7734 results about "Data transformation" patented technology

A computing system is disclosed for transforming document data into schema-conformant structured outputs. The system obtains document data comprising multi-format structured documents and classifies each document by type and class using vector-based modeling and structural feature analysis. An extraction configuration is selected for each document, the configuration comprising machine-executable instructions for parsing based on semantic and layout characteristics. The system extracts semantic data using structured inference, transforms the semantic data into schema-conformant outputs, and validates the outputs using temporal and domain-specific constraints. Validated structured data may be used for downstream processing, visualizations, or optimization based on performance metrics.

The invention provides a knowledge graph generation method and system for science and technology project risk control, and the method comprises the steps: obtaining a multi-source heterogeneous data set of a target science and technology project, converting structured index data into a standard vector sequence through a heterogeneous data fusion mechanism, and converting unstructured text data into a semantic vector sequence; converting the time sequence behavior data into a behavior pattern vector sequence, inputting the three into a risk quantitative evaluation model, generating a risk entity feature matrix and a risk association strength matrix, and determining a node distribution topology of the knowledge graph according to entity feature vectors in the risk entity feature matrix; and according to association strength values in the risk association strength matrix, determining an entity relationship topology of the knowledge graph, generating a dynamic knowledge graph of the target science and technology project, and identifying a potential risk propagation path in the dynamic knowledge graph. According to the invention, the risk identification result has the dynamic characteristic of real-time updating, and the traceability of the multi-dimensional risk characteristic is maintained.

An example operation may include one or more of querying data of a merchant read from a point of sale (POS) system of the merchant and converting the data into an encoding, executing a machine learning model on the input encoding to generate a vector that comprises vectorized values corresponding to latent features of the merchant embedded within slots of the vector, respectively, generating an entry comprising an identifier of the merchant, context of the merchant, and the generated vector, and storing the entry in the feature store.

According to the research and development document processing method and device provided by the embodiment of the invention, unified processing of text, voice and image information is realized by constructing the multi-mode document analysis engine. Different types of data are converted into standardized feature representations through cross-modal preprocessing and a semantic alignment network. The system adopts a deep learning model to identify research and development elements, establishes a multi-modal relation graph, and realizes intelligent extraction and correlation analysis of various types of information in research and development documents. According to the method, the defects of the traditional technology in the aspects of multi-modal information fusion and knowledge system construction are effectively overcome, powerful support is provided for research and development process management and knowledge asset accumulation, and the standardized management level of research and development documents is remarkably improved.

Disclosed in the present invention are a digital image calculation method and system for deformable template-based RGB-D camera multi-view matching. The method comprises the six steps of data acquisition, point cloud data preprocessing, feature point matching, re-registration of deformable templates, calculation of a point cloud data transformation relationship between large-view images, and point cloud fusion. The size of a non-adjacent image matching template is adjusted on the basis of a registration result of adjacent views to achieve correct registration of feature points of non-adjacent view images, thereby improving the matching precision, eliminating the accumulative error of an image set, providing a relatively accurate initial value for subsequent iteration of point cloud fusion, reducing the number of iterations, and implementing three-dimensional reconstruction of images.

The invention discloses a multi-source heterogeneous knowledge graph data fusion method and system, and the method specifically comprises the following steps: S1, collecting data from a plurality of heterogeneous data sources, cleaning the collected data, removing noise data and repeated data, and converting the data in different formats into a unified intermediate format; s2, a semantic model is established, and semantic heterogeneous concepts and relations in different data sources are recognized and aligned through a natural language processing technology and domain ontology knowledge. The invention relates to the technical field of knowledge graph data processing, and the multi-source heterogeneous knowledge graph data fusion method and system effectively reduce the problems of noise, repetition and semantic inconsistency in data through data cleaning, semantic alignment and conflict resolution, and ensure the accuracy and consistency of fused data, thereby improving the quality of a knowledge graph and improving the reliability of the knowledge graph. Reliable knowledge support is provided for application in the fields of medical treatment and the like.

