prompts. Based on the evaluation scores, the one or more processing devices are further configured to replace the current-iteration prompt. The one or more processing devices are further configured to output a final prompt generated in a final iteration.

This invention provides a method and system for automatic generation and multi-dimensional review of standard documents based on a large model, relating to the field of artificial intelligence technology. The method includes: Step 1, establishing a distributed database of multi-source documents and analyzing heterogeneous texts through natural language processing to obtain a standardized knowledge network; Step 2, extracting indicator elements based on the standardized knowledge network and forming a structured parameter library through verification and validation; Step 3, constructing a template library based on the structured parameter library, analyzing user needs by combining semantic matching, and automatically generating a standard document outline. This invention improves document generation efficiency and quality, reduces manual review costs, and enhances the comprehensiveness and accuracy of review.

A data processing method, an electronic device, and a storage medium. The method comprises: receiving a query request, wherein the query request comprises a target data table participating in a join operation; on the basis of the query request, executing a logical plan, wherein the execution of the logical plan comprises: constructing a data filtering condition corresponding to column statistical information, the column statistical information being information obtained by means of compiling statistics in advance on a column value range of columns included in the target data table; and executing a physical plan corresponding to the logical plan, wherein the execution of the physical plan comprises: performing partition pruning and / or dynamic filtering on the target data table on the basis of the data filtering condition, so as to generate a processed target data table, and executing the join operation on the processed target data table, so as to obtain an execution result.

A system comprises an executable graph-based model. The executable graph-based model comprises a first overlay node. The first overlay node comprises processing logic that is operable to interact with one or more associated nodes of the executable graph-based model. Further, the executable graph-based model comprises a first node that has the first overlay node associated therewith. The system further comprises a processing unit configured to receive a first stimulus associated with the first overlay node and, in response to the first stimulus being received, cause execution of said processing logic of the first overlay node. Execution of said processing logic of the first overlay node is based on the first node.

One embodiment of the present invention sets forth a technique for curating a data sample set. The technique includes determining one or more data sampling criteria based on a sampling objective for a data sample set associated with the machine learning model. The technique also includes selecting, from a set of unlabeled data samples, at least one data sample to be labeled and added to a data sample set associated with the machine learning model based on the one or more data sampling criteria. The technique also includes, for each selected data sample, supplementing the data sample set with the selected data sample and at least one association with a label.

A computer-implemented method may comprise creating a first view of a first data source comprising a first online analytical processing (OLAP) cube based on a first user input, creating a second view of a second data source based on a second user input, combining the first view and the second view, and creating metadata objects for elements of the first view and the second view. The method may further comprise generating a query execution plan comprising a first native query and a second native query based on a user-defined query specification and the metadata objects, executing the first native query on the first data source to retrieve a first dataset from the first data source and the second native query on the second data source to retrieve a second dataset from the second data source, and generating a federated dataset using the first dataset and the second dataset.

Aspects of the invention provide a method, system, and computer program product for retrieval augmented generation. In one aspect, the method includes receiving a query. The method further includes classifying the query to a first domain within a plurality of domains. The method additionally includes determining an ambiguity associated with classifying the query. The method also includes retrieving an index of domain-specific vector embeddings corresponding to the domains when the ambiguity does not exceed a threshold for ambiguity. The method further includes prompting a large language model with the query and the domain-specific vector embeddings. The method also includes receiving a query response from the large language model as grounded with the most relevant index results. The method further includes forwarding the query response.

A system and method for generating a database query based on a natural language query is presented. The method includes receiving an unstructured natural language query directed to a security database, wherein the security database includes a representation of a computing environment; selecting a group of database queries from a plurality of preexisting database queries based on a similarity to the unstructured natural language query; generating a context for processing by a language model, the context including the selected group of database queries, an identified technology, and a schema of the computing environment; processing a prompt and the generated context utilizing the language model to generate a second database query; and executing the second database query on the security database.

The invention relates to the technical field of artificial intelligence, can be applied to business scenes of financial science and technology, medical health and the like, and discloses a multi-modal information analysis and scheme reminding method, device, equipment and medium, which comprises the steps of receiving input data and converting the input data into multi-modal data, executing optical character recognition and image classification recognition to generate a recognition result, and sending the recognition result to a server; a natural language processing model is used for analyzing fuzzy description to generate an analysis result, a knowledge base is inquired, a knowledge graph is combined to generate an association result, the analysis result, the association result and user feature data are fused to generate an execution scheme, the execution scheme is compared with an abnormal list, supervision confirmation is triggered, and a compliance instruction is generated. And personalized reminding contents are generated. The information analysis integrity is improved through multi-modal recognition, natural language processing and the knowledge graph, supervision confirmation and personalized reminding are introduced, and intelligent, compliant and reliable reminding management is achieved.

Techniques are presented for recommending queries to search log information. The system provides useful insights and recommendations based on user needs and queries by utilizing the user context, with information about the user activities (e.g., recent alerts) and the user configuration in the system (e.g., applications configured by the user), to provide recommendations. There may not be enough context for a new user to provide good recommendations, so the system determines the context based on the activities of other users, such as more experienced users or users investigating the same type of problem. Based on the context, the user recommends natural language queries (NLQ) or system queries to accelerate the search process and assist the user during an investigation. Further, NLQs may be converted to complex search queries that use the search query language, and the NLQs may also be used as part of the context for the subsequent recommendations.

