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

29results about How to "Resolve confusion" patented technology

Pipeline sand flow monitoring method and system based on ultrasonic signal layered optimization

The invention relates to the technical field of oil and gas exploitation, in particular to a pipeline sand flow monitoring method and system based on ultrasonic signal layered optimization. The pipeline sand flow monitoring method mainly comprises the steps that firstly, a piezoelectric type ultrasonic sensor is used for collecting ultrasonic signals generated when gravel in a pipeline impacts a pipe wall; the method comprises the following steps: sampling a sand flow, carrying out adaptive nonlinear smooth filtering on an ultrasonic signal, carrying out noise suppression through sparsity analysis based on a frequency domain, finally constructing a mathematical model of a relationship between a sampling signal and the sand flow, and monitoring the sand flow according to the mathematical model. The problem that signals are prone to interference and confusion in a traditional ultrasonic monitoring method can be solved to the maximum extent, high-performance real-time measurement and accumulated sand production amount calculation of the sand production flow of the oil and gas pipeline are achieved, when the real-time sand production flow or the accumulated sand production amount exceeds an early warning value, an alarm is given out, a possible serious sand production event is prompted, and the real-time sand production flow of the oil and gas pipeline is monitored. And data support is provided for related decisions.
Owner:NORTHEASTERN UNIV CHINA

Freehand sketch-based three-dimensional model generation method and system

The invention discloses a three-dimensional model generation method and system based on a freehand sketch, and the method comprises the steps: carrying out the feature extraction of the freehand sketch, segmenting a freehand stroke into different part structures, extracting the part structure features as the local features of the sketch, fusing the local features of the sketch with the extracted global features of the sketch, and carrying out the rough generation of a network through a three-dimensional model, generating a rough voxel three-dimensional model by introducing fused sketch features as a condition, and constructing a three-dimensional voxel mask based on a voxel result of the rough voxel three-dimensional model through a three-dimensional model fine generation network and introducing the fused sketch features as a condition; and guiding the three-dimensional model fine generation network to intercept a part corresponding to the voxel mask from the sketch features, and generating a fine voxel three-dimensional model. A new data set 3DCM Sketch is made to train a model, so that a mapping relation between a cartoon model freehand sketch and a three-dimensional model is established.
Owner:ZHEJIANG UNIV +1

Self-adaptive pickup method and system based on multi-sound-source localization

The invention discloses a self-adaptive pickup method and system based on multi-sound-source localization, and the method comprises the steps: carrying out the feature extraction of collected multi-sound-source sound production data, and obtaining a comprehensive feature vector set; inputting the comprehensive feature vector set into a preset sound source localization model for processing to obtain target sound source features; according to the target sound source features, optimal pickup equipment parameters in the current environment are obtained through a preset pickup strategy prediction model; and according to the optimal pickup equipment parameters, setting adjustable parameters of the pickup equipment to carry out pickup. According to the invention, the target sound source is accurately positioned when the multiple sound sources produce sound at the same time, and the related parameters of the pickup equipment are set according to the information of the target sound source, so that more accurate and rapid pickup is realized.
Owner:GUANGZHOU BAOLUN ELECTRONICS CO LTD

Sampler for rice detection

The utility model relates to the field of rice detection, and discloses a sampler for rice detection, which comprises a sampling rod, fixed handles are symmetrically and fixedly mounted at the top of the sampling rod, a placement groove is formed in one side of the outer surface of the sampling rod, a storage pipe is rotatably mounted in the placement groove, and a storage groove is formed in the middle of one side of the storage pipe. Storage grooves are equidistantly welded to one side of the inner wall of the storage groove, an outer rotating rod is welded to the position, extending out of the sampling rod, of the top end of the storage pipe, a limiting frame is fixedly installed at the position, located on the outer surface of the outer rotating rod, of the sampling rod, and a limiting mechanism is further arranged in the limiting frame; according to the device, the sampling rod is matched with the storage pipe to sample a rice pile, so that the effect of stably taking out the sampled rice is achieved, the overall sampling effect of the rice is improved, the problem that rice samples with different depths are mixed with other rice is solved, and the rice detection accuracy is improved.
Owner:成都拾悦柒科技有限公司

Method and apparatus for training a generative model, generating training samples for a text classifier

