246 results about "Category recognition" patented technology

The invention discloses an emotion recognition method and system based on cross-modal alignment and matching enhancement. According to the method, firstly, feature extraction is carried out on text, audio and video modalities in a data set, and then a text and audio cross-modal emotion alignment module and a text and video cross-modal emotion alignment module are constructed respectively, so that cross-modal semantic alignment is realized. Constructing an emotion label matching module based on an alignment result, generating modal pairs with similar emotions but different labels by using a difficult negative sample mining strategy, and paying attention to cross-modal emotion consistency through a dichotomy task guide model; performing modal feature fusion on the three modals through a six-layer attention crossing mechanism, finally splicing feature vectors, inputting the spliced feature vectors into a long-sequence context fusion modeling module for deep modal fusion, and capturing cross-modal interaction information; and the fused features are sent to an emotion classification module, and a final emotion category recognition result is output.

The invention provides an electromagnetic signal automatic modulation identification method and system during testing based on time-frequency fusion. The method comprises the steps of firstly constructing an electromagnetic signal data set; secondly, optimizing a kernel function to realize time-frequency feature modeling, and constructing a double-input path; constructing a deep neural network again, inputting the preprocessed signal sample into a time-domain branch for processing, analyzing a time-frequency spectrogram through the time-frequency branch, and introducing a channel attention mechanism to realize feature fusion; secondly, freezing a time-frequency branch, only training a time-domain branch, outputting a logit value from an input signal through a neural network, and smoothing logit distribution into probability distribution through a scaling variable; carrying out sample slicing processing on an input signal, and realizing convergence by fusing a prediction result; and finally, optimizing affine parameters of the batch normalization layer to complete identification of the electromagnetic signal modulation category. According to the method, the recognition accuracy of the model in a complex wireless environment is improved, so that the electromagnetic signal can still be stably and reliably recognized under the condition of low SNR (Signal to Noise Ratio).

Generate accurate answers to user questions. [Solution] The information processing system includes: a state information acquisition unit that acquires state information indicating the state of an object in question in response to the notification of question information, which is a question from a user regarding the object in question; a category identification unit that identifies a question category, which is the category of the question; a user support control unit that selects the state information that is classified into the question category identified by the category identification unit from the state information acquired by the state information acquisition unit, generates an answer request information by attaching the selected state information to the question information, requests a language model to generate an answer to the question using the answer request information, and acquires the answer generated in response to the request.

A generator fault identification method, device, product and medium relate to the technical field of generator fault category identification. The method comprises the following steps: acquiring a vibration signal and a noise signal; performing multi-mode decomposition processing on the vibration signal and the noise signal to obtain a first sub-mode component and a second sub-mode component; determining a vibration signal sequence based on each first sub-mode component and the vibration signal; determining a noise signal sequence based on each second sub-mode component and the noise signal; determining a vibration characteristic matrix based on the vibration signal sequence; determining a noise feature matrix based on the noise signal sequence; determining a first recognition result and a first confidence coefficient based on the vibration feature matrix; determining a second recognition result and a second confidence coefficient based on the noise feature matrix; when the identification results are inconsistent, determining a fault identification result according to the confidence coefficient; and when the identification results are consistent, determining the first identification result as a fault identification result. The method is advantaged in that generator fault identification accuracy is improved.

The invention discloses a target image recognition and target detection method based on a video enhancement algorithm, and relates to the technical field of image processing. The method comprises the following steps: firstly, receiving a rain, snow and fog scene video stream through a visual sensor, extracting a video frame target image, performing video enhancement processing, eliminating rain and snow shielding, fog blurring and noise, and generating an effectively enhanced image which is complete in target contour, clear in details and adaptive to subsequent detection; inputting the image into an improved YOLO model of the rain, snow and fog scene, completing feature extraction and category recognition through an optimized feature extraction network, outputting a preliminary target bounding box and a category label, and judging whether a target to be detected and a specific category exist or not; and finally, if the target exists, counting the detection data and carrying out validity verification, thereby realizing high precision, low misjudgment and strong real-time performance of target detection in severe weather of rain, snow and fog, and further effectively solving the problem of high detection result misjudgment rate caused by parameter adjustment lag of adaptive filtering in the prior art.

