28 results about "Data approximation" patented technology

The invention discloses a data classification method and device. A specific embodiment of the method comprises the steps of determining knowledge data under a target coarse classification to which to-be-classified data belongs; determining target historical data approximate to the knowledge data; in response to determining that the target historical data comprises unclassified data, determining the target fineness of a classification standard to be adopted by the classification standard knowledge base according to the accuracy rate of a classification result of the historical to-be-classified data; a classification result of the unclassified data is determined and stored through a large language model according to a classification standard knowledge base adopting a classification standard of target fineness, and the fineness of the classification standard of the classification standard knowledge base is improved in stages; and determining a classification result of the to-be-classified data according to the classification result of the target historical data. According to the method and the device, the classification result with relatively high precision and relatively high accuracy can be obtained by utilizing the knowledge data, the historical data, the classification standard knowledge base and other data resources which are relatively low in precision and easy to obtain under rough classification, and the fineness of the classification standard of the classification standard knowledge base is improved in stages; and the precision and accuracy of the classification result of the to-be-classified data are continuously improved as time goes on.

The invention provides a rocket aircraft flow field correction method based on multi-fidelity data fusion, and the method comprises the following steps: 1, collecting low-fidelity data, and carrying out the construction of a low-fidelity data set: simulating the change process of an unsteady flow field around an object in a finite time step through a Reynolds time-average simulation method or a large vortex simulation method; 2, data correlation analysis is carried out, wherein a linear relation model yH = rho (x) yL + delta (x) of a non-viscous flow field yL and a viscous flow field yH of the rocket aircraft is established; step 3, neural network architecture design: constructing a low-fidelity data approximation network NNL; 4, performing hyper-parameter learning and optimization; defining a loss function; 5, performing data acquisition and preprocessing: performing high-fidelity viscous flow field data acquisition, and preprocessing the acquired high-fidelity and low-fidelity flow field data; and step 6, model training and verification.

A memory device and a data approximation search method thereof are proposed. The memory device includes a plurality of selection switch pairs, a plurality of memory cell string pairs, a sense amplifier, and a page buffer. The selection switch pairs receive multiple search data pairs, respectively. The memory cell string pairs are respectively coupled to a global bit line through the selection switch pairs. Each of the memory cell string pairs determines whether to provide current on the global bit line according to stored data of a selected memory cell pair and each of the search data pairs. The sense amplifier obtains multiple search results according to the current on the global bit line and at least one reference currents respectively corresponding to at least one similarity. The page buffer records the search results and generates similarity information by accumulating the search results.

The present invention relates to the field of data processing, and more specifically, to a method for intelligent wiring control of a junction box, the method comprising: obtaining the operating condition data of the sensor of the historical intelligent junction box, clustering based on the historical operating condition data, obtaining the historical data similar to the current operating condition data according to the clustering result, and calculating the temperature change rate under the same operating condition as the historical data; using the time series data to predict the time series sequence of the temperature change rate in the current operating condition data, and calculating the temperature stability deviation at the same time under the same operating condition; calculating the temperature anomaly value according to the historical data and the change rate and the temperature stability deviation similar to the current operating condition data, and judging whether the junction box has a risk according to the change of the continuous temperature anomaly value under the same historical operating condition. The present invention reduces the misjudgment of the single temperature threshold control and improves the accuracy of detection by identifying the deviation between the actual temperature change and the expected change.

One example method includes receiving a Quadratic Unconstrained Binary Optimization (QUBO) problem that comprises a matrix that includes various cells having data. It is then determined that one or more of cells is missing data or has corrupted data. A machine learning (ML) model performs a denoising process that removes random noise from the one or more cells having the missing data or corrupted data. This results in data being imputed to the one or more cells having the missing data or the corrupted data. The imputed data approximates the missing data or approximates an expected value of the corrupted data before the corrupted data was corrupted.

