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

140results about How to "Achieve training" patented technology

Fine-grained multi-mode prompt learning method based on visual language pre-training model

The invention discloses a fine-grained multi-modal prompt learning method based on a visual language pre-training model, and relates to the technical field of visual language pre-training models.The method comprises the steps that a multi-modal prompt learning vector used for learning visual features and text features is constructed, and a fine-grained multi-modal prompt learning model is constructed based on the fine-grained multi-modal prompt learning model; global differences, subtle distinguishing visual features and category difference text features among different visual categories are generated, and a multi-modal prompt learning vector is optimized based on a cosine similarity loss function. According to the invention, through combination of dual-granularity visual prompt and text prompt, the problems that in an existing prompt learning tuning method, cooperative reasoning cannot be carried out in a dual-mode prompt representation space, and fine distinguishing features are difficult to capture are effectively solved; and superior migration generalization ability and few-sample learning ability are verified on a plurality of main image identification reference data sets, and the performance is remarkably improved in downstream tasks.
Owner:TECH & ENG CENT FOR SPACE UTILIZATION CHINESE ACAD OF SCI

Intelligent agent construction method and system based on large language model, medium and equipment

The invention provides an agent construction method and system based on a large language model, a medium and equipment, and relates to the technical field of decision agent construction. According to the method, an appropriate large language model is selected, a series of prompt project texts are established for the large language model, target codes are generated as required by utilizing the large language model and prompt projects, and class library functions of a network model library, a reinforcement learning algorithm and a simulation training environment can be correspondingly called by running the codes. Finally, auxiliary construction and training of the decision-making agent are realized, and the problems in the existing decision-making agent construction and training process are solved.
Owner:BEIJING AEROSPACE CHENXIN TECH CO LTD

Knowledge graph construction method and device, medium, electronic equipment and program product

The invention relates to a knowledge graph construction method and device, a medium, electronic equipment and a program product. The method comprises the steps of obtaining target text data related to a target field; inputting the target text data into the trained information extraction model to obtain the entity relationship between the target entities; based on the target entity and the target entity relationship, constructing a target knowledge graph related to the target domain; wherein the information extraction model is trained in the following mode: obtaining sample text data which comprises a sample text, a sample entity label and a sample entity relation label, the sample text, the sample entity label and the sample entity relation label are obtained by processing data inquired from a multi-source knowledge graph comprising multiple domain knowledge and data obtained by inquiring a large language model, and the problem that the training data acquisition cost is extremely high or a large amount of training data is difficult to acquire is solved.
Owner:SHENHUA GUONENG ENERGY GRP +1

Lightweight monocular depth estimation method and device based on self-supervised deep learning

PendingCN119494866APreserve detailed featuresPreserve local detail featuresImage enhancementImage analysisFeature extractionRadiology
The invention relates to a lightweight monocular depth estimation method and device based on self-supervised deep learning, and the method comprises the steps: obtaining a plurality of continuous frames of images, carrying out the reconstruction of a target frame through a trained depth estimation model based on the adjacent frames of the target frame, and obtaining the depth information of the target frame, the training process of the depth estimation model comprises the following steps: obtaining a monocular video sequence, and constructing training data by extracting continuous multi-frame images; predicting relative pose information of two adjacent frames of images through pose coding and decoding; through multi-scale feature extraction and dynamic up-sampling, obtaining a feature map with local detail features reserved, and obtaining a depth map based on the feature map; and performing frame reconstruction based on the relative pose information and the depth map, and calculating a loss function value on the premise of considering triple loss based on semantic perception so as to realize training of a depth estimation model. The method has the advantages that detail features are fully reserved during up-sampling, and the expression effect on gradient-rich areas is good.
Owner:DONGHUA UNIV

Electronic device and method for neural network model training processing, and medium