The invention discloses an AI marking closed-loop method based on active learning and difficult case mining, and the method comprises the steps: carrying out the parallel calculation of uncertainty, representativeness and diversity three-dimensional value indexes after training an initial model, and carrying out the dynamic weighting screening of a high-value sample through a closed-loop feedback controller; difficult cases are recognized, DBSCAN clustering is adopted, similar sample expansion is retrieved, and the samples are stored in a dynamic pool; annotations are distributed, intelligent judgment is triggered for dispute samples after consistency verification, and labels are determined by fusing node reputation, model confidence and feature similarity; a mixed loss function is adopted for incremental training, and if the performance does not reach the standard, sampling, difficult examples and training parameters are adjusted in a linkage mode and then retry is conducted; the effectiveness of the difficult cases is evaluated after each round of iteration, the invalid difficult cases are eliminated, redundant clusters are combined, and the pool capacity is adaptively maintained; and the performance of the monitoring model is iteratively optimized until the standard is reached. According to the method, the labeling cost is reduced, and the boundary sample and long tail category recognition capability is improved.

The invention discloses an intelligent solid waste monitoring method and system based on multi-source data, and the method comprises the steps: carrying out the multi-source data monitoring of a solid waste putting region, mapping the preprocessed initial multi-modal data to an event reference time axis, generating a time mapping function, and carrying out the data processing of the time mapping function; performing space-time alignment on the initial multi-modal data based on a time mapping function and the spatial index of the initial multi-modal data to obtain candidate multi-modal data, performing cross-modal feature extraction on the candidate multi-modal data to obtain a feature embedding vector of each modal data, and performing attention feature fusion on the feature embedding vector of each modal data to obtain an attention feature fusion model; according to the method, multi-modal fusion features are obtained, solid waste category identification monitoring is performed on a solid waste putting area based on the multi-modal fusion features, cross-modal event synchronization is realized, cross-modal feature fusion efficiency is improved, a significant moment is focused by taking an event as a center, redundant data processing is reduced, and the identification accuracy of the solid waste is improved.

The invention is suitable for the technical field of visual inspection, and provides a zero-sample industrial anomaly detection method and device based on cross-modal semantic alignment and a medium, the method comprises the following steps: obtaining an initial image set and an initial annotation file of a plurality of parts, constructing a training sample data set, comprising an image sample, a text sample, a mask sample and a label sample of each part; based on the training sample data set, a zero-sample industrial anomaly detection model is constructed and trained, and the model comprises a visual feature coding module, a semantic feature coding module, a cross-modal feature alignment and fusion module and a prediction module; obtaining a target image and target text description information of a to-be-detected part, and inputting the target image and the target text description information into the trained zero-sample industrial anomaly detection model to obtain a target mask and a target label; based on the target mask and the target label, the industrial anomaly detection of the to-be-detected part is realized, the part category identification and segmentation accuracy is improved, and the industrial anomaly detection efficiency and accuracy are further improved.

The invention discloses a user power consumption behavior prediction method based on big data aggregation analysis, and particularly relates to the technical field of power data processing. The method comprises the following steps: constructing a user power consumption behavior matrix by collecting multi-dimensional historical power consumption data of a user; fusing environmental factors such as air temperature, humidity and weather types to generate an enhanced feature map; extracting key behavior nodes of a user through a multi-scale graph convolutional network, and introducing a time attention mechanism to generate a time sensitive weight vector; generating a user individual prediction feature vector in combination with the behavior node and the time weight, and outputting a future power consumption behavior prediction sequence; when the predicted volatility exceeds a set threshold value, model reconstruction and weight updating are triggered; if the volatility is within a threshold value, behavior category identification and prediction result output are completed; the method improves the accuracy and stability of user behavior prediction, has the advantages of being high in period recognition capability, sensitive in fluctuation response and high in adaptive adjustment capability, and is suitable for intelligent power grid load management.