ActiveCN116484968Bresolve confusionPattern recognitionSemantic vector
Embodiments of the present specification provide a method and apparatus for training a generation model and generating training samples for a text classifier. In the method for training the generation model, first processing and second processing are performed on a first text sample. The first processing includes determining a semantic vector of the first text sample by a first encoder. A first category of the first text sample is predicted based on the semantic vector by a text classifier, and a first prompt text corresponding to the first category is constructed. The second processing includes determining a first discrete vector corresponding to the first text sample in a target vector space by a second encoder. A reconstructed text of the first text sample is determined based on the first prompt text and the first discrete vector by a decoder. The generation model is trained based on a reconstruction loss determined based on the first text sample and the reconstructed text.
Owner:ALIPAY (HANGZHOU) INFORMATION TECH CO LTD

Textile cloth cleaning device

The utility model provides a textile cloth cleaning device which comprises a suction box and a penetrating box transversely penetrating through the suction box, a mounting shaft located above the penetrating box is further arranged in the suction box, and a driver for driving the mounting shaft to rotate is arranged outside the suction box. A plurality of attachment rods extending from one end of the mounting shaft to the other end of the mounting shaft are further fixedly arranged on the periphery of the mounting shaft, an exhaust pipe is further fixedly connected to the suction box, an exhaust fan is connected to the tail end of the exhaust pipe, and when the exhaust fan runs, airflow in the suction box enters the exhaust pipe after passing through the attachment rods; an inlet and a guide outlet which are located outside the suction box are formed in the two ends of the penetrating box respectively, an air outlet and an air inlet which are located in the suction box and located in the top face and the bottom face of the penetrating box respectively are further formed in the penetrating box, and an air inlet is further formed in the bottom face of the suction box; a filter box is further arranged on the suction box, and a filter plate is further arranged in the filter box in a drawing mode. The textile fabric suction device solves the problem that in the prior art, in the suction process of textile fabric, warp and weft are likely to be disordered or sucked into an exhaust fan from the lower portion.
Owner:YICHANG RUIKE TEXTILE CO LTD

A quick slotting marking device for plastic bobbin

ActiveCN224601786UQuick groovingRapid positioning
The utility model discloses a kind of quick slotting marking device of plastic bobbin, including rack, bobbin positioning mechanism, slotting execution mechanism and control system.Bobbin positioning mechanism is installed on rack, its positioning groove is V type or half-enclosing structure, cooperate semicircular positioning sleeve and limit block, realize bobbin fast accurate positioning, prevent deviation and shift.Slotting execution mechanism is integrated below positioning groove, contain linear slide, high-speed electric spindle and conical milling cutter, linear slide provides high-precision linear feed, ensure quick processing.Control system is composed of PLC controller and foot switch, cooperative control device operation.The utility model improves consistency and stability of clamping, optimizes structure layout, shortens tool stroke, realizes bobbin fast clamping, accurate positioning and high-efficiency slotting, single-piece processing time is short, marking has permanence, degree of automation is high, reduces artificial cost etc., comprehensive benefit is remarkable.
Owner:PERFORMANCE FIBERS KAIPING COMPANY

Moving target detection method based on sparse decomposition and block multi-channel background subtraction

The embodiment of the invention relates to a moving target detection method and device based on sparse decomposition and block multi-channel background subtraction, electronic equipment and a medium. The method comprises the following steps: acquiring each first binary matrix; obtaining a pre-constructed red channel matrix, a pre-constructed green channel matrix and a pre-constructed blue channel matrix, respectively processing the red channel matrix, the green channel matrix and the blue channel matrix based on a preset filtering algorithm to correspondingly obtain second to fourth binary matrixes, and respectively performing AND operation on the second to fourth binary matrixes to obtain a fifth binary matrix; according to the method, multi-channel information is comprehensively utilized, the problem that part of the target and the background are confused in the aspects of texture, gray scale, color and the like can be effectively solved, and through comprehensive utilization of motion saliency and morphological saliency information, the detection accuracy of the moving target is improved. The problem of interference of complex and changeable backgrounds, noise and the like on moving target detection is effectively solved.
Owner:NORTHWESTERN POLYTECHNICAL UNIV

