542 results about "Data consolidation" patented technology

The provided are a price elasticity analysis and prediction method and model based on deep learning. The model consists of a CNN layer and an RNN layer. The method comprises the following steps: S1, collecting historical data and merging the historical data into a multi-dimensional time series dataset; S2, extracting sentiment data and trend data from market news and social media; S3, inputting the data obtained into CNN for data preprocessing and feature extraction; S4, inputting the feature extracted by CNN into RNN for time series analysis; S5, training and optimizing model: using Adam algorithm to adjust the learning rate adaptively, and combining the momentum method and RMSProp algorithm to improve the generalization ability and prediction accuracy of the model. The provided combines the advantages of CNN and RNN, which can understand and predict the complex relationship between price and market behavior more comprehensively and accurately.

An AI-driven centralized orchestration system (100) with MCP protocol for real-time compliance and risk data management, including: a. a centralized integration and orchestration platform configured to connect heterogeneous enterprise IT systems through standardized API connections and execute automated workflows; b. a variety of domain-specific artificial intelligence (AI) agents that interface with IT service management (ITSM), vulnerability management, and endpoint and asset management platforms for data collection, analysis, and assessment; c. a Multi-Agent Communication Protocol (MCP) layer that enables structured communication, negotiation and coordination between AI agents in real time; d. a data consolidation module configured to aggregate, standardise and align heterogeneous data into a unified repository using machine learning models; e. a compliance reporting module for dynamically generating and distributing audit-ready compliance reports based on AI-analyzed data and triggered workflows; f. an alerting module configured to deliver context-dependent predictive notifications of compliance violations or risk anomalies through various communication channels; g. a predictive dashboard module capable of displaying compliance status, risk metrics, and proactive insights in real time via AI-driven visualization tools; i.e., where the orchestration platform, AI agents, and MCP layer together enable automated, scalable, and proactive compliance and risk actions.

In various examples, a framework is or provides an end-to-end solution that includes multi-sensor capture, data processing, inferencing, synchronization, alignment, and 3D rendering for multi-modal perception fusion pipelines. A multi-modal perception fusion pipeline may include a mixer, an aligner, an inference environment, and a multi-view renderer. The mixer may merge sensor data from different data sources into a single HashMap frame. The aligner may use calibration data for sensor-to-sensor coordinate transformations. The inference environment may receive multi-modality data and use custom preprocessing and custom postprocessing to generate inference results. The renderer may generate different sensor data renderings. The framework may include an application that uses configuration data to generate or configure a custom multi-modal perception fusion pipeline. The inference environment may access inference models using a uniform inference interface and support remote inference, allowing the pipeline to become an API client of the inference models.

Embodiments are directed to a file system that include object stores. An object store for write requests may be provided. Write ahead log (WAL) entries that include data blocks may be generated. A WAL object may be generated based on the WAL entries and stored in the object store. An in-memory overlay may be updated to associate the data blocks with the WAL object. A checkpoint operation may be executed to: generate an index object that includes index entries that associate other data blocks with data objects stored in the object store; update the index object to include index entries that associate the data blocks with the WAL object; store the updated index object in the object store; update the in-memory overlay to remove the association of the data blocks and the WAL object and update the in memory WAL to remove records of successfully checkpointed WAL objects.

The invention relates to the technical field of data acquisition, in particular to a multi-source heterogeneous bus data parallel acquisition recording method and system, and the method comprises the steps: initializing a task period and a maximum sampling period; scheduling the tasks in the task queue based on the task cycle, setting a time step length and marking schedulable tasks; setting sampling channels according to the number of schedulable tasks and distributing the sampling channels to sampling threads; packaging the acquired data into an acquired data packet and aligning by taking a timestamp as a reference; offset calculation and compensation are carried out on the collected data packet; controlling a data acquisition thread to start according to the data capacity and the sampling frequency; the time difference and the content similarity of adjacent data packets are detected, and intelligent data merging is executed; storing the processed data packet in real time; through the adaptive task scheduling and precise time alignment technology, efficient parallel acquisition and precise recording of heterogeneous bus data are realized, and the synchronism, integrity and processing efficiency of data acquisition are remarkably improved.

