574 results about "Emotion identification" patented technology

The invention belongs to the technical field of artificial intelligence and health monitoring, and particularly relates to an emotion recognition and intervention system based on facial micro-expression and physiological signal fusion. The emotion recognition precision is improved through space-time alignment analysis of facial micro-expressions and physiological signals, adaptive feedback is achieved in combination with cognitive load correlation modeling and a wearable multi-channel regulation and control terminal, cross-period emotion evolution prediction and group situation awareness are supported, a'awareness-decision-intervention 'complete closed loop is constructed, and the emotion recognition efficiency is improved. And the accuracy and initiative of emotion management in a complex environment are enhanced.

The invention discloses a digital human construction method and device based on a heterogeneous emotion semantic graph and long-sequence emotion modeling, and the method comprises the steps: obtaining multi-modal emotion input data of a text, voice and a visual image, extracting features, and constructing a multi-modal emotion feature set with a timestamp; constructing a heterogeneous emotion semantic graph which comprises user entity nodes, modal feature nodes and emotion concept nodes, modeling a semantic association, state transition and conflict suppression relationship through a multi-type edge structure, and introducing a dynamic evolution and conflict discrimination mechanism; performing time sequence modeling on the emotional state sequence by utilizing a local-global double-layer emotional modeling mechanism, and respectively capturing short-time fluctuation and long-time trend; performing cross-modal fusion on the emotional state and the modal features, and decoding the emotional state and the modal features into behavior parameters for controlling expressions, voices and actions of the digital human; and multi-modal emotion expression of the digital human is driven. Compared with the prior art, the emotion recognition accuracy and expression continuity and naturalness can be effectively improved.

The invention relates to the technical field of computer vision and emotion calculation, in particular to an emotion real-time recognition and long-term monitoring method based on facial expressions. According to the method, an emotion recognition result is obtained by recognizing a high-definition facial image, and the emotion recognition result, environment information and physiological state data are fused to obtain time-space aligned multi-modal data; performing emotional causal analysis based on the multi-modal data, and judging emotional causes by combining a rule engine and a machine learning model: outputting a real-time emotional state recognition result and a periodic emotional report according to the emotional causes, and performing differentiated feedback according to the emotional causes. According to the method, through multi-source data fusion and a causal inference mechanism, the accuracy and interpretability of emotion recognition are effectively improved, and the technical span from passive recognition to personalized active intervention is realized.

The invention relates to the technical field of data processing, and discloses an emotion recognition method and system based on multi-modal feature retrieval, a terminal and a storage medium, and the method comprises the steps: collecting a video signal and an audio signal of a subject, converting the audio signal into a text signal, and extracting a video feature, an audio feature and a text feature; retrieving in a single-mode feature retrieval library according to the video features, the audio features and the text features to obtain enhanced features; aligning the enhanced features to a unified feature space through a mapping module, inputting a double-branch structure, dynamically adjusting the weight of the enhanced features through a modal weight distributor to obtain weighted enhanced features, and querying in a multi-modal feature retrieval library according to the enhanced features to obtain multi-modal retrieval features; and fusing the weighted enhanced features and the multi-modal retrieval features, inputting the fused features into a multi-modal large model for processing, and outputting an emotion recognition result of the subject. According to the invention, accurate perception of the individual emotional state is realized.

The invention discloses a children language cognition rehabilitation assisting system and method based on a self-adaptive co-creation mechanism, and belongs to the field of medical artificial intelligence and psychological rehabilitation engineering. The system comprises five core modules, the modules are connected in a closed-loop mode in a data flow mode to form a sustainable and optimized interaction system, a semantic vector, an emotion vector and a task vector of child voice are fused, a fusion state vector is constructed through a dynamic weight generation network and a cross-modal attention mechanism, and the fusion state vector and the task vector are integrated. And generating a co-creation control instruction by adopting an attention-enhanced gating circulation unit and a strategy network, and further synthesizing an interactive voice signal with emotional expressive force. Synchronous fusion and linkage feedback of semantic understanding and emotion recognition can be achieved, the interaction strategy is dynamically adjusted according to the real-time state of children, strategy network parameters are optimized through online self-learning, and the naturalness, coherence and individual adaptability of rehabilitation interaction are improved.