Data arrangement method and system for multi-task large language model

The invention relates to the technical field of natural language processing, in particular to a data arrangement method and system for a multi-task large language model, and the method comprises the steps: obtaining an initial sample set of each task; dividing multiple tasks into two types of emotion significant tasks and emotion non-significant tasks; determining a data label category in the task; determining a category expression vector of each noun in the samples in the initial sample set; determining the feature weight of each noun under the data label category; on the basis of the similarity of the feature weights of each noun and other nouns under all the data label categories, feature vectors of the samples are obtained in combination with the importance indexes; performing sample classification based on the feature vectors; and training the initial large language model by using the general training set, storing weight parameters, and finely tuning the model trained by the specific training set based on the weight parameters to obtain a multi-task large language model. According to the method, on the premise that the multi-task type processing capacity is reserved, the customized large models for different tasks are obtained through the specific training set.
Owner:SHENZHEN YUNQI TIMES TECHNOLOGY CO LTD

Road disease detection method and device based on improved YOLOv5

The invention relates to a road disease detection method and device based on improved YOLOv5, and the method comprises the steps: obtaining a road image, carrying out the preprocessing of the road image, inputting the preprocessed road image into a trained road disease detection model, and obtaining a detection result; wherein the road disease detection model comprises the following steps: inserting an MASE module between a fourth network layer and a sixteenth network layer of YOLOv5; an MASE module is inserted between the ninth network layer and the tenth network layer; an MASE module is inserted between the fourteenth network layer and the nineteenth network layer; the output characteristic of the sixth network layer is bridged to the input end of the nineteenth network layer; the output characteristic of the eighth network layer is bridged to the input end of the 22th network layer; and obtaining a road disease detection model. According to the method, the fusion effect of the multi-scale features is enhanced, and the problem of loss of tiny disease features in multiple down-sampling stages is solved.
Owner:CHONGQING UNIV OF POSTS & TELECOMM

Live conference real-time subtitle generation method and system based on AI fusion

PendingCN122601879Aresolve confusionimprove readability
The application provides a live conference real-time subtitle generation method and system fused with AI, relates to the field of real-time subtitle generation, and comprises the following steps: collecting an audio stream and dividing the audio stream into segments, assigning a sound source identifier to each audio subsegment after sound source separation and identification; performing speech recognition on the identified audio and associating the sound source to generate identified text; correcting text ambiguity by using a context knowledge base containing a subject word table and historical text; cutting the text according to an audio energy envelope to form a subtitle unit; calculating a subtitle display time, assigning a vertical offset to subtitles with overlapping time but different sound sources to realize spatial separation; adjusting the subtitle display coordinates in combination with a disabled area determined by a video frame foreground, and rendering and outputting. The method realizes clear distinction and accurate presentation of multi-speaker subtitles, and improves the readability and user experience of conference live subtitles.
Owner:ZHONGSHIYUN (BEIJING) TECH CO LTD

An HPC trusted data question and answer method and system based on closed-loop feedback, an HPC trusted data knowledge base construction method and device

The application belongs to the technical field of natural language processing and knowledge engineering, and particularly relates to an HPC trusted data question and answer method and system based on closed-loop feedback, a device and an HPC trusted data knowledge base construction method. The method comprises the following steps: S1, collecting text data in the HPC field and screening out trusted text data; constructing a triple in the HPC field according to the trusted text data; S2, for the triple without conflict, removing the triple with consistent semantics, merging the triple with complementary information, and retaining the triple with refined description for the triple with refined attributes; for the triple with conflict, performing conflict resolution to obtain the triple without conflict; the conflict resolution comprises: retaining the triple with higher credibility; S3, constructing a vector knowledge base of HPC trusted data. The application solves the technical problem that the existing technology lacks adaptive trusted evaluation and conflict resolution mechanism in establishing a knowledge base, resulting in the generation of confused or wrong answers.
Owner:ZHENGZHOU UNIV

A multi-modal remote sensing fire smoke recognition method, apparatus, and computing device

PendingCN122289861ASuppression of background noise interferenceresolve confusionEngineeringThermal infrared
This application relates to the field of fire monitoring technology and provides a multimodal remote sensing fire smoke recognition method. First, remote sensing images are input into a target detection model, and features are extracted through multiple branches to output directional detection information. These multiple branches include a first branch and a second branch. The first branch extracts features from the input visible light spectral image, near-infrared image, and short-wave infrared image respectively; the second branch extracts features from the input thermal infrared image across multiple bands respectively. The directional detection information includes the category label, geometric center point coordinates, and rotated bounding box of the fire smoke target. Then, the directional detection information is input into a SAM model to segment the input remote sensing image, outputting a segmentation mask of the fire smoke target. Finally, the attribute information of the fire smoke target region is determined based on the input segmentation mask, including the coverage area and shape attributes of the fire smoke target.
Owner:AEROSPACE INFORMATION RES INST CAS +1

