Patents
Literature
Patsnap Eureka AI that helps you search prior art, draft patents, and assess FTO risks, powered by patent and scientific literature data.

499results about How to "Maintain consistency" patented technology

Power data security policy large model question-answering system and method based on relation pooling

The invention belongs to the technical field of electric power data security management and intelligent question answering, and particularly relates to an electric power data security policy large model question answering system and method based on relation pooling. The system comprises a power data security policy knowledge base, a language model, a question processing module, an answer generation module and a user output module. Data of the electric power data security policy knowledge base comes from an electric power data security policy file; the language model converts a natural language problem into a structured query for knowledge base retrieval; the question processing module retrieves policy terms related to the natural language question to serve as retrieval results; the answer generation module generates a final answer according to the natural language question and a retrieval result of the knowledge base; by introducing the intelligent question-answering system combining the large language model and the knowledge base, the problems of low efficiency, inaccurate interpretation, incapability of dynamically updating and the like in the existing power data security policy query and management are solved.
Owner:ECONOMIC TECH RES INST OF STATE GRID HENAN ELECTRIC POWER +1

Generation and evaluation method for obtaining long text description from laparoscopic surgery image

The invention discloses a generation and evaluation method for acquiring long text description from a laparoscopic surgery image, which comprises the following steps of: constructing a cue word containing the laparoscopic surgery image, short text description, a target bounding box and surgery knowledge, and constructing long text description data by utilizing a large language model based on the cue word; constructing an image long text description generation model which comprises a pre-trained visual encoder, a visual feature query converter, a language decoder and an external operation concept vector database; performing supervised training on the image long text description generation model by using the long text description data; constructing a long text description evaluation method to evaluate the trained model; the method comprises the following steps: acquiring an input laparoscope image video stream through a laparoscope image system, and screening a key frame as a to-be-processed image; and inputting a to-be-processed image into the trained and evaluated model to obtain an image long text description result. According to the method, the ability of understanding operation details in the image can be enhanced, and more comprehensive operation image description can be generated.
Owner:ZHEJIANG UNIV

Signal processing method of computer system

The invention relates to multi-mode signal processing, and provides a signal processing method of a computer system. The method comprises the following steps: acquiring different modal signal data by using a plurality of sensors and performing timestamp synchronization; a depth time sequence alignment network and a multi-layer dynamic time warping algorithm are utilized to ensure signal time consistency; multi-modal signal features are extracted and fused through a multi-stream depth feature extraction network and a cross-modal attention mechanism; the system adopts a dynamic convolution kernel generation and meta-learning technology to carry out adaptive signal processing; noise suppression and signal optimization are carried out by using a multi-mode noise reduction auto-encoder and a generative adversarial network, and parameters are optimized and processed through closed-loop feedback control and reinforcement learning strategies. According to the method, synchronization, fusion, adaptive processing, noise suppression and real-time feedback control of multi-mode signals are realized, and the method has the advantages of high precision, high robustness and real-time performance.
Owner:LUOYANG INST OF SCI & TECH

Automatic driving forced lane changing decision-making method based on dynamic continuous game

ActiveCN119117003Adecision intelligenceImprove adaptabilityDecision modelIn vehicle
The invention relates to an automatic driving forced lane changing decision-making method based on a dynamic continuous game, which belongs to the technical field of intelligent connected automobiles and comprises the following steps: acquiring motion state information of a self-vehicle and surrounding vehicles in a forced lane changing scene through a vehicle-mounted sensor and vehicle-to-vehicle communication; calculating a collision boundary; generating an initial decision based on non-cooperative non-zero and dynamic games; optimizing the initial strategy by adopting a game strategy based on information continuity; and outputting a final forced lane change decision under the condition that the strategy after game decision optimization based on information continuity is continuously kept for three periods. According to the automatic driving forced lane changing dynamic game decision-making method considering decision-making continuity, the decision-making model is constructed by adopting non-cooperative non-zero and dynamic games, so that the driving safety, comfort and efficiency are improved; through a dynamic game algorithm based on decision continuity, decision adaptability and predictability are enhanced, stability and consistency of decision output are ensured, and uncertainty and risk are reduced.
Owner:JILIN UNIVERSITY

