3107 results about "Data retrieval" patented technology

The invention relates to an intelligent question-answering system optimization method and device based on a knowledge graph, and the method comprises the steps: obtaining original knowledge data of a target knowledge domain, and constructing a knowledge graph structure model; extracting term information of entity nodes in the knowledge graph structure model, and constructing an entity term set; receiving a natural language question input by a user, executing a semantic understanding operation based on the standardized expression set to obtain a structured question semantic representation, and matching the question semantic representation with the case training set to obtain context semantic features; constructing a cue word template, and executing a query instruction generation operation to obtain a target query statement of the graph database; submitting the target query statement to a graph database to execute data retrieval operation, and obtaining query result data corresponding to the question semantic representation; and performing personalized rendering processing on the query result data based on the user portrait information to generate final question and answer return content. The method has the effect of improving the query accuracy.

The invention provides an intelligent retrieval method and system for unstructured asset content based on a large model, and relates to the technical field of data retrieval, and the method comprises the steps: carrying out semantic expansion on retrieval keywords through a knowledge graph enhancement module, obtaining asset feature vectors through a multi-modal feature extraction model, and constructing a hierarchical asset feature index database; the comprehensive similarity is calculated through a weighted fusion algorithm, and retrieval results are optimized and reordered through semantic comprehension and correlation analysis capacity of the pre-trained large model. According to the method, the retrieval precision and efficiency of the unstructured asset content are improved, and intelligent association analysis and semantic understanding of cross-modal assets are realized.

Systems and methods are described for a managed multidimensional search based on an application query and management policies. The application can receive a pipeline endpoint. The query can be sent to the pipeline endpoint. The pipeline can vectorize the query for comparison against a vector database of an identified dataset. The closest vectors can be converted back to content chunks. The system can generate prompts related to the content chunks and send those prompts to an AI model. The AI model can then output a response that includes the most relevant content, citations, and hyperlinks. These can be displayed in the application.

A system for improving data integrity through blockchain-based smart contracts, consisting of: a data input module configured to receive transaction data from at least one external source; a hashing unit coupled with the data input module and configured to generate a cryptographic hash of the transaction data; a smart contract execution engine that is operationally connected to the hashing unit and configured to execute predefined conditions associated with the transaction data, wherein the smart contract execution engine is configured to trigger automated processes based on compliance with these predefined conditions; a blockchain node interface in communication with a blockchain network, configured to validate and record the hashed transaction data, with the blockchain node interface transmitting validated data entries to be appended to a decentralized ledger; a verification module configured to check the integrity and authenticity of the attached data within the blockchain network; and A data retrieval unit with an interface to the blockchain network, configured to allow authorized users to access and retrieve validated transaction data from the decentralized ledger, with permissions governed by the terms of the smart contract.

The invention provides a security management and retrieval method based on Internet of Vehicles data, and the method comprises the steps: carrying out the cooperative training of a global key management model through a federated learning technology on the premise of not leaking the original data of all parties, and achieving a security key management scheme under the participation of multiple parties through a model parameter aggregation and updating mechanism; when data retrieval is needed, a user submits a retrieval request and identity authentication information, and after a system verifies the identity of the user, a ciphertext data identifier meeting conditions is matched in an attribute index according to a keyword and an authorization attribute of the request; the system acquires corresponding ciphertext data from a distributed database according to the ciphertext data identifier, and directly performs keyword matching calculation on the ciphertext data through a secure multi-party computing protocol under the condition of not decrypting the data; and according to the mined security threats and abnormal modes, a data encryption strategy and an access control strategy are dynamically adjusted, authority limitation or access blocking is performed on suspicious users, and the security protection capability of the system is improved.

Operators managing a cloud RAN collect vast amounts of data, e.g., node-level data, gNodeB level data, user level data, and flow-level data, which are utilized for network monitoring, evaluating key performance indicators (KPIs), and nodes management. Retrieving and visualizing information and values of different metrics is critical to managing network operation; however, data retrieval on large datasets is challenging. While foundation models perform poorly on large datasets, an accurate answer to a data query is generated by providing semantically similar metrics as context to a foundation model, thereby limiting the number of counters needed for processing the data query. The foundation model then generates a first output of metrics relevant to answering the data query and, based on the first output, generates a second output comprising query code (e.g., SQL or KQL) for computing the answer, thereby improving mathematical accuracy of the answer.