The invention discloses an MQTT message transmission optimization method and system. The method comprises the steps of analyzing a theme, extracting a device type, a data feature and a geographic position triple, calculating a hash value, and mapping a device to a specified Broker fragment cluster node to generate a fragment mapping table; processing the equipment data in the edge domain in the fragment mapping table through an edge calculation layer, removing invalid data according to a preset rule, merging the equipment data in the same fragment node, and embedding a fragment node ID for an aggregation message generated after merging; identifying a fragment node ID and routing to a target fragment node, positioning a corresponding shared memory pool, and writing the message into the shared memory pool; and responding to a direct access request of the client, so that the client directly accesses the data from the shared memory pool through the user mode network stack. According to the method, the problem of uneven load is effectively solved, multiple times of state switching in the data transmission process is avoided, and the MQTT message transmission efficiency is improved while the transmission cost is reduced.

A decision support system and a computer-implemented method of enterprise decision support include a data consolidation module, domain-specific machine learning models, an enterprise decision intelligence model, and a user interface layer. The data consolidation module collects data from both internal and external data sources. The domain-specific machine learning models generate decisions based on the collected data. The enterprise decision intelligence model integrates real-time trends and the decisions to provide context-aware recommendations. The enterprise decision intelligence model maintains a decision graph that connects decision variables of the domain-specific machine learning models in a causal relationship, with the domain-specific machine learning models interacting as an interconnected network. The decisions are influenced by affects of decision variables from other domain-specific machine learning models. The user interface layer facilitates interactive decision-making by way of the enterprise decision intelligence model and visualizing the recommendations.

The embodiment of the invention provides a data conflict automatic solution method and device, electronic equipment and a medium, and the method comprises the steps: automatically recognizing a data conflict through text comparison and semantic analysis; based on a rule base and a reinforcement learning algorithm, dynamically selecting an optimal conflict resolution rule based on the identified data conflict, and executing the conflict resolution rule; selecting an optimal version to be executed according to the conflict resolution rule, carrying out data merging, and storing key information of conflict data; under the condition that the integrity of AI language large model training data is guaranteed, redundant data is removed from the merged conflict data, and incremental updating is carried out.

Embodiments are directed to a file system that include object stores. An object store for write requests may be provided. Write ahead log (WAL) entries that include data blocks may be generated. A WAL object may be generated based on the WAL entries and stored in the object store. An in-memory overlay may be updated to associate the data blocks with the WAL object. A checkpoint operation may be executed to: generate an index object that includes index entries that associate other data blocks with data objects stored in the object store; update the index object to include index entries that associate the data blocks with the WAL object; store the updated index object in the object store; update the in-memory overlay to remove the association of the data blocks and the WAL object and update the in memory WAL to remove records of successfully checkpointed WAL objects.

The invention discloses an airport terminal security check passenger number hourly prediction method comprising the following steps: 1) preprocessing security check passenger flow characteristic data and terminal historical security check passenger data, and merging the preprocessed security check passenger flow characteristic data and terminal historical security check passenger data into a passenger security check number prediction data set; 2) constructing an NBMT-OneNet-based hourly security check passenger number prediction model; 3) training the hourly security check passenger number prediction model by using the passenger security check number prediction data set; and 4) obtaining security check passenger data and security check passenger flow characteristic data of the terminal to be predicted in the past T time period, and inputting the data into the hourly security check passenger quantity prediction model to obtain security check passenger data in the future T'time period. According to the characteristics of hourly airport security check data, the N-BEATS model and the MTGNN model are used for capturing the complex correlation between the time sequence trend and the variable, and the accuracy of the prediction result is effectively improved.