The invention relates to the technical field of electroencephalogram analysis, in particular to a domain-adaptive cross-subject electroencephalogram signal emotion recognition method, which comprises the following steps: acquiring an electroencephalogram signal, and preprocessing the electroencephalogram signal; inputting the preprocessed electroencephalogram signals into a trained electroencephalogram signal emotion recognition model to obtain an emotion classification result; the electroencephalogram emotion recognition model comprises a graph convolution feature extraction module, an attention module, a domain confrontation module and a classifier module. According to the method, the confrontation module formed by combining the gradient inversion layer and the domain discriminator is designed, and the change rule of the electroencephalogram of a person in positive, neutral and negative states is focused instead of the intensity of the reaction, so that the extracted emotional features have domain invariance, and the extraction accuracy is improved. And identification deviation caused by difference of different individuals in cross-subject emotion identification is eliminated.

The invention provides an emotion recognition method based on electroencephalogram feature fusion and a double-stage attention mechanism, and the method comprises the following steps: A, electroencephalogram signal processing: carrying out the preprocessing of an electroencephalogram signal; and B, double-stage attention feature fusion: in each selected frequency band, adopting a double-stage attention mechanism to fuse the electroencephalogram features, and generating fusion features for emotion classification. And C, double-branch feature extraction: performing double-branch 3D convolution processing on the fused features, extracting multi-scale space-spectral time features, and splicing the multi-scale space-spectral time features along a channel dimension to form uniform features. And D, classification and output: inputting the unified features into a classifier, and generating an emotion category prediction result through a flattening layer and a full connection layer. According to the method, the difference entropy, the power spectrum density and the difference entropy asymmetry feature are fused through unified three-dimensional feature representation, a double-stage attention mechanism is introduced, and high-accuracy emotion recognition is achieved.

The invention discloses an infant state recognition method and system based on traditional Chinese medicine five-tone monitoring analysis, and the method comprises the steps: synchronously collecting the crying sound, physiological signals and behavior videos of an infant, extracting the Mel-frequency cepstral coefficient of the audio, the heart rate variability, galvanic skin response and respiratory rate of the physiological signals, and the facial expression and limb movement features, and carrying out the recognition of the state of the infant through the Mel-frequency cepstral coefficient of the audio, the heart rate variability, galvanic skin response and respiratory rate. Performing structured integration by using a multi-modal feature fusion model; in combination with the five-tone theory of traditional Chinese medicine, a corresponding relation between audio features and five-organ states is established, and the robustness of five-tone and five-organ mapping is improved through fuzzy reasoning and a Bayesian mechanism; the system dynamically adjusts the weight coefficient of each mode, adapts to the individual and emotion historical trend, achieves more accurate emotion recognition and physiological evaluation, achieves cross-mode and multi-layer information fusion, improves the accuracy and interpretation ability of infant emotion and five-internal-organ state recognition, and provides a scientific basis for clinical evaluation and health management.

The invention relates to the technical field of artificial intelligence, can be applied to business scenes such as financial science and technology and medical health, and discloses a label generation method and device based on emotion recognition, equipment and a medium, and the method comprises the steps: carrying out the preprocessing of a target audio, and obtaining the processed audio data; executing voice transcription based on the processed audio data and extracting acoustic features; performing emotion analysis on the acoustic features and the transliterated text; executing intention and appeal recognition based on the transliteration text; performing enhanced matching on the emotion analysis result and the intention and appeal recognition result in a knowledge base; and generating a label set according to a knowledge base enhancement result. According to the method, the acoustic and semantic information of the audio data is jointly processed, and the knowledge base is combined for enhancing matching to realize multi-dimensional tag generation, so that the recognition accuracy and the industry adaptability are improved, and the structured application of the audio data is supported.

The invention discloses an electroencephalogram emotion recognition method based on multi-scale convolution and an attention mechanism. The method comprises the steps that firstly, original electroencephalogram signals are processed; secondly, extracting space and frequency features of the electroencephalogram signals by utilizing a feature pyramid network, and capturing multi-level information of local and global brain regions in a multi-scale convolution structure; a multi-scale attention aggregation module is further introduced, and brain region feature self-adaptive weighting is achieved through a parallel space and channel attention mechanism; secondly, global modeling and long-range dependence capture of time domain features are achieved through a Transform coding structure; and finally, outputting an emotion recognition result through a full-connection classifier. According to the method, the time domain, frequency domain and space domain features of the electroencephalogram signals can be extracted at the same time, efficient and accurate emotion classification is achieved, the robustness and universality of electroencephalogram emotion recognition are remarkably improved, and the method can be widely applied to the fields of intelligent human-computer interaction, mental health monitoring, emotion regulation and control and the like.