The invention provides an electronic device and method for neural network model training processing and a medium, a central processing unit is configured to perform storage control on intermediate tensors in neural network model training: for a generated first intermediate tensor, determining whether a current storage utilization rate of a memory of an artificial intelligence processing unit exceeds a first threshold, transferring the first intermediate tensor from the memory of the artificial intelligence processing unit to the memory of the central processing unit under the condition that the first threshold value is determined to be exceeded; and before the first intermediate tensor is used for calculation in the backward calculation, the storage position of the first intermediate tensor is judged, and under the condition that it is determined that the storage position is the storage of the central processing unit, the first intermediate tensor is retrieved from the storage of the central processing unit to the storage of the artificial intelligence processing unit so as to be used for the backward calculation. According to the application, the intermediate tensor can be dynamically unloaded to the memory of the central processing unit according to the storage occupation condition of the artificial intelligence processing unit.
Owner:SHANGHAI BIREN TECH CO LTD

Bidirectional DC / DC converter parameter identification method based on physical information machine learning

The invention provides a bidirectional DC / DC converter parameter identification method based on physical information machine learning, and relates to the technical field of parameter identification. The method comprises the steps of firstly completing establishment of a system dynamic model of the bidirectional DC / DC converter, secondly utilizing an implicit Runge-Kutta method to construct a relationship between a data intermediate state and an initial state as well as a relationship between the data intermediate state and an end state, applying the relationship to the system dynamic model, then inputting historical training data into a deep neural network to obtain the intermediate state of the data, and finally establishing a system dynamic model of the bidirectional DC / DC converter. And substituting the physical model as an input to realize seamless coupling of the physical model into training of the deep neural network. And then the trained PINN is used to realize online parameter identification. The hybrid design can seamlessly combine the data of the BDDC physical model, and effectively modulate the training stage, so that the training stage is forced to be executed to the underlying physical principle and constraint of the converter, and the required training data is greatly reduced.
Owner:ANHUI UNIV

Method for obtaining pigment cells through in-vitro culture of plectropomus leopardus skin tissue

The invention discloses a method for obtaining pigment cells through in-vitro culture of plectropomus leopardus skin tissues. The method comprises the following steps: step A, preparing a primary cell culture solution; step B, pretreating the plectropomus leopardus skin tissues to obtain pretreated fish skin tissues; step C-1, carrying out a digestion reaction on the pretreated fish skin tissue by an enzymolysis method to obtain an explant; and step C-2, carrying out in-vitro culture on the explant through an explant method to obtain the plectropomus leopardus skin tissue primary pigment cells. The plectropomus leopardus skin tissue is successfully separated and cultured into a plectropomus leopardus skin tissue primary pigmented cell group by combining an enzymolysis method and an explant method, so that coexistence culture of several kinds of pigmented cells is realized. Raw materials are provided for exploring the self function and gene regulation and control mechanism of the pigmented cells, and preconditions of in-vitro verification experiments are provided for further exploring the influence of the pigmented cells on the body color. Meanwhile, a foundation is laid for breeding of improved varieties of the plectropomus leopardus.
Owner:SANYA INST OF OCEANOGRAPHY OCEAN UNIV OF CHINA

Physical field prediction method based on deep fuzzy physical information neural network

The invention discloses a physical field prediction method based on a deep fuzzy physical information neural network, and the method comprises the following steps: S1, collecting physical field data, carrying out the preprocessing of the data with noise, and obtaining a processed training data set Dtrain and a test data set Dtest; s2, constructing a deep fuzzy physical information neural network model; s3, inputting a physical field training data set with Gaussian noise and a corresponding partial differential equation, and training the neural network model to obtain a trained neural network model; s4, physical quantities in different time-space coordinates in the test data set are calculated through the trained neural network model, and physical field prediction is achieved; the method solves the problems that the existing physical information neural network method does not consider the condition that noise exists in a training data set, the training effect of a deep neural network model is poor under the interference of a noise data set, and physical information in a partial differential equation cannot be accurately learned, so that the prediction performance of a physical field is seriously reduced.
Owner:SICHUAN UNIV

Unfavorable geological type identification method and system based on joint deep learning network

The invention provides an unfavorable geological type identification method and system based on a joint deep learning network, and relates to the technical field of geological disaster forecasting. Comprising the following steps: acquiring training information including geological data of an excavation section, geophysical prospecting inversion imaging information and drilling information; inputting the training information into a pre-established joint deep learning network model, performing data preprocessing, feature extraction and feature fusion in sequence to obtain joint feature representation, and based on the joint feature representation, obtaining a discrimination type and a morphological description of the unfavorable geologic body; wherein the joint deep learning network model comprises a DNN model, a CNN model and an RNN model, and the DNN model, the CNN model and the RNN model are respectively utilized to extract the features of the digital data, the image data and the text description data in the training information. The method can quickly and accurately carry out type discrimination and form description on the unfavorable geologic body in front of the tunnel, and reduces the manual forecasting pressure.
Owner:SHANDONG UNIV