Intelligent plant extraction control method and system

The invention relates to the technical field of plant extraction, in particular to an intelligent plant extraction control method and system, and the method comprises the following steps: based on historic plant extraction data, including temperature, pressure and pH value during extraction, analyzing the long-term trend of parameters, predicting the requirements of plant extraction conditions by simulating parameter reactions under various conditions, and obtaining a plant extraction result; and obtaining a parameter prediction result. According to the method, long-term trend prediction of parameters such as temperature, pressure and pH value is realized through analysis of historically recorded plant extraction data, so that the parameters of extraction equipment are adjusted in advance, changes of different plant materials and environmental conditions are effectively adapted, the extraction efficiency is optimized, and by dynamically simulating the expression of the extraction efficiency in various time periods, the extraction efficiency is improved. According to the innovative scheme, an optimal extraction time window is mined, resource consumption and extraction time in the extraction process are reduced, and meanwhile the quality and consistency of extracts are kept.
Owner:GUANGDONG SHIFEI COSMETICS CO LTD

Text generation method based on variational auto-encoder and diffusion model

The invention provides a text generation method based on a variational auto-encoder and a diffusion model. The text generation method comprises the following steps: S1, converting discrete characters into continuous embedded vectors by using a BERT encoder; s2, extracting original text keywords and constructing a vocabulary graph; s3, converting the continuous embedded vectors into potential spatial representation by using an encoder in the variational auto-encoder to form potential vectors; s4, gradually iteratively adding Gaussian noise in the forward process of the diffusion model to reach a pure noise state; s5, gradually denoising and reconstructing potential vectors in a reverse process of the diffusion model, so that sensitive information is more effectively fuzzified; s6, mapping the reconstructed potential vector into a text vector by using a decoder in the variational auto-encoder; and S7, restoring the text vector into text data by using a text generator. The method has the advantages that sensitive information can be efficiently removed, important key information is reserved, and the method is suitable for generating safe and high-quality text content.
Owner:CHONGQING UNIVERSITY OF SCIENCE AND TECHNOLOGY

Assembling, welding and positioning method and device for automobile parts

The invention relates to the technical field of assembly welding, and particularly discloses an assembly welding positioning method and device for automobile parts. A welding state image between a target hush pipe and a target partition plate is collected through a camera; carrying out welding state mask segmentation on the welding state image by using an image identification and analysis algorithm based on computer vision, and then carrying out welding state feature extraction on the segmented welding detection area state mask image; and according to the expression obtained through neighborhood importance optimization of the extracted welding detection state characteristics, intelligent detection on whether defects exist in the welding state between the target hush pipe and the target partition plate or not is achieved. In this way, tiny defects such as tiny cracks and internal pores can be captured, and therefore the accuracy of defect recognition is improved. Moreover, the detection speed is greatly improved, the consistency and stability can be maintained, and the probability of missing detection or false detection is reduced, so that each welding point is ensured to be subjected to strict quality control.
Owner:深圳市生利科技有限公司

Mine dynamic disaster fine monitoring and dynamic early warning method without scale effect

The invention discloses a scale-effect-free mine dynamic disaster fine monitoring and dynamic early warning method, which comprises the following steps of: arranging a multi-point micro-seismic monitoring network on a coal mine working face, and continuously acquiring and preprocessing micro-seismic signals; an innovative analysis positioning algorithm is adopted to accurately analyze the accurate position and time information of the micro-seismic source; in combination with signal features and positioning data, a four-dimensional joint kernel density estimation and confidence interval theory is innovatively applied, a rock burst risk assessment model is constructed, and a danger level classification standard is determined; and the system calculates risk indexes in real time and dynamically issues early warning. According to the invention, the precision, timeliness and reliability of monitoring and early warning of the dynamic disasters in the mining area are obviously improved, and key technical support is provided for safe production of a coal mine.
Owner:CHONGQING UNIV

