46 results about "Emotion classification" patented technology

This invention discloses a conversational emotion recognition method based on multi-scale temporal features and cross-modal fusion. Preliminary modal features obtained through processing with RoBERTa, 3D-CNN, and OpenSMILE models are input into a multi-scale temporal feature processing module. This module uses Bi-LSTM and Bi-GRU with different intermediate layers to process single-modal information. Next, a multi-modal interaction fusion module is used to interactively fuse the obtained features. This module mainly uses a cross-attention mechanism, taking one modality as the primary modality and fusing information from other modalities to obtain three fused modalities. The three modalities are then used in a hierarchical manner for interactive fusion, rotating among them as the primary modality. The resulting three feature information are then used for modal fusion using a graph constructed based on speaker identity for emotion classification. Furthermore, by concatenating the three preliminary modal features and speaker features, and processing them with MTFP and CIF to obtain fused features, multi-modal emotion recognition is assisted.

The application discloses a kind of based on multi-modal feature fusion sentiment analysis method and system, comprising: through Bi-GRU capture context relationship between text modal, speech modal and image modal each other, while based on cross-modal attention mechanism, text modal, speech modal and image modal are combined two by two, obtain the interactive sentiment representation between text-image, text-speech and image-speech modal, through the multi-head attention mechanism of regular term, text modal, speech modal and image modal are carried out joint sentiment representation, obtain the interactive sentiment representation of three kinds of modal, finally single modal, double modal and three modal emotion feature cascade are classified finally emotion.The application solves the problem that feature information is not enough rich due to the modeling of context information in the existing multi-modal sentiment analysis algorithm, also solves the information limited problem when using single-head attention mechanism for feature learning and the feature information redundancy problem existing in multi-head attention mechanism.

The application discloses a kind of view extraction method, electronic equipment and computer readable storage medium.Therein, method includes obtaining the extraction result after the information extraction model in the view extraction device is handled to positive sample training data;According to the extraction result, generate the training negative sample of the aspect word classification model, the sentiment classification model and the category and sentiment pairing identification model in the view extraction device;According to the positive sample training data and the generated training negative sample, the aspect word classification model, the sentiment classification model and the category and sentiment pairing identification model in the view extraction device are trained;Utilize the view extraction device after training to the text to be extracted and process, obtain the view information in the text to be extracted.The scheme provided in the application can improve the accuracy of view extraction.

The application provides a training method and system of an emotion classification model for multi-modal physiological signals, relates to the technical field of cross between artificial intelligence and biomedical signal processing, and the method comprises the following steps: collecting multi-modal physiological signals of a plurality of sample users; processing the multi-modal physiological signals of the plurality of sample users to obtain multi-modal physiological vectors of the plurality of sample users; using the multi-modal physiological vectors of the plurality of sample users to perform autoregressive pre-training on a large language model; using the multi-modal physiological vectors of the plurality of sample users and text vectors corresponding to emotion classification prompt texts to fine-tune the large language model subjected to the autoregressive pre-training, and obtaining an emotion classification model. In the process of emotion prediction, the problems of multi-modal signal mode loss, inconsistent sampling rates and non-uniform channel numbers can be effectively overcome, and the accuracy of emotion prediction is improved.

The present application relates to big data technology, and discloses a bad review classification method based on a BERT model, which comprises the following steps: data integration and data cleaning are performed on evaluation information to obtain effective evaluation data, and manual sentiment labeling is performed on the effective evaluation data to obtain labeled data; the labeled data is used to perform parameter tuning on a pre-trained BERT model, the trained BERT sentiment classification model is used to classify the evaluation data, positive sentiment data is removed, and data with an emotional category that is not equal to a star level in the evaluation is extracted, screened and labeled; the labeled data and the effective evaluation data are used to retrain the BERT model; negative sentiment data is subjected to word segmentation, a BTM (Bigram Topic Model) is used to extract a bad review theme of the negative word segmentation, and the evaluation information is classified according to the bad review theme. The present application also provides a bad review classification device, equipment and medium based on the BERT model. The present application can improve the accuracy of customer bad review information extraction.

The application provides a speech emotion classification method, system, storage medium and terminal, and the method comprises the following steps: constructing a speech emotion category set; acquiring a corresponding synthetic image for each emotion category; acquiring speech to be classified in terms of emotion, and acquiring text corresponding to the speech; extracting semantic features based on the text, extracting visual features based on the synthetic image, extracting acoustic features based on the speech, and extracting emotion features based on the speech emotion category set; acquiring acoustic semantic features and visual emotion features based on the semantic features, the visual features, the acoustic features, the semantic visual features and the emotion features; and acquiring an emotion classification result of the speech based on the acoustic semantic features, the visual emotion features and the converged emotion features. The speech emotion classification method, system, storage medium and terminal of the application realize arbitrary emotion classification of speech based on the interactive fusion of multi-modal information.

