231results about How to "Rich in features" patented technology

The invention discloses an image self-supervised learning method and system fusing contrast learning and feature mask modeling. An original image which is low in cost and does not need to be labeled is used as training data, a double-branch self-supervised learning network is constructed, one branch is a comparison learning branch based on a SimCLR framework, the other branch is a mask self-encoder branch based on a mask feature model, and the whole network comprises an image preprocessing module, an image feature extraction module and a shared weight encoder. And carrying out self-supervised training by combining the two branches with a loss function specially designed for the two branches, and finally obtaining a pre-training model capable of fully extracting image features. According to the method, the advantages of comparative learning and feature mask modeling are combined, information is effectively extracted from unlabeled image data, and image understanding is enhanced. The method has the main advantages that the robustness is high, the method is particularly suitable for limited data sets in the remote sensing and medical fields, the model precision is improved, and the data requirement and labeling cost are reduced.

The invention discloses an automatic fine ore sorting method and system based on XRT (X ray tomography) and hyperspectrum, which are used for realizing comprehensive fusion of ore surface and internal information by combining X-ray tomography and hyperspectral imaging technologies so as to improve the recognition precision and the sorting efficiency. XRT is used for extracting the internal structure and density characteristics of the ore, hyperspectral imaging is used for identifying the mineral composition characteristics of the ore surface, and information complementation is achieved. The system adopts a multi-modal convolutional neural network to perform independent feature extraction on XRT and hyperspectral data, and the extracted features are fused through a deep residual network. And the fused features are processed by a cross-modal attention mechanism to ensure that key features of different modals are fully integrated and optimized, and finally high-precision ore classification and sorting are realized. According to the method, the limitation of a single data source on feature extraction is overcome, the ore recognition and sorting precision is greatly improved, and the refined and intelligent development of ore sorting is promoted.

The invention discloses a trajectory prediction method and device based on a time-space diagram neural network learning model, and the method comprises the steps: carrying out the data cleaning and trajectory compression based on to-be-classified original trajectory data, and outputting a compressed grid sequence; based on the grid sequence, static track information classification is executed, and track static attributes are extracted; dynamic space-time image track classification is executed, and track dynamic space feature attributes are extracted; the method comprises the following steps: pre-constructing a directed weighted network based on a driving road section connectivity attribute feature, and completing training of a trajectory prediction model based on a trajectory static attribute, a dynamic space feature attribute and the directed weighted network; and based on the trajectory prediction model, inputting spatial-temporal characteristic data of a trajectory to be predicted, and obtaining an optimal trajectory path prediction result. According to the method, uncertain track geographical background information on the road network can be effectively utilized, and meanwhile, errors caused by map matching are avoided.

The invention discloses a cigarette packet appearance defect detection method and system based on deep learning, and relates to the technical field of appearance detection.When the system runs, multi-angle and multi-light-source image acquisition is carried out through a high-definition camera and scanning equipment, it is ensured that appearance details of cigarette packets are comprehensively and accurately captured, and the detection accuracy of the appearance defects of the cigarette packets is improved. According to the method, firstly, the image quality and consistency are further improved through image cutting, graying processing, denoising processing, image enhancement and data standardization of the data preprocessing module, a solid foundation is laid for subsequent defect detection, secondly, the defect detection module carries out feature extraction through strong and weak data enhancement and a feature extractor, and the defect detection accuracy is improved. By calculating the similarity of positive and negative samples in a feature space and a total loss function # imgabs0 #, defect identification and optimization are performed in combination with MSE loss, the defect detection precision and robustness of the model are improved, the evaluation module evaluates appearance defects in real time by matching with a preset threshold, and a continuously optimized detection closed loop is formed.

The invention discloses a robot visual touch sensing method and system based on transformer and comparative learning, and belongs to the technical field of robots. According to the method, an enhanced Swin Transform model is introduced to serve as a sensing model, the enhanced model takes Swin Transform as a backbone network, a coordinate attention mechanism is introduced into the backbone network, global information is extracted through a sliding window attention mechanism of the backbone network, local feature extraction is enhanced through the coordinate attention mechanism, and the global information is extracted through the sliding window attention mechanism. The global and local features in the visual and tactile data can be effectively extracted and fused. According to the enhanced Swin Transformer model, in-modal comparative learning and inter-modal comparative learning are specifically performed through multi-modal comparative learning training in a pre-training stage of an earlier stage, and richer and more accurate discrimination features are generated, so that the intelligent sensing and operation capability of the robot to the environment is effectively improved. According to the method, the features can be effectively extracted in multi-modal data fusion, and deeper multi-modal data fusion is realized by utilizing the correlation and synergistic effect of the features among different modals.