The present invention discloses an artificial intelligence-based adaptive big data storage and retrieval optimization system and method designed to intelligently manage and optimize large-scale distributed data environments. The system integrates data acquisition, distributed storage, metadata processing, adaptive learning, and retrieval optimization units configured to work collaboratively for continuous self-optimization. The invention employs deep reinforcement learning and predictive neural network techniques to dynamically analyze system telemetry, workload behavior, and data access patterns in real time, enabling proactive adjustment of data placement, caching, replication, and compression parameters across distributed nodes. The metadata processing framework utilizes graph-based dependency modeling to maintain semantic and contextual relationships among datasets, facilitating intelligent and context-aware data retrieval. The retrieval optimization unit interprets user queries semantically and computes the optimal retrieval route using latency prediction models and dynamic routing techniques.

The invention discloses a mechanical arm control method, system and equipment for realizing a multi-modal universal operation task. The method comprises the following steps: acquiring multi-modal data of text, voice and vision; performing modal alignment on the multi-modal input data, encoding the multi-modal input data into a uniform input representation vector, and splicing the uniform input representation vector into a multi-modal instruction paragraph; retrieving a user information voice database based on voiceprint features of the voice instruction data to obtain task associated voice data; instruction information is input into the strategy large model to obtain an action plan; a post-processing task action planning input controller controls a mechanical arm, and a multi-mode input instruction is updated in real time to perceive the latest task state; and performing closed-loop control based on the initial target instruction information and the environment perception information until the task is completed. The task planning and error correction capacity of the mechanical arm is improved through closed-loop control and voice data retrieval based on the large strategy model, and the dynamic adaptive capacity, the autonomous error correction capacity and the multi-mode interaction capacity of the mechanical arm are 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.

Systems and methods for translating natural language to SQL on a custom enterprise data warehouse powered by Generative AI. With an embodiment of the present invention, a natural language question may be converted to a meaningful and accurate database query, e.g., SQL query, relevant to tables existing in an enterprise data warehouse. An embodiment of the present invention is directed to a comprehensive approach of transforming a natural language query to a focused SQL query using domain specific data models across firmwide metadata systems and data systems. In response to a user query, an embodiment of the present invention performs metadata analysis, targeted data retrieval and then SQL generation. An embodiment of the present invention may apply data warehousing standards and guidelines followed in the enterprise and provide a plug-and-play type architecture and solution that is scalable to large warehousing and other systems.

The invention discloses a meteorological service center data visualization and interaction platform, and particularly relates to the field of meteorological data visualization, which comprises a multi-source heterogeneous data acquisition and preprocessing module, a space-time fusion and data enhancement module, a distributed storage and intelligent index module, a dynamic visualization module, an intelligent decision and early warning module and an interaction module. According to the invention, multi-source meteorological data are collected through an API and a protocol, and wavelet transform noise reduction processing is carried out by using an edge computing node; carrying out space-time alignment and fusion, and filling missing data with LSTM; dynamic visualization and interaction are realized by using WebGL (Web Graphics Library) and ARCore / ARKit; the WRF and the Transform are integrated to generate early warning information, and decision suggestions are pushed through a natural language interface; according to the method, the WRF numerical model and the Transform algorithm are combined, accurate meteorological early warning is provided for the user, meanwhile, the geographic space index is constructed based on the GeoHash algorithm, efficient geographic space query and data retrieval are achieved, a real-time feedback mechanism and a multi-dimensional visual view are provided, and the operation process and experience of the user are optimized.

