51 results about "Data complexity" patented technology

The invention discloses an intelligent management system and method for knowledge graph quality evaluation and self-repairing, belongs to the technical field of knowledge graphs, and aims to solve the problems that in traditional knowledge graph management, manual auditing efficiency is low, an effective automatic repairing means is lacked, and data complexity and real-time changes are difficult to deal with. The system firstly collects multi-source heterogeneous data in a target field, cleans the data through a deep learning noise recognition model, extracts entities and relationships by using a natural language processing technology, and adds metadata to convert the entities and relationships into graph structure data; then, a graph framework is defined based on the ontology, entity semantic alignment is achieved in combination with a graph neural network, and a knowledge graph is constructed by complementing implicit relations with the help of a pre-training language model. Then, the quality of the atlas is quantitatively evaluated through a four-layer quality evaluation system, meanwhile, a repair scheme is generated based on vulnerability feature extraction, knowledge base matching and decision fusion, and intelligent self-repair is achieved; the map can be monitored in real time and evaluated regularly, a repair strategy and a knowledge base are optimized through reinforcement learning, it is ensured that the map is kept accurate and time-efficient for a long time, and the practical value is improved.

The embodiment of the invention discloses a multi-modal large model optimization method and device for a complex task and a medium, and relates to the technical field of multi-modal large models.The method comprises the steps that multi-modal input data are received, modal specific feature extraction is carried out on the multi-modal input data, and initial feature representation of each modal is generated, the multi-modal input data comprises image data, text data and audio data; generating a dynamic parameter adjustment strategy based on a pre-acquired task type and input data complexity, and adjusting calculation parameters of a multi-modal encoder in the multi-modal large model according to the dynamic parameter adjustment strategy to determine a corresponding optimization modal processing sub-module; and performing cross-modal fusion by optimizing the modal processing sub-module and the initial feature expression to generate a fused multi-modal feature expression, and performing semantic analysis and reasoning on the multi-modal feature expression by using a pre-trained multi-modal large model to generate a task output result.

The invention belongs to the technical field of industrial equipment anomaly detection, discloses an unsupervised equipment anomaly detection method oriented to high-dimensional time series data, and aims to solve the problem that a traditional anomaly detection model is difficult to effectively learn and train due to scarcity of abnormal samples and too high multivariate time series data dimensionality in an actual industrial scene. The one-dimensional time sequence data is learned through a plurality of convolutional auto-encoder networks by using an integrated learning strategy, so that the data complexity of model processing is effectively reduced, an attention extrusion and excitation mechanism is fused, the attention of the model on a specific channel is enhanced, the perception ability of the model is improved, and the interference of redundant information is reduced. And finally, integrating the hidden feature information and the reconstruction difference information of the time sequence data of each dimension, and calculating a new reconstruction error as an abnormal score of the sample. According to the method, the high-dimensional time series data-oriented unsupervised equipment anomaly detection precision can be effectively improved.

The invention discloses a multi-modal data processing method and system based on an attention mechanism, and relates to the technical field of deep learning, and the method comprises the steps: collecting a multi-modal data set, carrying out the multi-scale time sequence calibration through dynamic time warping, and obtaining a time sequence alignment data stream; performing cross-modal semantic association on the time sequence alignment data stream to form a multi-modal feature vector; performing sparse processing on the multi-modal feature vector by using a multi-head self-attention mechanism to generate potential sparse representation; and carrying out coarse graining analysis and fluctuation mode capture on the potential sparse representation, generating a feature sequence length and a variance descriptor, and carrying out spectral entropy calculation to obtain a data complexity score. According to the method, cross-modal semantic association is performed by using canonical correlation analysis, and meanwhile, differential processing is performed on samples with different complexities through the hierarchical adaptive processing model, so that dynamic matching of computing resources is realized, and the resource utilization rate of multi-modal data processing is remarkably improved.