Fault report generation method based on dynamic window size in edge cloud scene

The invention relates to the technical field of computers, in particular to a fault report generation method based on the size of a dynamic window in an edge cloud scene, which comprises the following steps of: S1, performing data processing according to acquired data to obtain preprocessed data, and inputting the preprocessed data into a pre-training model for training to obtain an adjustment model; s2, multi-modal input data generates a multi-modal KV cache according to the adjustment model, encoding is carried out to obtain an encoding set, KV key value pairs are screened according to the encoding set, decoding is carried out after the KV key value pairs are combined, KV cache compression is carried out on the decoded data through Page Attelation to obtain matched compressed data, and a window is dynamically adjusted according to the compressed data; and S3, receiving second real-time operation state data of the edge equipment, generating a second historical fault report, and judging whether the second historical fault report meets the model requirements or not. Through LOOK-M and paged attention technologies, KV cache of a large model is reduced, memory use and calculation efficiency are optimized, model fine tuning is introduced, and it is ensured that a generated fault analysis report has high accuracy and real-time performance.
Owner:PIO CLOUD COMPUTING (SHANGHAI) CO LTD

Temperature characteristic controllable multilayer ceramic dielectric capacitor and preparation method thereof

The invention relates to a temperature characteristic controllable multilayer ceramic dielectric capacitor and a preparation method thereof, the multilayer ceramic dielectric capacitor is formed by a dielectric layer A and a dielectric layer B through mutual staggered superposition and firing, the dielectric layer A is composed of barium titanate, magnesium oxide, manganous-manganic oxide, vanadyl acetylacetonate, rare earth oxide A, rare earth oxide B, silicon dioxide, calcium carbonate and zirconium oxide, and the dielectric layer B is composed of barium titanate, magnesium oxide, manganous-manganic oxide, vanadyl acetylacetonate, rare earth oxide A, rare earth oxide B, silicon dioxide, calcium carbonate and zirconium oxide; the dielectric layer B is composed of barium titanate, magnesium oxide, manganous-manganic oxide, vanadyl acetylacetonate, rare earth oxide C, rare earth oxide D, silicon dioxide, calcium carbonate, zirconium oxide and nickel oxide; the multilayer ceramic dielectric capacitor is formed by the dielectric layers A and the dielectric layers B in a staggered and stacked mode through firing, the combination of the double dielectric layers is different from a traditional single dielectric layer, and the capacitor has the advantages of being high in dielectric constant and high in temperature stability at the same time.
Owner:FUJIAN TORCH ELECTRON TECH CO LTD

Multi-modal sentiment analysis method based on non-homogeneous hierarchical fusion

The invention discloses a multi-modal sentiment analysis method based on non-homogeneous hierarchical fusion, which comprises the following steps: S1, constructing a non-homogeneous hierarchical fusion network model which comprises a multi-modal word correction module, a Transform aggregation module, a cross attention fusion module and a function-based attention fusion module; s2, modal feature extraction is carried out through a multi-modal word correction module; s3, fusion of the visual mode and the voice mode is executed through a Transform aggregation module, and a video and voice fusion mode is obtained; s4, executing fusion of the text mode and the video and audio fusion mode through a cross attention fusion module; s5, dynamically adjusting the weight of each dimension in each modal representation through a function-based attention fusion module; and S6, predicting a final emotion regression label through regression analysis calculation. The emotion semantic information fusion method solves the problems of relatively large information density difference among voice, vision and texts, relatively high multi-mode isomerism difficulty and relatively poor effect in an emotion semantic information fusion method in the prior art.
Owner:CHINA THREE GORGES UNIV

