24results about How to "Informative" patented technology

The invention discloses an automatic optical detection method and device and a storage medium. The method comprises the steps that original overlook image data of a wafer substrate are collected under irradiation of a first light source; acquiring multi-frame side illumination image data of the wafer substrate under the illumination of a plurality of second light sources in sequence; adjusting the brightness of the original overlook image data according to the multi-frame side-view image data to obtain target overlook image data; loading a preset defect classification network; inputting the target overlook image data into a first feature extraction structure to extract multi-stage first target defect features; inputting the multi-frame side illumination image data into a second feature extraction structure to jointly extract a second target defect feature; inputting the multi-level first target defect features and the second target defect features into a feature fusion structure to be fused into third target defect features; and respectively inputting the third target defect characteristics into a plurality of classification head structures to divide the types of the physical defects existing in the wafer substrate. And the defect detection accuracy of the wafer substrate is improved.

The invention provides a binary program variable type recovery method and device and a model training method and device. The recovery method comprises the steps of obtaining a target binary program; obtaining a plurality of to-be-recovered samples according to the target binary program; determining a target training sample with the highest similarity with the to-be-recovered sample in the training sample set through the target learning model; and determining the data type corresponding to the target training sample as the data type of the variable corresponding to the to-be-recovered sample. According to the method and the device, binary program slicing is carried out by using the data stream information between the functions to obtain the training sample containing the cross-function variable information, so that the training sample with richer information amount is obtained. The target learning model obtained after the first learning model is trained based on the training sample set can reliably recognize more important features from complex and uncommon data types, so that the data types of the variables can be recovered more accurately.

The application discloses a camellia seed oil adulteration identification method based on triglyceride isomers; the method comprises the following steps: collecting the data of the first mass spectrum information and the second mass spectrum information of glycerides of the oil sample standard by an ultra-high performance liquid chromatography-quadrupole time-of-flight-high resolution mass spectrometer; extracting the peak area content of the top 27 glyceride compounds; identifying and extracting the isomer content of the top 27 glyceride compounds; screening characteristic isomer compounds according to variable projection importance; establishing an adulteration identification model according to the principal component analysis and the least square-discriminant analysis of the isomer content; and identifying the sample in the adulteration identification model. The adulteration identification model can not only distinguish camellia seed oil and high-oleic oil, but also has a highest prediction accuracy of 100% for the type of high-oleic oil, and has a minimum identification adulteration concentration of 2%, thereby significantly improving the identification accuracy of camellia seed oil.

The application discloses a deep learning DOA estimation method based on original IQ data. The application uses I and Q components of the original signal as the input of the model to improve the performance. The application aims to solve the DOA estimation problem of a single signal source, and models the single signal source DOA estimation problem as a single-label multi-classification problem. By discretizing the DOA range, the possible directions of arrival are taken as corresponding labels. A convolutional neural network is designed to adapt to different numbers of snapshots, and accurate DOA estimation can be adaptively obtained for input signals of different lengths. Experimental results show that, compared with existing deep learning DOA estimation methods based on covariance matrix as input, the scheme has more excellent performance, and can provide a more reliable solution for array signal processing.

The invention provides a post information-based method and system for automatically generating back call and visit conversational skills. The method comprises the following steps: receiving an information record table of back-calling personnel, extracting key contents, and obtaining each job experience corresponding to each job company; corresponding back adjustment points are established on the basis of the job companies, back adjustment child nodes corresponding to different back adjustment attributes are sequentially established downwards along the back adjustment points on the basis of the job experiences, and the back adjustment attributes comprise subjective attributes and objective attributes; performing objective back-call operation on the job company corresponding to the back-call sub-node with the objective attribute, and performing authenticity evaluation on the first back-call result based on the job experience to obtain a first evaluation value; performing subjective back-call operation on the job company corresponding to the back-call sub-node with the subjective attribute, and performing quality evaluation on the second back-call result based on the job experience to obtain a second evaluation value; and determining a back tone score based on the first evaluation value and the second evaluation value. According to the invention, the back adjustment efficiency is at least improved.

