557results about "Metadata text retrieval" patented technology

The invention relates to the technical field of equipment operation and maintenance intelligent retrieval, and provides an equipment operation and maintenance data enhanced retrieval method based on a knowledge graph and a large language model, which comprises the following steps: (1) constructing and dynamically maintaining the knowledge graph containing equipment operation and maintenance field entities and relationships; (2) analyzing natural language query of a user, performing multi-hop association retrieval in the knowledge graph, and screening out a related evidence set; (3) constructing a structured cue word based on the evidence set, and driving a large language model to generate a preliminary diagnosis report; and verifying, correcting and formatting the preliminary diagnosis report into a final visual report. According to the method, deep intention understanding and multi-hop association mining of natural language query of a user are realized by constructing a dynamically evolved equipment operation and maintenance knowledge graph, and a reliable evidence chain and a structured cue word constraint mechanism based on the knowledge graph are introduced to ensure that the generated diagnosis report is strictly based on field professional knowledge; the problem that the real semantic intention of user query cannot be deeply understood in traditional retrieval is effectively solved.

The embodiment of the invention provides a multi-modal fusion entity retrieval enhancement generation method and device, and the method comprises the steps: carrying out the blocking and adaptive text extraction of multi-modal data in an offline stage, obtaining the text block data corresponding to each modal data, extracting the entity and relation of the text block data according to a language model, constructing an entity triple, and carrying out the segmentation and adaptive text extraction of the entity triple. Fusing the entity triad with the text block data to obtain an offline knowledge graph, and constructing a data index; in the present stage, a query statement of a user is received, text block data most similar to the query statement are retrieved in a knowledge graph through a data index, after entity aggregation is carried out on the retrieved text block data, the text block data are reordered according to retrieval scores, an entity aggregation result is obtained, entity ordering is carried out according to the entity aggregation result, and the entity aggregation result is obtained. By means of the multi-modal retrieval method and device, the efficiency and accuracy of multi-modal retrieval can be improved.

The invention discloses an appearance patent graph retrieval method and infringement detection system based on a multi-modal large model, and relates to the technical field of intelligent retrieval, and the method comprises the steps: carrying out the feature extraction of each patent picture in an appearance patent database through a multi-modal large language model, and storing the features in a vector database; generating an embedded vector of the target picture and a description text for describing the appearance characteristics of the target picture by utilizing a multi-modal large language model; calculating the similarity between a target picture embedding vector and each picture embedding vector in a vector database, performing retrieval to form a preliminary candidate set, and then calculating the semantic similarity between a target picture description text and a patent text corresponding to each picture in the preliminary candidate set; performing fusion to obtain a retrieval result of comprehensive sorting; correlating the corresponding patent law text, positioning and marking related text description, and forming a visual evidence chain combining vision and text evidence. According to the method, the vision and text bimodal information is fused, so that the whole-process intelligentization from image understanding to infringement judgment is realized.

The invention discloses a knowledge document-oriented method for structurally and stably presenting large language model output. The method comprises the following steps of: preprocessing a knowledge document and converting the knowledge document into a text by a system; the back-end service module adopts a prompt word engineering technology based on a preset JSON mode, constructs a structured prompt containing clear instructions and output format constraints, calls a large language model to carry out analysis and information extraction on text contents, and forces the model to generate structured JSON data following the preset mode; the back-end service provides access to the structured JSON data for the front-end application; and the front end executes templated mapping rendering according to a preset user interface component template isomorphic to the JSON mode, and fills the content of each field of the JSON into a corresponding visual component. According to the method, through the cooperation of the back-end constraint prompt word engineering and the front-end modularized template rendering, the defects that the output content format of a large language model is unstable and is difficult to be directly applied to standardized interface presentation are relieved.