The invention provides a converter valve fault identification method based on voiceprint small sample learning, and belongs to the technical field of artificial intelligence, and the method comprises the steps: obtaining a to-be-identified target audio comprising converter valve environment noise, and carrying out the noise reduction processing based on FRCRN, and obtaining a noise-reduced audio signal; carrying out feature extraction based on the Mel frequency cepstrum coefficient and the Gammatone filter bank cepstrum coefficient, and carrying out dimension reduction on features based on a principal component analysis method to obtain feature vectors; inputting the feature vector into a voiceprint recognition model which is completely trained based on a voiceprint small sample for recognition, and obtaining a recognition result; according to the method, the to-be-recognized audio is denoised based on the FRCRN, most noise in the converter valve environment can be filtered out, and the technical effect of accurately recognizing the to-be-recognized audio is achieved; by adjusting the structure of the voiceprint recognition network, useful information of the features can be highlighted, redundancy of repeated information is reduced, and therefore the recognition accuracy of the voiceprint recognition model in the converter valve noisy environment is improved.

The invention discloses a dialogue emotion recognition method and device based on a multi-modal large model, and relates to the field of emotion recognition, and the method comprises the steps: obtaining all statement sets in a dialogue in a current scene; each statement comprises an audio mode, a video mode and a text mode; constructing a dialogue emotion recognition model; the dialogue emotion recognition model comprises a feature extraction layer, a bidirectional gating unit, a multi-modal large model, a BERT language model, a modal information complementation module, a semantic graph-based multilayer residual image convolutional network and a full connection layer; and according to all statement sets in the dialogue, adopting the trained dialogue emotion recognition model to obtain an emotion recognition result. The dialogue emotion recognition method and device can improve the accuracy and robustness of dialogue emotion recognition.

The invention discloses a remote sensing target detection method based on a target feature enhanced multi-scale fusion network, and the method comprises the steps: constructing a multi-layer feature aggregation module as a main feature extraction module, and better extracting the target features of each category; a multi-channel feature fusion module is constructed, the network layer parameter quantity is reduced, a cross-stage hierarchical structure is adopted to design an MCFCSP module, richer gradient combination and feature expression are realized, and the network feature fusion capability is enhanced; by adopting a top-down and bottom-up feature fusion strategy, information interaction between different levels of features is promoted; fractional Fourier transform convolution is constructed, and parameters are adjusted according to the characteristics of small targets and the change of scenes to adapt to small targets of different types, different sizes and different complexities. The method provided by the invention has the characteristics of high detection precision, low calculation complexity, strong feature representation capability and the like, can effectively improve the detection precision of the small target, and further improves the detection performance of the small target of the remote sensing image.

The invention relates to a maritime activity knowledge extraction method and device based on a large language model. The maritime activity knowledge extraction method and device are used for maritime knowledge extraction. The method comprises the steps that an initial cue word is preset, a cue word optimization strategy is set to optimize the initial cue word, the optimized cue word is used for guiding a large language model to conduct statement transcription on reconstructed data, and a preliminary extraction result is obtained; labeling the preliminary extraction result according to a preset extraction error label system, taking a labeled text as a similar error text, carrying out statement structure analysis on the similar error text, generating a simulation text question and answer pair, carrying out feedback modification on the optimized prompt word, and obtaining a simulation result; and utilizing the modified cue word to guide a large language model to perform knowledge extraction on the marine activity data to obtain marine knowledge. By adopting the method, offshore knowledge extraction can be realized.

The invention discloses a multi-modal recommendation method and system for enhancing user representation through a graph convolutional neural network, and the method comprises the steps: extracting project embedding, original user embedding and original ID embedding from an input data set; features are extracted from neighbors of users, aggregation operation is carried out to enhance user representation so as to generate user embedding after aggregation of other user information, and then the user embedding and project embedding are spliced into a user-project collaborative interaction matrix; extracting features of each mode for an input data set, and constructing a user-item diagram of each mode in combination with the user-item collaborative interaction matrix; and obtaining recommendation items of the user through multi-modal information representation, multi-modal feature fusion and recommendation results. According to the method, the recommendation accuracy is improved by introducing the multi-modal information, meanwhile, a user feature enhancement technology is introduced, user features and features of similar users are subjected to aggregation operation to obtain personalized embedding of the users, and finally the recommendation accuracy of the multi-modal recommendation system is improved.