This invention belongs to the field of service robot visual scene recognition technology, and provides a knowledge-enhanced method and system for object category recognition in multi-service robots. The method acquires scene images of the robot's operation, extracts visual information feature maps from these images, obtains preliminary predictions of target detection boxes and their object categories, and converts these visual information feature maps into scene information vectors. Trusted target label nodes from a pre-constructed knowledge graph are selected, and a matching vector is formed based on the converted scene information vector and target detection box information. The similarity between the matching vector and edges starting from the trusted target label nodes is calculated, and the query prediction result for the object category in the scene image is determined based on the similarity. Finally, the query prediction result for the object category in the scene image is fused with the preliminary prediction result to obtain the final object category recognition result.

This invention provides a method for fish passage behavior recognition based on a multimodal large model. First, imaging sonar image sequences and underwater optical video sequences of fish passing through fish passages or facilities are simultaneously acquired, and the multimodal data are aligned through time stamp synchronization and spatial calibration. Then, fish target detection, segmentation, and feature extraction are performed on the sonar image sequences and optical video sequences respectively to obtain the fish's spatial location, body length, water depth, motion state, morphological structure, and posture features. The obtained acoustic and optical features are input into a multimodal coding and fusion model based on the Transformer architecture, and a unified fish behavior representation vector is constructed through a cross-modal attention mechanism. During the training phase, model parameters are adjusted through a multi-task learning approach using cross-entropy loss, mean squared error loss, and contrastive learning loss, ultimately achieving fish passage behavior category recognition and prediction of individual and group passage difficulty scores.

The application discloses a slice detection method, medium, equipment and device, wherein the method comprises the following steps: acquiring a field of view image of a slice in a slice clamp to be detected, and inputting the field of view image into a first slice category recognition model pre-trained, so as to perform image recognition on the field of view image through the first slice category recognition model, and obtain a first slice type corresponding to the field of view image, wherein the first slice type comprises an abnormal field of view image and a non-abnormal field of view image; if the first slice type is the non-abnormal field of view image, inputting the field of view image into a second slice category recognition model, so as to output a second slice type corresponding to the field of view image through the second slice category recognition model, wherein the second slice type comprises a clear image and a motion blur image; the slice can be automatically detected, the misjudgment caused by invalid content on the slice is avoided, and the accuracy of the slice detection result is improved.

The application discloses a modulation category identification method and related device, electronic equipment and storage medium, wherein the modulation category identification method comprises: extracting a first feature map of a to-be-identified signal; wherein the first feature map comprises first sub-feature maps of a plurality of channels, and the first sub-feature maps of the plurality of channels have the same resolution; performing prediction on the first feature map based on a plurality of dimensions to obtain weight parameters of the first feature map in each dimension, and weighting the first feature map based on the weight parameters in each dimension to obtain a weighted feature map in each dimension; wherein the plurality of dimensions comprise at least one of a channel dimension and a spatial dimension; fusing at least the weighted feature map in each dimension to obtain a fused feature map; and classifying based on the fused feature map to obtain a modulation category of the to-be-identified signal. The above scheme can improve the accuracy and robustness of modulation category identification.

The invention mainly discloses a quality detection cooperative interaction suite group, which is used for performing defect detection on a continuous material conveyed by a roll-to-roll mechanism. Particularly, the quality detection cooperative interaction suite set further provides the following functions: (1) intuitively displaying the position of the detected flaw on the continuous material; (2) when the flaw detection result is misjudged, a user (a quality inspector) operates a tablet computer provided by the quality detection collaborative interaction suite group to delete the misjudged flaw detection result online; (3) when a flaw category identification error occurs in a flaw detection result, the user operates the tablet computer to correct the flaw category identified by the error online; and (4) when missing detection occurs, the user operates the tablet computer to add one or more images containing flaws into the database.