Method, system, equipment and application for realizing multi-dimensional coherent symbiosis between physical world and digital world

The invention discloses a method, a system, equipment and application for realizing multi-dimensional coherent symbiosis between a physical world and a digital world, and relates to the field of virtual reality. According to the application, the entities in the physical world can have the networking capability no matter whether the entities can be networked or not. Through an immersion gateway in a specific field domain, entities in a physical world can be mapped into a digital world, and a multi-dimensional digital body is provided in the digital world and has different forms and functions. In the field domain deployed by the application, the entity of the physical world and the digital body of the digital world can realize the relationship of Coherent Symbiosis, can influence and synchronize with each other, and can keep consistent, harmonious and derived.
Owner:ZHIXINTONG TECHNOLOGY CO LTD +1

Intelligent scheduling method for optimizing time distribution of different grouping batches in tobacco shred production

The invention discloses an intelligent scheduling method for optimizing different grouping batch time distribution in tobacco shred production, and belongs to the technical field of tobacco production, and the method comprises the following steps: S1, data collection and processing: carrying out data collection through a sensor arranged on a tobacco shred production line, arranging the collected data into a time sequence data set, and carrying out data processing; s2, model training: training a prediction model by using the processed data, and adjusting model parameters to optimize the prediction model; and S3, optimizing a production plan: analyzing a result of the prediction model, and determining an optimal scheduling scheme. Prediction model training is carried out by utilizing historical data and real-time data, so that the prediction model can adapt to continuously changing production conditions, then prediction data is output in real time by utilizing the trained model, a prediction result is analyzed to optimize a production plan, batch scheduling is dynamically adjusted, the resource utilization rate is optimized, the downtime is reduced to the maximum extent, and the production efficiency is improved. The overall production efficiency is improved.
Owner:HEBEI BAISHA TOBACCO

Small-spacing display screen intelligent driving method and system based on glass substrate

The invention discloses an intelligent driving method and system for a small-spacing display screen based on a glass substrate, and relates to the technical field of display driving, and the method comprises the steps: building a light source characteristic model of the small-spacing display screen based on the glass substrate according to the current intensity of an input signal and the adjustment parameters of a backlight source; acquiring brightness output at the current moment according to the light source characteristic model, and acquiring operation parameters of the small-spacing display screen based on the glass substrate at the current moment; according to the brightness output and operation parameters at the current moment, multi-dimensional adjustment factors are calculated, and the multi-dimensional adjustment factors comprise a brightness compensation factor, a power optimization factor and a backlight dynamic adjustment factor; and performing threshold judgment according to the multi-dimensional adjustment factor, and when a preset threshold condition is met, performing brightness compensation, power optimization and backlight dynamic adjustment. Through comprehensive application of dynamic brightness adjustment, self-adaptive power optimization and multi-dimensional adjustment factors, stability, energy conservation and adaptive optimization of the display effect under different environmental conditions are realized.
Owner:SHENZHEN MINGZHI INTEGRATED CIRCUIT TECH CO LTD

Projector control method and projector

The invention relates to the technical field of projectors, in particular to a projector control method and a projector. The method comprises the following steps: performing image projection signal processing on target projection image data to generate initial projection picture data; performing projection point cloud space-time registration on the initial projection picture data by using the dual laser radar assembly to obtain projection scanning point cloud space data; performing shielding area geometric feature analysis on the projection scanning point cloud spatial data, determining an ideal projection area, and generating ideal rectangular projection area data; performing intelligent projection control parameter processing on the ideal rectangular projection area data to obtain intelligent projection control parameters; and performing projection attitude control instruction processing on the intelligent projection control parameters to obtain projection control optimization effect data. According to the invention, the projection control parameters are automatically adjusted through intelligent identification of the projection surface, so that the projector can maintain a stable projection effect in different environments, and the quality of a projection image is remarkably improved.
Owner:GUANGZHOU HONGHANG DIGITAL TECH CO LTD