The invention relates to the field of voice recognition, in particular to a voice recognition method and system of an intelligent voice robot. The method comprises the following steps: collecting user real-time dialogue audio and a user dialogue monitoring image; performing noise reduction separation processing on the real-time dialogue audio of the user, and performing audio distortion optimization to obtain a distortion optimized dialogue audio; performing micro-expression recognition on the user dialogue monitoring image, and performing emotional state feature mining so as to generate real-time emotional state features of the user; performing user semantic pause recognition on the distortion optimization dialogue audio, and performing key vocabulary feature analysis to obtain a key field of each frequency domain unit; and carrying out multi-scale convolutional learning on the key field of each frequency domain unit, and then carrying out audio context association mining so as to generate a user audio context association map. According to the invention, efficient and accurate speech recognition is realized.

The invention discloses a data classification method and system based on a deep multi-path attention adaptive graph convolutional network, and relates to the technical field of medical image processing. Rs-fMRI data is acquired and preprocessed to obtain a BOLD sequence, a function connection feature vector is constructed and input into a DMAGCN model, and finally an optimal model is acquired through five-fold cross validation for classification. The data quality is guaranteed through data preprocessing, and a foundation is laid for accurate analysis. Functional connection feature vectors effectively represent data, after a model is input, a Transform backbone network and an MLP branch network can extract multi-source domain features, non-imaging data are utilized in combination with a graph network, the model can learn rich features, and generalization and adaptability are enhanced. According to the method, the classification accuracy is improved, the performance is excellent when uncertain data classification such as autism spectrum disorder is processed, related disease research is promoted, and an efficient and reliable method is provided for medical data classification.

The invention provides a keratoconus image classification method based on an improved deep learning self-attention mechanism, and the method comprises the steps: obtaining a four-refraction report graph through a three-dimensional anterior segment analysis and diagnosis system, carrying out the image preprocessing of the four-refraction report graph through employing a method for extracting a region of interest, and obtaining a four-refraction report graph data set; constructing a network model based on a multi-directional axis attention mechanism, and inputting the four-refraction report graph data set into the constructed network model based on the multi-directional axis attention mechanism for training to obtain a trained network model based on the multi-directional axis attention mechanism; and carrying out image preprocessing and data enhancement on the four-refraction report graph to be processed, and inputting the four-refraction report graph to be processed into the trained network model based on the multi-directional axis attention mechanism to carry out cornea conus classification. According to the method, unique directional feature information in the corneal topographic map is efficiently captured, the information of the whole image can be comprehensively considered, and the diagnosis accuracy is improved.

The invention discloses a drainage basin rainfall runoff prediction method and device fusing a mechanism model and a machine learning model, and a program product. The method comprises the following steps: firstly, constructing a seasonal Markov chain model by taking a seasonal rainfall state transition probability as a conditional transition probability; simulating the rainfall state of each day in a preset simulation period by adopting a seasonal Markov chain model, simulating the rainfall capacity of each day according to the distribution obeyed by the rainfall capacity of each seasonal characteristic time period, and generating a rainfall sequence in the preset simulation period; predicting the runoff yield of each day under a specified rainfall sequence in a preset simulation period by adopting a drainage basin mechanism model, and counting the earlier-stage accumulated rainfall capacity and seasonal characteristics as the input characteristics of runoff yield prediction; and finally, taking the input features of all runoff prediction in a preset simulation period and the corresponding runoff simulation values as a data set, training a machine learning model, and predicting the runoff in the future by adopting the trained machine learning model. The method is high in prediction efficiency and high in prediction precision.

The invention provides a broadband marketing strategy making method and device and a readable storage medium, and relates to the technical field of communication, and the method comprises the steps: obtaining EDPI data corresponding to target broadband account information in a preset time interval; obtaining a poor network quality score of the user in each time period in a preset time interval according to the EDPI data; according to the poor network quality score of each time period, obtaining a network quality change condition of the user in a preset time interval, and obtaining a poor network quality portrait of the user; and performing user family attribute portrait analysis based on the EDPI data to obtain a key dimension for constructing a user family attribute accurate portrait. According to the method, the device and the medium, the problem that an existing broadband poor quality detection technology and a user portrait construction method can only help an operator to identify and solve network problems to a certain extent and cannot be effectively converted into a marketing strategy for improving user satisfaction and enhancing competitiveness can be solved.