The invention relates to a deep learning cloud particle target detection method based on a dynamic detection head. According to the method, firstly, complexity evaluation is carried out on a cloud particle image data set, the weighted information entropy, the weighted texture complexity and the weighted local standard deviation of each image are calculated, and the comprehensive complexity is calculated based on the complexity indexes. Then, according to the overall complexity grade of the data set and the image data complexity, a detection head selection standard is formulated, and a proper dynamic detection head combination is selected according to the standard; and finally, performing target detection on the cloud particle image data set by using the selected dynamic detection head combination. Through the method, the most suitable detection head combination can be adaptively selected, the target detection precision and efficiency are effectively improved, and the method is particularly suitable for a large-scale cloud particle image data set with complexity difference.

The invention belongs to the technical field of artificial intelligence, and particularly relates to an AI-based file data content accurate and deep analysis and interpretation method, which comprises the following steps: acquiring multi-format file data and file meta-information, constructing an AI analysis network, extracting text semantic vectors, image visual features, table structure information and document layout features, and constructing a multi-dimensional semantic map. According to a user query intention, semantic extension is performed in combination with a domain knowledge base, an enhanced semantic description vector is generated through a graph attention mechanism, semantic reasoning and relation mining are performed by adopting an improved knowledge distillation Transform model, and a deep analysis conclusion is generated through a multi-hop reasoning model in combination with file data complexity, information density and user requirements. And generating a personalized interpretation report in combination with a user role and a task scene, and outputting an analysis result through a visual interface. Therefore, the problems of poor understanding ability, poor file adaptability and the like in the prior art are solved.

The invention provides a map rendering method and device, equipment and a storage medium, and the method comprises the steps: obtaining multiple real-time data of equipment where a client is located in the operation process of the client, and the real-time data comprises map request data; for each performance dimension, at least one sub-score of the performance dimension is calculated according to the real-time data, and the performance dimension comprises the network condition, the equipment performance and the data complexity; obtaining a plurality of existing rendering strategies, wherein each rendering strategy comprises a rendering mode and a performance score calculation mode; for each rendering mode, calculating the adaptability score of the rendering mode according to the calculation mode of the performance score of each performance dimension and the sub-score of the performance dimension, and taking the rendering mode with the highest adaptability score as a target rendering mode; according to the method, switching is carried out on the basis of the current rendering mode and the target rendering mode to achieve map rendering, and the map rendering system has the environment self-adaptive capacity by dynamically sensing data of multiple performance dimensions.

This invention discloses a method and system for fitting safety monitoring data based on adaptive hybrid basis functions, belonging to the field of computer-aided data analysis technology. The method achieves fully automatic high-precision curve fitting through a six-layer adaptive architecture: it automatically analyzes the trend complexity, periodicity, noise level, and nonlinearity of the data using multi-dimensional feature recognition technology; it calculates the data complexity score based on the feature analysis results and intelligently selects basis function combinations from an extended basis function library containing 32 sub-functions across 8 categories; it constructs a dynamic weighted hybrid basis function model, achieving adaptive adjustment of model parameters through time-varying weight functions and coupling correction terms; and it employs a multi-model dynamic fusion mechanism, integrating multiple candidate models based on six-dimensional confidence evaluation. This invention innovatively introduces adaptive regularization technology and a hierarchical optimization strategy, effectively balancing fitting accuracy and generalization ability, and possesses advantages such as full automation, strong robustness, and complete uncertainty quantification.

The application relates to the technical field of digestive tract detection, and discloses a digestive tract detection system based on artificial intelligence, which comprises a data acquisition unit, a preprocessing unit, a feature extraction unit, an abnormality detection unit and a result display unit. The application focuses on endoscopic images, accurately preprocesses the images into grayscale images and normalizes the grayscale images, reduces data complexity, highlights textures, and is beneficial to subsequent analysis; the application effectively extracts texture features, quantitatively presents subtle changes, accurately identifies lesions, scientifically judges abnormalities according to thresholds and displays the abnormalities, and realizes automatic and standardized detection. Meanwhile, physiological indexes are introduced, multidimensional data is integrated, and the function of the digestive tract is comprehensively reflected; the indexes are finely processed, individual differences and dynamic changes are considered, abnormal fluctuations are captured, and diseases are early warned; the application accurately detects abnormalities, cooperatively displays image and index results, and helps medical staff comprehensively judge. The application comprehensively and deeply detects, improves the accuracy of early screening, efficiently comprehensively diagnoses, has wide clinical applicability, promotes intelligent and accurate diagnosis and treatment, and the like.

