55 results about "Schema analysis" patented technology

Systems and methods are provided for multi-schema analysis of patient specific anatomical features from medical images. The system may receive medical images of a patient and metadata associated with the medical images indicative of a selected pathology, and automatically classify the medical images using a segmentation algorithm. The system may use an anatomical landmark detection algorithm leveraging Deep Reinforcement Learning (DRL) techniques to automatically locate one or more anatomical landmarks associated with the patient specific anatomical feature within the medical images. A 3D surface mesh model may be generated representing the patient specific anatomical features including the located one or more anatomical landmarks. The located one or more anatomical landmarks may be used to guide placement of a 3D model of a medical device that may be fused with the 3D surface mesh model to generate a patient specific 3D model of the medical device.

The invention relates to the field of data processing, in particular to an automatic risk identification method and system for an electric energy meter based on big data of the electric energy meter, and the method comprises the steps: collecting operation data of multiple dimensions of the electric energy meter, segmenting the operation data according to a time window with a fixed time length, and obtaining a data block containing an operation data time sequence of each dimension, performing feature extraction on the current data block and constructing a feature vector; inputting the feature vector into a trained isolated forest model, and calculating an original abnormal score; and correcting the original abnormal score to obtain a corrected abnormal score, constructing an abnormal threshold, and judging that the current data block of the electric energy meter has an abnormal risk when the corrected abnormal score is greater than the abnormal threshold. According to the method, the anomaly detection capability of the isolated forest is deeply fused with physical law and time sequence mode analysis, so that the corrected anomaly score not only contains static feature anomaly information, but also integrates dynamic evolution mode information, and the accuracy and reliability of risk identification of the electric energy meter are comprehensively improved.

This invention discloses a product carbon footprint data management system and method based on the Internet of Things (IoT), relating to the field of environmental protection technology. The method includes: collecting raw data from each stage of a product's entire lifecycle to generate carbon genome metadata; calculating the stage-specific carbon emissions of the product at each stage of its lifecycle based on the carbon genome metadata; constructing a carbon genome sequence of the product based on the carbon genome metadata and the corresponding stage-specific carbon emissions, and performing time-series pattern analysis based on the carbon genome sequence; summarizing the stage-specific carbon emissions of each stage of the lifecycle to calculate the product's total lifecycle carbon footprint; generating a standardized carbon footprint index based on the product's total lifecycle carbon footprint and a dynamic benchmark value; calculating the product's carbon footprint for future periods based on historical carbon genome sequence data; and generating carbon reduction operation parameters based on the product's future carbon footprint prediction results. By accurately collecting and correcting data through IoT sensors, combined with carbon footprint prediction, scientific carbon emission management is provided.

The invention relates to the technical field of mobile application development, and discloses a mobile application framework rapid construction method and system, and the method comprises the steps: analyzing a state persistence code of a to-be-upgraded basic component, and generating a state mode difference report; recognizing an upper-layer component set based on the component dependency graph and extracting a state access mode; analyzing the state persistence code and the data processing logic of the upper-layer component, and generating a state dependence propagation graph; state change propagation analysis is executed, and an upper layer component state field needing synchronous migration is marked; matching the migration strategy to generate a state migration script and arranging an execution sequence according to an inverse topology sequence; and executing the state transition script to complete component hot replacement and state data loading. According to the method, the problem of cascade state inconsistency caused by non-synchronous migration of an upper-layer component state copy when a basic component state structure is changed is solved.

The present application relates to the technical field of medical image processing, in particular to an ANA cell image multi-mode analysis and prediction method, system, device and medium, through a target detection network, interval cells in an original image are detected, a dynamic sampling mechanism is triggered to cut and sample a sliding window of continuous multiple frames of effective images, and a sample image block set obtained by sampling is input into a constructed multi-label classification network, a CBAM attention module and a category decoupling attention module are embedded in a backbone network of the multi-label classification network, enhanced features are extracted, and the probability that a detection image belongs to one or more categories of cell nucleus types is output. The present application reduces background interference through a dynamic sampling mechanism, enhances small sample category recognition ability through category decoupling attention, optimizes multi-label output through category correlation punishment, and improves the accuracy and clinical practicability of ANA cell image multi-mode analysis.