The invention discloses a cross-crowd wearable ECG emotion recognition method based on a hybrid convolution-Mama network. The method comprises the following steps: S1, constructing a multimedia emotion induction experiment normal form for old people and cognitive impairment groups, and collecting wearable ECG data; s2, the collected original electrocardiosignals are subjected to standardization preprocessing; s3, constructing a hierarchical scale perception convolution module to perform multi-scale morphological feature extraction on the preprocessed electrocardiogram data; s4, performing physiological baseline remodeling on the feature map by using a non-local channel convolution attention mechanism; s5, constructing a bidirectional state space model based on a Mamba2 architecture, and carrying out long-time-history time sequence dependence modeling; and S6, fusing the spatio-temporal features to carry out emotion category probability prediction and implement personalized model fine tuning. According to the method, core challenges in ECG emotion recognition can be successfully solved, and a complete processing link from multi-dimensional sensing of signals to individualized noise filtering to efficient context understanding is constructed.

The invention belongs to the technical field of artificial intelligence and brain-computer interfaces, and discloses a multi-task self-supervision graph neural network emotion recognition method and system based on time-space-frequency fusion, and the method comprises the steps: firstly carrying out the graph modeling of an EEG signal from a time domain, a space domain and a frequency domain, then designing three types of self-supervision tasks, namely, a time sequence puzzle, a space puzzle and a frequency puzzle, the EEG signals are partitioned and rearranged according to time, space and frequency, and the model is guided to autonomously learn key structural features and potential modes in the EEG signals by predicting the original sequence. And meanwhile, a comparative learning task is introduced to realize semantic consistency constraint under different feature perspectives, so that the discrimination and robustness of feature expression are further improved. And the network adopts a dynamic weight distribution mechanism to carry out joint optimization on multi-task loss. The method can effectively improve the capturing capability of the spatial-temporal dynamic characteristics of the electroencephalogram signals, enhances the generalization of the model and the robustness of noise labels, and shows high accuracy in emotion recognition.

The embodiment of the invention relates to the field of data processing, and provides a multimode fusion emotion recognition method and device based on electroencephalogram and eye movement signals, and the method comprises the steps: extracting electroencephalogram signals corresponding to K reference users used during model training, and obtaining a first electroencephalogram signal set, obtaining an eye movement signal set corresponding to K reference users used during model training, and obtaining a first eye movement signal set; performing feature fusion on first electroencephalogram signals in the first electroencephalogram signal set and first eye movement signals in the first eye movement signal set to obtain a first mixed feature information set; training an initial model by using the first mixed feature information in the first mixed feature information set to obtain a target model; performing emotion mode recognition on a target user by using the target model to obtain a target emotion mode recognition result; and the accuracy of the target model in performing emotion mode recognition on the target user is improved.

The invention discloses a cross-subject electroencephalogram emotion recognition method and system based on adaptive fuzzy domain confrontation. The method comprises the steps that target domain electroencephalogram signal features to be recognized are acquired; to-be-identified target domain electroencephalogram signal features are input into the self-adaptive fuzzy domain adversarial networks in the trained source domain network branches, electroencephalogram signal feature samples are mapped into fuzzy member vectors through a fuzzy encoder, and corresponding fuzzy feature embedding is generated; a task classifier is used for carrying out emotion classification on fuzzy feature embedding; and obtaining a final emotion classification result according to the emotion classification result of each source domain network branch. The method aims to describe the uncertainty of emotions by introducing a fuzzy logic system, so that the robustness, generalization ability and recognition accuracy of an electroencephalogram emotion recognition model in a cross-subject scene are improved.

The invention discloses a VR emotion quantitative management method and system based on physical and psychological interaction, and relates to the field of psychotherapy, and the method comprises the steps: collecting the heart rate variability data, the electrodermal response data and the EEG alpha wave power data of a user in a resting state, and obtaining the EEG alpha wave power data of the user based on the heart rate variability data and the electrodermal response data; generating color, density and physical boundary parameters of the initial emotion energy field; and rendering a dynamic emotion energy field in the VR environment according to the initial emotion energy field parameters, and detecting the distance change between the user and the dynamic emotion energy field through a field density growth algorithm. According to the method, heart rate variability, electrodermal response and EEG alpha wave data are fused by adopting an S-shaped curve function to generate emotion energy field parameters, accurate mapping of physiological states and virtual environments is established, emotion recognition sensitivity is improved, treatment efficiency is improved, field density attenuation rate is dynamically controlled innovatively through parasympathetic nerve activation degree, and the treatment effect is improved. And the synergistic effect of behavior intervention and nerve regulation is realized.