The invention is suitable for the technical field of natural language processing, relates to a hierarchical memory and context awareness retrieval method of a large role model and a related product, and aims to solve the problems of limited model memory duration, insufficient retrieval correlation and insufficient personality consistency in a long dialogue. According to the invention, a short-term-middle-term-long-term three-level memory architecture is adopted, and a memory attenuation and migration mechanism is combined, so that dynamic metabolism of memory is realized; related memories are recalled accurately through a context semantics and role personality double-sensitive double-stage retrieval algorithm; relying on a personality-linked memory fusion and response generation strategy, the reply is ensured to fit personality setting; and a closed-loop adaptive learning mechanism of dialogue-memory-retrieval-generation-feedback is constructed, and the memory quality is continuously optimized. According to the method, the role large model can have the human-like continuous memory ability, the continuity, retrieval accuracy and personality consistency of long dialogues are remarkably improved, and the long-term personalized interaction requirements of scenes such as digital personality assistants and dialogue agents are met.

The invention discloses a knowledge graph construction method which comprises the following steps: acquiring document data from different sources, extracting long content from the document data, and segmenting the long content into a plurality of semantic text blocks; for each semantic text block, extracting all entities from the semantic text block by using a large language model, and analyzing the relationship between the entities; constructing a global semantic association graph based on all entities and the relationship between the entities, and dividing the global semantic association graph by using a graph clustering algorithm to form a plurality of knowledge communities; and creating corresponding entity nodes for the entities, creating corresponding edges for relationships between the entities, creating corresponding community nodes for the knowledge communities, and establishing belonging relationships between the community nodes and the corresponding entity nodes to form a knowledge graph, and storing the knowledge graph in a graph database system. On the basis, the knowledge extraction precision and the cross-domain generalization ability can be improved, and a hierarchical knowledge system can be formed.

Disclosed herein are system, method, and computer program product aspects for semantic search in a model-based prompt builder system. A system generates a search retriever object based on a search index comprising unstructured data. The search retriever object includes metadata specifying one or more details of a vector search operation to be performed on the search index. The system obtains search results by performing the vector search on the search index based on the one or more details of the vector search operation provided by the search retriever object and a search query. The system provides the search results to a prompt generator configured to use a model to generate a reply to a prompt request requiring the search results.

Disclosed is a mutually generative artificial intelligence system based on multi-dimensional spatiotemporal information vector graphics, relating to the field of artificial intelligence and engineering applications. Based on a geographic information system (GIS) or a computer-aided design (CAD) platform and a data source, a multi-dimensional vector spatiotemporal large model terminal, a multi-dimensional spatiotemporal information processing agent terminal, and an intelligent information system application terminal are constructed. For multi-dimensional spatiotemporal data such as two-dimensional and three-dimensional vectors and temporal states, a multimodal spatiotemporal large model having an understanding capacity for an engineering professional knowledge system, a data processing flow, multi-dimensional vector graphics, and thematic graphics-text documents is pre-trained to achieve the mutual expression and generation of engineering multi-dimensional vector graphics and thematic graphics-text documents and to form an intelligent engineering graphic data processing application.

The invention relates to a table information retrieval method and device, computer equipment and a storage medium. The method comprises the following steps: determining a table picture and a table title of a searchable table; based on the cue word template, according to the position information of the table link of the searchable table, the table title, the table abstract generation instruction and the table abstract specification, generating a table cue word; generating a table summary text according to the table prompt word, determining summary fragments, performing vectorization processing on the summary fragments, and determining summary text vectors; storing the table abstract text, a text identifier corresponding to the table abstract text, a link sequence number of a table link, a table picture address of the searchable table and an abstract text vector into a vector database; and obtaining an information retrieval request sent by a user, performing information retrieval on the vector database, and determining an information retrieval result corresponding to the information retrieval request. According to the scheme, the accuracy and integrity of information retrieval can be improved.