In embodiments, a method includes dynamically detecting a current revision to a software service running within a container and identifying whether the current revision specifies a significant change or not. In response to the identification, the method further includes selecting a time window in which to analyze the service's usage patterns (the “analyzed time window”) and determining whether to include data regarding the service's usage patterns prior to the current revision in the analyzed time window or not. The method further includes recommending a right-sizing implementation for the service based on the usage patterns in the analyzed time window. In embodiments, until data for the entire analyzed time window has been acquired, the method only implements right-sizing recommendations that increase resources available to the service. Once such data has been acquired, the method implements right-sizing recommendations that both increase and decrease such resources.

The invention discloses a power distribution network architecture evolution planning method, system, equipment and medium, and the method comprises the steps: obtaining power distribution network basic data and social power demand driving factors, and obtaining a power distribution network basic data set through data preprocessing; obtaining a typical development scene set through uncertainty modeling and multi-scene generation and reduction; in combination with system operation constraints, site selection and sizing of the multi-port flexible interconnection device are optimized, and a preliminary site selection and sizing scheme is obtained; a multi-stage investment decision model is constructed and solved, and a preliminary staged construction path is obtained; calculating a power supply reliability index through a fault mode analysis method, and evaluating economy in combination with a cost model to obtain a quantitative evaluation result; and performing global sensitivity analysis through a Morse algorithm, and adjusting an optimization strategy to obtain a final power distribution network architecture evolution planning scheme. The flexibility and the reliability of the power distribution network are remarkably improved.

The invention relates to an intravenous anesthesia instantaneous dose regulation and control method and device based on operation stage recognition, and belongs to the technical field of medical big data and intelligent control. A deep learning model is used for carrying out high-dimensional feature fusion and time sequence mode analysis, current and future surgical operation stages are dynamically and accurately identified and predicted, an ideal target drug concentration is dynamically set by querying a built-in knowledge base generated by big data mining, and a model prediction controller is driven to calculate an optimal instant infusion rate, so that the optimal instant infusion rate is obtained. Advanced and accurate drug regulation and control are achieved, a closed-loop feedback mechanism is introduced, parameters are adaptively adjusted on line according to actual physiological reactions, and control individualization and safety are ensured. According to the invention, the crossing from passive feedback to active predictive control is realized, the stability and safety of anesthesia depth are obviously improved, and the method has great clinical application value.

The invention relates to the technical field of image detection, in particular to a multi-modal data video inspection concentration degree analysis and early warning method and system, and the method comprises the steps: collecting face video data, and extracting eye micro-motion features, eyebrow morphological features and forehead myoelectricity visual features in face features; collecting heart rate variability data and galvanic skin response data in the physiological signals; personalized standardization processing is carried out, and Z-score feature vectors relative to the deviation degree of the user's base line level value are obtained through conversion; on the basis of the Z-score feature vector, constructing a time sequence feature vector, inputting the time sequence feature vector into a multi-modal time sequence fusion network for time sequence collaborative mode analysis, and outputting a current concentration degree probability value and a concentration degree prediction value at a future specified time point; and triggering a grading early warning mechanism based on the current concentration degree probability value and the concentration degree predicted value. According to the invention, information complementation is utilized in multi-modal data fusion, so that the robustness and accuracy of state recognition are improved.

An example method includes identifying, using a first NLP agent, a database of an enterprise containing desired data, selecting, using a second NLP agent, a schema analysis tool that is believed to be suited to a type of the database, establishing, using a third NLP agent, a connection to the database, extracting, using a fourth NLP agent, schema information from the database, comparing, using a fifth NLP agent and the schema analysis tool and based on the schema information, a structure of a schema of the database to a structure of a schema of a similar database, determining, based on the comparing, a change to make to the schema of the database, sending, using a sixth NLP agent, an instruction to a network element of the enterprise to make the change to the schema of the database, and validating, using a seventh NLP agent, the change to the schema.