The invention provides a group psychological data fluctuation early warning method based on VR emotion data processing, which comprises the following steps: acquiring multi-modal physiological signals such as electroencephalogram, heart rate variability and skin conductance of a user and behavior data such as voice, expression and virtual trajectory in real time, performing sliding window processing and feature extraction, fusing into multi-dimensional features, inputting the multi-dimensional features into an emotion recognition model, and performing emotion recognition on the emotion recognition model; generating an individual emotion dynamic sequence; a dynamic heterogeneous graph is constructed by combining the social relation and the emotion similarity, the emotion influence intensity between nodes is judged by using a dual-channel graph attention mechanism, and a propagation path is traced through an integral gradient method, so that interpretable group emotion diffusion mode recognition is realized; according to the method, a typical propagation mode and a time sequence convolutional network are combined, a group emotion intensity evolution trend is predicted, when fluctuation exceeds a threshold value, an emotion propagation path thermodynamic diagram is automatically generated and early warning is pushed, and the interpretability of an emotion propagation path and prediction and response efficiency of group psychological fluctuation are improved.

The invention provides an in-vehicle music and light adaptive adjustment method based on emotion recognition, and the method comprises the steps: collecting multi-modal sensor data reflecting the physiological and behavior states of a driver in real time through a plurality of vehicle-mounted integrated sensors in a vehicle, and combining the data type of the multi-modal sensor data, processing the multi-modal sensor data, extracting target features of the multi-modal sensor data, and inputting the target features of the multi-modal sensor data into a preset multi-modal fusion deep learning model for emotion recognition to obtain a current emotion state of the driver, and searching and matching a corresponding target music and light adjusting strategy in a preset emotion environment adjusting strategy library based on the current emotion state of the driver, and dynamically adjusting the music and light in the vehicle based on the target music and light adjusting strategy.

The invention discloses a pet emotion multi-modal recognition and intelligent training decision system and method, and relates to the technical field of artificial intelligence, and the method comprises the steps: synchronously collecting multi-modal data, carrying out cross-modal space-time alignment, carrying out species adaptive emotion recognition, generating a personalized training intervention instruction, executing and feeding back a training effect, and continuously optimizing model parameters. The system comprises a multi-modal data acquisition module, a cross-modal space-time alignment module, a species adaptive emotion recognition module, an individualized training decision engine module, an intelligent execution and feedback module and a long-term learning and model updating module. Through adoption of the technical scheme, the method and the device aim at solving the problem of spatial-temporal dislocation of multi-modal data in the prior art, and can realize improvement of time sequence consistency of emotion recognition, improvement of cross-species generalization ability, establishment of a dynamic feedback loop and continuous adaptation to individual behavior changes of pets.

The invention discloses an emotion response analysis and distribution system and method based on campus propagation, and relates to the technical field of information processing and emotion calculation. Comprising the following steps: acquiring a comment text, user feature information, user interaction information and a content topic label; performing emotion recognition on the comment text based on the user feature information, and performing correction in combination with a preset group weight coefficient to obtain a group characterization emotion value; constructing time sequence emotion data based on the emotion value and performing trend prediction to obtain a propagation popularity prediction result; constructing a propagation topological graph by using the user interaction information, and determining an opinion leader node and a key propagation path; calculating an emotion sensitivity coefficient of the topic, and generating a distribution priority matrix; and dynamically adjusting the rhythm and range of content distribution according to the priority matrix. According to the invention, the accuracy of campus public opinion perception and the timeliness of the distribution strategy can be improved.

The invention discloses an emotion recognition method based on multi-modal signal fusion, and relates to the technical field of emotion recognition, and the method comprises the steps: obtaining an electroencephalogram signal and a peripheral physiological signal to form a multi-modal signal, and carrying out the preprocessing of down-sampling, baseline correction and band-pass filtering on the multi-modal signal; based on the preprocessed signal, extracting a difference entropy feature and a power spectrum density feature; mapping the extracted features into a standardized space grid to generate a feature tensor with a uniform structure; performing adaptive weighting on the mapped feature tensor by using a frequency band fusion attention mechanism, and generating a frequency band weight through global average pooling and a full connection layer; inputting the weighted features into a full connection layer of the parameterized hypermatrix, and performing feature compression and modeling through matrix decomposition and reconstruction; a multi-task learning framework is adopted, classification results of emotion titer and awakening degree are output at the same time based on compressed features, and multi-task collaboration is optimized through a shared feature layer and a dynamic loss weight.