The invention provides a component-level collaborative editing control method, which is applied to a multi-user collaborative editing control system, and the system comprises a plurality of front-end engines and a back-end server. A front-end engine obtains user editing operation data and a rear-end real-time version snapshot, component structure difference comparison is carried out, and a component operation list is generated; and performing component conflict judgment based on the operation list, merging and editing operation data according to a conflict judgment result and a preset conflict resolution strategy, generating processed version snapshots, sending the processed version snapshots to a rear end, storing the processed version snapshots by a rear-end server, and sending the processed version snapshots to each front-end engine. Compared with the prior art, the method has the advantages that the data transmission quantity and the load of the rear-end server are reduced by a lightweight architecture through the front-end component level difference comparison and the preset conflict resolution strategy, the rear-end server does not need to be frequently requested for conflict resolution and data merging, the response speed and the collaborative editing efficiency are remarkably improved, and the user experience is improved. And better user experience is brought to the user. The system has the same beneficial effects.

The invention discloses a nursing scene data enhancement and generation method for intention recognition model training, and belongs to the technical field of artificial intelligence and smart old-age care. The method aims at solving the problems that in the prior art, high-quality nursing scene training data is deficient, and the obtaining cost is high. According to the core technical scheme, the method comprises the steps that firstly, a staring sequence and other context information (such as time, place and physiological signals) of a user are processed through a multi-modal information fusion model, and a structured initial situation vector is generated; secondly, inputting the vector into a scene generation model combined with a nursing knowledge base, and automatically generating a batch of basic nursing scene data with intention labels; key points are that a data enhancement module is introduced, and a plurality of innovative strategies such as situation element disturbance, virtual physiological data synthesis, gaze path variation and virtual scene deduction are adopted to deeply process basic data, so that the diversity and complexity of a data set are greatly enriched; and finally, combining the basic data with the enhanced data to construct a final comprehensive training data set. According to the method, large-scale and high-fidelity training data can be generated in a low-cost and high-efficiency manner, and the accuracy and robustness of the intention recognition model in a real nursing environment are remarkably improved.

The invention provides a multi-modal evolutionary knowledge injection method and system, and the method comprises the steps: obtaining basic dynamic multi-modal evolutionary knowledge through automatically and continuously collecting network dynamic update news events and object entity knowledge, generating an evolutionary knowledge text description abstract data set, and eliminating abnormal image data through clustering operation. Dynamic clustering multi-modal evolution knowledge is obtained; constructing a multi-modal evolution knowledge data set, and carrying out analysis and evaluation on the multi-modal evolution knowledge data set; training the multi-modal intelligent model through the target evolutionary knowledge, verifying the task performance improvement degree of the multi-modal intelligent model and the learning ability of the multi-modal intelligent model to the target evolutionary knowledge, and constructing a knowledge injection tuning multi-modal intelligent model; and merging the data after knowledge enhancement with the data before knowledge enhancement, performing knowledge enhancement on the knowledge injection adjustment and optimization multi-modal intelligent model, merging the knowledge enhancement and injection into collaborative adjustment and optimization, performing collaborative enhancement on the knowledge injection adjustment and optimization multi-modal intelligent model, and performing network dynamic data knowledge enhancement collaborative accurate reasoning.

The invention discloses a multi-source data merging method and merging equipment based on rule chain configuration, and relates to the technical field of data fusion. In the method, merging equipment generates a structured configuration file through a visual configuration interface, and decouples a variable data source association relationship and a field mapping rule from a program code, so that a user can dynamically define a data merging task in a visual manner without modifying and redeploying a bottom program code, and the user experience is improved. And the execution triggering condition of each data source node is determined through the directed acyclic graph execution plan, so that the data processing tasks with the dependency relationship can be executed in series according to the dependency relationship, and the data processing tasks without the dependency relationship can be executed in parallel, thereby improving the merging efficiency of the multi-source data.

The invention relates to an intermediate result storage and transparent replacement method and device for an asynchronous materialized view and electronic equipment, and the method comprises the steps: designing a storage structure of the materialized view, and obtaining an asynchronous incremental materialized view with a prepolymerization storage structure; when new data are inserted into the basic table, the asynchronous materialized incremental view is updated by using increment, and preset specific data are merged in the updating process to obtain a merged view; and rewriting query logic, and transparently rewriting the original query into a materialized view in combination with the asynchronous incremental materialized view. According to the method, through the design of a storage structure of the asynchronous incremental materialized view, a rewriting method for keeping query semantics and optimization of incremental data merging in the asynchronous incremental materialized view, the real-time query performance is effectively improved, and meanwhile the expandability and flexibility of the system are kept.