Method for controlling sludge bulking and realizing sludge granulation by using iron-carbon micro powder

The invention discloses a method for controlling sludge bulking and realizing sludge granulation by using iron-carbon micro powder. The method comprises the following steps: crushing and grinding iron-carbon particles, and screening to obtain iron-carbon micro powder with the particle size of 50-200 microns; adding the iron-carbon micro powder into the expanded activated sludge system according to the adding amount of 0.5-5.0 kg / m < 3 >; and after addition, the sludge bulking phenomenon is rapidly controlled, and the sludge settling performance is obviously improved. Besides, the iron-carbon micro powder is used as a crystal nucleus, and the iron-carbon powder plays a micro-electrolysis role, so that the formation of the aerobic granular sludge is promoted, and meanwhile, the pollutant removal performance of the system is improved. The problem of sludge bulking in wastewater can be effectively solved, and the aerobic granular sludge with efficient treatment performance can be cultured.
Owner:ZHEJIANG UNIV OF TECH

Waist exoskeleton robot based on series elastic drivers

The invention provides a waist exoskeleton robot based on serial elastic drivers, and relates to the technical field of medical robots. The waist exoskeleton robot comprises two binding pieces, namely a lower binding piece and an upper binding piece arranged above the lower binding piece; the four series elastic drivers are arranged in a bilateral symmetry mode in pairs, the upper end of an upper connecting rod of each series elastic driver is rotatably connected with the waist protection plate of the upper binding piece, and the lower end of a lower connecting rod of each series elastic driver is rotatably connected with the waist protection plate of the lower binding piece. The device has the beneficial effects that the four elastic drivers connected in series generate upward driving force to jointly drive the upper binding piece and the lower binding piece to generate upward traction force, so that an upward traction effect is generated on the lumbar vertebra, and the lumbar vertebra is stretched in a standing posture and a sitting posture; waist muscle movement is simulated to achieve traction rehabilitation or rehabilitation exercise prescription training of the waist of the human body, the four series elastic drivers form a parallel mechanism, and the portability of the parallel waist exoskeleton is improved.
Owner:KUNMING UNIV OF SCI & TECH

Visual function training instrument and control system

The invention discloses a visual function training instrument and a control system, and belongs to the technical field of visual function training.The visual function training instrument comprises a shell, an eyepiece is arranged on one side of the shell, three sets of light sources with different wave bands are fixedly installed on the two side walls of the shell, the light sources are electrically connected with light wave adjusting mechanisms, and the light wave adjusting mechanisms are electrically connected with the eyepiece. The device comprises a shell, a moving mechanism is arranged in the shell, the moving mechanism comprises a transmission belt, two rotating mechanisms are connected to the transmission belt in a clamped mode, each rotating mechanism comprises a first motor and a rotating block, the rotating blocks are connected to the output ends of the first motors in a sleeving mode, and target objects for training are installed at the output ends of the two first motors. Through three stages of training, blood circulation of the eyes can be quickly broken through, ciliary muscles can be exercised, crystalline lenses can recover normal regulation force, light with nutrition needed by normal development of the eyes is supplemented, and the visual function training effect is improved.
Owner:CHENSHIMING HEALTH TECHNOLOGY (CHONGQING) CO LTD

Spatial-temporal data prediction method and system for heterogeneous photovoltaic diagram structure data fusion

The invention belongs to the technical field of data processing. The invention provides a spatio-temporal data prediction method and system for heterogeneous photovoltaic diagram structure data fusion, and the method comprises the steps: a current client obtains a photovoltaic power generation prediction result of the current client at each moment in the future after a current moment based on the historical photovoltaic power generation data of the current client and a trained global model; the global model training process comprises the steps that the central server distributes a global model pre-trained according to a photovoltaic generating capacity data set to all clients, and each client trains the global model through independent local graph data to perform local updating; each client uploads a local update result to a central server for aggregation, and the central server trains a GCN part of a global model according to an aggregation result and distributes the trained global model to each client for use; on the premise of ensuring data privacy of each client, updating and training of a global model are realized, and prediction comprehensiveness is greatly improved.
Owner:INFORMATION COMM COMPANY STATE GRID SHANDONG ELECTRIC POWER