The invention discloses a customer service dialogue multi-modal dynamic emotion track detection method, system and device based on a large model and a medium, and belongs to the technical field of emotion track detection, and the method comprises the steps: collecting multi-modal original data in a customer service dialogue in real time; performing modal integrity analysis on the collected multi-modal original data, and identifying available modals and missing modals; extracting modal specific features based on the identified available modalities, and inputting the modal specific features into a pre-trained large language model; deducing the emotional state of the current dialogue fragment from the modal specific features by using a pre-trained large language model; according to the emotional states of the continuous dialogue segments, an emotional track is dynamically constructed, and the emotional track represents the change trend of emotions along with time; and outputting the emotion track to perform customer service quality control. According to the method, emotion recognition can still keep stable output under the condition of mode missing or signal degradation, and the reliability in a complex communication scene is remarkably improved.

The invention relates to the technical field of intelligent interaction, in particular to an interaction system based on emotion recognition, and the system comprises the steps: collecting multi-modal sensing data and environment context of a user; the feature matching module is used for constructing a first situation feature by utilizing each single-dimensional feature deviation degree obtained by calculating the current multi-modal sensing data of the user and a corresponding coupling feature deviation degree when the first situation is matched, and constructing a second situation feature when the first situation is not matched; constructing a second situational feature by using the deviation degree of each single-dimensional feature obtained by calculating the current multimode sensing data of the user; the emotion risk index calculation module is used for fusing the first situation feature or the second situation feature according to a pre-trained fusion model to obtain an emotion risk index; and the interaction module is used for triggering the interaction strategy of the corresponding level according to the relationship between the emotion risk index and the latest emotion risk threshold. In the emotion recognition process, the current situation type of the user is fused, and the accuracy of emotion recognition is greatly improved.

The present application belongs to the field of artificial intelligence and health monitoring technology, and specifically relates to an emotion recognition and intervention system based on facial micro-expression and physiological signal fusion. The disclosed system integrates multi-modal synchronous acquisition, dynamic feature fusion decoding and individualized closed-loop intervention functions. Through the spatio-temporal alignment analysis of facial micro-expression and physiological signals, the emotion recognition accuracy is improved. Combined with cognitive load correlation modeling and wearable multi-channel regulation terminals, adaptive feedback is realized, cross-period emotion evolution prediction and group situation awareness are supported, a complete closed loop of "perception-decision-intervention" is constructed, and the accuracy and initiative of emotion management in complex environments are enhanced.

The invention relates to the field of sign language emotion interaction, and provides a multi-mode sign language emotion interaction system and method based on an intelligent agent architecture, and the system comprises a recognition module which is used for recognizing a current task type based on multi-mode data of a user, and generating a task scheduling instruction; the large language model module is used for generating feedback content by utilizing a large language model according to the task scheduling instruction; the emotion module is used for extracting keywords from the dialogue history and environment context information of the user, judging the emotion of the user through an emotion recognition algorithm, generating prompt words with humor / comforting elements by utilizing a large language model in combination with the emotion and the keywords of the user, and sending the prompt words to the user; according to the cue word, utilizing a large language model to select proper language content to generate feedback content with emotion; and the generation module is used for displaying the feedback content with the emotion to the user in a sign language form and / or a voice form through a digital person. According to the method, the defects that an existing system is fragmented and cannot be expanded, and situations cannot be understood are overcome.

The invention provides an emotion recognition method, device and equipment based on electroencephalogram signals and a medium. The emotion recognition method based on the electroencephalogram signals comprises the steps that original electroencephalogram signals under all electrode positions are obtained; electroencephalogram characteristic data are extracted according to the original electroencephalogram signals; extracting frequency band and spatial features from the electroencephalogram feature data to obtain a space-frequency feature map; a bidirectional Mama network is adopted to extract time sequence characteristics of the space-frequency characteristic pattern in each time period, and a time sequence characteristic sequence is obtained; fusing each time sequence feature in the time sequence feature sequence on a time period dimension to obtain a fused time sequence feature; and recognizing the fusion time sequence features by using a feedforward neural network to obtain an emotion recognition result. According to the emotion recognition method and device based on the electroencephalogram signals, the equipment and the medium, deep feature fusion can be achieved, hidden features related to emotion changes in the electroencephalogram can be fully mined, and the accuracy of emotion recognition is improved.