The invention discloses a multi-modal database-oriented adaptive index structure selection method, which comprises the following steps of: analyzing statistical characteristics such as data dimensions, variances, sparseness and distance distribution of each modal, calculating hidden dimensions of the modals, and describing effective data complexity of the modals; based on a preset index adaptation rule, automatically mapping each mode to an optimal index type in the candidate index structure set, and completing automatic construction of a local index and binding of the local index and a global routing structure according to the optimal index type; on the basis, the multi-modal query can be automatically routed to the corresponding index to execute retrieval according to the index mapping relation. According to the method, an index structure self-adaptive selection mechanism without manual configuration is realized, the index maintenance cost of the multi-modal database can be remarkably reduced, and the query efficiency and expandability in a complex retrieval scene are improved.

The invention specifically discloses a vehicle-pile-network multi-space-time regulation potential quantification method based on a space-time diagram, and relates to the technical field of smart power grids. The method comprises the following steps: S1, based on a Monte Carlo simulation method, establishing a city-level vehicle-pile-network interactive operation base line under constraint conditions; s2, potential index parameters are calculated and adjusted, key factors influencing potential parameters are screened by means of Pearson's correlation coefficients, and data complexity is reduced; and S3, constructing a multi-space-time adjustment potential quantitative evaluation model based on the space-time diagram neural network STGNN, and realizing adjustment potential prediction in combination with an online learning framework. The method can sense the adjustment potential of the vehicle-pile-network system in all directions, improves the operation digitization level and scheduling flexibility of the power grid, enhances the operation stability of the power grid, and provides technical support for the construction of a novel power system.

Embodiments of the present specification provide a model training method, device, program product and storage medium, the method comprising: obtaining, according to at least one preset category, an initial data set corresponding to the at least one preset category respectively; if it is determined that the initial data set does not satisfy a preset balance condition, adjusting the initial data set so that the adjusted data set satisfies the balance condition; wherein the balance condition comprises one or more of the following: a condition that the data amount of the data set is balanced in different languages, a condition that the data amount of the data set is balanced in different lengths, or a condition that the data amount of the data set is balanced in different data complexities; determining at least one training task of a preset model, and training the preset model based on the adjusted data set of the preset category corresponding to the training task.

The application provides a method and system for checking the cross-modal information consistency of a maintenance plan based on a large model, and relates to the technical field of big data analysis. The method comprises the following steps: identifying a target maintenance plan through a power large model, determining key maintenance content, an unstructured proportion, and an attachment type complexity; obtaining a text data complexity and a business risk index based on key maintenance content analysis, as a first checking difficulty coefficient and a second checking difficulty coefficient; determining a third checking difficulty coefficient according to the unstructured proportion and the attachment type complexity evaluation; taking the expected review time limit of the target maintenance plan as a constraint, formulating an adaptive checking depth and an adaptive checking breadth based on the first checking difficulty coefficient, the second checking difficulty coefficient, and the third checking difficulty coefficient; and performing cross-modal information consistency checking on the target maintenance plan according to the adaptive checking depth and the adaptive checking breadth. The dynamic allocation of resources for checking the cross-modal information consistency of a maintenance plan is achieved.

The invention discloses an adaptive parking page display method and device, equipment and a storage medium, and the method comprises the steps: responding to a user operation, and transmitting a parking state query request to a remote control platform; receiving a feedback result of the remote control platform on the parking state query request; determining a target display page and a page data template based on the parking function type identifier, the parking execution stage identifier and the map identifier; and determining a corresponding data transmission strategy according to the current communication state and the data complexity identifier, and loading and displaying the target display page based on the data transmission strategy and the page data template. The target display page and the page data template are determined based on the parking function type identifier, the parking execution stage identifier and the map identifier, and then the corresponding data transmission strategy is determined according to the current communication state and the data complexity identifier. The page matching accuracy and the real-time performance and adaptability of data transmission and information display are improved.