The invention relates to the technical field of bioinformatics, in particular to a gene pool data retrieval method and system and a storage medium. The method comprises the following steps: acquiring multi-source genome data, performing quality control on the multi-source genome data based on an FAIR principle, and performing efficient storage and indexing by utilizing a distributed storage system so as to obtain a distributed genome database; performing cross-species homology analysis on the distributed genome database, and constructing a multi-level evolutionary tree model, so as to obtain evolutionary relationship map data; mapping gene structures and functions among different species according to the evolutionary relationship map data so as to obtain cross-species gene mapping data; receiving retrieval query data input by a user; and performing query type identification on the retrieval query data to obtain optimized query data. Through the multilevel evolutionary tree model and cross-species gene mapping, gene function comparison and prediction among different species are realized.

Retrieval of structured tabular data in a retrieval-augmented generation (RAG) platform is described. An example method includes receiving a tabular file including structured data, extracting short and long metadata from the file, and generating a dataset agent object using the extracted metadata. A human-readable description is associated with the structured data, and the dataset agent object and metadata are stored in a metadata index. A natural language query is received through a query agent object rendered within a canvas including interconnected agent objects. A dataset agent object is identified based at least in part on metadata filtering using the natural language query and short metadata. A structured query conforming to structured query language syntax is generated using a large language model (LLM) and executed on the structured data. A response including the result set and dataset agent identifier is generated and transmitted to a downstream agent object for further processing.

The embodiment of the invention provides a data retrieval method, device and system, and relates to the technical field of data processing.The method comprises the steps that an original retrieval statement and an associated retrieval statement are obtained, and a target retrieval statement is obtained; and performing keyword extraction on the target retrieval statement to obtain a retrieval keyword. Retrieving in a knowledge graph database based on the retrieval keyword to obtain a first retrieval result including the first data file; performing retrieval in a basic database based on the retrieval keyword and the target retrieval statement to obtain a second retrieval result including a second data file; performing retrieval in the vectorization database based on the statement feature vector of the target retrieval statement to obtain a third retrieval result including a third data file; and determining a target retrieval result comprising the target data file from the first retrieval result, the second retrieval result and the third retrieval result based on the interaction information of each data file, so as to improve the accuracy of data retrieval and improve the user experience.

A system for an automated real-time management of a directed acyclic graph (DAG) based on predictive analytics of DAG input-related data including a processor of a graph compute manager (GCM) node configured to host a machine learning (ML) module and connected to at least one DAG source entity node over a network and a memory on which are stored machine-readable instructions that when executed by the processor, cause the processor to: acquire the DAG input-related data from the at least one DAG source entity node; parse the DAG input-related data to derive a plurality of key features; query a local DAGs' database to retrieve local historical DAGs'-related data associated with previous DAG parameters based on the plurality of key features; generate at least one feature vector based on the plurality of key features and the local historical DAGs'-related data; and provide the at least one feature vector to the ML module for generating a predictive model configured to produce at least one DAG update parameter for updating the DAG at the at least one DAG source entity.

The invention provides a shield tunneling parameter intelligent optimization method and system based on an AI big language model, and relates to the technical field of tunnel construction optimization. Comprising the following steps: training an open source large model to obtain a preliminary shield tunnel construction industry large model; an upstream task and a downstream task which are relatively independent are set, and the upstream task comprises a tunneling speed prediction module, a tool wear prediction module, a ground surface settlement prediction module and a tunneling attitude prediction module; a downstream task combines an RAG technology and an NSGA-III multi-objective optimization framework, four prediction modules and an energy consumption calculation formula serve as objective functions, the value range of constraint conditions is determined, a tunneling parameter optimization module is established, a professional shield tunnel construction industry large model is formed, and scientific and intelligent decision making of tunneling parameters is achieved. According to the method, information in multiple aspects can be comprehensively considered during decision making, the reasoning process is output, and scientificity, comprehensiveness and reliability of decision making are ensured.

The invention relates to the technical field of video detection, in particular to a video anomaly detection method based on a large language model, and the method comprises the steps: constructing a searchable knowledge base through normal videos; after video clips are extracted from a to-be-detected video, a description text is obtained through the large language model; encoding the description text into a vector, and retrieving in a knowledge base to obtain a plurality of most similar behavior patterns; and inputting the most similar behavior patterns and the description text into the large language model, and reasoning whether the video to be detected is abnormal or not through guidance of a third prompt word. By introducing the large language model, the problem that a traditional video anomaly detection method is lack of interpretation is solved, a detailed natural language reasoning process can be output while anomaly detection is carried out, the background, behavior logic and reasoning basis of abnormal event occurrence are clearly described, and the understandability and decision reference value of a detection result are greatly improved.

To improve the accuracy of responses to instructions in a natural language format by a user in data analysis.SOLUTION: A data analysis device 1 includes: a reception unit 13 configured to receive input information in a natural language format by a user; a background information acquisition unit 15 configured to acquire table information indicating multiple data tables to be an object of data analysis as analysis background information; a prompt generation unit 16 configured to acquire a prompt template used in data analysis and generate a system prompt by assigning the input information and the analysis background information to the acquired prompt template; an input / output control unit 17 configured to transmit text information including the input information and the system prompt to a pre-learned language model 6 that can interpret a natural language and receive a response output from the pre-learned language model 6 by the transmission; and a display control unit 3a configured to generate display data based on the response received by the input / output control unit 17.SELECTED DRAWING: Figure 2