The invention relates to the technical field of brain-computer interfaces and emotion calculation, in particular to an electroencephalogram emotion recognition method based on adaptive multi-stream graph fusion and gated space-time Transform, which comprises the following steps: constructing and training an electroencephalogram emotion recognition model, and inputting to-be-detected signal data into the trained electroencephalogram emotion recognition model to obtain a detection result; the electroencephalogram emotion recognition model comprises a self-adaptive multi-stream graph fusion network, a gating enhanced time sequence block and an emotion classification head; the average accuracy and the F1 score of the method are superior to those of the existing mainstream model, and the superiority of the method in the aspect of improving the personalized emotion recognition performance is proved.

The present application relates to the technical field of emotion recognition, in particular to an asynchronous multi-modal emotion recognition method, device, equipment and medium. The present application respectively carries out pulse coding on each modality biological data of the user, obtains the pulse sequence of each modality biological data, applies cross-modal synchronous neurons to each pulse sequence based on the firing time of pulse coding, obtains the emotion feature of the user, and finally applies an emotion classifier to the emotion feature to obtain the emotion classification result. Since the pulse sequence formed by the pulse coding of the present application can record the time when the biological data changes, and the cross-modal synchronous neurons are applied to the pulse sequence according to the firing time of the pulse coding to analyze the emotion feature, the combination of the pulse coding and the cross-modal synchronous neurons of the present application can identify the time when each multi-modal biological data changes, and identify the emotion feature of the user according to the time sequence before and after the change of the multi-modal biological data, so as to improve the accuracy of emotion recognition.

The invention discloses an emotion recognition method based on spatio-temporal multi-scale attention convolutional neural network, which comprises: collecting EEG data of subjects for preprocessing to obtain EEG data containing spatial dimension and temporal dimension; constructing a lightweight convolutional neural network including two-stream spatio-temporal feature construction layer, hybrid attention mechanism layer, high-order fusion layer and classification layer; wherein the two-stream spatio-temporal feature construction layer comprises a temporal feature extraction module and a parallel spatial feature extraction module; the high-order fusion layer is used to re-learn from the learned global convolution kernel to the representation of the local hemisphere convolution kernel; the trained lightweight convolutional neural network is used to identify EEG data, and the emotion recognition results of the subjects are obtained. By constructing a lightweight model with fewer parameters, the accuracy and efficiency of EEG-driven emotion recognition are improved.

The invention provides a bidirectional emotion interaction head ring system based on a multi-mode brain-computer interface. The bidirectional emotion interaction head ring system based on the multi-mode brain-computer interface comprises an exclusive emotion recognition algorithm module, a bidirectional emotion interaction output module, an intimacy relation synchronization and emotion interaction module, a system control module and a head ring structure. The system control module and head ring structure comprises a master control MCU, a multi-mode fusion processor, a Bluetooth / ultra-low power consumption communication module, an electrode self-adaptive pressurization structure and an ultra-light flexible head ring structure. The bidirectional emotion interaction head ring system based on the multi-mode brain-computer interface has the advantages of being high in monitoring precision, timely and effective in intervention, high in family participation degree, capable of being continuously worn and the like, emotion management is converted into active adjustment from passive recording, scientific, stable and sustainable emotion management support can be provided for a user in all stages, and the user experience is improved. The overall mental health level of the user is improved, and the method has clear practical value and industrial application prospect.

The invention provides an emotion recognition method and device, computer equipment and a storage medium, and relates to the field of artificial intelligence, and the method comprises the steps: obtaining multi-modal data of a pet; performing feature extraction on the multi-modal data to obtain a feature vector of each modal; determining relevancy among the modals by using the feature vectors, and performing feature aggregation on the feature vectors by using a pre-trained graph neural network and the relevancy to obtain enhanced feature vectors of the modals; and performing attention fusion on each enhanced feature vector to obtain a fusion feature vector, and performing emotion recognition according to the fusion feature vector to obtain a target emotion type of the pet. Therefore, the relevancy between the modals can be determined by utilizing the feature vectors of the modals extracted from the multi-modal data, and feature enhancement is performed on the feature vectors of the modals according to the relevancy, so that the relevancy between the pet multi-modal data is fully mined, and the accuracy of pet emotion recognition is improved.