A data management method of a data lake comprises the following steps: S1: collecting data information and uploading to an initial data pool module to classify a complex data system, and then delivering the classified data to a data pool processing module; S2: the different types of data pool processing modules comprise an analog signal data pool processing module, an application program data pool processing module and a text data processing module, each module processes data information of its own type to realize unified data management; S3: a thread pool occupancy rate model is constructed, and data containing a removal mark and an archiving mark are managed and scheduled to an archiving data pool module. Through the above scheme, the internal rules of numerous data are found and corresponding storage is realized, and the technical problem that current data complexity is not easy to arrange is solved.

The application provides a STEP model dynamic rendering method and system based on componentization processing, and the method comprises the following steps: when a local update request for a STEP model component is detected, a target component is first determined, then an independent component relationship table obtained by pre-extracting independent components, attributes and topological relationships is used to determine an influence domain in combination with update operation information. Subsequently, the new components in the influence domain are subjected to grid re-triangulation and lightweight processing, and a component-grid mapping table recording the mapping relationship between the component ID and the vertex mapping range and the like is updated according to the processing result. Finally, an incremental update package is generated based on the updated mapping table, and GPU rendering is performed by using the incremental update package. According to the scheme, the influence domain is accurately positioned through componentization processing, the data processing amount is reduced, the grid is lightweighted to reduce the data complexity, the incremental update package avoids full data transmission and rendering update, and the rendering efficiency and performance are effectively improved.

In some implementations, data obtained by a temperature management system for delivering temperature management therapy to a patient is presented, within a single display region, as a graph of patient temperature over time representing the timespans of all phases of a multi-phase temperature management therapy. The graph may be fitted to present each phase separately in a manner that retains data complexity. The graph may include power data representing power output over time by a temperature management device. Data from other devices may be incorporated into the graph. A portion of the data may be patient temperature data and / or patient physiological data gathered during a time preceding temperature management therapy by the temperature management device.

The invention relates to the technical field of computer data processing, and discloses a method for improving the super-division operation performance of an AI computing chip, and the method comprises the following steps: S1, collecting low-resolution image data, and carrying out the partitioning processing of the low-resolution image data, and obtaining image blocks; s2, performing data complexity analysis on the image blocks to quantify complexity information of the image blocks, and generating an entropy graph according to the complexity information obtained through analysis; s3, adaptively distributing the image blocks to a detailed calculation path or a low-complexity calculation path according to complexity information of the image blocks in the entropy graph so as to start asynchronous super-division operation; and S4, receiving an asynchronously output super-division operation result from the calculation path and the low-complexity calculation path. According to the method, the complexity of the image blocks is analyzed, and differential calculation path processing is adopted, so that the overall calculation amount and power consumption of super-division operation are reduced, and the operation performance of an AI calculation chip is improved.

The application discloses a data arrangement method, device, product, equipment and medium, comprising: determining the storage space after the data allocation position in the storage space corresponding to the target volume as a first storage space, and determining the storage space before the data allocation position as a second storage space; traversing the file data in the target volume to obtain a target file data set; determining the space in the first storage space that does not belong to the data in the target file data set to obtain a target space; determining the data stored in the second storage space and belonging to the target file data set to obtain target data; constructing a first moving set based on the target data; moving the data in the first moving set to make the target data and the original data in the first storage space form continuous data; and describing the continuously used space in the first storage space in a VDL description mode. In this way, the data complexity and algorithm complexity can be reduced, and the storage access performance of the elastic file system can be improved.

The invention relates to the technical field of semiconductor manufacturing quality control, in particular to a space-time coupling virtual measurement intelligent labeling method based on feature space geometry, which comprises the following steps: S1, acquiring multi-dimensional sensor time sequence data of semiconductor manufacturing equipment as a labeling sample set, and performing manifold value evaluation on the labeling sample set; s2, establishing an adaptive time weight model based on data complexity, establishing a dynamic space weight model based on local sparseness based on an adaptive kernel function, combining the adaptive time weight model, the dynamic space weight model and manifold value evaluation, and defining a time-space coupling value score; s3, taking the time-space coupling value score as an input, and establishing a three-layer optimization architecture to realize a globally optimal sample combination; s4, combining the samples selected by each cluster to form a final label set, performing quality evaluation on the final label set, and generating standardized label output according to a quality evaluation result; and an accurate value basis is provided for subsequent intelligent selection.