Multi-task image processing method, system and equipment

The invention discloses a multi-task image processing method, system and device, and relates to the technical field of image processing, and the method comprises the following steps: constructing a multi-task network model; inputting the image data set into a multi-task network model to respectively obtain an infrared enhanced image, an infrared super-resolution image, an infrared and visible light image fusion image and an infrared image colorization image; and calculating a loss function between different images output by the multi-task network model and the infrared image and the visible light image in the input image data set, and carrying out loop training on the multi-task network model. According to the technical scheme, through unified training of the multi-task model, local details are effectively extracted, global consistency is kept, the processing efficiency and the image quality are greatly improved, redundant steps in the processing process are reduced, and the robustness and adaptability of the system are improved.
Owner:CHANGCHUN UNIV OF SCI & TECH

User track privacy protection method and system fusing generative model and three-stage personalized differential privacy

The invention discloses a user track privacy protection method and system fusing a generative model and three-stage personalized differential privacy, and relates to the technical field of data security, and the method comprises the steps: obtaining real user track data, and carrying out the preprocessing of the real user track data to form standardized track representation; training a depth generation model to generate synthetic trajectory data; performing density clustering on the synthetic trajectory to obtain a feature region and calculating a region centroid; point-level privacy budgets are distributed according to three stages of the area proportion, the centroid distance and the global density; constructing an adaptive elliptical disturbance domain based on the regional covariance, sampling candidate confusion points in the disturbance domain and applying road feasibility screening; and calculating a score based on the privacy budget and the utility function, and sampling replacement points by adopting an index mechanism to output a privacy protection trajectory. According to the technical scheme, the track structure continuity and the road semantic consistency are remarkably improved under the condition that the differential privacy constraint is met, and the privacy intensity and the data availability are both considered.
Owner:BEIJING UNIV OF TECH

Terrain data updating method, device and system

The invention relates to the technical field of smart mines, unmanned driving technologies and maps, and discloses a topographic data updating method, device and system. The method comprises the following steps: acquiring and storing initial topographic data of a target area, receiving and processing position data uploaded by at least one operation device, and preprocessing the position data to generate topographic change area data; generating a topographic data acquisition task based on the topographic change area data, issuing a task instruction corresponding to the topographic data acquisition task to topographic data acquisition equipment, and enabling the topographic data acquisition equipment to execute the task instruction according to the target acquisition path so as to perform topographic data acquisition; and receiving and processing the topographic data acquired by the topographic data acquisition equipment, and performing data updating on the initial topographic data through the topographic data acquired by the topographic data acquisition equipment to obtain updated topographic data. According to the invention, the updating efficiency and accuracy of the topographic data can be improved.
Owner:EACON TECHNOLOGY CO LTD +1

Graph optimization GNSS and IMU integrated navigation method based on dynamic window

The invention discloses a dynamic window-based graph optimization GNSS (Global Navigation Satellite System) and IMU (Inertial Measurement Unit) integrated navigation method, which improves the adaptability, calculation efficiency and positioning accuracy of a system in a dynamic environment by introducing a dynamic window strategy and a key frame mechanism. According to the method, the size of a sliding window is dynamically adjusted according to a real-time motion state, environment change and computing resources: when the environment is complex or high precision is needed, the window is enlarged to contain more historical information; when the environment is stable or computing resources are limited, windows are reduced to improve computing efficiency. Meanwhile, threshold values of position and posture changes are set, and only when the variable quantity of the current state and the latest key frame state exceeds the threshold values, new key frame nodes are added, key motion information is captured, and redundant calculation is avoided; according to the method, the optimal balance between the positioning precision and the calculation efficiency in a complex dynamic environment is realized, the method is suitable for an embedded platform with limited resources, and the requirement of high-precision real-time navigation is met.
Owner:GUIZHOU ELECTRIC POWER DESIGN INST