The invention discloses a knowledge retrieval enhancement method and system for a keyword knowledge graph. The method comprises the following steps: constructing a keyword knowledge graph, forming a bidirectional collaborative index with a vector knowledge base, extracting global core keywords in a document through a large model, mining relationships of same words, similar words and ambiguous words among the keywords, applying a type consistency constraint, and binding the keywords and document information as an association relationship. And accurate and efficient retrieval is realized by combining keyword expansion, retrieval range constraint and result fusion. The method has the advantages that recall integrity is improved, semantic consistency is enhanced, accurate association is achieved, dynamic scenes are adapted, and finally efficient and accurate retrieval is achieved.

The invention belongs to the technical field of artificial intelligence and natural language processing, and particularly relates to an intelligent document checking method based on a large language model. And cooperatively executing wrongly written character and term checking, standard version checking, structural integrity checking, compliance checking, consistency checking, calculation accuracy checking and common error checking in sequence. In each verification step, deep semantic extraction of a large language model and a retrieval enhancement generation technology of an external domain knowledge base are combined, and strict preprocessing regularization and consistency gating verification are supplemented. According to the method, the illusion of autoregression generation of the language model is effectively inhibited, the logic coherence of the overlength document in context and parameter characteristics is guaranteed, intelligent automatic verification with extremely high accuracy, low false alarm rate and completely traceable auditing process is realized, and the quality and efficiency of complex document processing in various industries are greatly improved.

The invention discloses a BEV-based scene-level text search point cloud retrieval method and device and electronic equipment, and the method comprises the steps: projecting a three-dimensional point cloud into an aerial view, and generating a BEV image; encoding the image by using a pre-trained vision-language model to obtain BEV feature vectors, storing the BEV feature vectors in a vector database, and constructing a point cloud feature library; meanwhile, encoding a user query text to obtain a text feature vector; searching a matching scene from the feature library by calculating the cross-modal similarity between the text and the BEV feature vector; and finally, mapping a retrieval result to original point cloud data and outputting the original point cloud data. By means of the method, the feature alignment problem of the point cloud and the natural language is solved, and the retrieval method which directly and efficiently utilizes essential features of the point cloud data to be in seamless joint with the natural language is achieved.

The invention provides a multi-agent system and a multi-agent dialogue management method. The system comprises a main agent, a dialogue management module and a plurality of sub-agents, and the sub-agents correspond to processing of tasks in different business fields respectively; the main agent is used for calling the dialogue management module under the condition that a user request is received; the dialogue management module is used for acquiring historical information corresponding to the user request, analyzing the historical information and returning an analysis result to the main agent; the main agent is further used for determining corresponding request task data and a target sub-agent in the multiple sub-agents according to the analysis result and the user request, and sending the request task data to the target sub-agent; the sub-agent is used for processing based on the request task data, obtaining a task processing result and returning the task processing result to the main agent; and the main agent is also used for returning a corresponding natural language reply to the user according to the task processing result of the sub-agent.

The invention relates to a distributed integrated energy system instruction data set automatic generation method and system based on agent cooperation. The method comprises the following steps of: S1, purifying a seed data set in the field of the distributed integrated energy system by using an information metrology method; s2, on the basis of the purified seed data set, constructing an intelligent agent to generate an instruction data set in parallel; and S3, performing quality evaluation and closed-loop optimization on the instruction data set. According to the method, firstly, core questions and answers are purified from high-influence literatures and laws and regulations through information metrology and a knowledge graph to serve as seeds, and data accuracy is ensured; parallel expansion, screening and duplicate removal are carried out by a generator and a calibrator; and finally, a feedback closed loop is finely adjusted, cue words and verification rules are continuously optimized, and high-quality and wide-coverage question and answer pairs are quickly produced, so that the diversity and the accuracy are ensured, the labor cost is saved to the greatest extent, and the application effect of a large language model in the field of a distributed comprehensive energy system is improved.