The invention relates to a plant non-histone lysine crotonylation site identification method and a plant non-histone lysine crotonylation site identification system. The method comprises the following steps: extracting non-histone lysine crotonylation Kcr sites from a protein sequence to form a data set; extracting a first feature vector by using a self-attention mechanism and a smoothing function through a protein language model ESM2; capturing a long-distance dependency relationship and context information in the protein sequence through a bidirectional long-short-term memory network, and extracting a second feature vector; and carrying out feature fusion processing and then carrying out classification prediction to obtain a Kcr site identification result. By constructing a protein sequence data set, ESM2 utilizes a self-attention mechanism and a smoothing function, and BiLSTM captures a long-distance dependency relationship and context information in the protein sequence, efficient feature extraction of the protein sequence is realized, and more comprehensive information can be provided through fusion processing, so that the detection precision of Kcr site detection and recognition is improved.

The invention belongs to the field of particulate matter measuring and sensing, and particularly relates to an aerosol particle size distribution sensor and an aerosol particle size distribution measuring method.The aerosol particle size distribution sensor comprises a particle containing cavity, a spectrum sensing chip and a plurality of white light LED light sources located at different scattering angles; each scattering angle is a rotation angle formed by rotating the light beam propagation direction of the light source at the particulate matter accommodating cavity to the direction pointing to the spectrum sensing chip from the center of the particulate matter accommodating cavity; the plurality of light sources are used for sequentially emitting white light into the particle accommodating cavity, and the spectrum sensing chip is used for collecting scattered light generated by to-be-detected particles in the particle accommodating cavity based on the white light to obtain an aerosol scattered spectrum signal so as to analyze aerosol particle size distribution; the scattering angle combination formed by the scattering angles is obtained through optimization by taking the minimum aerosol parameter deviation between different aerosols of which the aerosol scattering spectrum signal difference value is smaller than a threshold value as a target. Accurate measurement of aerosol particle size distribution is realized through the sensor with a simple structure.

The invention provides a fish ingestion intensity evaluation method based on improved VGG16 and a spectrogram, and relates to the field of aquaculture. The method comprises the following steps: acquiring fish ingestion sound signals by adopting a hydrophone, dividing the ingestion sound signals into four types of intensities of'strong ', 'medium', 'weak 'and'no', manually marking the ingestion sound signals, converting the sound signals into spectrograms, and constructing a fish ingestion sound signal data set; an attention mechanism fusion module is designed, the attention mechanism fusion module is integrated on a convolutional neural network, a fish ingestion sound signal data set is used as input, and automatic grading of ingestion intensity is achieved. The method provided by the invention can efficiently evaluate the fish ingestion intensity so as to judge the fish appetite. The method can be applied to fish feeding strategy optimization and behavior research.

The invention relates to a lithium ion battery internal short circuit detection method based on an improved GAF, and belongs to the field of lithium battery detection, and the method comprises the steps: amplifying a voltage deviation through a curve Manhattan distance, selecting a reference curve to divide all curves, and calculating the curve Manhattan distance between an internal short circuit curve and the reference curve through a sliding window; converting the one-dimensional data into a two-dimensional image through an improved Grubrum angle field; according to an application scene, the severity of the short circuit is divided into z classes, z Grubrum angle field image data sets are correspondingly constructed, a model is used for classifying the image data sets, and the possibility of each class is obtained according to the probability corresponding to a classification result. According to the method, the Manhattan distance of the curve is calculated by using the sliding window, the voltage deviation characteristic is amplified, and the time characteristic of data is reserved; by improving the Grubm angle field, images with different internal short circuit degrees show different contour features, and the internal short circuit fault of the battery can be effectively detected and tracked.

The invention discloses a rare earth mining area land utilization fine classification method for hyperspectral remote sensing images, and belongs to the field of remote sensing. Based on a hyperspectral remote sensing image of a rare earth mining area, an object-oriented feature extraction module and an object-oriented one-dimensional convolutional neural network classification model based on a multilayer attention mechanism are designed, and a rare earth mining area land utilization classification task is completed through the two modules. By combining the object-oriented and convolutional neural network, the classification precision of different land utilization categories is enhanced, and the phenomenon of salt and pepper noise in the classification result is avoided at the same time.