The invention provides an intelligent vehicle man-machine sharing collision avoidance control system and method under critical working conditions, and the method comprises the steps: collecting and transmitting the current state and surrounding environment information of a vehicle through a sensing system; off-line learning and large-scale vehicle data are used for approximately solving a collision avoidance inaccessible state set, and a Hamiltonian-Jacobian accessibility value function and an action-value function are subjected to off-line iteration updating through a large amount of real vehicle collision avoidance data collected in advance; based on the accessibility value function and the action-value function, the collision avoidance capability and the collision avoidance intention of the driver are quantified, and the man-machine control weight is dynamically distributed; and generating machine operation based on a reachability heuristic reinforcement learning algorithm, generating final operation to be executed in combination with the man-machine control weight, the driver operation and the machine operation, and executing collision avoidance operation. According to the method, the collision risk of the vehicle state and the collision avoidance intention of the driver action can be evaluated theoretically, and man-machine conflicts are reduced to the greatest extent on the premise of ensuring that no collision occurs.

To provide a technique for supporting selection of an optical system parameter performed by an operator using an optical system.SOLUTION: An image processing device 100 constituting an image processing system 10 used by an operator includes: an optical system database 110 that stores imaging data obtained by imaging in the past using an optical system 140 constituting the image processing system 10; an approximate function creation unit 121 that defines a feature amount based on the imaging data as a function of an optical parameter based on the imaging data and the optical parameter; a search unit 122 that searches, using the function, for the optical parameter that yields better imaging results than the imaging data; and an optical system control unit 123 that controls the optical system 140 according to the searched out optical parameter to perform imaging.SELECTED DRAWING: Figure 1

The invention discloses a fan blade defect detection system and method based on artificial intelligence, and relates to the technical field of fan blade defect detection.The method comprises the steps that the detection reference value of historical fan blades to the fan blades is evaluated; evaluating a data consistency state of imaging parameters among target historical fan blades in historical blade imaging data, analyzing a data approximation condition of marked imaging parameters among the target historical fan blades, and evaluating an influence condition of the marked imaging parameters on fan blade imaging under different numerical spans; obtaining marked imaging data; according to the marking imaging data and the application imaging data of the fan blade, the fan blade is shot in a domestic power plant to obtain a fan blade image, and defect detection is performed on the fan blade according to the fan blade image to obtain defect detection data, so that the reflecting capability of the image to the real condition of the fan blade is fundamentally improved; and the accuracy of fan blade defect detection is improved.

The invention discloses a comprehensive identification method for various suspected diseases based on representation, blood data and medical image fusion. An artificial intelligence theory and an intelligent identification and analysis technology are utilized. The representation, the blood data and the medical image are fused, and the relation between each data and disease recognition and the recognition rate are judged through multi-data association. Disease feature items dynamically input through a simulated annealing method are used as an input layer, outer circulation is set as disease feature input items, inner circulation is set as feature corresponding to diseases as input items, and the diseases are intelligently recognized by improving a deep neural network method and adjusting parameters. And dynamically inputting to an improved neural network framework, adaptively adjusting parameters to recognize diseases through middle layer calculation, and improving the efficiency of intelligently recognizing the diseases. The artificial intelligence method is utilized to solve the problems that multiple diseases are difficult to recognize, suspected diseases of other diseases are omitted and the like, comprehensive recognition of multiple types of suspected diseases becomes the key, and the method is applied to hospital specialist departments and physical examination medical centers.

The invention provides an input noise multi-class Gaussian process-containing liquid rocket engine variational inference learning and diagnosis method, which comprises the steps of introducing noise and establishing a multi-class Gaussian process model with noise, converting a data classification problem into a posterior approximation problem based on Gaussian variational inference, and adopting a small-batch data approximation method to obtain an input noise multi-class Gaussian process-containing liquid rocket engine variational inference learning and diagnosis result. And performing optimization estimation on the variation lower bound, obtaining approximate posteriori distribution by maximizing the variation lower bound, and establishing a classification prediction model. According to the method, the multi-class Gaussian process is used as a bottom layer classifier model, additive Gaussian noise is introduced, a variation inference method is used for approximating posterior distribution of model hidden variables, and the classifier model containing input noise is optimized, so that fault diagnosis is carried out on the liquid rocket engine, and the fault classification accuracy of the liquid rocket engine containing the input noise is improved.