The invention provides a building material retrieval method, which comprises the following steps of: acquiring a building material retrieval request described by a natural language of a user, performing deep semantic analysis by using a large language model to extract key information such as names, specifications, performances, scenes and the like, and generating a keyword set; performing synonym, hypernym, hypernym, industry term and associated word expansion on the keywords based on material attributes and semantic correlation to form an expanded keyword set; comprehensively retrieving multi-dimensional attributes such as names, specifications, performance, manufacturers, prices and the like in the building material database to obtain preliminary results; and performing weighted scoring and sorting by using multiple factors such as a semantic matching degree, an attribute matching degree, user evaluation and a market trend, and outputting a visual chart. According to the method, the building material retrieval accuracy, efficiency and user experience can be improved, and diversified retrieval requirements of professional users in the building industry are met.

The invention discloses an AI file query method based on human-computer interaction, which comprises the following steps: S1, collecting user input, and generating a query text; s2, intention recognition and slot extraction are performed on the query text, a slot set is generated, and standardization processing is performed; s3, utilizing the improved CoSent model to generate a query vector and a document vector, and storing the query vector and the document vector in a vector index; s4, retrieving the candidate document based on the query vector in the vector index, calculating semantic similarity and obtaining a comprehensive score in combination with a matching result; s5, carrying out reordering on the candidate documents; s6, generating a permission set based on the user identity, and executing permission filtering and field masking; and S7, inputting the document fragments passing the permission filtering and the query text into a text generation model, outputting a query result, and recording a log and user feedback. According to the invention, the accuracy and safety of file query are obviously improved.

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for generating answers to medical questions using neural networks and other components. In one aspect, a method includes: obtaining question data representing a medical question; obtaining a plurality of document snippets from a medical database that stores medical documents; for each document snippet in the plurality of document snippets, determining a relevance score for the document snippet by using a ranking neural network based on the document snippet and the medical question; selecting, based at least in part on the relevance scores, a subset of the plurality of document snippets; generating a prompt that includes (i) the medical question and (ii) the subset of the plurality of document snippets; and generating an answer to the medical question based on processing the prompt using a generative neural network.

The invention provides a unified context and multi-level memory cooperation system and method for an LLM agent, and belongs to the field of artificial intelligence. The system comprises a unified context module which is used for aggregating and structuring all input information required for organizing agent operation, and providing an integrated context view for an LLM agent core; the LLM agent core is used for executing task planning, tool calling, result evaluation and response generation based on the context provided by the unified context module; and the multi-level memory system is connected with the unified context module and the LLM agent core and is used for hierarchically storing, managing and feeding back experience and knowledge of the agents. According to the method, the problems that an existing LLM intelligent agent is limited in context, low in memory efficiency and lack of self-correction capacity are solved, and the intelligent level and reliability of complex task processing are remarkably improved.

The invention relates to a model reasoning acceleration method and device, computer equipment and a readable storage medium. The method comprises the steps of inputting obtained initial text data into a target reasoning model for reasoning, scheduling and executing draft token generation, context token retrieval and probability calculation prediction distribution of an initial text in parallel through an asynchronous execution engine, and sequentially obtaining a draft token set, a retrieval token set and probability distribution of tokens; integrating the draft token set and the retrieval token set to generate a target draft tree; and based on a tree attention mechanism, performing recursive verification on the target grassy tree according to the probability distribution, determining an effective token sequence from the target grassy tree, updating the initial text data according to effective tokens, and executing the step of inputting the initial text data into the target reasoning model for reasoning until a preset ending condition is met. By adopting the method, the hardware resource utilization rate and the model reasoning speed can be improved on the basis of not sacrificing accuracy.

A retrieval optimization method adaptive to multi-dimensional storage of power documents relates to the technical field of information retrieval, and comprises the following steps: firstly, preprocessing user query, identifying power business scenes and technical types of the user query, and extracting a query keyword set and a query vector; then, a three-level progressive retrieval strategy is adopted to retrieve in an electric power document library composed of a metadatabase and a vector data at the first level, candidate documents are screened based on keyword matching and business scenes; in the second stage, further filtering is carried out through similarity calculation of a query vector and a technical abstract vector; in the third stage, final accurate screening is completed in combination with full-text vector similarity and electric power professional rules; finally, information integration and structured output are conducted on the result, the problems that in traditional power document retrieval, the result is inaccurate, and efficiency is low are solved, and retrieval precision and response speed are remarkably improved.