The invention provides a medical large model intelligent inquiry reasoning method and system, and the method comprises the steps: obtaining the input information of a user, and carrying out the processing of the input information, including intention recognition, entity recognition and historical information summarization; sequentially performing pre-retrieval, multi-modal database retrieval and knowledge reordering according to the information obtained after processing; generating an inquiry strategy according to the information obtained after knowledge reordering, and performing information retrieval enhancement generation on the medical large model according to the information obtained after knowledge reordering and the inquiry strategy; and generating content according to the generated medical large model. According to the method, reasoning and replying of symptom description and health problems input by the user are achieved through the generative medical large model and multi-modal data retrieval, the method is suitable for intelligent health management and medical consultation in the medical field, and the intelligent level of medical services and the user experience are effectively improved.

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 relates to an intelligent operation and maintenance method and apparatus based on a knowledge graph and a large model, and an electronic device. The method comprises the steps of collecting multi-source runtime data of a Kubernetes cluster; constructing a knowledge graph with time dimension based on the resource change event, recording termination time in response to graph relationship failure, recording starting time in response to a newly added relationship and not setting the termination time, and associating the entity with the performance index and the log data; responding to the diagnosis request, scheduling a specialized agent by a coordination agent through multi-agent cooperation to retrieve associated information from multi-source data, and iteratively integrating to generate a structured context; and inputting the generated structured context information into a large model reasoning service to output a fault root cause diagnosis and solution. The technical problems that information dispersion and relevance are weak, root cause positioning is difficult and time-consuming, comprehensive context sensing ability is lacked and expert experience is excessively relied on are solved.

The invention discloses a literature semantic search method and system based on elastic search, and relates to data retrieval. The literature semantic search method comprises the steps that vectorization processing is conducted on a noun phrase list by means of a text2vec-based-multilingual model trained based on a CoSENT method; according to the semantic vector, performing approximate nearest neighbor search in a second retrieval module to obtain first candidate data; inputting the query text data into a first retrieval module, and performing keyword matching through a BM25 algorithm to obtain second candidate data; fusing the first candidate data and the second candidate data to obtain third candidate data; a Sequence Matcher algorithm is adopted to calculate character string similarity between expansion words in the third candidate data, a similarity threshold value is set based on the length of the longest common subsequence, duplicate removal is carried out, and fourth candidate data is obtained; and performing weight distribution based on positions and similarity scores on the fourth candidate data, and enhancing the distinction degree of the extension words by expanding a score interval to obtain extension word recommendation list data. According to the method, the accuracy of document retrieval is remarkably improved.

Aspects of the present disclosure provide techniques for enhanced electronic data retrieval. Embodiments include receiving a natural language query and identifying one or more electronic data sources indicated in the natural language query using a named entity recognition (NER) machine learning model trained through a supervised learning process based on training natural language strings associated with labels indicating entity names. Embodiments include determining one or more additional electronic data sources related to the one or more electronic data sources using a knowledge graph that maps relationships among electronic data sources. Embodiments include retrieving data related to the natural language query by transmitting requests to the one or more electronic data sources and the one or more additional electronic data sources and providing a response to the natural language query based on the data related to the natural language query.

The invention relates to the technical field of intelligent voice interaction, in particular to an intelligent voice interaction system and an electronic student identity card, and the system comprises a voice input processing module, a semantic decomposition module, a task allocation module, a logic execution module, a dynamic response module and a voice interaction adjustment module. According to the invention, by analyzing the frequency domain and time domain features of the voice signal, accurately capturing voice details, improving the recognition accuracy, analyzing and recombining semantic content word by word, supporting accurate extraction and task description of complex semantics, analyzing resource consumption and dependency relationship, optimizing a task sequence, and improving the efficiency and adaptability of the system; task execution is combined with data retrieval and content classification, it is ensured that key tasks and associated tasks are carried out in a coordinated mode, uncompleted tasks are dynamically fed back and marked, supplementary information is assembled, dialogue continuity and response naturalness are enhanced, a voice interaction adjustment module analyzes uncompleted instructions and repeated calling, and adaptability to demand changes and service efficiency are improved.