The invention provides aluminum foil tensile strength testing equipment, which comprises a rack, a first testing mechanism, a material pulling mechanism and a second testing mechanism, and is characterized in that two guide rods are symmetrically arranged on the rack; the first testing mechanism comprises two fixing assemblies, a first electric telescopic rod and a tension meter, and the two fixing assemblies are slidably connected with the two guide rods respectively; the first electric telescopic rod is detachably arranged between the rack and one fixing assembly, and the tension meter is detachably arranged between the rack and the other fixing assembly; the material pulling mechanism comprises two electric driving modules and a material pulling assembly, the two electric driving modules are symmetrically arranged on the rack, and the material pulling assembly is connected with the two electric driving modules. According to the aluminum foil tensile strength testing equipment, the tensile strength of an aluminum foil material can be tested when the aluminum foil material is flatly laid or wound and conveyed, so that the actual production environment is better fitted, and obtained testing data are more referential.

This application provides a method for inverting the dynamic changes of the seabed sedimentary environment based on three-phase potential, including in-situ data processing, electrical signal calibration, mathematical model establishment, and dynamic change analysis. By deploying a seabed electrode array, signals such as spontaneous potential, resistivity, and redox potential are acquired in real time. An inversion algorithm is used to deduce seabed sedimentary environment characteristics, such as seabed interface location, suspended particle concentration, sediment density, porosity, and water content. This method, combined with multi-frequency signal analysis, can monitor changes in the seabed sedimentary environment in real time and identify sediment movement. Compared with existing technologies such as CN118153411B and CN110411923B, this invention covers richer inversion content, and the complementarity of potential signals improves monitoring accuracy and efficiency, exhibiting stronger adaptability and reliability. This method has lower equipment and maintenance costs, is suitable for large-scale, long-term monitoring, and can provide innovative solutions in fields such as deep-sea monitoring, environmental assessment, and resource exploration.

This invention relates to the field of distribution network fault location technology and discloses a fault location decision method for an off-site distributed fault location device. It utilizes an off-site power grid sensor acquisition system to collect current information from each outgoing line and busbar, establishing typical fault samples and forming a typical fault sample space. Then, a zero-sequence network diagram is constructed based on the current information collected by the power grid sensor acquisition system. Circuit equations are written based on the zero-sequence network diagram, and the adiabatic equivalent of the circuit equations is applied using the servicing principle. Finally, the sequence parameters that indicate the phase transition development trend of the system are solved. This off-site distributed fault location device fault location decision method can correctly solve the uncertainty between fault symptoms and faulty lines, achieving fault location for low-current grounding systems. Furthermore, the correlation analysis-based fault diagnosis requires fewer samples, involves less computation, and is easy to master.

The utility model relates to a multifunctional microscopic imaging analyzer which comprises a base, an object carrying assembly, a light source assembly, an imaging assembly and a light path adjusting assembly, the light source assembly comprises a fluorescent assembly, a white light assembly and a coherent light assembly; the imaging assembly comprises a fluorescence camera used for capturing an image obtained through fluorescence multichannel imaging; the bright field camera is used for capturing images obtained by white light bright field imaging and quantitative phase imaging; along a light path from a sample to the imaging assembly, the light path adjusting assembly sequentially comprises an objective lens, a first right-angle mirror, a tube mirror, a second right-angle mirror and a first beam splitter prism cube. According to the multifunctional microscopic imaging analyzer disclosed by the utility model, by optimizing the light source configuration and the light path design, a highly integrated imaging system is realized, so that a user can complete various imaging requirements on one device, the cost is saved, and the use convenience and the experiment flexibility are improved.

This invention discloses a heuristic dynamic memory weighting and recall reordering method, comprising six steps: initial impression value calculation, Ebbinghaus forgetting curve modeling, recall depth parameterization, multi-dimensional independent sorting, multi-dimensional result fusion, and recall-triggered impression value inversely proportional increment. This invention simulates the natural decay of memory through an 8-stage Ebbinghaus forgetting curve, achieves a recall-as-reinforcement effect through an inverse impression value increment mechanism, comprehensively considers semantic similarity, temporal freshness, and memory importance through multi-dimensional reordering, and flexibly adjusts the breadth and depth of recall through recall depth parameterization. This invention provides two forgetting curve implementation methods: discrete-stage lookup table method and continuous curve calculation method (including exponential decay type and power-law decay type), suitable for different application scenarios. This invention significantly improves the intelligence level and anthropomorphism of AI long-term memory systems, enabling AI to perform natural memory recall like humans.