Method and system for analyzing software or firmware of computing systems to assess security properties includes loading predicate device input data including characteristics about predicate devices; translating predicate device input data into predicate device model data describing characteristics or dependencies of the predicate device input data relevant to the analysis; determining digital twin configuration data used to configure digital twin; loading the digital twin configuration data onto the digital twin; storing configuration data in the memory; instructing the digital twin to configure itself to implement the loaded digital twin configuration data; determining security analysis to be carried out on the digital twin; simulating the predicate device; executing security analysis on the digital twin; generating output data describing the result of execution of the security analysis; storing output data pertaining to the result; and determining if the result satisfies a predetermined condition, and if so, executing action corresponding to the result.

The present disclosure provides a method and system for orchestrating automated data processing and transformation. A centralized orchestrator receives a request to process a client dataset and initiates a data ingestion process to obtain sample data. A semantic analysis module analyzes the sample data to determine semantic types of data fields. A transformation module generates data transformation instructions based on the determined semantic types. The orchestrator deploys a data processing pipeline to a client-controlled environment and configures privacy preservation parameters to identify and obfuscate potential personally identifiable information. The pipeline applies the transformation instructions and privacy parameters to the dataset. A configuration module determines data storage configurations for the transformed dataset. The transformed dataset is stored according to the configurations in a client-controlled or cloud environment. A machine learning module generates a model based on the transformed dataset, which is stored in a model repository accessible to the client.

A computer-implemented method for evaluating and optimizing a large language model (LLM) includes receiving input data for a large language model; transforming the input data into a standardized format compatible with a multi-metric evaluation framework; applying a set of evaluation metrics to the transformed data, wherein the set of metrics comprises a hallucination metric, a groundedness metric, a relevance metric, a recall metric, a precision metric, a consistency metric, and a Coherence metric; generating an error function that quantifies an overall performance of the LLM, wherein the error function takes as input parameters of the LLM and incorporates the set of evaluation metrics to produce an error score; minimizing the error function wherein a lower error score indicates better performance of the LLM; and outputting an improved LLM with improved parameters.

The invention discloses a knowledge conversion and fusion processing method and system for massive power grid operation data, and the method specifically comprises the steps: obtaining the attributes, including the alarm type, timestamp and severity, of equipment granularity based on alarm event data collected by a power distribution automation terminal, and carrying out the data cleaning and standardization processing, converting the multi-source heterogeneous alarm data into uniform event granularity representation; fusing the alarm event data and the operation event data, carrying out space-time alignment and causal association on the two types of events based on timestamps and equipment ID attributes, constructing a cross-data-source event semantic link network, and carrying out association analysis on a semantic relationship between the events; and according to a fault diagnosis result, historical records related to fault processing are extracted from the operation event knowledge base, similar fault processing modes are matched, and a specific fault processing scheme is generated in combination with factors of severity and influence range of the current fault.

The present invention provides a privacy-enhanced structured data simulation and generation method and system. The method comprises: step 1, a data conversion phase: performing normalization preprocessing on data; step 2, a probabilistic graphical model construction phase: on the basis of a Bayesian form, constructing the posterior distribution for variational inference from the data having undergone normalization preprocessing in step 1, obtaining an association relationship between the features of structured data by using a Stein variational gradient descent method, and when introducing differential privacy noise, using a Monte Carlo estimation algorithm to automatically obtain the amount of noise that needs to be added for each update step; and step 3: a data generation phase: using the association relationship obtained in step 2 as a metric set to generate more accurate simulation data than real data. The beneficial effect of the present invention is that: the method of the present invention avoids gradient clipping when applying DP-SGD, thereby avoiding the selection of clipping parameters and reducing the adverse effects of gradient clipping on an inference process.

The invention provides a non-performing asset cross-scene question and answer framework based on a knowledge graph, and relates to the field of artificial intelligence and legal science and technology, and the framework comprises a framework, a knowledge fusion layer is provided with a multi-source data access module which is used for obtaining heterogeneous data of a law and regulation database, a judicial case library, an enterprise financial statement system and an asset transaction platform; configuring a legal entity analysis engine, and converting the unstructured legal text into an entity-relationship-attribute triple which can be represented by a knowledge graph based on an ontology mapping technology; setting a financial data standardization component, and converting the financial data in different formats into unified semantic representation through a predefined financial index mapping rule; the knowledge fusion layer of the framework can integrate multi-source heterogeneous data such as laws and regulations, financial data, business processes and the like through a multi-source data access module, a legal entity analysis engine, a financial data standardization component and the like.