The invention provides a technical supervision document retrieval method and a related device, and belongs to the field of technical supervision document retrieval. The method comprises: acquiring a user query intention; retrieving from a database according to the query intention of the user to obtain a natural language answer facing the user question; the database construction method comprises the steps of obtaining an existing technical supervision document; performing analysis and knowledge extraction on the technical supervision document to obtain a knowledge multi-tuple; after the knowledge multi-tuple is verified, time dimension attributes are added to the knowledge multi-tuple; and respectively storing the knowledge multi-tuples added with the time dimension attributes according to data types to obtain a database. According to the technical supervision document retrieval method and device, the problem of low accuracy of technical supervision document retrieval is solved.

The invention relates to the technical field of digital archive management and information retrieval, and discloses a digital archive multi-modal data semantic enhancement fusion retrieval method and system.The method comprises the steps that a policy cycle time axis and a policy term evolution graph are constructed, tense logical reasoning is conducted on archive seals, and permission effectiveness evolution is derived; the temporal permission feature vector and the content semantic vector are fused to generate a multi-modal representation vector, and cross-policy-cycle semantic enhancement retrieval is realized by combining query expansion and temporal permission filtering, so that the problems of missing detection and misjudgment of policy and regulation archives in seal permission historical evolution and term cross-cycle retrieval are solved.

The invention discloses a retrieval enhancement generation method and system fusing multi-modal and hybrid retrieval, and relates to the technical field of multi-modal fusion and hybrid retrieval, and the method comprises multi-modal information fusion framework construction, row hybrid retrieval execution, adaptive weight distribution and context construction, and structured intelligent content compression and generation. According to the retrieval enhancement generation method and system fusing multi-modal and mixed retrieval, the limitation that a traditional RAG system depends on a single text vector library is broken through by integrating multi-source information, multi-modal information sources such as contract original texts, expert suggestions, dialogue history and external similar cases are integrated through a unified framework, the comprehensiveness of information coverage is ensured, and the retrieval enhancement generation efficiency is improved. According to the method, more abundant factual basis is provided for result generation, and for double guarantee of semantics and keywords, a parallel mixed retrieval method is adopted to be combined with vector retrieval and full-text retrieval, so that the defect of a single retrieval mode is avoided, and the accuracy and correlation of retrieval results are improved.

The invention discloses an RAG-based hospital infection prevention and control strategy generation system and an implementation method. The generation system comprises a knowledge base construction module, an RAG engine module, an intention recognition module, a task disassembly module, a mixed retrieval center module, a multi-model collaborative verification module and a retrieval enhancement generation module. The implementation method comprises the steps that an RAG engine module receives a problem and triggers an intention recognition module to carry out deep semantic analysis on the problem; the task disassembling module is used for decomposing the problem into a sub-task sequence; the mixed retrieval center module synchronously initiates dual-channel retrieval and outputs an optimal knowledge fragment set; the multi-model collaborative verification module calls a special AI small model to carry out hard constraint verification on key medical parameters while scheduling the large model to carry out preliminary reasoning; and the retrieval enhancement generation module automatically triggers multi-dimensional evaluation, and selects an optimal generation scheme by comparing model performance scores. According to the method, consumption of invalid retrieval resources can be avoided, and the problem processing efficiency is improved.

The invention discloses an intelligent integrated management system for building construction quality and safety, which relates to the technical field of industrial safety system services, and is characterized in that each batch of raw materials and each key component are endowed with a unique digital identity label, so that the unique digital identity label becomes a unique mapping which cannot be tampered by a physical entity in the digital world; in the subsequent circulation process, any data such as quality detection, construction operation, environmental parameters and personnel information are bound to the identifier through the Internet of Things equipment and the edge gateway, and the data packets with the digital identifier are submitted to a block chain consensus network jointly maintained by suppliers, construction, supervision, construction and the like for evidence storage. The distributed account book and consensus mechanism of the block chain ensures that the data submitted by any party can be permanently recorded only after being verified by other participating nodes, thereby ensuring the authenticity and integrity of all key quality records.