Pipeline sand flow monitoring method and system based on ultrasonic signal layered optimization

The present invention relates to the technical field of oil and gas production, and specifically to a pipeline sand flow monitoring method and system based on ultrasonic signal layered optimization, wherein the pipeline sand flow monitoring method mainly comprises: firstly, using a piezoelectric ultrasonic sensor to collect ultrasonic signals produced by gravel hitting the pipe wall in the pipeline, and performing adaptive nonlinear smoothing filtering on the ultrasonic signals, and then performing noise suppression based on frequency domain sparsity analysis, and finally constructing a mathematical model of the relationship between the sampling signal and the sand flow, and using this to monitor the sand flow. The present invention can solve the problem of signal susceptibility to interference and confusion in traditional ultrasonic monitoring methods to the greatest extent, and realize high-performance real-time measurement of sand flow in oil and gas pipelines and calculation of cumulative sand output. When the real-time sand flow or cumulative sand output exceeds the warning value, an alarm will be issued to indicate possible serious sand events, providing data support for relevant decisions.
Owner:NORTHEASTERN UNIV CHINA

Continuous learning method based on prototype prompt and virtual logic value

ActiveCN119598272Aresolve confusionNeural learning methodsAlgorithmEngineering
The invention discloses a continuous learning method based on class prototype prompts and virtual logic values, relates to the technical field of pattern recognition, and provides a prompt query mechanism based on a class prototype in the aspect of selecting and adding a prompt method by training a task specific prompt for each task. And the prompt momentum is added to the originally fixed query function for updating, so that the problem of non-uniform prompt addition is eliminated. Meanwhile, according to the method, virtual generation logic is added into logic output by the classifier, so that the classifier has a better classification boundary, and the purpose of solving the problem of confusion between tasks is achieved. According to the method, the problem of non-uniformity of prompt query in the existing method is solved, and the problem of serious disastrous forgetting phenomenon due to the fact that confusion between tasks cannot be fully relieved is solved.
Owner:NORTHWESTERN POLYTECHNICAL UNIV

Multi-type high-voltage tower three-granularity attitude estimation system and method

The invention belongs to the technical field of image processing, and discloses a multi-type high-voltage tower three-granularity attitude estimation system and method.The system comprises an attitude estimation model, a PAF-based key point connection module and a high-voltage power transmission tower attitude generation module; the attitude estimation model is used for carrying out key point identification under three specified granularities on the to-be-detected high-voltage power transmission tower image, and a key point identification result comprises key point position information and key point position direction information; the key point connection module based on the PAF is used for constructing key point connection according to the key points and the position direction information under each granularity; and the high-voltage power transmission tower attitude generation module is used for forming the attitude of the high-voltage power transmission tower according to the connecting lines obtained under different granularities. The method not only can effectively estimate the attitude of the high-voltage power transmission tower, but also has good generalization ability.
Owner:INFORMATION & TELECOMM COMPANY SICHUAN ELECTRIC POWER +2

An interactive control method and device based on SPI analog CAN communication and a medium

ActiveCN122339888Bresolve confusionimprove accuracyData packCheck digit
The application discloses an interactive control method and device based on SPI analog CAN communication and a medium, the method comprises the following steps: based on the SPI data sending device, for the specified data to be sent, the corresponding CAN extended frame ID and CRC check code are spliced, and the data to be sent is obtained by encapsulation; based on the SPI data receiving device, the received data packet is unpacked, and the specified data carried in the data packet is verified and analyzed through the CAN extended frame ID and CRC check code carried in the data packet. Under the premise of retaining the advantages of SPI physical layer, high-speed transmission, simple hardware interface and the like, the frame identification and error correction mechanism of the CAN bus are introduced through CAN message format encapsulation, the problems of no identification of traditional SPI data and confusion of multi-device data transmission are solved, the CRC check covers the CAN extended frame ID and valid data, the check range is wider, the error detection accuracy is higher, and the short board that the existing improvement scheme can only realize basic error detection is overcome.
Owner:国网(山东)电动汽车服务有限公司