A system and method for a federated deep learning platform utilizing homomorphically-compressed and encrypted data. The system comprises multiple client devices, each with a local dataset, and a central server hosting a deep learning core. Client devices convert local data into codewords, which are also homomorphically encrypted. The central server processes these encrypted codewords without decryption, preserving data privacy. The platform supports at least two architectural variants: a conventional Transformer trained on codewords, and a Latent Transformer operating on latent space vectors. Both variants eliminate the need for embedding and positional encoding layers. The system aggregates encrypted model updates from clients, enabling collaborative learning while maintaining data confidentiality. Additional features comprise differential privacy implementation and adaptive federated optimization techniques. This innovative approach allows for efficient, privacy-preserving distributed learning across diverse datasets, addressing key challenges in federated learning such as data heterogeneity, non-IID distributions, and communication efficiency.

The invention discloses a large-model complaint intention recognition method based on sentiment analysis, and the method comprises the steps: obtaining call voice data of a customer, and converting the call voice data into text data; preprocessing the text data, and removing noise and marking components; performing emotion feature analysis on the text data, extracting an emotion feature value, and generating an emotion vector; the emotion vectors and the text data are input into a large model together, and the large model combines the emotion feature values and context semantics to generate intention feature vectors; constructing an emotion-intention state vector, inputting the emotion-intention state vector into an asynchronous dominant actor commentator algorithm model, and generating a corresponding complaint intention probability value; judging a complaint intention probability, and generating risk early warning; and preferentially distributing high-risk customers and responding to customer demands. Through combination of voice data preprocessing, text semantic feature extraction, emotion intensity quantitative analysis and a multi-modal fusion algorithm and efficient risk assessment based on an asynchronous dominant actor reviewer model, the early warning and response capabilities of customer complaint risks are significantly improved.

A data processing method and system based on Flink unified stream and batch processing, and a device and a medium, which relate to the field of big data processing. The method comprises: establishing an SQL statement construction rule on the basis of data elements specified in an SQL file standard and a logic relationship between the data elements, so as to perform SQL statement construction on a service to be performed, and obtain a query statement file, wherein the data elements comprise a source table SQL, a destination table SQL and a data conversion SQL; submitting configuration parameters of the SQLs and the query statement file to a Flink cluster, so as to obtain corresponding data processing task information; and the Flink cluster receiving a target data source table on the basis of the data processing task information, processing the data source table on the basis of a predetermined processing mechanism, and then writing corresponding data into a data destination table. The present invention is applicable to different data processing tasks without the data read and write modules in the present invention being rewritten, and it can be ensured that data is executed at least once during a running process of a task.

A system for sentiment analysis in language texts based on deep learning, consisting of: a preprocessing unit configured to receive and normalize raw text input from various sources, with the unit performing tokenization, punctuation removal, text stemming, and standardization to prepare text data for analysis; an embedding unit that is operationally connected to the preprocessing unit and is configured to convert normalized text data into numerical representations, wherein the embedding unit also contains pre-trained language embeddings to capture semantic relationships in the text and dynamically selects embeddings based on the source and linguistic context of the text data; a sentiment analysis neural network (SANNet) operationally connected to the embedding unit, comprising layers of a convolutional neural network (CNN) for local pattern recognition and layers of a recurrent neural network (RNN) configured to capture sequential dependencies within text data, with the SANNet also including an attention mechanism to dynamically weight word relevance based on contextual meaning, and the SANNet being trained to interpret and classify complex sentiment patterns in the text; A context module integrated into the neural network for mood analysis. The module includes a bidirectional transformer layer for the simultaneous processing of forward and backward word dependencies, enabling the system to capture complex language structures, including sarcasm, irony, and mixed emotions, and thus perform an accurate mood classification; an output interpretation unit that is operationally connected to the neural network for sentiment analysis and is configured to convert probability-based classification results into human-readable sentiment categories with associated confidence levels, wherein the output interpretation unit also provides interface compatibility for external applications, thus enabling direct integration of sentiment classifications; A continuous training module connected to the neural network for sentiment analysis. The module is configured to use real-time user feedback and sentiment accuracy metrics to retrain the SANNet, thus ensuring adaptive learning for evolving language patterns and domain-specific contexts; a GPU / TPU-optimized processing card that is operationally connected to the neural network for sentiment analysis and is configured to accelerate deep learning calculations within the system, thereby enabling high-throughput, real-time sentiment analysis.