Digital-real fusion test method for reliability of blade disc structure of aero-engine

The invention discloses a number-real fusion test method for reliability of a blade disc structure of an aero-engine, and is applied to the field of time-varying reliability evaluation of the aero-engine. The method comprises the following steps: acquiring response data of a key part of a leaf disc structure under a full flight cycle; establishing a finite element virtual entity to obtain a time-varying input variable and a time-varying output response of the aero-engine bladed disc structure under the full flight cycle; establishing a physical information embedded loss function, and establishing an optimal physical information embedded multi-response regression model based on a Bayesian neural network inference framework; and extracting a large batch of time-invariant data sets, fitting a limit state function by using the established multi-response regression model, and calculating the reliability of the time-varying system based on the Monte Carlo thought to complete the reliability evaluation of the time-varying system. According to the method, a complex time-varying reliability evaluation problem is converted into a time-invariant response regression problem, and the calculation precision is effectively improved while the calculation task is simplified.
Owner:BEIHANG UNIV

Cardiopulmonary resuscitation equipment for medical rescue in emergency department

The invention relates to the technical field of emergency department medical rescue, in particular to cardio-pulmonary resuscitation equipment for emergency department medical rescue, which comprises a back plate, a support frame is fixedly mounted on the left side wall of the back plate, a bearing plate is fixedly mounted at the top end of the support frame, and a pressing and clinging assembly is arranged on the left side of the lower end surface of the bearing plate; the pressing fit assembly comprises an electric push rod fixed to the left side of the lower end face of the bearing plate, a fit pressing plate is fixedly connected to the bottom end of the electric push rod, a storage cavity is formed in the inner bottom end of the fit pressing plate, and a bag cushion is fixedly installed on the bottom end face of the fit pressing plate; a first hydraulic conveying pipe communicating with the interior of the storage cavity is fixedly installed on one side of the upper end face of the attaching pressing plate. The chest of a patient can be tightly fixed through synchronous expansion of the bag cushion, it can be ensured that a pressing head of the cardio-pulmonary resuscitation machine accurately and stably acts on a pressing part of the patient, and pressing position deviation caused by body movement or posture change of the patient is avoided.
Owner:CHONGQING MEDICAL UNIVERSITY AFFILIATED THIRD HOSPITAL(FANGDA HOSPITAL)

Product appearance defect identification method, device, equipment and medium

The invention belongs to the technical field of machine vision detection, and discloses a product appearance defect identification method and device, equipment and a medium. The method comprises the following steps: obtaining a to-be-recognized image of a product appearance, and processing the to-be-recognized image into a binary image; carrying out contour extraction in the OpenCV model to obtain a contour boundary of the product defect in the to-be-identified image; using a Douglas-Peucker algorithm to extract contour vertex coordinates from the contour boundary, and calculating the contour area of the product defect based on the contour vertex coordinates; determining a minimum bounding box containing a contour boundary through a contour searching method, extracting vertex coordinates of the bounding box, and calculating the area of the bounding box based on the vertex coordinates of the bounding box; and based on the contour area and the bounding box area, calculating an area error ratio of the contour area to the bounding box area, and based on the area error ratio, determining an identification result including qualified product appearance and unqualified product appearance. The detection efficiency can be effectively improved, and the product omission ratio is reduced.
Owner:DONGGUAN LVJUREN PURIFICATION TECH CO LTD

Remote control anti-delay video transmission method based on future scene generation network