Radar measurement distance fitting method and device based on deep learning

The invention provides a radar measurement distance fitting method and device based on deep learning, and the method comprises the steps: inputting a radar distance measurement data sample which comprises a radar measurement distance data true value, corresponding dynamic factor data influencing radar distance measurement, and corresponding static factor data influencing radar distance measurement; extracting static data features of the static factor data and dynamic data features of the dynamic factor data; splicing the static data features and the dynamic data features corresponding to the radar ranging data samples to obtain a high-dimensional target feature vector; and performing radar measurement distance data prediction based on the high-dimensional target feature vector, and constructing a loss function between a radar measurement distance data prediction value and a radar measurement distance data true value at the same time, thereby realizing model training, and obtaining an optimal training model. According to the method, the tendency and periodicity of the factors and the dependency relationship between the factors are considered, feature extraction of the mixed factors is realized, and the prediction result is more accurate.
Owner:NAT UNIV OF DEFENSE TECH

Method and system for extracting advanced semantic information from multiple physiological signals

The invention discloses a method and a system for extracting advanced semantic information from various physiological signals, and belongs to the field of time sequence data processing. Synchronously acquired electroencephalogram signals and other physiological signals are respectively input into an electroencephalogram base model and a physiological encoder, and semantic representations of the electroencephalogram signals and the other physiological signals are extracted as advanced semantic information to realize downstream tasks based on the physiological signals; the electroencephalogram base model is a pre-training model, and the training process of the physiological encoder comprises the following steps: giving a multi-channel time sequence of two sections of synchronously acquired electroencephalogram signals and other physiological signals; semantic representation of the electroencephalogram signals is extracted through a pre-trained electroencephalogram base model; semantic representations of other physiological signals are extracted through a physiological encoder; and aligning the semantic representation of the electroencephalogram signal with the semantic representation of other physiological signals by adopting a comparative learning method so as to train the physiological encoder. According to the invention, a machine can understand physiological signals and complete various downstream tasks related to medical care.
Owner:ZHEJIANG UNIV

Urban building three-dimensional reconstruction method and system based on virtual modeling

The invention relates to the technical field of image enhancement three-dimensional reconstruction, in particular to an urban building three-dimensional reconstruction method and system based on virtual modeling, and the method comprises the steps: obtaining a gray-scale map and a depth map of an urban building at different visual angles through employing a camera carried by an unmanned plane; obtaining the depth homogeneity of each pixel point in each depth map based on the similarity degree of the depth value change in the local window of each pixel point in each depth map; based on the spatial difference and gray level distribution difference of point cloud data of each visual angle and the adjacent visual angle thereof, and the gray level difference condition of pixel points at the same position in the gray level images of each visual angle and the adjacent visual angle thereof, the reflection standard difference and the depth homogeneity are combined; and obtaining a luminosity compensation weight of each pixel point in each visual angle grey-scale map to construct a loss function, and training a deep learning model to obtain a three-dimensional model of the urban building. According to the invention, the accuracy of virtual modeling three-dimensional reconstruction is improved.
Owner:XINZHIHANG MEDIA TECH GRP CO LTD

Storage, calculation and training integrated cloud computing server optimization method based on human brain neural network

The invention discloses a storage, calculation and training integrated cloud computing server optimization method based on a human brain neural network. The method comprises the following steps: S1, designing a self-adaptive learning model based on the human brain neural network; s2, forming an integrated framework; s3, adopting a novel processor design; s4, optimizing an adaptive learning model architecture of the human brain neural network through a deep learning technology; s5, dynamically adjusting distribution of computing resources based on the real-time data flow and the computing requirements; s6, realizing data transmission path optimization by designing an adaptive data routing algorithm; s7, self-optimization is realized in the cloud computing server by using a synaptic plasticity mechanism of the adaptive learning model, and the adaptive learning model can autonomously adjust parameters and optimize performance according to historical data and a current state; and S8, integrating an intelligent fault detection and repair module in the adaptive learning model. The system state is monitored in real time, faults are detected and repaired, and the reliability and stability of the system are improved.
Owner:HUNAN UNIV OF SCI & ENG