A method for extracting a cultivation area based on time series filtering

The application discloses a kind of based on time series filtering aquaculture area extraction method.The method includes: obtaining multi-temporal optical image data to target area and pre-processing, constructs time series image dataset;Sample dataset for aquaculture area extraction model training is constructed;A kind of aquaculture area extraction model with hierarchical progressive characteristics and spatial adaptive capacity is constructed;Model training learns the spatial structure characteristics and time evolution characteristics of aquaculture area, obtains aquaculture area initial mask;Time series filtering processing is executed, through constructing time sequence stability discrimination mechanism, transient noise is inhibited, and the extraction result of time series consistent aquaculture area is obtained;Change analysis module of aquaculture area is constructed, and the spatial distribution of aquaculture area in different time phases is automatically compared and analyzed, and the boundary extraction and spatial area quantitative representation of each time phase aquaculture area are obtained.The present application can effectively alleviate the problem of spectral confusion and space-time change interference, improve the stability and reliability of aquaculture area extraction result in time dimension.
Owner:ZHEJIANG UNIV

Intelligent tourist guiding and indicating device for scenic spot

ActiveCN224199809Uresolve confusionAvoid going in the wrong directionAdvertisingTraffic signalsSimulationOperations research
The utility model discloses an intelligent tourist guiding and indicating device for a scenic spot, and relates to the technical field of scenic spot equipment. The device comprises a stand column, a supporting sleeve is fixedly connected to the surface of the stand column, and an indication board is installed on one side of the supporting sleeve. A guide assembly is arranged on one side of the stand column and comprises a base installed on one side of the stand column, a map board installed on the top of the base and a route strip installed in the map board. Through the cooperation of the guiding assembly and the indicating assembly, the situation that in the prior art, tourists are mixed up due to the fact that the indicating angles of scenic spot guiding indication boards are close is effectively solved, the advancing routes of the tourists can be clearly and accurately indicated through the arrangement of the multiple indication boards and the lamp strips, and the tourist guiding effect is improved. The situation that the tourist walks in the wrong direction due to indefinite indication is avoided, in addition, the device is further provided with a voice broadcast function, the use experience of the tourist is further improved, and the tourist can obtain the needed information more conveniently.
Owner:NANNING COLLEGE FOR VOCATIONAL TECH

Mobile medical vehicle with intelligent navigation and emergency call functions

The invention discloses a mobile medical vehicle with intelligent navigation and emergency call functions, and relates to the technical field of medical vehicles, the mobile medical vehicle comprises a medical bed, one side of the medical bed is connected with a navigation panel, the medical bed is internally provided with a connecting cylinder, the connecting cylinder can slide up and down along the height direction of the medical bed, and the connecting cylinder is connected with the navigation panel. An external thread groove is formed in the outer surface of the connecting cylinder, a mounting plate is connected into the medical bed, an internal thread groove matched with the external thread groove is formed in the mounting plate, and when the connecting cylinder is pressed to move downwards, the mounting plate and the external thread groove are matched with each other to drive the connecting cylinder to axially rotate; a signal can be transmitted to the navigation panel through the conflict switch by pressing the connecting cylinder by a patient, so that medical staff can be reminded in time; when the illness state is critical, the buzzer body is matched with the connecting plug to give out a strong alarm to quickly attract surrounding support. By means of the design, medical staff can efficiently deal with emergencies while focusing on the state of the patient.
Owner:THE FIRST MEDICAL CENT CHINESE PLA GENERAL HOSPITAL

A snow and ice identification method and system based on remote sensing images

This invention discloses a method and system for snow and ice identification based on remote sensing images. The method includes: acquiring remote sensing images of the target area and performing sensor-specific preprocessing and topographic radiometric correction to obtain a standardized surface reflectance image; extracting improved spectral index features, scale-adaptive texture features, and topographic occlusion compensation features based on multi-level feature coupling rules to construct a multi-dimensional feature set; generating a snow and ice probability map through a feature pyramid network based on an attention mechanism; generating an initial snow and ice mask using a dynamic window adaptive threshold segmentation strategy, combined with elevation zonation constraints and multi-temporal change trajectories; and finally, removing transient coverage and noise through spatiotemporal consistency joint optimization to generate an accurate snow and ice coverage map. This invention effectively solves the problem of spectral confusion between snow and ice, clouds, and bare rock, overcomes the influence of topographic shadows and transient interference, and significantly improves the accuracy and reliability of snow and ice identification in complex environments.
Owner:NORTHWEST INST OF ECO ENVIRONMENT & RESOURCES CAS