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 discloses a course data intelligent multi-dimensional retrieval system based on deep learning, and relates to the technical field of course retrieval. The course data retrieval platform is in communication connection with a knowledge graph construction module, a user intention analysis module, a user portrait construction module, a personalized recommendation engine module and a retrieval display module, and all the modules are in electric signal connection; the knowledge graph construction module is used for collecting course data from multiple sources and constructing a course domain knowledge graph. According to the natural language processing technology based on deep learning, deep semantics queried by a user can be deeply analyzed, fuzzy or implicit requirements can be understood, limitation of traditional keyword matching is broken through, intent features and entity relationships can be extracted by combining a knowledge graph, specific entities and relationships queried by the user can be accurately mapped, and user experience is improved. Therefore, a more accurate retrieval result is provided, and personalized requirements of users are met.

The invention belongs to the field of data retrieval, and provides a multi-modal scientific data retrieval method and system based on abstract-assisted cognitive enhancement. According to the technical scheme, a multi-modal scientific data semantic representation model based on a large model is constructed, professional domain knowledge and a structure guiding mechanism are combined, and a multi-modal scientific data semantic representation model is constructed; generating a structured abstract containing the key knowledge; and then, on the basis of knowledge such as keywords and description information provided by the structured abstract, a multi-modal scientific data retrieval model guided by directional thinking chain multipath is constructed, multi-dimensional correlation analysis of scientific data is realized through combination of cognitive prompt knowledge enhancement and multi-step dynamic reasoning, and the data resource retrieval performance in the field of scientific data is improved.

The invention provides a knowledge question and answer rapid processing method and system based on artificial intelligence, and relates to the field of artificial intelligence. A multi-modal knowledge graph is constructed, collected multi-source teaching data is fused through a mixed retrieval strategy, and the mixed retrieval strategy comprises semantic retrieval, vector retrieval and metadata retrieval; multi-level question and answer processing is executed based on an RAG enhancement framework, a multi-modal input intention is analyzed, cross-library joint retrieval is performed, and an optimization answer is generated in combination with a teaching scene; distilling the global model to a lightweight TinyBERT architecture, dynamically optimizing question and answer quality through a cognitive reinforcement learning framework, positioning a key document from a comprehensive retrieval list, evaluating an optimized answer, and reconstructing an answer with a key document verification score; according to the invention, the professional skill level of teachers and students in the fields of artificial intelligence and large model application can be improved, and the personalized requirements of teachers and students in teaching, scientific research and innovation courses can be met.

The invention relates to the technical field of artificial intelligence large language models, and discloses a data attribution analysis task processing method, system and device based on a large language model and a storage medium. The data attribution analysis task processing method is applied to data attribution equipment and specifically comprises the following steps that S101, user input is received through a multi-mode input interface, and the user input comprises natural language problems, structured data files or API data streams; by means of the natural language understanding ability of the large language model, the system can directly analyze service problems put forward by a user in a daily term, professional data query languages are not needed, non-technical personnel can conveniently use the system, the data retrieval time is shortened to be within 3 minutes from 30 minutes on average through the automatic SQL query generation technology, the efficiency is improved by 10 times, and the method is suitable for large-scale popularization and application. The system can intelligently identify the database fields corresponding to the business indexes and generate optimized query statements.

Disclosed herein are methods and systems for a training a model for real-time patient diagnosis. A system may include a computer configured to receive audio data and video data of a clinical encounter, the audio data comprising spoken words by an entity and the video data depicting the entity; retrieve clinical data regarding the entity; execute a model using the words of the audio data and the retrieved clinical data regarding the entity as input, the execution causing the model to output a plurality of clinical diagnoses for the entity; concurrently render the corresponding video data and audio data and the plurality of clinical diagnoses via a computing device associated with a user; and store an indication of a selected clinical diagnosis of the plurality of clinical diagnoses responsive to receiving a selection of the clinical diagnosis at the computing device.