The invention provides a model bias-based convolutional neural network federated learning back door defense method. The method comprises the following implementation steps: constructing a federated learning system; each client obtains a training sample set; each client performs iterative training on the local model; the central server calculates model bias and detects a back door model weight; and the central server obtains a backdoor defense result. According to the method, the offset of the local model is calculated by using the distribution external sample set, the back door model is effectively detected, the method adapts to a complex or non-independent identically distributed environment, and the defense effect is remarkably improved; meanwhile, the central server adopts an anti-learning mechanism to remove the backdoor, approximates backdoor features by using out-of-distribution data, simulates potential influences of the backdoor features, enables a model to gradually forget the backdoor features through anti-learning, efficiently weakens the backdoor effect, avoids high calculation overhead of reverse engineering, and further improves the defense efficiency.

The application provides an SRAM-based digital domain in-memory computing method and device. First, input data and bit high-low order of the input data are acquired, and SRAM in-memory computing arrays corresponding to the input data respectively are determined according to the bit high-low order of the input data. Different preset approximate adder trees are included in different SRAM in-memory computing arrays, the different preset approximate adder trees include preset approximate full adders with different calculation accuracies, and the structure of the adder tree is a Wallace tree structure. Finally, the input data are subjected to approximate operation through the preset approximate adder tree, and a data approximate operation result is obtained. Through the above method, in combination with the application of the preset approximate full adder and the Wallace tree structure, the preset approximate adder tree with different accuracies can be selected to perform data calculation according to the bit high-low order of the input data while reducing the area and power consumption of the adder tree, and the calculation accuracy is improved.

The invention relates to detecting anomalous values in a multimodal distribution using an empirical cumulative distribution function. A method for detecting anomalies is provided. The method receives data and organizes the data according to a plurality of time periods and a number of updates for each of the plurality of time periods. The organized data approximates a first unimodal and a second unimodal. The first unimodal and the second unimodal have a first peak and a second peak, respectively. The method identifies dimples across a plurality of time periods and determines a density of the dimples. The density is compared to a predetermined threshold to determine whether the recess is in a selectable configuration. A unimodal analysis is then performed on the first unimodal and the second unimodal in response to the depression being a selectable morphology. The method also determines whether the second single modality is abnormal based on the single modality analysis, and discards updates associated with the second single modality when the second single modality is abnormal.

A learning device (100) includes a defective part shape data storage unit (107) for storing defective part shape data, generated from a new defective product image by a trained model constructed by a learning model generation unit (105), in association with the new defective product image. The image processing device (200) includes: a defective part shape addition unit (207) for extracting defective part shape data, corresponding to a defective product image approximate to input product shape data, from the defective part shape data storage unit (107) and adding the defective part shape data to the product shape data; and a defective product image generation unit (210) for generating a defective product image by optical simulation based on inspection illumination information and the product shape data including the added defective part shape data.

A random access memory may include memory banks and arithmetic approximation units. Each arithmetic approximation unit may be dedicated to one or more of the memory banks and include a respective multiply-and-accumulate unit and a respective lookup-table unit. The respective multiply-and-accumulate unit is configured to iteratively perform shift and add operations with two inputs and to provide a result of the shift and add operations to the respective lookup-table unit. The result approximates or is a product of the two inputs. The respective lookup-table unit is configured produce an output by applying a pre-defined function to the result. The arithmetic approximation units are configured for parallel operation. The random access memory may also include a memory controller configured to receive instructions, from a processor, regarding locations within the memory banks from which to obtain the two inputs and in which to write the output.

A coding technology is provided that makes it possible to encode and compress axis-dependent data that depends on the coordinate values ​​of each axis of an industrial machine. A data coding device 1 includes a model approximate encoder 11 that generates coded axis-dependent data in which the axis-dependent data is encoded, based on some axis-dependent data that depends on the coordinate values ​​of each axis of an industrial machine and a linear combination model that approximates the axis-dependent data as a linear combination of axis data concerning the industrial machine.

Provided is an encoding technology with which it is possible to encode and compress shaft-dependent data that is dependent on coordinate values of each shaft of an industrial machine. A data encoding device 1 comprising a model approximation encoding unit 11 that, on the basis of some shaft-dependent data that is dependent on coordinate values of each shaft of an industrial machine and a linear combination model that approximates the shaft-dependent data as a linear combination of shaft data pertaining to the industrial machine, generates encoded shaft-dependent data in which the shaft-dependent data is encoded.