Mechanical assembly three-dimensional target detection method and system based on CAD model domain point cloud data

The invention belongs to the technical field of three-dimensional target detection, and particularly discloses a mechanical assembly three-dimensional target detection method and system based on CAD model domain point cloud data, and the method comprises the steps: obtaining model domain point cloud and corresponding labels based on a CAD three-dimensional model of a mechanical assembly, and enabling the labels to reflect the types and positions of parts; training a detector and a domain discriminator through the point cloud data of the model domain and the real domain, and taking a maximum domain discriminator error and a minimum detector error as loss functions; the detector comprises a feature extractor and a label predictor, the feature extractor extracts point cloud features, the domain discriminator discriminates whether the features are from the model domain or the reality domain, and the label predictor outputs corresponding labels according to the model features. And inputting the real domain point cloud into the trained detector, and outputting a corresponding label. According to the invention, the parts of the assembled assembly can be accurately identified and positioned.
Owner:HUAZHONG UNIV OF SCI & TECH

A training method and device for a multi-task model

Disclosed are a method and device for training a multi-task model, which are used to train an initial multi-task model. The initial multi-task model may include at least one first abnormal sub-task layer. The method provided by the present disclosure can use a training data set to train at least one pre-established first single-task model to obtain first model parameters corresponding to each first single-task model, wherein the first single-task model includes a second abnormal sub-task layer, the second abnormal sub-task layer is obtained based on the first abnormal sub-task layer, and the initial multi-task model is updated based on the first model parameters to obtain a trained multi-task model, so as to realize the training of the initial multi-task model. This solves the problem in the prior art that when training a multi-task model, if an abnormality occurs during the training process, the training data needs to be reused to train the multi-task model, thereby reducing iteration time and improving training efficiency.
Owner:BEIJING HORIZON ROBOTICS TECH RES & DEV CO LTD

Hand holding structure of fitness equipment and use method of hand holding structure

The invention discloses a hand holding structure of fitness equipment and a using method of the hand holding structure. The hand holding structure comprises a connecting base, a first dividing plate is fixedly connected to the left side surface of the connecting base, a second dividing plate is fixedly connected to the right side surface of the connecting base, a thrust roller bearing is fixedly connected to the outer surface of the connecting base, and a rotating shaft is rotationally connected to the outer surface of the connecting base; a first pin shaft is fixedly connected to the end of the right side of the left supporting arm, the first pin shaft is rotatably connected with the connecting base, the left supporting arm is slidably connected with the first index plate, and a first arc-shaped lower support is fixedly connected to the end of the left side of the left supporting arm. The front-back angle of the left supporting arm and the front-back angle of the right supporting arm are changed, the shape of the device can be flexibly adjusted according to using requirements in the using process of the device, and the using requirements of various fitness enthusiasts are fully met.
Owner:JIANGSU COLLEGE OF NURSING

An adaptive remote sensing deep learning detection method for tailings ponds

The adaptive tailings pond remote sensing deep learning detection method provided by the present invention is used for large-scale tailings pond identification and extraction. The present invention proposes a new tailings pond remote sensing extraction framework, namely: first, a feature pyramid network is used to perform deep feature learning of tailings ponds of different sizes based on a tailings pond remote sensing image data set; second, a cascade positioning optimization module is used to locate the tailings pond according to the characteristic value and use a multi-level detector to optimize the positioning coordinates; third, candidate detection objects are obtained according to the positioning optimization value, and multi-dimensional features are extracted and fused based on the deep learning algorithm and the traditional feature extraction algorithm to generate feature vectors; finally, an adaptive feature learning classifier is used to perform integrated learning and classification based on the feature vector, eliminate false alarm targets and extract tailings ponds. The present invention has the advantages of high positioning accuracy, low false alarm rate, and wide application range, and can provide an important basis for dynamic updating of tailings pond distribution information and safety management.
Owner:HUAZHONG NORMAL UNIV

Fiber composition classification method based on one-dimensional convolutional neural network