The invention discloses a personalized federal confrontation cross-modal hashing method based on double prototypes, which mainly comprises the following steps of: clustering local class-level prototypes uploaded by a client at a server side to obtain a clustering prototype, averaging to obtain an unbiased prototype, and according to gradient change, obtaining an unbiased prototype; generating personalized hierarchical weights for the client network using the super network; the client constructs an adversarial learning process by using approximate hash codes and clustering prototypes of the two modal networks, keeps the consistency between an unbiased prototype and a local class-level prototype, and further embeds the unbiased prototype into a training process of a client model; after local training is completed, all network parameters and local class-level prototypes of the client side are uploaded to the server; and after the last communication round is completed, generating a to-be-retrieved hash code based on the final client parameter, and providing an original data retrieval result according to the original data position information corresponding to the hash code with the minimum distance.

An emergency response assistant system may generate emergency response insights and provide the insights to an emergency responder application for an emergency communications center (ECC), an operations center, or a first responder. The emergency response assistant system may include a data retrieval system and an augmentation and generation system. The data retrieval system may be configured to transform emergency response procedures into vectors that are stored in a vector database. The augmentation and generation system may be configured to perform a vector search of the vector database with an AI model using context from call (e.g., a 911 call) characteristics and external data sources and may be configured to display the results on a user interface of an emergency management application to provide emergency response procedure suggestions to a user of an ECC computing system, an operations center computing system, or a first responder computing device.

The invention discloses a cognitive impairment man-machine interaction method and system based on emotion analysis, and relates to the field of cognitive impairment man-machine interaction, and the method comprises the steps: collecting the physiological information, language information and expression information of a user in real time, carrying out the feature fusion, forming a time series data set, and carrying out the emotion recognition and classification; based on a user emotion recognition classification result, establishing a generative adversarial network to generate man-machine interaction dialogue content matched with the current context and emotion in real time; when it is detected that the emotion recognition result of the user is negative emotion, a cognitive disorder emotion pacifying strategy is retrieved based on big data, emotion pacifying is conducted on the user, and related data are recorded; by analyzing historical related data of negative emotions of a user, an emotion prediction model is constructed, possible emotion changes are recognized in advance, and a man-machine interaction pacifying strategy is adjusted.

The invention discloses a legal supervision clue mining method and system based on full-text retrieval and a large model, and belongs to the field of data collection and data retrieval and large model application. The method comprises the steps that S1, supervision rules and retrieval keywords are sorted; s2, full-text retrieval: carrying out data retrieval by utilizing keywords for supervising thematic sorting and a full-text retrieval system, and collecting all related image-text data in a specified time period from various data sources; s3, information distillation and information filtering; s4, constructing a knowledge base of thematic analysis; s5, searching and sorting the knowledge base; and S6, carrying out intelligent analysis and clue mining on the large model. According to the legal supervision clue mining method based on the image-text electronic data, basic data are collected through automatic keyword full-text retrieval, and valuable legal supervision clues can be mined from massive data through automatic element analysis and dialogue reasoning analysis of a large model, so that the legal supervision clue mining efficiency based on the image-text electronic data is improved.

A method includes obtaining chunks of information and generating training samples for an embedding model using the chunks of information. Generating the training samples includes using at least one large language model to generate training samples in which different ones of the chunks of information are and are not relevant to different potential queries. The method also includes training the embedding model using the training samples. In some cases, the embedding model may represent a retriever model. For example, an input query may be obtained at the retriever model, and the retriever model may be configured to identify a specified number of chunks of information relevant to the input query. One or more of the chunks of information may be provided from the retriever model to a generative model, and the generative model may be used to create a response to the input query.

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.

The invention relates to the technical field of data retrieval, in particular to an information technology retrieval consultation system and method. The method comprises the following steps: acquiring user input data; extracting modal key information of the user input data to obtain multi-modal key semantic information data; performing data preprocessing on the multi-modal key semantic information data to generate standard user input data; performing historical retrieval information retrieval on the standard user input data, and when a historical retrieval record is retrieved, performing accurate portrait construction on the standard user input data to generate a user accurate retrieval portrait; and when no historical record is retrieved, performing retrieval reasoning on the standard user input data to generate a user fuzzy retrieval portrait. By combining multi-modal information extraction, accurate and fuzzy portrait construction, cross-context inheritance, dynamic knowledge fusion and sentiment analysis optimization, the problems of low retrieval precision, incomplete information coverage and poor user experience in the prior art are solved.