The invention relates to the technical field of fine-grained visual identification, in particular to a method for improving fine-grained visual identification precision under a low data volume, which comprises the following steps: acquiring an image with a low data volume scene characteristic, constructing a data set based on the image, preprocessing the data set, and dividing the preprocessed data set into a training set and a test set; a visual identification model is constructed, the visual identification model takes a ResNet-50 model as a backbone network, a segmented attention calculation unit is inserted between a Stage 4 of the ResNet-50 model and a global average pooling layer, and a loss function of the model is constructed based on cross entropy loss, divergence loss and multi-head consistency loss output by the segmented attention calculation unit; training the visual identification model by using the training set to obtain a trained visual identification model, the training including optimizing model parameters by using a loss function; and inputting the test set into the trained visual identification model, and outputting a fine-grained category identification result. The performance under the condition of low data volume is improved, and the key area positioning precision is improved.

The invention discloses a renewable resource recovery control method and system based on big data, and relates to data processing. The method comprises the following steps: performing feature extraction on a multi-source data set to obtain a multi-dimensional feature vector including a torque feature, an acoustic feature and a vibration feature; respectively constructing a material elongation at break prediction model and a material category identification model based on machine learning; constructing a mechanical property fingerprint database indexed according to material categories; obtaining an elongation at break prediction value through the material elongation at break prediction model, and obtaining a material category through the material category identification model; and searching a corresponding clustering subset in a mechanical property fingerprint database according to the identified material category, and calculating the control parameters of the renewable resource crusher through a preset parameter mapping relation in combination with the predicted value of the elongation at break. Aiming at the problem that in the prior art, image recognition cannot directly reflect mechanical parameters such as the elongation at break of the plastic material, accurate recognition of the wire drawing tendency of the plastic material is achieved, and inherent defects of visual recognition are avoided.

The embodiment of the invention provides a category identification method, electronic equipment and a program product. The category identification method comprises the following steps: acquiring a target point cloud corresponding to a to-be-identified target; extracting current target features based on the physical measurement quantity of the target point cloud; determining current category probability distribution based on the current target features and historical target features of the to-be-recognized target; and determining the category of the to-be-identified target based on the current category probability distribution and the historical category probability distribution of the to-be-identified target. Through the scheme of the embodiment, the calculation overhead can be reduced, the data processing efficiency can be improved, the behavior trend of the target is comprehensively considered, the influence caused by inaccurate single measurement is reduced, and the decision accuracy and robustness of the system are improved.

The invention belongs to the technical field of identity recognition, and discloses a millimeter wave-based identity recognition method, which comprises the following steps of: S1, acquiring an echo signal received by a millimeter wave radar; s2, acquiring phase information of a reflection target object at a specific position in any antenna signal channel of the echo signal at a certain moment; s3, acquiring a plurality of continuous phase information of a reflection target object at a specific position in any antenna signal channel of the echo signal in a time period according to the operation in the step S2, wherein the plurality of continuous phase information form a phase fluctuation signal of the reflection target object at the specific position; s4, subtracting phase information of adjacent positions of the phase fluctuation signal to obtain a vibration signal of a reflection target object at a specific position; s5, extracting signal features of the vibration signals; and S6, comparing the signal features with a signal feature database or inputting the signal features into a pre-trained target object category identification model to obtain the category of the reflection target object. According to the invention, the frequency domain feature or / and the time domain feature of the vibration signal generated by the reflection target object is / are used as the core feature to realize target object identity recognition, and the recognition accuracy is high.

The invention discloses an unmanned ship garbage collection method and system based on multi-source fusion and causal reasoning, and the method comprises the steps: carrying out the physical consistency fusion of multi-source observation data, and completing the detection, category recognition and material parameter estimation of floating garbage through a multi-mode deep learning network; constructing a two-dimensional local flow field around the unmanned ship, and giving short-time drift trajectory prediction and drift risk indexes on a target scale; constructing and training a parameterized causal prediction model, and evaluating the expected decline amount of the total load of the garbage in the whole water area after each sub-area is cleaned, so as to obtain a task priority sequence; the probability that a target enters an effective area of a collection port and the risk that the target is pushed away by a flow field under different approaching directions and speed strategies are given through a behavior prediction network before contact, finally fuzzy control input is constructed, and approaching and collection behaviors are adjusted in a self-adaptive mode according to different garbage materials and flow field disturbance. And high recovery stability and robustness are maintained in a complex hydrodynamic environment.