The invention provides a data evaluation method and device based on historical local anomalies, equipment and a medium. The method comprises the following steps: performing data preprocessing on historical data in environmental monitoring, calculating a k-neighborhood distance, a reachable distance, a local reachable density and a local anomaly factor, and generating reference density distribution information; processing the reference density distribution information, merging test data points with historical data one by one to calculate an LOF value, screening out potential abnormal samples in combination with a set threshold, and generating potential abnormal sample information; for potential abnormal samples, Z-Score is calculated according to feature dimensions, and abnormal index information of each dimension is generated in combination with a set threshold value; processing the potential abnormal sample information and the abnormal index information of each dimension, marking a sample abnormal state and positioning an abnormal source index, and generating a sample abnormal state mark and abnormal source index positioning information; and processing the sample abnormal state mark and the abnormal source index positioning information to generate abnormal information of the environmental data.

The invention discloses a short burst SOQPSK carrier synchronization method based on an RPT-Net network. The short burst SOQPSK carrier synchronization method comprises the following steps: preprocessing a signal, and merging time domain data of the signal and quartic data into input data; a multi-level residual convolutional network is adopted to extract cross-symbol local phase features, fine phase changes in SOQPSK signals are captured through layer-by-layer stacked convolution operation, the gradient degradation problem of a deep network is relieved in combination with a residual connection mechanism, and the local characterization capacity for phase jump and frequency offset disturbance is enhanced; through a phase perception position coding module, the time domain signal is converted into a complex number form, an instantaneous phase is extracted, orthogonal basis coding is constructed to represent phase change, and deep fusion with position coding is carried out; a Transform coding layer is introduced, a multi-head self-attention mechanism is utilized to capture a long-distance symbol dependency relationship, global phase consistency constraint is optimized, long-term influence of frequency offset on signals is captured, and time sequence error propagation is effectively inhibited.

The invention provides a knowledge question-answering method and device based on a large model and a medium, and relates to the technical field of knowledge questions.The method comprises the steps that a data query period corresponding to a question text is obtained through a first large language model; if the duration of the data query time period is smaller than the preset duration, determining a target operation and maintenance tool from a plurality of preset operation and maintenance tools through a second large language model; controlling the target operation and maintenance tool to perform data acquisition, and taking the acquired data as intermediate data corresponding to the target operation and maintenance tool; performing data compression on the intermediate data based on the character number of the intermediate data to obtain target data; merging the target data into the context information, and obtaining an answer text according to the context information and a specified large language model after merging is completed; according to the method, input overflow, model reasoning failure or response delay caused by too large data volume or exceeding of the context length limit of the large language model can be avoided, the stability of answer generation is ensured, and the user experience is improved.

The invention discloses a numerical simulation method for a river water and sediment transportation process based on a multi-GPU parallel framework. The method specifically comprises the following steps: dividing a calculation region into triangular grid calculation regions with the same number as GPUs; the variables are initialized; creating two CUDA flows to control parallel calculation of the two GPUs, and storing data of each river channel into the corresponding GPU; directly carrying out data communication between the GPUs; in each GPU, calculating a source item and flux of each triangular grid to obtain a water depth value, and calculating a water level value of each grid according to the water depth; according to the obtained water level value, water level result data calculated in each GPU are stored in a CPU to complete water level data merging; and calculating to obtain the water level values of each river reach and the outlet section of the river at each moment. According to the river sediment transportation process simulation method based on triangular grid multi-GPU parallel computing, the water and sediment transportation process of the river area can be efficiently simulated, and the water level value of the section can be rapidly predicted.