A medical image disease diagnostic system that is included in a clinical medical diagnosis workflow. In one embodiment, a user interface is configured to assess a medical imaging application that provides for viewing, analyzing, and annotating of medical images and medical non-image data and medical training data. A processor includes a pre-trained subsystem configured to generate AI pre-trained models based on the medical image and medical non-image data, a training data generation subsystem configured to generate the medical training data, and a medical image model training subsystem configured to transform the medical image and medical non-image data into the medical training data. The medical image model training subsystem is further configured to train or generate the pre-trained AI models based on the medical training data, and a model drift subsystem is configured to determine accuracy of the pre-trained AI models. A diagnostic reporting subsystem configured to generate clinical diagnostic reports.

The invention discloses an intelligent driving track prediction method, device and equipment and a storage medium, relates to the technical field of intelligent driving, and discloses an intelligent driving track prediction method which comprises the following steps: acquiring environment laser radar data, environment radar data and environment image data; converting the environment laser radar data, the environment radar data and the environment image data into aerial view features; performing feature alignment on the aerial view features based on a sensor field angle identifier to obtain multi-modal sensing features; determining a candidate trajectory according to the multi-modal sensing features; and determining a target trajectory from the candidate trajectories according to a target cost function to complete intelligent driving trajectory prediction. According to the scheme, the complex driving environment can be accurately understood in the intelligent driving process so as to predict the optimal driving track.

The invention discloses a multi-source heterogeneous data dynamic protocol security exchange adaptation system, which comprises a protocol analysis engine, a data encryption module, a data format standardization engine and a routing strategy engine, and is characterized in that the protocol analysis engine is respectively connected with a data source, the data encryption module and the data format standardization engine; the data format standardization engine is connected with the routing strategy engine, and the routing strategy engine is connected with the nodes. The invention discloses a multi-source heterogeneous data dynamic protocol secure exchange adaptation method. Comprising the following steps of protocol analysis and data conversion, data encryption and sensitive data desensitization, integrity verification and anomaly detection, routing strategy and intelligent scheduling, data distribution and storage, and dynamic extension and protocol adaptation, and the dynamic conversion of different protocol data ensures that various types of data can be smoothly interacted. Meanwhile, an advanced data security enhancement technology is integrated, multiple protections such as encryption and authentication are carried out on transmitted and stored data, and the data security is effectively improved.

The present invention provides a method for impact analysis of port construction on a coastal ecotone based on remote sensing data, which belongs to the technical field of remote sensing application. The method quantifies landscape data and satellite image data, and then converts the data into intuitive images to observe the spatio-temporal change of the coastal ecotone after port construction. The method includes: step 1: obtaining remote sensing image data of a research region; step 2: preprocessing the remote sensing image data to obtain processed images; step 3: establishing an evaluation system of human disturbance indexes; and step 4: generating a spatio-temporal distribution map of regional disturbance indexes. The present invention provides a method capable of quantifying the impact range and the impact degree of the port construction factor on the coastal ecotone, provides an idea for reducing the impact of port construction on a surrounding environment.