The present invention provides a fiber component classification method based on a one-dimensional convolutional neural network, which belongs to the intersection of cloth textile component analysis and artificial intelligence technology. The classification method comprises the following steps: cloth fiber near-infrared spectrum data collection, one-dimensional convolutional neural network construction, convolutional neural network hyperparameter selection, one-dimensional convolutional neural network parameter training, and model result verification. The purpose of the present invention is to provide a fiber component classification method based on a one-dimensional convolutional neural network, which does not require the experience and knowledge of experts in the field, automatically extracts effective features from one-dimensional fiber near-infrared spectrum data for determining the various fiber categories contained in the textile to be tested, and realizes an end-to-end training and prediction model framework. Experiments show that the method provided by the invention can effectively solve the problem of textile fiber component classification and significantly improve the accuracy of classification results.
Owner:池明旻

Training method and device for gas reservoir recovery ratio prediction model

The invention discloses a training method and device for a gas reservoir recovery ratio prediction model, which can be applied to the field of deep learning, and the method comprises the steps: obtaining historical feature data of a plurality of gas reservoirs in a preset time period, and then performing iterative training on a first network in the gas reservoir recovery ratio prediction model by using dynamic continuous feature data in the historical feature data, and in each iterative process, adjusting network parameters of the first network until a loss function of the first network reaches a minimum value. And performing iterative training on the second network by using static discrete feature data in the historical feature data, and in each iteration process, adjusting network parameters of the first network until a loss function of the second network reaches a minimum value. The trained gas reservoir recovery ratio prediction model can be used to predict the recovery ratio of the gas reservoir, and the two deep learning models are coupled, so that the generalization ability of the model can be enhanced, and the prediction accuracy and stability can be improved.
Owner:HEFEI UNIV OF TECH

Leaping ability training device

The invention discloses a leaping ability training device which comprises a leg muscle training mechanism, a lower bouncing mechanism, an upper bouncing mechanism and a lower bouncing mechanism. The upper bouncing mechanism is arranged at the top end of the lower bouncing mechanism; the leg muscle training mechanism comprises a base, a guide plate is slidably mounted at one end of the base, a supporting frame is mounted at the top of the guide plate, a foot squatting plate is mounted at the top of the supporting frame, and a spring for driving the foot squatting plate is mounted on the base; chair legs are detachably installed at the end, away from the foot squatting plate, of the base, a seat is installed at the top ends of the chair legs, and a safety rod acting on the chair legs is installed on the base. Leg muscles can be trained through the leg muscle training mechanism, so that legs are trained, and the subsequent bouncing effect is improved; the lower bouncing mechanism can improve the bouncing effect of the upper bouncing mechanism, and therefore bouncing training is conducted.
Owner:WUXI INSTITUTE OF TECHNOLOGY

A speech conversion method based on autoencoder framework

The invention belongs to the technical field of speech conversion, and specifically relates to a speech conversion method based on an automatic encoder framework. The system framework constructed by the invention comprises only one encoder, so that the Mel spectrum information of the original input is not lost during the training process, and perfect reconstruction is achieved; the extractability of three speech features of content, timbre and rhythm is ensured by combining training through an encoder and a decoder with two constraint models; and the extractability of the three speech features of content, timbre and rhythm is further ensured by adopting a discriminator; when the invention performs speech conversion on audio with different contents, the training of paired data is not involved, and the model training process only reconstructs itself, so efficient speech conversion is achieved; and it is ensured that all speech features are completely separated, and the conversion is performed on speech style.
Owner:SICHUAN XW BANK CO LTD +1

Image storage method and device, electronic equipment and storage medium

The embodiment of the invention provides an image storage method and device, electronic equipment and a storage medium, and is applied to the technical field of images. According to the method provided by the embodiment of the invention, the to-be-stored image can be encoded through the encoder of the deep learning model, the classifier classifies the encoded first image feature, and the decoder decodes the sampled first potential spatial feature to obtain the first decoded image. Calculating a second loss value according to the first decoded image and the to-be-stored image, and calculating a first loss value according to the first classification result and the extraction code; and adjusting parameters of the deep learning model through the loss value to realize training of the deep learning model. According to the image storage method and device, storage of the to-be-stored image is realized through training of the deep learning model, the first coding information after coding of the to-be-stored image is stored in the potential space, a storage device cannot directly view the to-be-stored image, and the image can be read only by extracting the code, so that the image storage security is improved.
Owner:HANGZHOU HIKVISION DIGITAL TECHNOLOGY CO LTD