The invention provides a robot multi-mode touch sensing device based on electrical capacitance tomography, and the device comprises a flexible electrical capacitance tomography sensor which is disposed at an execution tail end of a robot and is used for sensing capacitance measurement values in a non-contact stage and a contact stage respectively; the multi-mode signal processing unit is used for acquiring the capacitance measurement value in real time, processing the capacitance measurement value to generate multi-mode touch information and feeding back the multi-mode touch information to the robot control system; wherein object category identification is carried out based on the capacitance measurement value in the non-contact stage, if the identified object is a contactable object, ECT image reconstruction is carried out by using the capacitance measurement value in the contact stage to obtain a contact image, and the contact image is converted into contact force distribution through a gray scale-pressure mapping relation. And carrying out object contour extraction by using the geometric features of the contact image. The adaptability and safety of the robot in a complex environment are improved, and the method is particularly suitable for the field of robots needing fine operation and environment interaction.

The invention relates to the technical field of part identification, and discloses a part identification method and device based on an industrial large model, and the method comprises the steps: carrying out the image block division and embedded transformation of an original image of an industrial part, obtaining a first Token sequence, carrying out the two-dimensional discrete cosine transformation of the first Token sequence, and obtaining a second Token sequence; fusing the second Token sequence with a plurality of prototype feature vectors selected from a category prototype memory library to obtain a memory guide vector; performing gating modulation and residual connection processing on the second Token sequence based on the memory guide vector to obtain a third Token sequence; and performing iterative refinement on the third Token sequence to obtain a fourth Token sequence, and performing global pooling and classification prediction on the fourth Token sequence to obtain a category identification result of the industrial parts, thereby enhancing the discrimination of the part characteristics, and effectively solving the technical problem of difficult identification of small samples of rare parts.

The application provides an intent category identification method and device, electronic equipment and a storage medium. The method comprises: obtaining to-be-identified text; identifying the intent category of the to-be-identified text using an intent identification model to obtain the intent category of the to-be-identified text. The intent identification model is obtained by training using a simulation data set. The simulation data set comprises unknown intent text having logical conflicts with original text and known intent text having no logical conflicts with the original text. The intent identification model trained using the simulation data set containing unknown intent text effectively identifies the intent category of the text, avoids the situation that a traditional model still classifies unknown intent category text into a known intent category, and thus enables the intent identification model trained using the simulation data set to effectively identify the intent category of unknown intent text.

The application provides a method and device for identifying the category of image text, a computer readable storage medium and an electronic device, and relates to the technical field of computers. The method comprises: extracting text detection features, text region information and text recognition features of an image to be identified; performing structural processing on the text detection features, the text region information and the text recognition features respectively to obtain multi-dimensional reference features; and identifying the category of the text content of the image to be identified according to the multi-dimensional reference features. In this way, the text detection features, the text region information and the text recognition features corresponding to different feature extraction stages are subjected to feature extraction to obtain multi-dimensional reference features, and then the category of the image text is identified based on the multi-dimensional reference features, so that a more accurate category recognition result can be obtained.

This application discloses a training method, apparatus, electronic device, and storage medium for a hair recognition model. The method includes: acquiring a first historical hair image for training, and adjusting the image parameters of the first historical hair image to obtain a second historical hair image; training a constructed feature extraction model using the first and second historical hair images, and extracting features from each hair image in the first historical hair image using the trained feature extraction model to obtain a first image feature, and extracting features from each hair image in the second historical hair image to obtain a second image feature; loading a constructed category recognition model, and training the category recognition model using training data to obtain a trained category recognition model; and fine-tuning the feature extraction model and category recognition model using a third historical hair image obtained from the training data to obtain a hair recognition model. This improves the accuracy of hair recognition.