Disclosed is a digital image calculation method and system for RGB-D camera multi-view matching based on a variable template, the method includes six steps: acquiring data, preprocessing point cloud data, performing feature point matching, re-registering a variable template, calculating point cloud data transformation relationships among large-view images, and performing point cloud fusion. A size of a non-adjacent image matching template is adjusted based on registration results of adjacent angles of view, and correct registration of feature points of images from non-adjacent angles of view is accordingly achieved, which improves matching accuracy, eliminates cumulative errors in image sets, and provides more accurate initial values for subsequent iterations of point cloud fusion, such that the number of iterations is reduced, and three-dimensional reconstruction of images is implemented.

A computer-implemented method includes converting tabular data to a text representation, generating metadata associated with the text representation of the tabular data, outputting one or more natural language data descriptions indicative of the tabular data in response to utilizing a large language model (LLM) and zero-shot prompting of the metadata and text representation of the tabular data, outputting one or more summaries utilizing the LLM and appending a prompt on the one or more natural language data descriptions, selecting a single summary of the one or more summaries in response to the single summary having a smallest validation rate, receiving a query associated with the tabular data, outputting one or more predictions associated with the query, and in response to meeting a convergence threshold with the one or more predictions generated from the one or more iterations, output a final prediction associated with the query.

The invention relates to the technical field of oil field databases, and discloses a dynamic data management method, device, equipment and medium for an oil and gas field database, and the method comprises the steps: docking multi-source data of the oil and gas field database, the multi-source data comprising a shaft sensor real-time monitoring data flow, geologic modeling gridding structure data and an equipment management tree coding table; the method comprises the following steps: performing abnormal value cleaning and timestamp alignment on real-time monitoring data flow of a shaft sensor, converting geologic modeling gridding structure data into a reservoir unit set with a coordinate system label, extracting a set membership chain of well IDs and equipment IDs in an equipment management tree-shaped coding table, generating an identifier system with a unified coding format, and storing the identifier system in a database; the identifier system comprises a well identifier, a reservoir unit identifier and a device identifier; generating a structured data pool based on the identifier system; and when the data pool is updated, sending a change instruction to a plurality of subsystems of the oil and gas field database, and updating each subsystem based on the change instruction.

The invention discloses an unmanned aerial vehicle navigation reasoning method and system based on visual perception and a large language model, and belongs to the field of unmanned aerial vehicle navigation and artificial intelligence, and the method comprises the steps: collecting an image of a target area through a camera carried by an unmanned aerial vehicle; pixel-level perception is carried out on the image through a pre-trained visual perception model, and visual information is converted into structured data; converting the structured data into key statements which can be processed by a large language model by adopting retrieval enhancement generation and combining with a predefined knowledge base; adopting a prompt project and thinking chain technology, and outputting a navigation instruction by the large language model according to the key statement and the current task; when a target of an unknown type is encountered, an active learning process is started, and real-time updating of an edge end knowledge base is realized through human intervention; according to the method, the problems of understanding and decision making of the unmanned aerial vehicle on a dynamic scene in a complex environment are effectively solved, data-driven intelligent support is provided for autonomous flight of the unmanned aerial vehicle, and the method has the advantages of being high in real-time performance, high in environmental adaptability and good in decision making reliability.

The invention relates to a large model jailbreak attack detection method, and the method comprises the steps: S1, building a jailbreak attack detection model based on a hybrid expert model and a Transform architecture, the jailbreak attack detection model comprises a multi-layer MoE-Transform structure, and training the jailbreak attack detection model through employing a positive unmarked learning method; s2, acquiring input text data, and converting the text data into vector representation; s3, inputting the vector representation into a trained jailbreak attack detection model, and outputting a high-level feature vector through a multi-layer MoE-Transform structure; s4, the high-level feature vector passes through a full connection layer, and the prison break attack probability is output; and determining a jailbreak attack condition based on the jailbreak attack probability. According to the method, the accuracy and efficiency of prison break attack detection are remarkably improved, real-time defense of large-model prison break attacks is ensured through automatic detection, and potential safety risks are reduced.