Dialogue abstract generation method based on large language model LLM auxiliary tag and two-dimensional centrality and storage medium thereof

PendingCN122087104Aresolve confusionControllable screeningBiological modelsNatural language data processingLinguistic modelNetwork model
The invention relates to the technical field of natural language processing, in particular to a dialogue abstract generation method based on a large-scale language model LLM auxiliary tag and two-dimensional centrality and a storage medium thereof.The method comprises the steps that the large-scale language model LLM is used for generating an intention tag of a dialogue utterance, and a training set TS with a high-quality tag is constructed after confidence coefficient screening; taking a pre-training model as a backbone, and training a deep learning network model fusing a large-scale language model LLM auxiliary label and two-dimensional centrality based on the training set TS; inputting a to-be-processed dialogue into the trained deep learning network model F, and outputting a dialogue abstract; according to the method, the accuracy, the integrity and the interpretability of the dialogue abstract can be improved.
Owner:FUZHOU LIANCHUANG ZHIYUN INFORMATION TECH CO LTD

A forest canopy density estimation method based on a lightweight gradient shape perception network

The present application belongs to the technical field of forestry remote sensing monitoring and image processing, and in particular to a forest canopy density estimation method based on a lightweight gradient morphological perception network. The method comprises the following steps: step 1: obtaining a forest canopy remote sensing image dataset; step 2: constructing a tree crown segmentation model based on a lightweight gradient morphological perception network; step 3: training with a boundary-enhanced compound loss function; and step 4: using the trained model for inference and forest canopy density estimation. The present application can efficiently run directly on a consumer-grade unmanned aerial vehicle or a portable device, meet the needs of rapid forestry investigation, accurately capture the small gradient changes between tree crowns, effectively cut the adhered tree crown boundaries, significantly improve the geometric precision of segmentation, effectively filter out redundant information such as undergrowth background and non-tree crown shadows, solve the texture confusion problem, and have extremely high practical value.
Owner:JILIN AGRICULTURAL UNIV

Aspect-level sentiment analysis method and system based on gated dilated convolution and graph convolution

The present invention relates to an aspect-level sentiment analysis method and system based on gated dilated convolution and graph convolution, and the method comprises: representing the context and aspect words in the sentences of the text to be analyzed by word vectors respectively, and obtaining the embedding of the context and aspect words respectively; inputting the obtained embedding of the context and aspect words into a gated dilated convolutional neural network to obtain the context representation incorporating the aspect information; inputting the context representation incorporating the aspect information into a graph convolutional neural network to obtain the predicted sentiment polarity of the text to be analyzed. The present invention combines the gated dilated convolutional network and the graph convolutional neural network, effectively utilizes the text language information, and at the same time emphasizes the importance of aspect information in aspect-level sentiment analysis, thereby improving the accuracy of the aspect-level sentiment analysis task.
Owner:EPIC HUST TECH WUHAN

Primer for identifying diploid D genome cotton seed and multiplex PCR (Polymerase Chain Reaction) method

The invention discloses a primer for identifying diploid D genome cotton seeds and a multiplex PCR (Polymerase Chain Reaction) method, and belongs to the field of molecular biology. The primer consists of a specific primer and a control primer. The specific primer F1 / R1 can specifically identify diploid D genome cotton seeds. The control primer F2 / R2 is designed according to a cotton seed conserved region and is used for determining the availability of a cotton genome and the stability of PCR reaction. The multiplex PCR method taking F1 / R1 and F2 / R2 as primers can amplify two bands of 550 bp and 1200 bp in diploid cotton seeds and tetraploid cotton seeds of A, B, C, E, F and G genomes. And only a 1200bp band is amplified from 13 diploid cotton seeds of the D genome, so that the D genome cotton seeds can be quickly identified and can be quickly and accurately distinguished from other genome cotton seeds, and the problem that the D genome cotton seeds are confused with other cotton seeds is solved.
Owner:CHANGCHUN UNIV OF SCI & TECH