The present invention proposes a method for judging the stage of tobacco leaf baking process, which belongs to the technical field of tobacco leaf baking. The method for judging the stage of tobacco leaf baking process, before actual baking, inputs preset baking parameters of the entire baking process through the control end of the baking room; in the entire baking process of actual baking, according to the calibrated data collection time t of the baking process stage, collects the hyperspectral information of tobacco leaf state index X; and establishes characteristic spectral data of tobacco leaf state index X at the collection time t through the hyperspectral information collected at the time t; compares the characteristic spectral data of tobacco leaf state index X at the actual baking time t with the pre-calibrated hyperspectral information; and judges the stage of the current tobacco leaf baking process through the comparison result. The automation of the stage judgment of the tobacco leaf baking control process can be realized, and the efficiency of judging the stage of the baking process can be improved.

The application discloses a wind power daily scene generation method based on a tensor self-organizing mapping neural network, and comprises the following steps: obtaining a daily scene data set of multiple wind farms; clustering the daily scene data set by using a tensor self-organizing mapping neural network; constructing a variational autoencoder for each cluster respectively to extract hidden features from the daily scene data; performing random simulation and sampling on the daily scene data of each cluster by using the hidden features to obtain a daily scene hidden variable data set; decoding and reconstructing the daily scene hidden variable data set to obtain reconstructed daily scene data of each cluster; and aggregating the reconstructed daily scene data of each cluster to obtain a reconstructed daily scene data set. After clustering the daily scene samples, the application respectively reduces the dimension and reconstructs the samples of each cluster, improves the accuracy of the reconstructed daily scene data, significantly reduces the spatial and temporal correlation error of the reconstruction by considering the time and space correlation of the scene data, and strengthens the feature expression ability of the generated scene.

The invention provides an X-ray tube primary optical testing device. The X-ray tube primary optical testing device comprises a protective shell, a radiation source and a detector, wherein the protective shell is used for testing a test article; the radiation source and the detector are arranged in the protective shell and are adjustable in position; the detector is used for receiving a signal sent by the radiation source; a test article is placed in the protective shell; two groups of adjusting mechanisms which are oppositely arranged and are distributed on the left side and the right side of the test article are arranged in the protective shell; the adjusting mechanisms are used for adjusting the positions and the angles of the radiation source and the detector in the protective shell; the inclination angles and positions of the radiation source and the detector are adjusted through the adjusting mechanism, so that the imaging accuracy and definition can be improved, as images are allowed to be obtained at different angles, the geometric structure of the detection system is optimized, and more comprehensive information is provided. In addition, adjustment of inclination angles and positions of the radiation source and the detector can meet different detection requirements. In addition, by adjusting the positions of the radiation source and the detector, the unnecessary detection time can be reduced, and the detection efficiency is improved.

The present invention belongs to the technical field of picture transaction management, and specifically relates to a picture transaction platform management system based on artificial intelligence. By setting an upload entry in the picture display page of the transaction platform, historical purchasers are allowed to upload the usage status image and usage evaluation of the picture on the picture details page, thereby using the historical usage evaluation of the picture to screen the picture when performing picture retrieval, and can help purchasers better evaluate whether the picture is suitable for their needs by displaying the real usage status image and evaluation, thereby improving the accuracy and satisfaction of the selection. In addition, by increasing the upload of the usage status image and usage evaluation of the historical transaction pictures, the usage scenario is extracted from the usage status image with effective and positive evaluation and updated in the picture details page, thereby realizing the dynamic update of the picture application scenario, and can discover the potential value and new application scenario of the picture in actual application through the analysis of the actual usage scenario.