The invention relates to a multi-modal sensing and edge computing cooperative control method and system for an intelligent gate. The method comprises the following steps that a gate edge node schedules a multi-modal sensing unit to perform cooperative data acquisition; dynamically determining a multi-sensor cooperation strategy according to the environment and the target, carrying out confidence fusion, and generating a comprehensive sensing result containing vehicle identity, container identity and container condition initial judgment information; according to the service type, the data complexity and the real-time load of the gate edge node, partial or all sensing data and analysis tasks are distributed to a station edge server or a cloud server for processing through a dynamic task unloading strategy; and receiving a processing result, making a decision in combination with a local sensing result, and generating a gate control instruction. According to the invention, all-weather, high-precision and automatic intelligent management and control of gate operation are realized through multi-modal sensing fusion and cloud side end cooperative computing, and the passing efficiency, the identification reliability, the safety and the operation economy are remarkably improved.

A first analysis of a mass range of a first sample is performed using a separation coupled mass spectrometer, producing a first set of multivariate data that includes both retention time and mass spectral data. A second analysis of a mass range of a second sample is performed using a separation coupled mass spectrometer, producing a second set of multivariate data that includes both retention time and mass spectral data. Each of the first set and the second set is divided into two or more subsets corresponding to two or m / z sub-ranges of the mass range. One or more chromatographic peaks in each of the two or more subsets of the first set are independently aligned with one or more chromatographic peaks in each corresponding subset of the two or more subsets of the second set using an alignment method.

The application discloses a surface roughness prediction method based on a diffusion model and neural structure search, performs quantile normalization on process parameters, and performs Z-score standardization on surface roughness values; synthetic process parameter data meeting physical consistency and distribution fidelity is generated; a balanced, high-variety mixed training set is constructed to alleviate the data scarcity problem in a small sample scene; a Gaussian process-based Bayesian optimization strategy is adopted to automatically search for an optimal prediction network architecture matching the data complexity; then residual correction and structure fine-tuning are performed to improve the generalization ability and prediction robustness of the model under a small sample, and a surface roughness prediction value is output. The generalization ability and robustness of the model are improved, higher-precision surface roughness prediction can be realized, thereby providing a general solution for small-sample, high-dimensional and strong nonlinear process modeling in the field of precision manufacturing, and the surface quality prediction of other precision machining processes can be further popularized.

The invention relates to a lightweight edge computing enabling security and protection video analysis method, and belongs to the technical field of video analysis. The method comprises the following steps: constructing a multi-modal fusion lightweight edge video analysis model, and realizing feature extraction and fusion of video, audio and sensor data; designing an adaptive edge computing resource scheduling algorithm, and dynamically allocating computing resources according to data complexity; and an edge-cloud collaborative security protection mechanism is established, and equipment authentication, data encryption and behavior auditing are realized. The method has the advantages of low deployment cost, high analysis precision, high response speed, high security and the like, and is suitable for various security scenes such as smart communities and industrial parks.

The application discloses a semi-supervised gas identification method based on DBSCAN and random forest algorithm, and measures organic gas indexes, pm2.5 indexes and environmental temperature data, determines whether the environment belongs to a known stable or unknown complex gas environment according to data complexity and whether the place is marked with a gas category, uses a random forest algorithm to obtain a gas identification result and a known abnormal gas warning if the environment is a known stable gas environment, and otherwise, jointly uses the random forest algorithm and a DBSCAN algorithm to perform gas classification and identification, in a labeled result of the random forest algorithm, if a certain gas category in the label is an abnormal gas, the gas category is divided into an abnormal gas, in an unlabeled result of the DBSCAN algorithm, if certain clustering data deviates from a set threshold, the certain clustering data is marked as an abnormal gas, and the gas classification results of the two are verified through coincidence degree cross verification, the specific category of the labeled result is corresponded to the unlabeled result, abnormal gas detection and gas classification are realized, and the application is suitable for local complex gas environment identification of an industrial system.