A plastic product production unloading device

ActiveCN224408209UStable formresolve confusionFixed frameProcess engineering
The utility model belongs to the technical field of plastic product production unloading, especially a kind of unloading device for plastic product production, including unloading guide frame, the front side fixed mounting of unloading guide frame has fixed frame, cooling setting box is cooperated with fan, cooling cooling in the transmission process of plastic product, accelerate product setting, avoid the deformation problem caused by temperature too high;Compared with the function that only transmission unloading of traditional unloading device can be carried out, the design ensures the form stability of plastic product in the unloading stage, improves product quality stability;Industrial high-definition camera and fill light can carry out quality detection to plastic product, realize automatic classification in combination with subsequent transmission structure: qualified product is transferred to second conveying belt by suction cup after being transmitted by first conveying belt;Unqualified product falls into collecting frame through unqualified product guide frame;This automatic classification replaces manual screening, solves the problem that qualified product and unqualified product are confused, reduces the artificial cost of warehouse link.
Owner:SHANDONG XINSHENG TAIHUAN ENERGY TECH CO LTD

A multimodal large-scale AI creative generation system and method

PendingCN122676005Aresolve confusionCorrespondence is accurate
This invention relates to the field of artificial intelligence technology and discloses a multimodal large-scale AI creative generation system and method. The system includes a semantic parsing module, a feature encoding initialization module, an attention intervention module, and an image decoding module. The method includes: extracting independent creative entities and their bounding box coordinates from the input prompt sequence, constructing an entity semantic dependency matrix; generating a key matrix and initializing latent variables in the latent space; iterating incrementally over time steps, calculating cross-attention and extracting specific entity attention subgraphs, constructing a dynamic two-dimensional Gaussian mask based on the dependency matrix, calculating the gradient of the partial derivative of energy loss to update the current latent variables and denoise; obtaining the final deterministic latent variables and decoding the output visual content. This invention solves the problem of multi-entity layout confusion in multimodal large-scale AI creative generation by using semantic constraints and gradient intervention of the dynamic mask during the denoising cycle.
Owner:HORGOS NEW NUMBER INFORMATION TECHNOLOGY CO LTD

Pixel-level data enhancement method based on small target detection in complex scene

The invention provides a pixel-level data enhancement method based on small target detection in a complex scene. The pixel-level data enhancement method comprises the following steps: S1, preparing data; s2, randomly copying and pasting the instance target; s3, updating the enhanced data label and the mask; and S4, determining whether the data volume is sufficient. According to the pixel-level data enhancement method based on small target detection in the complex scene provided by the invention, the data set is expanded by simply copying and pasting the instance target on the target detection data, so that the limitation of spending a large amount of manual annotation in the past is broken through; meanwhile, compared with an existing enhancement means, the data enhancement effect is more suitable for solving the problem of small target detection in a complex scene, one-pixel-level data enhancement is achieved, the enhanced data is relatively attached to original target detection data, mosaic style pixel blocks cannot appear near pasted target pixels, and the detection accuracy is improved. The problem of confusion with a low-pixel detected target is solved, and invalid operation of data enhancement due to complex data background environment is avoided.
Owner:CHINA ELECTRIC POWER RES INST TECH GRP CO LTD +1

Chinese character splitting and combining method, device and equipment and readable storage medium

The invention provides a Chinese character splitting and combining method and device, equipment and a storage medium, and the method comprises the steps: obtaining a to-be-processed object which is a to-be-split Chinese character or a to-be-combined element, and the element comprises components and parts; constructing a Chinese character configuration graph type database; on the basis of the Chinese character configuration graph database, a corresponding relation table among Chinese characters, Chinese character configuration graphs and splitting results is constructed, and the splitting results are Chinese character components obtained after the Chinese characters are split; splitting the to-be-split Chinese characters according to the Chinese character configuration graph database, the corresponding relation table and a preset splitting method to obtain split radicals and components; or combining the to-be-combined elements according to the Chinese character configuration graph database, the corresponding relation table and a preset combination method to obtain a combined Chinese character. According to the Chinese character splitting and combining method, the problems that at present, Chinese character splitting is not standard, and component principles are not unified can be solved.
Owner:SICHUAN UNIV