The application discloses a digital microfluidic chip integrating myocardial tissue culture and multimode detection, and belongs to the microfluidic chip field.The digital microfluidic chip comprises a lower substrate, an upper substrate and a sealing gasket; the lower substrate and the upper substrate are connected through the sealing gasket around the lower substrate and the upper substrate, and a space for liquid drop flow is formed in the middle; the lower substrate is provided with a functionalized partition electrode array, which comprises a liquid storage area, an electrical physiological acquisition area and a biochemical detection area; the electrical physiological acquisition area adopts an MEA electrical physiological acquisition array and is used for acquiring field potential signals of myocardial tissue in situ; a recess for accommodating a solid-phase carrier is formed in an electrode of the biochemical detection area, and a myocardial injury marker is captured through the solid-phase carrier; the upper substrate is made of a transparent material and is provided with a channel communicating with the liquid storage area and the electrical physiological acquisition area; and the digital microfluidic chip drives liquid drops through a dielectric wetting effect, integrates myocardial tissue culture, electrical physiological signal monitoring and biochemical marker detection on the same chip, and realizes in-situ synchronous detection of electrical physiology and biochemistry in a dual-mode manner.

The embodiment of the invention provides an information interaction system and method based on meta universe and computer equipment, and relates to the field of financial science and technology or other related fields. The system comprises a virtual image generation module, an information interaction module, a product recommendation module and a privacy protection module. The virtual image generation module is used for generating a virtual image according to image information sent by a user side when a login request of the user side is received for the first time, and the virtual image is a unique identity label of the user; and the information interaction module is used for receiving a user request of the user side, determining interaction information from other user sides based on the user request and the user virtual image, generating interaction data and sending the interaction data to the user side. The system is constructed based on the meta universe technology, the user performs information interaction with other users based on the unique virtual image generated by the system, and compared with the mode that the user only obtains information from an application program, the user can obtain more information, and the sense of participation and the sense of experience of the user are improved.

The invention belongs to the technical field of biology, and particularly relates to a honeysuckle SSR molecular marker development method based on honeysuckle genome sequencing and application of the developed SSR molecular marker in honeysuckle germplasm resource identification. The SSR molecular marker developed by the invention has the characteristics of good stability and high effectiveness. Eight pairs of SSR molecular marker primers are obtained by taking honeysuckle as a material through genome sequencing, SSR site analysis and identification, SSR primer design, SSR-PCR reaction system establishment, SSR-PCR amplification and effectiveness detection, and 30 honeysuckle germplasm resources can be effectively identified. The SSR molecular marker obtained by the invention can be used for germplasm resource identification, genetic diversity analysis and molecular-assisted new variety breeding of honeysuckle.

This invention relates to the field of artificial intelligence technology and discloses a method for identifying marine environmental risks based on big data. The method includes: standardizing marine environmental monitoring data to obtain a standardized dataset of the ocean; performing correlation analysis on the standardized dataset based on a pre-set risk knowledge base to obtain risk correlation features of the ocean; constructing a topology of the risk correlation features based on historical risk events of the ocean to obtain an environmental risk feature map of the ocean; tracking the trajectory of the environmental risk feature map to obtain the spatiotemporal evolution path of the ocean; simulating the spatiotemporal evolution path to obtain a risk evolution trajectory report of the ocean; and comprehensively evaluating the risk evolution trajectory report to obtain the risk level and early warning information of the ocean. This invention can improve the efficiency of marine environmental risk identification based on big data.

The application relates to the technical field of plasma detection, in particular to a double-channel ion energy probe based on a magnetic deflection effect. The application provides a double-channel ion energy probe based on a magnetic deflection effect, which comprises an upper permanent magnet plate, a lower permanent magnet plate, a double-channel collimator and a double-channel probe; the double-channel collimator penetrates into a shell; the double-channel collimator comprises a scanning channel and a reference channel; the scanning channel and the reference channel are connected with different values of voltage; the double-channel collimator is used for enabling ions to enter the shell along the channel direction; the upper permanent magnet plate and the lower permanent magnet plate are fixed at the upper and lower ends of the shell respectively so as to form a uniform magnetic field; the double-channel probe is arranged in the shell and comprises a scanning collection probe and a reference collection probe which are respectively coplanar with the scanning channel and the reference channel; and the scanning collection probe and the reference collection probe are respectively connected with different values of voltage. The scheme can provide an ion current probe with high signal-to-noise ratio.