The warehouse alarm method and device, the electronic equipment and the computer readable storage medium provided by the application meet the same category recognition result of continuous multiple frames of pictures, and the difference between the time stamps corresponding to the adjacent two frames of pictures of the continuous multiple frames of pictures is less than the first threshold value, so that the recognition result of the continuous multiple frames of pictures is determined as a valid recognition result, the timeliness and accuracy of the recognition result are ensured, and then it is judged whether the staff wears a safety helmet based on the valid recognition result. Meanwhile, the state recognition of the warehouse operation equipment is improved, the misrecognition problem caused by the shaking of the recognition box is effectively avoided, and the false alarm rate is greatly reduced.

The application discloses a bearing surface defect detection method and system based on improved YOLO-LMSE, S1, collecting bearing defect images; S2, performing data enhancement and preprocessing on the original image set to obtain standardized image data; S3, dividing the standardized image data into a training set, a test set and a verification set; S4, constructing a YOLO-LMSE bearing defect detection model; S5, inputting the bearing defect data set into YOLO-LMSE for training; S6, performing comparative testing on the trained YOLO-LMSE and an original YOLOv11m model on the test set, and verifying the performance difference of the model in bearing defect position positioning, category identification and confidence output; S7, performing multi-dimensional comparison between YOLO-LMSE and mainstream target detection algorithms, comprehensively evaluating the detection performance, calculation efficiency and parameter scale of the model, and determining the industrial deployment applicability of the model. The application can effectively adapt to the deployment requirements of resource-limited industrial scenes, improve the efficiency and reliability of bearing defect detection, and provide a powerful guarantee for the stability of industrial production.

The application provides a kind of blood vessel anastomosis skill automatic evaluation method based on computer vision technology, it is related to video processing technical field, the method is to utilize unlabelled blood vessel anastomosis operation video data, visual feature extraction model is trained, obtains pre-trained visual feature extraction model, blood vessel anastomosis operation video data is extracted, and blood vessel anastomosis skill visual feature is obtained;Blood vessel anastomosis skill visual feature is up-sampled using high-resolution pyramid, and high spatial resolution feature map is obtained;Using a variety of downstream task models, high spatial resolution feature map is operated action class identification, target segmentation and tip position identification;Action time consumption is calculated using operation action class, motion trajectory is obtained using instrument tip position, suture binary mask is identified using target segmentation, multidimensional index is calculated, and blood vessel anastomosis skill automatic evaluation result is obtained.The application solves the problem that the prior art is difficult to improve small target recognition accuracy.

The invention discloses a disease identification method, device and system, and a storage medium, and the method comprises the steps: inputting a to-be-identified disease image, and sequentially extracting the deep and shallow features of the to-be-identified disease image through a multi-layer feature extraction module; generating hierarchical prototypes of corresponding categories in different depth feature spaces, and fusing the hierarchical prototypes to form a comprehensive prototype; performing prototype classification reasoning based on the comprehensive prototype and a learnable measurement mechanism, and outputting disease categories; in the training process, the distinction degree between prototypes is enhanced by introducing prototype separation constraints; in the incremental learning stage, an original prototype of a new category sample is finely adjusted by adopting an elastic prototype updating strategy, a category prototype is newly added by utilizing a prototype classifier expansion strategy, and the old category recognition performance is ensured not to be lost. By adopting the technical scheme of the invention, similar category confusion can be effectively inhibited, and the accuracy and robustness of disease identification under a small sample condition are improved.

The application belongs to the technical field of bridge health monitoring, and particularly relates to a structure damage identification method based on a deep reconstruction network and multi-dimensional feature fusion, which comprises the following steps: obtaining an acceleration signal of a target bridge structure; inputting the acceleration signal into a Res-UNet-AE autoencoder to obtain a reconstructed signal, and calculating a reconstruction error and a signal-to-noise ratio according to the reconstructed signal; inputting the acceleration signal and the reconstructed signal into a perception autoencoder to obtain a perception index; fusing the reconstruction error, the signal-to-noise ratio and the perception index to obtain a three-dimensional damage feature space; and performing unsupervised clustering and identification according to the three-dimensional damage feature space to obtain a damage category identification result of the target bridge. The application can realize accurate differentiation of different working conditions of a structure without relying on any damage label.