The invention relates to the technical field of attendance management, in particular to an attendance management method. According to the technical scheme, the method comprises the following steps: selecting and initializing an attendance system; daily attendance management, wherein the daily attendance management comprises a clock-in mode and clock-in exception processing; evaluating and examining and approving the automatic reissuing card; and attendance data analysis and report generation. According to the attendance management system, a multi-source data collection and comprehensive analysis mechanism is added, and based on a comprehensive judgment function and an equipment fault possibility evaluation function, an evaluation result is used for optimizing the judgment accuracy of automatic card supplement, so that misjudgment is avoided, and the work efficiency is improved. The automatic examination and approval decision function is used for automatically judging according to conditions such as comprehensive evaluation and late times of employees and manually examining and approving related information decisions, so that the workload and the management cost of the employees are reduced, the accuracy and the reliability of attendance data are improved, and the system can adapt to the requirements and changes of enterprise attendance management.

The invention discloses an aircraft assembly point cloud registration method and device based on LiDAR scanning data, and belongs to the field of three-dimensional point cloud processing. The method comprises the following steps: acquiring a source point cloud and a target point cloud of an airplane model; performing feature extraction and downsampling on the source point cloud and the target point cloud to obtain downsampling points, and jointly constructing a local patch by each super point and nearby K sampling points; calculating a prediction rigid body transformation matrix of the source point cloud and the target point cloud; calculating density consistency loss, attitude consistency loss, geometric consistency loss and point matching loss of the global prediction rigid body transformation matrix and the real rigid body transformation matrix, and comprehensive loss of the global prediction rigid body transformation matrix and the real rigid body transformation matrix, and optimizing the global prediction rigid body transformation matrix for point cloud registration by taking the minimum comprehensive loss as a target to obtain a target rigid body transformation matrix; and registering the source point cloud and the target point cloud according to the target rigid body transformation matrix. And high-efficiency and high-precision aircraft point cloud registration is realized.

The invention discloses a radar human body action recognition method based on a lightweight model, and the method comprises the steps: 1, constructing an FMCW radar model, and collecting and obtaining the radar echo data of a human body under different postures; 2, constructing a micro-Doppler graph data set, and dividing the micro-Doppler graph data set into a training set, a verification set and a test set according to a set proportion; step 3, constructing an improved Faster Net network model, and inputting the preprocessed training set and verification set into the improved Faster Net network model for action recognition; 4, training the improved Faster Net network model: using an AdamW optimizer, using a cross entropy loss function as a loss function, and continuously updating model parameters to obtain an optimal model; and 5, processing radar sampling data to be detected to obtain micro-Doppler feature data to be detected, and inputting the optimal model to obtain a classification result of human body action recognition. The method has remarkable advantages in the aspect of action recognition.

The invention relates to the technical field of image recognition, in particular to a sleep post recognition method and system. The method comprises the following steps: collecting a sleep post video sample; extracting a sleep post picture sample from the sleep post video sample; labeling a label of each sleep post picture sample; determining a target detection area in the sleep post picture sample; initial feature extraction is carried out on the target detection area; determining a spatial attention feature of each initial feature based on a spatial attention mechanism; fusing the initial features and the spatial attention features to obtain new features; constructing a training sample by using the new features and the labels, and training by using the training sample to obtain a sleep post identification model; acquiring a to-be-detected video / picture in real time; whether the person in the to-be-detected video / picture is in the sleep state or not is judged by using the sleep recognition model. By adopting the method, the accuracy and accuracy of sleep recognition can be improved.

The invention relates to the field of astronomy transient source recognition combining astronomy and artificial intelligence, and when a transient source recognition task in mass data shot by a large-view-field high-sampling-rate telescope is carried out, an existing method generally uses a single classification model only depending on image data and is difficult to deal with complex and changeable data. The invention provides an astronomical transient source identification method for dynamically updating a multi-modal model. The method comprises the following steps: constructing the multi-modal model for classification by combining image data, a point spread function and physical information; and in combination with manual examination, selecting samples with wrong classification and possible transient source candidates, storing the samples and the possible transient source candidates as a new sample set, injecting the new sample set into the original training set, and loading the weight of the last training for retraining, so that dynamic adjustment and optimization of the model are realized. The method can effectively cope with mass data generated by a telescope with a large field of view and a high sampling rate, and ensures that the model always keeps efficient and accurate recognition performance under a complex background and weak signals.