The invention provides a kiwi fruit freshness indicating array and a preparation method and application thereof. The kiwi fruit freshness indicating array is composed of six indicating labels D1-D6, wherein the indicating label D1 comprises a purple sweet potato anthocyanin indicator; the indication label D2 comprises a curcumin indicator; the indication label D3 comprises an alizarin indicator; the indication label D4 comprises purple sweet potato anthocyanin and an alizarin indicator; the indication label D5 comprises purple sweet potato anthocyanin and curcumin indicators; the indication label D6 comprises alizarin and a curcumin indicator. The indication array comprises six indicators, can simultaneously indicate the freshness state of kiwi fruits, and has the advantages of comprehensive information, accurate measurement result, visual and clear result, easy implementation of the preparation method, low cost, and simple operation in use.

The application discloses a training method and device of a time sequence application model based on medical time sequence data, and relates to the fields of medical information and artificial intelligence. The method comprises the following steps: obtaining medical training samples; generating soft labels for the medical training samples based on classification judgment auxiliary information corresponding to the medical training samples, wherein the classification judgment auxiliary information represents continuous variables for distinguishing and quantifying the feature difference degrees of different samples in the same category; the soft label is a continuous distribution probability value, and the soft label is used for reflecting the confidence degree of the medical training sample belonging to a target category; and the neural network is iteratively trained according to the medical training samples and the soft labels of the medical training samples, so that a time sequence model is obtained. The application solves the technical problem that the robustness of the trained model is poor due to the excessively simple classification of the training labels in the prior art.

This invention relates to a multi-channel micro-area angle-resolved monitoring system and method. The monitoring system includes: a relatively movable incident arm and a receiving arm, the incident arm having at least two incident channels and the receiving arm having at least two receiving channels; an ellipsoidal beam path assembly and a holographic interference beam path assembly selectively and positionally adjustable in the incident and receiving channels; and a light source, a photodetector, and a large numerical aperture lens arranged in coordination. The ellipsoidal beam path assembly can be used to measure the ellipsoidal deviation of the sample, and the holographic interference beam path assembly can be used to perform off-axis digital holographic measurement of the sample. Furthermore, the relative movement of the incident arm and the receiving arm, combined with the large numerical aperture lens, allows for adjustment of the incident angle of the incident beam, thereby acquiring more comprehensive multi-dimensional optical signals and more accurately monitoring the optical properties of the sample.

The utility model relates to the field of medical instruments, and discloses a hand function training device which comprises an electroencephalogram cap and a muscle stimulator, the electroencephalogram cap is electrically connected with the muscle stimulator, the electroencephalogram cap is used for collecting electroencephalogram signals, and the muscle stimulator is used for receiving the electroencephalogram signals and sending out electrical stimulation signals based on the electroencephalogram signals. According to the hand function training device, training of the hand muscles and the central nervous system of the patient can be achieved, the hand muscles of the patient are trained through the hand function training device, the autonomous training consciousness of the patient can be stimulated, brain nerve repairing and remodeling of the patient are facilitated, and the rehabilitation effect of the patient is improved.

The utility model relates to a kind of point type smoke fire detector response threshold test tool, the tool includes box support, the left and right ends of box support have the opening consistent with its inner cavity contour, opening and inner cavity form horizontal test flue together;The tool further includes hollow rotating shaft vertically arranged on test flue, driving component for driving hollow rotating shaft to rotate, mounting seat in longitudinal movable cooperation with hollow rotating shaft, and adjusting component for adjusting the up-down position of mounting seat;The upper end of hollow rotating shaft penetrates test flue and is rotatably connected with box support;Hollow rotating shaft is provided with multiple and is side by side along the width direction of test flue;The utility model whole structure is simple, and it is convenient to adjust, and through adjusting component and rotatable hollow rotating shaft, multi-attitude test in horizontal all directions and longitudinal direction can be realized.