The invention provides a table query method and device, and the method comprises the steps: responding to a received source query statement, and loading a to-be-queried table associated with the source query statement and metadata associated with the to-be-queried table; according to the metadata, analyzing a hierarchical relationship among fields in a header structure of the to-be-queried table, and constructing a field hierarchical mapping table according to the hierarchical relationship; wherein the field hierarchy mapping table is used for indicating a mapping relationship between a field path of each field and a column index of each field path in the to-be-queried table; and according to the plurality of key entities and the field level mapping table in the source query statement, querying the to-be-queried table at least once to obtain a query result matched with the query intention of the source query statement, thereby effectively solving the problem of field identification under a complex nested header, and improving the query efficiency of the to-be-queried table. The adaptive capacity and the query accuracy of the system to diversified table structures are remarkably improved, and the intelligent level, the practicability and the automation degree of the table question-answering system are enhanced.

Some embodiments provide a method for identifying a first pattern formed by a first set of document elements. The method associates a tag that identifies the first pattern with the document. The method then identifies a second pattern formed by a second set of document elements and the tag. The method associates a second tag with the document. The second tag identifies the second pattern and is associated with a fact. Some embodiments provide a graphical user interface (GUI) for manually processing tags associated with a document. Further, different embodiments provide a system for performing iterative fact-extraction on a set of documents.

The invention provides an intelligent research report analysis method, system and device based on multi-mode and self-adaptive RAG, and the method comprises the steps: obtaining a research report and a query intention, the query intention being corresponding to the complexity category of a query problem; performing multi-modal analysis based on the research report to obtain target data; performing adaptive retrieval based on the query intention in combination with the target data, and matching different retrieval strategies for retrieval to obtain a retrieval result; performing correlation evaluation and reordering on the retrieval results to return information fragments, and generating structured answers through a self-defined prompt project by utilizing a preset large model based on the query intention and the information fragments; and carrying out support evaluation on the structured answer to obtain a query result and carrying out visual expression. According to the method, core contents such as multi-modal understanding, intelligent retrieval, answer credibility and visual display and the like in financial research and report analysis are systematically solved, and the method has relatively high technical innovation and practicability and is particularly suitable for financial scenes with high requirements on data accuracy and analysis depth.

This invention relates to a data processing system for obtaining app types. The system includes: a first database, a second database, a third database, a processor, and a memory storing a computer program. The first database includes an original set of apps, the second database includes a sample set of apps, and the third database includes a set of non-sample apps. When the computer program is executed by the processor, the following steps are implemented: obtaining a target tag set corresponding to the initial app list; obtaining the final tags of the non-sample apps based on the sample app set and the target tag set; and obtaining the app type corresponding to the non-sample apps based on the final tags. This invention provides a novel method for obtaining app types. By applying different processing methods to non-sample apps, tags for all apps are obtained, thereby classifying the apps and achieving higher accuracy in obtaining app types.

The application discloses a kind of text prediction methods based on data lake, belong to artificial intelligence technical field, including: obtaining initial text data generated by application;The initial text data is filtered, and qualified text data is put into text type data pool as metadata;Text disambiguation model is constructed;According to the metadata and the corresponding metadata identifier, generate original data set;According to the metadata, the corresponding original process data and the corresponding metadata identifier, generate original process data set;Original data set and original process data set are respectively input into text disambiguation model, and obtain original data fitting value and original process data fitting value;The corresponding metadata and original process data are combined as keyword;Markov chain keyword prediction model is constructed, and the hot-cold transition probability of keyword that last user asked is used to predict the hot-cold transition probability of keyword that user may initiate next time;Output the preset scheme of question that user may care.