The invention discloses genipin modified ginkgo protein and whey protein composite gel and a preparation method thereof, and belongs to the field of functional food. The method comprises the following steps: (1) uniformly mixing a prepared ginkgo protein solution and a prepared whey protein solution, and adjusting the pH value to obtain composite sol; (2) adding a genipin reagent into the composite sol, carrying out a cross-linking reaction, and after the reaction is completed, adjusting the pH value again to obtain a genipin-treated composite sol; and (3) carrying out thermal induction gel formation on the genipin-treated composite sol, taking out and cooling to obtain the genipin-modified ginkgo protein and whey protein composite gel. Animal protein and plant protein are combined through the cross-linking agent genipin, so that the prepared composite gel is more nutritional, pollution to the environment is reduced, application in food production is facilitated, meanwhile, the composite gel treated with the cross-linking agent genipin has more diversified functional characteristics, and the composite gel is suitable for being applied to food production. And the food can be provided for people with different requirements.

The invention discloses a super-large-span high-precision special-shaped structure construction monitoring method, equipment and a medium, relates to the technical field of image processing, and provides a building construction monitoring and optimization process based on a construction data model library and live image data. The actual situation of a construction site can be monitored more accurately, it is ensured that the construction precision, progress and quality conform to expectations, deep feature extraction can be conducted on the building framework point cloud segments through the feature extraction backbone network, the building framework point cloud segments are fused based on the extracted local features, more comprehensive overall features can be obtained, and the construction efficiency is improved. The extraction precision of the building structure is enhanced, the building framework generated according to the overall features is compared with the construction data model library, rod piece machining can be secondarily guided, the practicability and accuracy of the model library are improved, and the precision, efficiency and quality of building construction are improved.

The invention provides a multi-group behavior recognition method based on space-time interaction reasoning, and mainly relates to the problem of how to effectively mine space-time interaction so as to carry out individual behavior, group clustering and multi-group behavior recognition. According to the method, a space-time interaction relationship reasoning strategy is put forward to pay attention to interaction relationships between individuals and between groups, meanwhile, features such as appearances, position distances and space-time trajectories are considered, and the accuracy of behavior recognition is improved. Firstly, the interaction relation between individuals is explored by analyzing features of nearest neighbors of the individuals and position distance features. Secondly, dividing the individuals into a plurality of small groups in combination with behavior similarity and spatio-temporal trajectory characteristics; and finally, a group interaction reasoning module is constructed, interaction among different small groups and individuals is mined, and the individuals having small influence on group behaviors are excluded according to importance. According to the method, the space-time interaction characteristics of the individuals and the groups are fully considered, and the problem that space-time interaction characteristics are not fully mined in behavior recognition is solved.

The present invention belongs to the technical field of vehicle positioning, and specifically discloses a vehicle positioning method based on multi-view and multi-scale feature fusion. A multi-view multi-scale pyramid fusion neural network is proposed in the method of the present invention. At the input level of the network, a multi-channel range image RIV projected by a lidar point cloud and a BEV representation generated by a normal distribution transformation are used to complement each other at global and local scales, thereby improving the overall understanding of the scene. Multi-view input effectively alleviates the limitations of a single view and improves the robustness and anti-interference of the model. At the network architecture level, a self-attention mechanism using Mamba is proposed. The present invention can not only make full use of the complementary correlations between multiple views, but also encode and integrate contextual information across multi-scale features. The global descriptor finally generated is feature-rich, thereby improving the accuracy of vehicle positioning.

The invention relates to an emotion recognition method, device and equipment based on high-frequency electrocardiosignals and a storage medium. The method comprises the following steps: segmenting an electrocardiosignal of a target object to obtain an electrocardiosignal sequence; the non-concentric signal wavelets comprise a QRS wave group and other wavelets; performing high-frequency feature extraction on the QRS wave group and other wavelets to obtain high-frequency QRS wave group features and other high-frequency wavelet features; fusing the wavelet coding features of the electrocardiosignal wavelets, the position codes of the electrocardiosignal wavelets, the high-frequency QRS wave group features and other high-frequency wavelet features to obtain a fused feature sequence; determining the position weight of each electrocardiosignal wavelet in the electrocardiosignal sequence; performing context feature extraction on the fused feature sequence, and performing attention processing based on the position weight in the extraction process to obtain context features of the electrocardiosignal; and identifying an emotional state according to the context features. By adopting the method, the accuracy of emotion recognition based on the electrocardiosignals can be effectively improved.