The invention discloses a low-complexity large-model long-sequence memory modeling method. The method comprises the following steps: firstly, constructing a fractional order state space model FOSSM by introducing a Capto fractional order derivative to replace an integer order differential operator; then, based on an asymptotic behavior of a Mittag-Leffler function, establishing a theoretical relationship between a power law attenuation property of an FOSSM memory kernel and a fractional order parameter; deducing the theoretical advantage boundary of the FOSSM in the aspect of power law data approximation compared with the standard SSM; and finally, the non-rational fractional order operator is converted into a rational transfer function through an Oustaloup rational approximation method, and efficient discretization of calculation complexity is realized. According to the method, power law long-range dependence can be modeled naturally, more matched mathematical representation is provided for a sequence with heavy-tailed time correlation, and the problem of path repetition caused by insufficient historical track memory in unmanned equipment navigation and the problem of poor interaction continuity caused by weak context keeping ability in man-machine interaction in a traditional method are solved.

The present invention makes it possible to detect an approximation error amount in approximating and encoding axis-dependent data that depends on the coordinate value of each axis of an industrial machine. An approximation error detection device 1 comprises an approximation error amount detection unit 11 that detects an approximation error amount with an absolute value greater than or equal to a predetermined threshold among approximation error amounts in performing model approximation encoding of axis-dependent data on the basis of a part of the axis-dependent data that depends on the coordinate value of each axis of an industrial machine, and on a linear combination model that approximates the axis-dependent data as a linear combination of data on each axis of the industrial machine.

The invention provides a mass hydrology and water conservancy data compression method and system based on small-scale stationary features, and the method comprises the steps: obtaining hydrology and water conservancy data, and inputting a time vector data set of hydrology and water conservancy of a specific watershed; distinguishing small-scale data and large-scale data of the hydrological and hydraulic data, and performing iterative compression on the small-scale data; calculating an average value and a standard deviation of the small-scale data set, and approximately representing small-scale data by adopting normal distribution; calculating the deviation between each data in the small-scale data set and the average value, approximately representing the deviation by adopting an integer number of resolution standard deviations, and constructing integer matrix storage; and distributing all the small-scale data in a preset range, adopting a plurality of bits to sequentially encode each integer compression data in the integer matrix in a fixed-length manner, and using Huffman to encode the compression data according to different characteristics of different integer distribution frequencies. According to the method, the data with controllable precision loss is constructed to approximately represent the original data, so that the information entropy of the small-scale region in the data stream is effectively reduced.

To provide an estimation system, estimation device, and control program capable of improving the reliability of estimation results.SOLUTION: In a disease estimation system, an estimation device (3) comprises an approximator (32) that outputs an estimation result related to a disease of a patient and reference data indicating a basis for the estimation result from first data of the patient, and an output section (33) that outputs the estimation result and the reference data. The approximator (32) is learned using learning data including second data of the same type as the first data, and teacher data including diagnostic results corresponding to the learning data. The approximator (32) outputs reference data including third data retrieved from the second data included in the learning data.SELECTED DRAWING: Figure 2

The invention relates to a method for calculating (10) an operating variable (B) of an electric machine (12), comprising at least the steps of providing (14) a data set (16) formed from a plurality of sample points (c), multidimensional and depicting operating parameters of the electric machine (12) and specifying parameter values (C) of a periodic parameter of the operating variable (B) of the electric machine (12) in one dimension, specifying a query point (q) deviating from the sample points (c) in the dimensions of the data set (16), identifying (20) sample points (c) of the data set (16) locally assigned to the query point (q) as reference sample points (c 11 , c 12 , c 21 , c 22 ), parameter correction (24) of the parameter value (C 12 ) at least one second reference sample point (C 12) by a periodic shift depending on a parameter relationship between the parameter value (C 12 ) of the second reference sample point (c 12 ) and the parameter value (C 11 ) of a first reference sample point (c 11 ) to reduce periodically caused parameter discontinuities (18), calculating (26) an approximated parameter value (C q ) at the query point (q) by data approximation (28) at least depending on the corrected parameter value (C' 12 ), calculating (34) the operating variable (B) at least dependent on the approximated parameter value (C q ). Furthermore, the invention relates to an electric machine (12).