The present application relates to the technical field of image detection, in particular to a multi-modal data video inspection concentration analysis and early warning method and system, the method comprising collecting facial video data, extracting eye micro-motion features, eyebrow shape features and forehead muscle television features in facial features; collecting heart rate variability data and skin electricity reaction data in physiological signals; performing individualized standardization processing, converting into Z-score feature vectors of deviation degree relative to user's own baseline level value; based on the Z-score feature vectors, constructing time sequence feature vectors and inputting into a multi-modal time sequence fusion network for time sequence collaborative mode analysis, outputting current concentration probability value and concentration prediction value at a specified time point in the future; triggering a hierarchical early warning mechanism based on the current concentration probability value and the concentration prediction value. The present application utilizes information complementation in multi-modal data fusion, thereby improving the robustness and accuracy of state recognition.

The application provides a meta-learning enhanced burst order multi-constraint distribution emergency scheduling method, comprising: acquiring the time distribution mode and intensity change trend of continuous burst order flow through historical order data collection, and determining the regularity difference capture result; according to the regularity difference capture result, using meta-learning model training to obtain evolution trend judgment parameters of subsequent demand prediction; if the evolution trend judgment parameters exceed the preset threshold, starting resource allocation optimization to obtain an acceleration processing means allocation scheme under a dynamic coordination mechanism; for the preliminary scheduling sequence, using genetic algorithm iteration to determine the minimum path of the chain delay situation, and obtaining the optimization output of order mode analysis; through the final execution plan, using particle swarm optimization algorithm fusion to determine the compensation measures of resource allocation lag, and obtaining the complete sequence of overall distribution emergency scheduling.

The system according to this embodiment aims to analyze customers' communication usage data and behavioral patterns to provide optimal pricing plans and promotions. [Solution] The system according to the embodiment comprises a collection unit, an analysis unit, a proposal unit, a provision unit, and an update unit. The collection unit collects customer communication usage data and behavioral patterns. The analysis unit analyzes the data collected by the collection unit. The proposal unit proposes optimal pricing plans and promotions based on the analysis results obtained by the analysis unit. The provision unit provides the content proposed by the proposal unit to the user. The update unit periodically re-analyzes the data based on the content provided by the provision unit and updates the proposals.

The invention discloses a power grid network attack countering method and system based on flexible gray level self-adaption, and the method comprises the steps: obtaining the multi-level gray point information of a power grid, carrying out the abnormal flow analysis, carrying out the shadow asset recognition processing based on an analysis result, and obtaining the shadow asset recognition data, obtaining known attack data of the power grid, carrying out attack mode analysis, constructing an attack link graph of a known attack mode to obtain an attack link analysis model, recognizing an abnormal access behavior corresponding to shadow asset recognition data through the attack link analysis model, carrying out target asset threat analysis to obtain asset threat analysis data, and sending the asset threat analysis data to the power grid. And attacker positioning is carried out according to the asset threat data, a corresponding attack countering strategy is called in combination with the known attack means similarity to carry out attack source blocking processing on the positioned attacker, and power grid network attack countering data is obtained. The power grid attack is accurately traced and attack countering is carried out from the source, so that data support of attack countering is provided for operation safety of the power grid.

We provide the system. [Solution] Data collection means, An analysis means that analyzes the information obtained by the aforementioned data collection means and predicts the trends of financial assets, A display means for visualizing the predictive information obtained by the analysis means, A means for analyzing consumption patterns using electronic transaction history, A means for presenting an asset management method based on the analysis results of the aforementioned consumption patterns, A system that includes this.