The invention discloses a remote control anti-delay video transmission method based on a future scene generation network. The remote control anti-delay video transmission method comprises the following steps: synchronizing time references of a remote control vehicle and a remote cockpit; original video stream data of the environment where the remote control vehicle is located is collected; adding a camera number and timestamp information into the original video stream data; preprocessing the decoded video stream data to generate a plurality of paths of future scenes; generating multiple paths of future scene video stream data; camera numbers and timestamp information are added to the multiple paths of future scene video streams; decrypting, decoding and distributing the data; performing packet loss and time delay detection on the original video stream data, and performing visual quality optimization on the future scene video stream data; and a complete and continuous video stream is formed. According to the method, the delay in video transmission is greatly reduced, and the video content at the future moment can be predicted and generated in advance in future scene generation, so that the video blank possibly occurring due to transmission delay or data packet loss is effectively filled.
Owner:NANJING UNIV OF AERONAUTICS & ASTRONAUTICS +1

Automatic optimization control method for resistance spot welding

The invention discloses an automatic optimization control method for resistance spot welding, which relates to the technical field of resistance spot welding, and comprises the following steps of: acquiring welding object parameters and material information, selecting a proper electrode cap, and calculating an ideal welding current value; a historical database and a prediction model are established to predict the optimal combination state of current and pressure, and the welding process is optimized; ideal parameters are integrated into control parameters, and spot welding equipment is controlled to automatically complete spot welding work; a centering test is carried out before welding, so that the abnormal welding condition is avoided; through an intelligent algorithm and historical data analysis, welding parameters in the resistance spot welding process are automatically adjusted, efficiency and stability are improved, defective products are reduced, energy is saved, and higher-quality welding and higher production efficiency are achieved.
Owner:CHINA AUTOMOTIVE TECH & RES CENT CO LTD

Three-phase permanent magnet synchronous motor

The invention relates to the technical field of motors, in particular to a three-phase permanent magnet synchronous motor which is composed of a motor shell, a stator and a rotor and further comprises a cooling mechanism, the cooling mechanism is used for cooling the interior of the motor, and the cooling mechanism comprises an annular cooling cylinder fixedly arranged on one side of the motor shell. The stator and the rotor can be efficiently cooled through the annular cooling cylinder and the spiral liquid cooling pipe, and the design of the heat conduction assembly and the cooling assembly ensures that the temperature of each part in the motor is uniformly distributed, so that potential problems caused by local overheating are avoided. The uniform cooling helps to maintain the performance consistency and reliability of the motor, and the motor drives the first draft fan and the second draft fan to enable the cooled air to circulate in the motor shell and the rotor while starting, thereby improving the cooling efficiency, and enabling the cooling effect to be more remarkable.
Owner:DONGYING HERUI PETROLEUM TECH CO LTD

Intelligent identifying and positioning device for ground marking and management and control method of intelligent identifying and positioning device

The invention discloses an intelligent identifying and positioning device for ground lineation and a control method thereof, and relates to the technical field of intelligent equipment.The intelligent identifying and positioning device comprises a mounting base, a controller, a first support and a fixing seat, connecting blocks are welded to the two ends of the mounting base, and a driving motor is mounted on one side of one connecting block through a screw; according to the device, the recognition camera is used for capturing ground lineation images, the ground lineation images are converted into digital signals containing position and angle information, the signal receiving unit in the controller receives the signals, preprocessing and feature extraction are carried out through the image processing unit, and the recognition camera is used for recognizing the ground lineation images and converting the ground lineation images into the digital signals containing the position and angle information. The accurate position and angle of lineation are accurately determined; the control logic unit calculates the required adjustment amount according to the extracted feature information, and outputs a control signal to the executing mechanism through the driving control unit, so that accurate adjustment of the scribing equipment is realized; the closed-loop control mechanism ensures high precision and high efficiency of scribing.
Owner:武汉慧友佳华电子有限公司

Medical image segmentation method and device based on hierarchical multi-scale CNN-Transform