The invention provides a large-scale feature data storage and query method. The large-scale feature data storage and query method comprises the following steps: S1) feature data storage: writing real-time feature data into an original column cluster of HBase and retaining a preset number of historical versions; s2) regularly merging historical data: regularly merging historical version data in the original column cluster through a batch processing task, and writing the merged data into a new summary column cluster; s3) feature data query: when feature data is queried, preferentially reading data from the summarized column cluster, and if the data is not found, returning to the original column cluster for query; and S4) dynamic scheduling and data cleaning: dynamically adjusting a feature data merging strategy according to the access frequency of the feature data, and regularly cleaning out-of-date data.

The invention relates to the technical field of data processing, in particular to a cloud platform data analyzing and processing system based on front-end segmentation, which comprises the steps of synchronously displaying fields and paging information to construct export parameters, cloning rendering data to establish a running state, monitoring page turning change to generate buffer content, and segmenting and packaging buffer data according to a memory state. And pushing the data to the local, rolling back the page structure, and completing the export of the process ending identifier. According to the method, export parameters are constructed by synchronously searching fields, header structures and paging numbers; a data clone structure is established in combination with field mapping and paging tracks; field changes are monitored to generate buffer contents; paging data are split according to memory occupation and packaged into local caches; and pushing data to the local and rolling back a display structure to support key links of export processes such as field tracking, memory control, data merging and page recovery.

Systems, methods, and computer program products for using machine learning to determine whether to dispute a chargeback request are provided. A dispute processing system receives a chargeback request for a transaction, transaction data and service provider data associated with the transaction. The dispute processing system incorporates the transaction and service provider data into a template. Next, the dispute processing system uses a machine learning framework to generate machine learning scores that indicates a likelihood of successfully winning the chargeback request and avoiding pre-arbitration. Using the machine learning scores, the transaction data, the service provider data, and at least one dispute processing rule, the dispute processing system determines a likelihood of successfully challenging the chargeback request. Based on the likelihood of successfully contesting the chargeback request, the dispute processing system generates a contestation document from the template, and submits the contestation document to contest the chargeback request.

The invention relates to an operation duration prediction method and system based on department distribution adjustment, electronic equipment and a readable storage medium, and belongs to the technical field of medical data processing. The method comprises the following steps: screening out features which have obvious influence on operation duration through principal component analysis (PCA) and SHAP technologies; on the basis of feature screening, designing a modular prediction model for operation duration distribution characteristics of different departments; through a dynamic calling mechanism, selecting an optimal prediction model according to the department to which the operation belongs to perform operation duration prediction; according to the invention, through a feature screening strategy, the interpretability of the model is enhanced, so that the prediction model is closer to clinical requirements; according to the method, by analyzing the similarity of operation duration distribution, data of departments with similar distribution are merged and trained, so that the problem of insufficient data volume of part of departments is solved, and the data utilization rate and the generalization ability of a prediction model are improved; according to the method, the accuracy, the adaptability and the reliability of operation duration prediction are improved.

Systems and methods for Protocol Data Unit (PDU) Set identification for end-to-end encrypted traffic, such as QUIC traffic between a User Equipment (UE) and Application Server (AS). Mechanisms can include one or more of: (i) additional path identification with corresponding Connection IDs (CIDs), such as for even and odd sets; (ii) sharing of key information for access to set sequence numbering; (iii) coalescing PDU set identification information in capsules with encrypted packet data for PDUs over encrypted channels; and / or (iv) elimination of capsule information for a PDU set in subsequent transmissions following initial transmissions in order to reduce signaling overhead.

There is provided a method for automatically generating a cyber crisis scenario, performed by a computing system. The method may comprise classifying types of content included in a cyber crisis report and extracting image data and text data from the cyber crisis report, inputting the image data into an image processing model and extracting attack procedure / behavior information included in the image data, inputting the text data into a text processing model and generating structured attack procedure-related data from each attack procedure included in the text data, generating threat behavior data corresponding to the attack procedure-related data, and merging the threat behavior data with the attack procedure-related data, matching the attack procedure-related data to the attack procedure / behavior information and generating a cyber crisis scenario template and automatically generating a cyber crisis scenario based on the attack procedure-related data and the cyber crisis scenario template.