The invention relates to the technical field of rock mechanics, and discloses a rock three-dimensional reconstruction method and system based on multi-source information fusion, and the method comprises the steps: obtaining and preprocessing data, carrying out the spatial feature learning of a fusion feature vector through a 3D-CNN network, and constructing a three-dimensional voxel model of rock microscopic damage; converting the fused image data into a point cloud model of the underground cavern surrounding rock structure by adopting a three-dimensional reconstruction algorithm based on point cloud, and constructing a digital twin framework of the underground cavern surrounding rock structure based on an implicit surface reconstruction algorithm; feature parameters output by the three-dimensional voxel model and the digital twinning framework are used as input, and the optimal supporting opportunity and supporting parameters are output through an LSTM-CNN fusion model; in the underground engineering construction process, surrounding rock deformation data are collected in real time, and a supporting scheme is adjusted in real time through a depth deterministic strategy gradient algorithm; according to the method, the scientificity and timeliness of support design under complex geological conditions can be improved.

The invention relates to the technical field of industrial internet data acquisition, in particular to a data acquisition method and system based on an industrial internet operating system, and the method comprises the following steps: S1, detecting and recognizing data sources of a plurality of industrial devices and sensors; s2, collecting original data from a data source in real time, and preprocessing the original data; s3, distributing part of calculation tasks to a plurality of edge nodes; s4, storing the data in a distributed database or cloud storage in a classified manner; s5, performing fragmentation processing on the data in the cache; s6, performing data synchronization and consistency verification; and S7, converting the data into a corresponding format. According to the invention, by implementing efficient data fragmentation processing, a dynamic storage strategy and secure data consistency verification, the processing speed and storage efficiency of the industrial internet data acquisition system and the security and integrity of data are remarkably improved, and the requirements of high efficiency and high reliability of modern industrial production are effectively supported.

The invention is suitable for the technical field of recruitment portraits, and provides a recruitment talent portrait generation method and system based on multi-dimensional information, and the method comprises the following steps: collecting the resume information of candidates; performing data cleaning and data conversion on the resume information; performing feature extraction, analyzing candidate online behavior data based on a natural language processing technology, and extracting behavior patterns and interest points; performing model training and evaluation based on historical resume data to obtain a talent portrait model; the resume information, the behavior modes and the interest points of the candidates are input into a talent portrait model, candidate portraits are obtained, and the candidate portraits comprise skill ability evaluation, occupational development potential and culture adaptation degree; and providing personalized vocational development suggestions and post matching recommendations according to the candidate portraits. According to the method, through feature extraction and machine learning model training, a detailed talent portrait is generated, the scientificity of recruitment decision making is improved, suitable candidates are rapidly identified, and vocational suggestions are provided for the candidates.

The invention relates to the technical field of data acquisition, and discloses a multi-protocol extensible data acquisition system architecture and method with a unified interface standard, and the architecture comprises a data source management module which is used for storing data source configuration information and distributing protocol identifiers; the protocol adaptation module comprises an analysis unit and a matching unit and is used for realizing data format conversion and protocol compatibility verification; the data conversion module is used for generating target data through format conversion and semantic mapping; the data verification module and the anomaly detection module are used for comparing and monitoring data integrity based on an integrity algorithm and a threshold value; the data quality monitoring module and the early warning module are used for comparing and evaluating data quality through a consistency model and a threshold value; and the result output module transmits the early warning information to a target system. The method comprises the steps of data source configuration, protocol adaptation, data conversion, integrity and quality monitoring, early warning and the like. The system expansibility and the data reliability are improved, and the method is suitable for multi-scene data acquisition.

The invention discloses an interface parameter extraction method and device based on slot filling and a medium, and relates to large model application. The method comprises the steps that semantic analysis is conducted on natural language query through a pre-trained large language model, an intermediate parameter set containing intention types and slot filling parameters is generated, and accurate conversion from natural language parameters to structured interface specifications is achieved through multi-stage standardization processing; based on a dynamic matching mechanism of parameters and interface metadata, an interface calling chain including parallel calling, transaction compensation and data conversion nodes is constructed, and a multi-source aggregation data set is generated through cross-interface data verification and space-time alignment processing; and finally, in combination with dynamic template selection and semantic generation rules, outputting a multi-modal interaction report fusing the structured visual component and natural language interpretation.