The invention relates to the field of data processing, in particular to an intelligent wiring control method for a junction box, and the method comprises the steps: obtaining the working condition data of a sensor of a historical intelligent junction box, carrying out the clustering based on the historical working condition data, obtaining the historical data similar to the current working condition data according to the clustering result, and carrying out the clustering of the historical data. Calculating the conversion rate of the temperature under the same working condition in the historical data; using the time sequence data to predict the time sequence of the temperature change rate in the current working condition data, and calculating the temperature stability deviation at the same moment under the same working condition; and calculating a temperature abnormal value according to the historical data approximate to the current working condition data, the conversion rate and the temperature stability deviation, and judging whether the junction box has a risk or not according to the continuous change of the temperature abnormal value under the same historical working condition. According to the invention, by identifying the deviation between the actual temperature change and the expected change, the misjudgment of single temperature threshold control is reduced, and the detection accuracy is improved.

This invention provides a method for estimating the health status of lithium-ion batteries based on Gibbs Variational Inference Multiple Imputation (GVIMI). The method includes: constructing a lithium-ion battery degradation model with missing data; transforming the data imputation problem into a posterior approximation problem based on Gibbs variational inference; optimizing the variational lower bound using a mini-batch data approximation method; obtaining an approximate posterior distribution by maximizing the variational lower bound; and establishing a multiple imputation and health status prediction model. This invention uses a hybrid method combining Gibbs sampling and variational inference as the underlying imputator, introduces a variationally complete conditional model, and uses Gibbs variational inference to approximate the posterior distribution of the model's latent variables, optimizing the imputation model with missing data. This improves the accuracy and robustness of lithium-ion battery health status estimation in scenarios with missing data.

The application discloses a data classification method and device. One embodiment of the method comprises: determining knowledge data under a target coarse classification to which to-be-classified data belongs; determining target historical data similar to the knowledge data; in response to determining that the target historical data includes unclassified data, determining a target fineness of a classification standard to be adopted by a classification standard knowledge base according to an accuracy rate of a classification result of historical to-be-classified data; determining and storing a classification result of the unclassified data by a large language model according to the classification standard knowledge base adopting the classification standard of the target fineness, and the fineness of the classification standard of the classification standard knowledge base is improved in stages; and determining a classification result of the to-be-classified data according to the classification result of the target historical data. The application can obtain a classification result with high precision and high accuracy by using low-precision and easily-obtained data resources such as knowledge data under coarse classification, historical data and a classification standard knowledge base, and the fineness of the classification standard of the classification standard knowledge base is improved in stages, so that the precision and accuracy of the classification result of the to-be-classified data are continuously improved over time.

The present invention provides a training method, an application method, a device and a medium for a video content description model. The training method includes obtaining a target video and a content description of the target video, extracting verbs and templates from the content description, performing encoding processing and feature sampling on the verbs and templates to obtain a first latent variable feature, extracting target visual features from the target video, and performing data approximation processing on a prior latent variable encoder and a language decoder according to the first latent variable feature and the target visual features to obtain a video content description model. According to the video description model of the present invention, open-ended descriptions can be generated, that is, descriptions of different types can be generated from many perspectives using different expressions.

The invention relates to the technical field of medical data processing, in particular to a medical-field-oriented multi-modal medical data approximate query processing method and system, and the method comprises the steps: detecting the multi-modal type of medical data, and selecting a corresponding query strategy according to the data type and data distribution characteristics; mapping the data to a unified semantic vector space by using a zero sample generation model, and calculating cross-modal similarity to generate a preliminary query result; taking the preliminary query result as input, constructing a multi-target optimization algorithm taking query precision, response time and resource consumption as optimization targets based on an error range, calculation time limitation and calculation overhead set by a user, performing refined screening on the preliminary query result, and dynamically adjusting a query strategy; and receiving feedback information of a user on a query result, and dynamically adjusting model parameters and a query strategy to realize continuous optimization of query performance. According to the invention, through similarity comparison, dynamic threshold optimization and doctor feedback closed loop, high precision and fast response of medical query are realized.