The application relates to the field of petroleum technology, in particular to a cyclone coupling demulsification separation system based on a high-voltage pulse electric field, which comprises a demulsification separation unit, a data acquisition unit, a pretreatment unit and a data analysis unit. The demulsification separation unit is used for demulsification dewatering of target emulsified oil wastewater through cyclone and spiral electric field. The data acquisition unit is used for collecting demand information. The pretreatment unit is used for initial water content state detection of the target emulsified oil wastewater, and a pretreatment mode is selected according to the initial water content state. The data analysis unit is used for determining an analysis adjustment mode according to a dewatering state, and the analysis adjustment mode is used for detecting a reference value of impurity content or adjusting dewatering parameters. In the adjustment of the dewatering parameters, a first pressure drop and a second pressure drop are detected to determine a pressure drop state, and the data analysis unit determines a pulse voltage adjustment mode according to the pressure drop state. The working parameters are adjusted according to the quality state of actual emulsified oil wastewater and the dewatering effect, so that the precision of demulsification working parameters is improved, and the actual working demand is met.

The invention discloses a multi-source heterogeneous data management method and device, electronic equipment and a storage medium, and the method comprises the steps: dynamically selecting a first processing node through a mode analysis model based on a mode processing performance parameter of a data cleaning node; dynamically selecting a second processing node through a timestamp calibration model based on a time calibration performance parameter of the time sequence calibration node; dynamically selecting a third processing node through a value domain conversion model based on the code conversion performance parameter of the code conversion node; and executing a mode conflict analysis task by using the first processing node, executing a time sequence calibration task by using the second processing node, executing a coding system conversion task by using the third processing node, and generating standardized data. An end-to-end data governance process from mode analysis to time sequence calibration to code conversion is formed, finally, a data set with a unified structure, time alignment and code standardization is generated, and the data governance efficiency and accuracy are remarkably improved.

A method includes dynamically detecting a current revision to a software service running within a container and identifying whether the current revision specifies a significant change or not. In response to the identification, the method further includes selecting a time window in which to analyze the service's usage patterns (the "analyzed time window") and determining whether to include data regarding the service's usage patterns prior to the current revision in the analyzed time window or not. The method further includes recommending a right-sizing implementation for the service based on the usage patterns in the analyzed time window. In embodiments, until data for the entire analyzed time window has been acquired, the method only implements right-sizing recommendations that increase resources available to the service. Once such data has been acquired, the method implements right-sizing recommendations that both increase and decrease such resources.

The application discloses a kind of water and electricity plant intelligent operation and maintenance management system and method based on machine learning, belong to water and electricity plant operation and maintenance technical field.The application collects water and electricity plant multidimensional data, carries out data preprocessing, storage enters data warehouse;Unified metadata label is defined, and data blood relationship tracking mechanism is established;Determine the starting point of tracing, based on storage location backtracking, trace data access history, according to data flow chart backtracking, integrated data traceability chain is obtained;Entity recognition and relationship extraction are carried out, and Neo4j is used to build associated graph;The relationship between power grid dispatching data and equipment operation is analyzed, and the associated graph is adjusted;Identify dominant abnormality and implicit abnormality, based on associated graph fusion, obtain water and electricity plant abnormal data;The trend of equipment operation data and sensor monitoring data is predicted, combined with residual analysis positioning deviation value, obtain data fluctuation mode, analyze correlation, obtain the source of water and electricity plant abnormal data.

The invention discloses a power transmission and distribution equipment operation state self-optimization system based on a large parameter model, relates to the technical field of power transmission and distribution equipment optimization, and is used for collecting operation data of equipment and generating a space-time synchronization signal set. Searching feature pairs appearing across signals on a time axis; feature pairs with the number larger than a preset threshold value are extracted and marked as symbiotic fault pairs, and a symbiotic fault mode is generated; analyzing the energy equilibrium state distortion degree and the energy conversion efficiency deviation degree, and fusing to generate a health index; determining the fault type and the residual service life based on the physical layer evidence and the effect layer evidence; operating parameters most sensitive to equipment health are extracted; according to the sensitivity coefficient of the operation parameter and in combination with the current health index, the suggested fine tuning amount of each parameter is analyzed; and the stability of the system after parameter adjustment is monitored in real time, feedback calibration is formed, and a historical maintenance case library is updated. The accuracy of data analysis is improved; and the security of the control strategy is ensured.