This invention discloses an adaptive index structure selection method for multimodal databases. By analyzing the statistical characteristics of each modality, such as data dimensionality, variance, sparsity, and distance distribution, the hidden dimension of each modality is calculated, and its effective data complexity is characterized. Based on preset index adaptation rules, each modality is automatically mapped to the optimal index type in the candidate index structure set, thereby automatically constructing local indexes and binding them to the global routing structure. Furthermore, multimodal queries can be automatically routed to the corresponding index for retrieval based on the index mapping relationship. This invention achieves an adaptive index structure selection mechanism that requires no manual configuration, significantly reducing the index maintenance cost of multimodal databases and improving query efficiency and scalability in complex retrieval scenarios.

The invention discloses an AI reasoning method, an AI reasoning system and a storage medium. The method comprises the following steps: acquiring one or more image data; obtaining a model library, wherein each network model in the model library has a corresponding reasoning parameter; adjusting the reasoning strategy in real time according to the data complexity of the image data and hardware load information to obtain a calibration strategy; determining a target reasoning parameter based on a calibration strategy, and adjusting the image data based on the calibration strategy; and selecting a target network model from a model library according to the target reasoning parameter, and inputting the adjusted image data into the target network model one by one or in batches for online reasoning to obtain a reasoning result output by the target network model. Through real-time monitoring of a hardware load state and data complexity analysis, a reasoning strategy is dynamically adjusted, so that the accuracy loss is controllable while the reasoning speed is increased, the balance between the speed and the accuracy is realized, and then efficient AI reasoning is realized.

The invention relates to a cloud particle image data complexity judgment method, which comprises the following steps of: firstly calculating weighted information entropy, weighted texture complexity and weighted local standard deviation of data of each cloud particle image, then evaluating the comprehensive complexity of the cloud particle image data by synthesizing the weighted information entropy, the texture complexity and the local standard deviation, and finally judging the complexity of the cloud particle image data. And the complexity is marked as low, medium or high. According to the method, a complexity voting mechanism is further designed, different complexities are comprehensively evaluated through multiple rounds of weighted voting, and finally the complexity level of data of each image is determined. The method can effectively process the complex scene in the cloud particle image, improves the processing precision and efficiency of the complex image, does not depend on target detection, and is suitable for rapid evaluation of large-scale cloud particle image data.

This invention discloses an industrial automation software testing method and apparatus based on edge devices, belonging to the field of industrial automation software testing technology. The method, executed by an edge device, includes: acquiring images of the industrial equipment interface and environmental sensor data; dynamically calculating adaptive rank parameters based on the device's own resource status and data complexity; performing local low-rank adaptive fine-tuning on the visual basis model; extracting and fusing features from images and sensors to obtain multimodal fusion features; identifying user interface elements and their coordinates based on these features; receiving test cases and executing automated operations through a USB-HID controller; recording and comparing results to calculate the inconsistency rate, and deciding whether to trigger retraining or upload parameters to a central server for federated learning. This invention achieves non-intrusive, highly robust, adaptive, and offline-supporting automated testing of closed industrial systems, solving the testing challenges under conditions of resource heterogeneity, network instability, and harsh environments.

The present application relates to the technical field of biomedical engineering industry, and particularly relates to a cell aging detection method and system based on multi-omics metabolites. The present application obtains multi-omics detection information of a cell sample, and according to the time sequence change similarity of the expression information of molecules between different omics, all stable associated molecule pairs are screened from different omics corresponding molecule pairs. Then the expression activity coefficient of each functional module in each omics is determined, and the expression correlation coefficient between the functional modules of different omics is further obtained. Finally, a multi-omics correlation network is constructed and the aging state of the cell sample is evaluated. The present application deeply integrates multi-omics data, screens the correlation of cross-omics molecules based on time sequence linkage constraints, divides the high-dimensional data in the omics into functional modules with biological significance, reduces the data complexity, constructs a multi-omics correlation network, and thus facilitates the mining of the synergistic regulation mechanism between different omics, and accurately evaluates the cell aging state.