Multifunctional training device

The utility model discloses a multifunctional training device which comprises a bottom plate, a fixing seat is fixedly installed in the middle of the top of the bottom plate, the interior of the fixing seat is hollow, a seat is fixedly installed at the top of one end of the fixing seat, pedals matched with the seat are fixedly installed on the two sides of the top of one end of the bottom plate, and the pedals are fixedly installed on the bottom plate. A multifunctional training mechanism is mounted on the fixed seat; the multifunctional training mechanism comprises a guide rail, a pulley, a moving plate, a pull rod, a pull rope, two guide rods, a moving block, a spring and an adjusting plate, the number of the guide rods is two, the two ends of the two guide rods are fixedly connected with the opposite side faces in the fixing base respectively, and the moving block and the adjusting plate are installed on the two guide rods in a sliding mode. By means of the structure, the same training device can meet the requirement for training of arms, waists and legs of people at the same time, is small in occupied area, suitable for crowded and narrow positions such as families and offices and convenient to use for physical training of people.
Owner:董红心

Training method, device, equipment and medium for interface data generation model

The embodiment of the present invention discloses a training method, device, equipment and medium for an interface data generation model. The method includes: determining the basic model parameters of a pre-built basic interface data generation model, and determining the hardware parameters of the current server to which the basic interface data generation model is applied; updating the basic model parameters according to the hardware parameters to obtain a candidate interface data generation model after the initial update; inputting the current training data in the model training data set into the candidate interface data generation model, outputting the current interface data, and determining the model evaluation score of the candidate interface data generation model according to the current interface data; iteratively training the candidate interface data generation model according to the model evaluation score and the hardware parameters to obtain a target interface data generation model. The accuracy of training the basic interface data generation model is improved, thereby improving the accuracy of subsequently determining the interface display data based on the target interface data generation model.
Owner:HANGZHOU HAOLINK INTELLIGENT TECHNOLOGY CO LTD +1

Screening culture equipment for corn transgenic breeding

The utility model relates to the technical field of breeding screening equipment, and discloses corn transgenic breeding screening culture equipment which comprises a heat preservation box, a motor is fixedly connected to one side of the heat preservation box, a rotating shaft is rotatably connected to the interior of the heat preservation box, an eccentric wheel is fixedly connected to the periphery of the rotating shaft, and a vibration screen plate is slidably connected to the interior of the heat preservation box. The eccentric wheel abuts against the lower portion of the vibration sieve plate, a limiting groove is formed in the heat preservation box, limiting blocks are fixedly connected to the two sides of the vibration sieve plate, the limiting blocks are slidably connected to the interior of the limiting groove, one rotating shaft is fixedly connected to the output end of the motor, and a transmission wheel is fixedly connected to one end of the rotating shaft. According to the corn screening and cultivating device, through cooperation of the motor, the rotating shaft, the eccentric wheel, the belt, the transmission wheel, the vibrating screen plate, the limiting block and the limiting groove, screening and cultivating of corn are achieved, and through cooperation of the door plate and the dismounting assembly, the heat preservation box is convenient to open.
Owner:SHAANXI INST OF BIOLOGICAL AGRI

Information recommendation model training method, information recommendation method, device and server

The present disclosure relates to a training method, information recommendation method and device for an information recommendation model. The information recommendation model training method includes: obtaining initial sample features and actual operation results of sample accounts for sample recommendation information; the initial sample features are obtained based on sample account features and sample information features; the initial sample features are input into the information recommendation model to be trained to obtain predicted operation results of the sample account for sample recommendation information; the model includes a gating structure and multiple feature extraction layers, the multiple feature extraction layers are used to output multiple target sample features, the output value of the gating structure represents the importance of each target sample feature, and the predicted operation result is obtained based on the multiple target sample features and the output value of the gating structure; based on the difference between the predicted operation result and the actual operation result, the information recommendation model is trained to obtain a trained information recommendation model. The present disclosure can improve the recommendation accuracy of the trained information recommendation model.
Owner:BEIJING DAJIA INTERNET INFORMATION TECH CO LTD