The invention discloses a medical image segmentation method and device based on hierarchical multi-scale CNN-Transform, and relates to the field of deep learning, a medical image segmentation model based on CNN-Transform is constructed and trained, a trained medical image segmentation model is obtained, a to-be-segmented medical image is obtained and input to the trained medical image segmentation model, and the to-be-segmented medical image is obtained. Inputting a to-be-segmented medical image into the stem layer for block segmentation to obtain a block image, and inputting the block image into a coding module to obtain a coding feature of a first stage and a coding feature of a third stage; inputting the coding feature of the first stage and the coding feature of the third stage into a double-layer feature fusion module to respectively obtain a calibrated coding feature of the first stage and a calibrated coding feature of the third stage; and inputting the calibrated coding characteristics of the first stage and the calibrated coding characteristics of the third stage into a decoding unit to obtain a prediction segmentation result. According to the method, the modeling capability of the model on the multi-scale long-range dependency relationship and the local space information can be improved.
Owner:THE FIRST AFFILIATED HOSPITAL OF XIAMEN UNIV +1

Virtual fitting video generation method, model training method and electronic equipment

The invention discloses a virtual fitting video generation method, a model training method, electronic equipment and a computer readable storage medium. The video generation method comprises the following steps: acquiring a human body video and a costume picture corresponding to target costume; extracting target clothing features and human body features corresponding to the video frames; fusing the target clothing feature with each human body feature in a spatial dimension; performing feature adjustment on the target clothing feature based on each human body feature to obtain each human body matching clothing feature matched with the human body in each video frame; and fusing each space fusion feature and each human body matching clothing feature in a time dimension to obtain a time fusion feature, and obtaining each human body try-on video frame on which the target clothing is tried according to the time fusion feature. Through the scheme provided by the invention, the generated virtual try-on video has better inter-frame continuity and fluency, so that the authenticity of the final virtual try-on video is improved, and the virtual try-on effect is better.
Owner:TAOBAO CHINA SOFTWARE

Commodity recommendation system and method based on artificial intelligence

The invention discloses a commodity recommendation system based on artificial intelligence, and the system comprises a user behavior tracking module which is used for collecting and processing the multi-source behavior data of a user; the commodity feature extraction and fusion module is used for acquiring and analyzing multi-modal information of commodities; the dynamic updating module is used for adjusting a recommendation list in real time according to instant user behaviors and long-term preferences in combination with short-term memory and long-term memory; the situation awareness module takes external factors such as time, place and weather as input; the explanatory enhancement module is used for adding an explanatory layer for a black box model by using an explanatory machine learning model; the personalized sorting optimization module is used for dynamically adjusting the feature weight and improving the click rate and the conversion rate; and the privacy protection module is used for protecting user privacy by adopting a differential privacy technology. According to the commodity recommendation system and method provided by the invention, many problems existing in a traditional recommendation system are overcome, and a more efficient, more intelligent and safer commodity recommendation service is realized.
Owner:KECHUANGTONG CHENGDU CO LTD

Machine vision unit applied to intelligent security management system of intelligent community

The invention discloses a machine vision unit applied to a smart community intelligent security management system, and relates to the technical field of image processing, and the machine vision unit comprises an image obtaining module which obtains a real-time video stream monitored at night, and carries out the frame cutting to obtain a plurality of frames of images; the multi-frame image fusion module is used for processing the multi-frame image by using a multi-exposure fusion algorithm to generate a fused image; the self-adaptive correction module is used for self-adaptively adjusting the brightness and the contrast ratio of the fused image and carrying out detail enhancement and color correction; the image processing module is used for removing noise and enhancing details through bilateral filtering and a multi-scale Retinex algorithm; and the image post-processing module is used for performing color balance adjustment to ensure that the images are natural and consistent. Through multi-frame image fusion, adaptive correction, multi-scale detail enhancement and color balance processing, the definition, detail expression and recognition precision of the image in a night monitoring scene are remarkably improved, the adaptability and robustness of the system are enhanced, and meanwhile redundant information and resource consumption in the processing process are reduced.
Owner:SHANGHAI TIANQI INTELLIGENT BUILDING CO LTD