This invention relates to the field of terahertz technology and provides a method and system for terahertz mode decomposition based on spatial and spectral resolution imaging. Addressing the limitations of existing technologies in achieving high-precision, non-invasive mode field imaging and analysis in the terahertz band, this invention proposes an innovative solution: A high-precision two-dimensional displacement platform drives a single detection unit to scan the output face of the terahertz waveguide under test point-by-point, performing frequency scanning at each point and recording the power at each frequency point on each spatial coordinate. Through data synchronization and spatial gridding reconstruction algorithms, the time-series data is reconstructed into a spatially aligned three-dimensional data cube. Based on this three-dimensional data cube, a spatial and spectral resolution imaging (S²) mode decomposition algorithm is executed to decompose and reconstruct the mode field distribution, relative power, and group delay difference of each guided mode propagating in the waveguide. This method effectively solves the problem of a lack of area array detectors in the terahertz band and achieves low-cost, high-flexibility, and high spatial resolution terahertz waveguide mode analysis through a systematic data processing flow.

The present invention provides an integrated migration technology that integrates (1) dynamic schema analysis and business logic estimation under authority constraints, (2) restoration of multimodal UI / UX, (3) collaborative implementation of AI groups and real-time conflict resolution, (4) transparent security migration, (5) quality assurance for non-disruptive switching, and (6) detection of bottlenecks during operation and continuous monitoring of business KPIs. [Solution] This invention runs the old and new systems in parallel using the same input obtained from mirroring or recording / playing back production traffic, acquires the output difference and execution metrics, calculates Q_mig from UIm / APIm / Lat / Lat_CVaR, and determines the stage switching based on the m-of-n criteria of T_window and T_hold. In case of non-delivery or critical errors, it automatically rolls back and audits the basis for the decision using a hash chain + time signature. The authentication method is also migrated through transparent hashing during the initial authentication.

We provide the system. [Solution] A means of collecting business activity data from business terminals, A means for transferring the aforementioned business activity data to a central server, The central server includes means for analyzing behavioral patterns based on the business activity data, A means for generating suggestions for improving work efficiency based on the results of the analysis of the aforementioned behavioral patterns, A means of notifying users of the aforementioned proposal on a monthly basis, A system that includes this.

The application provides a path driving rhythm mode analysis method and system based on DNA sequence characterization, comprising the following steps: S1, preprocessing an original taxi trajectory data set to obtain a preprocessed taxi trip trajectory flow data set; S2, constructing an OD cost matrix to obtain the distance cost of each trajectory point in each trajectory flow in the road network; S3, constructing a driving rhythm sequence of the trajectory according to the distance cost of the trajectory in the road network in combination with the passing time and average speed between the trajectory points; S4, calculating the similarity between the driving rhythm sequences in each scene; and S5, taking the similarity as a score to perform clustering analysis on the driving rhythm sequences in each scene to obtain the mode and emotional trend of the taxi drivers for path selection in each scene. The application can mine excellent path selection modes and typical path selection emotional trends, and is helpful for the improvement and personalized customization of path planning algorithms.

The application relates to the technical field of ultrasonic equipment quality control and evaluation, and discloses an ultrasonic quality control dynamic evaluation method and system. The method is based on multi-dimensional feature fusion and dynamic mode analysis, real-time quality control data of ultrasonic equipment is collected, a quality control database is constructed after being labeled and pretreated. Multi-dimensional features are extracted from the database to construct a feature matrix, the feature matrix is sliced by using a self-adaptive window segmentation algorithm, redundant sub-matrices are removed by using a dynamic time warping algorithm, a global feature tensor and a similarity correlation graph are formed. Current data are converted into target feature sub-matrices in real time, dynamic matching degrees with the global feature tensor are calculated, quality control features are output and reconstructed by multi-modal fusion, and the quality control state is evaluated by calculating a deviation and combining a dynamic threshold rule. The method and the system can realize real-time and accurate evaluation of the quality of ultrasonic equipment, improve the diagnostic accuracy, and have a wide application prospect.