The invention provides a financial abnormal behavior detection method and system based on federated learning privacy protection, and relates to the technical field of artificial intelligence and data security, and the method comprises the steps: merging a candidate sample with original data, then carrying out local training, and outputting an update parameter of a local model; the locally updated model weight parameters are encrypted, and security aggregation is carried out after updating; and decrypting the updated weight of the encryption model, re-encrypting the global model and returning the encrypted global model to the local node, decrypting the global model by the local node, comparing the global model with the local model in precision, updating parameters, and performing loop iteration until the performance index of the global model tends to be stable. The problems that cross-mechanism abnormal behavior detection samples are insufficient, the model generalization ability is weak, and the recognition accuracy and efficiency are affected due to scattered financial data and high privacy requirements are solved. Federal learning and pseudo sample generation are combined, multi-mechanism collaborative modeling is realized on the premise of protecting data privacy, and model training quality and detection performance are improved.

The invention discloses a Tranformer network-oriented hybrid precision multiplier, which is applied to an FPGA (Field Programmable Gate Array), and is used for allocating a target high-resolution image according to the weight precision of the weight data of the current layer of the target Tranformer network, the feature map precision of the feature map data of the target high-resolution image and a preset data allocation rule. Determining a first quantity of weight data and a second quantity of feature map data of a single calculation cycle; according to the first quantity of weight data and the second quantity of feature map data, recoding the weight data and the feature map data after determining a target recoding algorithm to obtain weight coded data and feature map coded data; performing multiplication calculation on the weight coding data and the feature map coding data in a single calculation period to obtain an initial product result of the single calculation period; and decoding the initial product result, and merging the multiple sub-feature map data of all the calculation periods corresponding to the current layer of the target Transform network to obtain target feature map data. According to the method, the resource utilization rate is improved on the basis of ensuring the model precision.

The invention discloses an ultra-short-term photovoltaic output prediction method and system based on data parallel processing. The prediction method comprises the following steps: acquiring meteorological prediction data in a first preset time period; the following three steps are executed in parallel through three independent processes: performing statistics on photovoltaic output prediction data based on meteorological prediction data; mechanism photovoltaic output prediction data are obtained according to the output characteristics of the photovoltaic panel and the meteorological prediction data; and merging the statistical photovoltaic output prediction data, the mechanism photovoltaic output prediction data, and the historical meteorological data and the historical photovoltaic output data in the second preset time period into an input data set, training a convolutional neural network, and generating final prediction photovoltaic output data. According to the method, the real-time requirement of ultra-short-term prediction is met in efficiency, error reduction is realized through multi-model fusion and data depth utilization in precision, the actual operation requirement of a photovoltaic power station is adapted in practicability, and a reliable technical scheme is provided for ultra-short-term photovoltaic output prediction.

The disclosure is generally directed to a method and system for charge station management including collecting data related to a plurality of charge stations, the data identifying location data, an operator, and a data provider for each of the plurality of charge stations, collating the data to match the location data with the operators of each of the plurality of charge stations, and merging the location data based on a set of criteria including the data from each of the data providers within an identified geohash location. Merging includes setting a geohash about a data provider, and merging location data within the predetermined perimeter to remove redundant locations based on a set of criteria, including criteria identifying a same operator within the geohash.

The invention provides a webpage content theme extraction method and system. The method comprises the steps that a crawler obtains original text data, picture data, audio data and / or video data in a webpage; extracting text data based on the picture data, the audio data and / or the video data, and merging the extracted text data with the original text data to obtain comprehensive text data; analyzing the comprehensive text data by using an SAC-KG language model and automatically constructing a knowledge graph, and generating a natural language text describing a triple contained in the knowledge graph by using an NLP large model; the natural language text is reduced to a preset word number range to serve as a generated theme extraction result about webpage content; wherein key frame images and audio data contained in the video data are extracted, the audio data are converted into text data by using a voice recognition model, and the text data contained in the key frame images and / or picture data are extracted based on an OCR technology.