The invention belongs to the field of image generation and retrieval, and particularly relates to a radar quality management knowledge graph generation method and system. Performing data fusion on the relationship between the entities to obtain data after data fusion; storing the fused data into a graph database, and establishing a radar quality management related knowledge graph; the method comprises the following steps: constructing a quality evaluation system of radars of various models based on a radar quality management related knowledge graph, and defining indexes and index weights according to an entity relationship triple; on one hand, a radar quality related knowledge graph is established, on the other hand, the radar quality related knowledge graph is combined with a quality evaluation system, overall quality evaluation and fault control of the radar are achieved, and rapid and automatic knowledge base construction and updating can be achieved. A large amount of labor cost is saved, and basic data is provided for quality problem rapid troubleshooting, failure mode analysis, fault root cause analysis and quality file intelligent processing.

The invention provides a spot welding equipment fault prediction model training and fault prediction maintenance method and device, relates to the technical field of electric digital data processing, and aims at preprocessing dimension working condition parameters of spot welding equipment and control equipment and determining a target detection object by utilizing clustering screening based on a fault occurrence rate threshold value. For each target detection object, introducing a Boruta algorithm and an SHAP value to select a target feature item with relatively significant influence, constructing a first training data set, and training a fault prediction binary classifier to predict whether the target detection object has a spot welding fault or not; meanwhile, failure mode analysis data is converted into a mapping table to construct a second training data set, a fault recognition model is obtained through training, and recognition of fault components, fault types and priorities is carried out on target detection objects which possibly break down so as to guide predictive maintenance work. According to the method, accurate prediction and rapid identification of spot welding faults are realized, fault risks can be predicted in advance, time is won for equipment maintenance, and production loss is reduced.

The invention provides a fault prediction method and device based on multi-modal data fusion. The method comprises the steps of collecting multi-modal data of a monitoring area; processing the multi-modal data to obtain feature information of each modal; based on the feature information of each mode, performing cross-modal reasoning analysis by using a pre-trained large language model to obtain a first hidden danger prediction result; inputting the feature information of each mode into a trained deep learning model to carry out space hidden danger mode analysis to obtain a second hidden danger prediction result; and carrying out bidirectional integration on the first hidden danger prediction result and the second hidden danger prediction result, and generating fault early warning information according to an integration result. According to the method, high-precision and real-time early warning and intelligent traceability of the safety risk of the chemical industrial park are realized through bidirectional verification of multi-modal data dynamic fusion, large-model intelligent reasoning and deep learning prediction.

The invention discloses a request data number swiping prevention risk control method based on a medical scene. The method comprises the steps that a user request sequence, equipment fingerprints, identity credentials and interaction behavior data are collected to construct a feature data set; constructing a depth behavior encoder model, and obtaining depth feature representation through multi-scale feature fusion and an attention mechanism; using a dynamic behavior clustering algorithm to identify a user behavior mode and track an evolution process; constructing an adversarial sample to enhance the robustness of the model; evaluating the number brushing behavior based on the reconstruction error, the depth feature representation and the behavior mode evolution trend; and outputting a detection result and executing risk early warning, access control and behavior traceability processing. Through deep feature learning and dynamic mode analysis, individual and group number brushing behaviors in a medical service platform can be effectively identified, the accuracy and adaptability of number brushing prevention detection are improved, and the fairness and safety of medical services are guaranteed.

The embodiment of the invention relates to the technical field of information, and discloses an anti-fraud recognition method and device based on multi-modal environment characteristics, a medium and a product, and the method comprises the steps: obtaining interaction data which comprises image data, audio data and text behavior data; performing complex background environment identification on the image data; extracting local detail features and global semantic features of the image data, and performing risk feature extraction on the face in the image to output image risk features; performing acoustic scene and interaction mode analysis on the audio data; carrying out acoustic environment analysis on the background noise signal, extracting acoustic interaction characteristics reflecting human-computer interaction differences, and outputting acoustic environment risk characteristics; performing logic consistency analysis on the text behavior data by using a large language model in combination with user behaviors and structured data to obtain behavior logic risk features; and performing multi-modal comprehensive weighted scoring based on the above characteristics, and determining a final anti-fraud identification result.