This invention belongs to the field of natural language processing and artificial intelligence technology, and discloses a text classification method and system based on multi-task learning. Existing text classification methods suffer from problems such as isolated task processing and inconsistent category order during training and inference in campus public opinion scenarios. This invention uses a shared encoder to extract semantic features of the text, which are then processed by a subsequent regularization module. At least two parallel task classification modules simultaneously complete topic classification and sentiment classification. This multi-task text classification model uses joint loss for optimized training and introduces a category alignment mechanism to ensure deployment stability. This invention significantly improves processing efficiency and reduces resource consumption by outputting multi-dimensional results in a single inference by a single model; it achieves joint performance optimization by utilizing task relevance; and it fundamentally avoids prediction errors through the category alignment mechanism, greatly enhancing the reliability and practicality of the system.

The steps of the EEG emotion recognition system based on contrast learning and implicit emotion regulation mechanism are as follows: first, the preprocessed EEG feature matrix is divided into left and right brain two-dimensional EEG feature matrices according to the left and right electrode distribution respectively; the obtained and a randomly initialized adjacency matrix are input into a dynamic connection EEG representation extraction module to obtain left and right brain shallow emotion representations and left and right brain deep emotion representations respectively, and an emotion classification loss is calculated. Then, the obtained and are input into an automatic reverse regulation module to calculate a contrast loss; the obtained and are input into a brain lateralization mutual learning module to calculate a KL loss. The total loss obtained from and is used to constrain the system, and EEG emotion recognition network parameters γ are obtained. Finally, the EEG data to be tested is input into the EEG emotion recognition network, and the final emotion recognition result is obtained using γ. The present application further improves the EEG emotion recognition accuracy from the perspective of biological mechanism.

The application relates to the technical field of data processing, in particular to a data correction method and device, equipment, medium and program, wherein the method comprises the following steps: acquiring chat data of a user on an owner social platform; inputting the chat data into a neural network model, and outputting a corresponding first emotion classification result by the neural network model; matching and scoring the chat data according to an emotion dictionary to obtain a corresponding second emotion classification result; and dynamically correcting the first emotion classification result and the second emotion classification result to obtain a final emotion classification result. Therefore, the problems of poor accuracy and reliability of emotion data in the related art are solved.

The application discloses a kind of fine-grained sentiment analysis methods based on event calculation, comprising: step 1: using large language model to extract the event summary of each text, unsupervised event clustering analysis is carried out by clustering algorithm, representative data is screened out to obtain event cluster, and event key elements are extracted based on each event cluster using large language model.Step 2: fine-grained six-classification sentiment analysis is realized based on the pre-training model fine-tuned by labeled data, and the model semantic understanding ability is strengthened by introducing expert-driven unsupervised calibration mechanism for secondary fine-tuning training.Step 3: construct event-sentiment joint analysis framework, sentiment analysis is carried out using the trained sentiment classification model for the obtained event cluster, and the final sentiment distribution of each event is counted by designing structured output template.

This invention discloses a method for constructing an emotional dictionary for urban planning across multiple stakeholders, relating to the fields of natural language processing and urban planning information technology. This method addresses the differences in planning commentary discourse among three stakeholders: officials, experts, and the general public. First, it collects multi-source corpora and performs preprocessing such as text segmentation, word segmentation, and part-of-speech tagging. Then, it uses the TF-IDF-POS algorithm with incorporating part-of-speech weights to select seed words, and combines this with an improved PMI algorithm with adaptive thresholds and scaling factors to mine new domain-specific words. Subsequently, it constructs a three-layer association of "text—topic—emotional words" through formal concept analysis to achieve semantic expansion of the dictionary. Finally, it uses SO-PMI to complete preliminary polarity labeling, fine-tunes the BERT model to achieve accurate sentiment classification, and generates a subject-specific emotional dictionary. This invention solves the problems of poor domain adaptability, insufficient subject differentiation, and low sentiment recognition accuracy of general emotional dictionaries. The constructed dictionary is highly targeted and semantically rich, achieving an accuracy rate of 88.46% in sentiment analysis of expert comments, effectively supporting precise decision-making and governance in urban planning.

The application provides a pre-training language model training method, a text sentiment classification method and device, and relates to the technical field of natural language processing. The pre-training language model training method comprises the following steps: obtaining a training sample and sequence text information corresponding to the training sample; performing word segmentation processing on the sequence text information to obtain a plurality of segmented words included in the training sample; obtaining a basic feature vector of each segmented word in the plurality of segmented words and a semantic element feature vector of each segmented word, and splicing the basic feature vector of each segmented word and the semantic element feature vector of each segmented word to obtain an input text vector; processing the input text vector based on a masking task and a sentence relationship task in the pre-training language model to obtain a loss function of the pre-training language model, and training the pre-training language model based on the loss function. By adopting the technical scheme, the semantic representation between sentences can be improved, and the classification of the text sentiment can be accurately predicted.

The present disclosure provides a text attribute-level sentiment classification method based on distance information and related equipment, and relates to the technical field of natural language processing. The method comprises: obtaining fusion feature information of each word in a target sentence in a text to be classified and word embedding information of an attribute word, wherein the fusion feature information of each word in the target sentence is obtained by integrating the word embedding information, local distance embedding information and global distance embedding information thereof; and processing the fusion feature information of each word in the target sentence and the word embedding information of the attribute word to obtain sentence representation information of the target sentence; and finally obtaining the sentiment classification of the target sentence according to the sentence representation information of the target sentence. When determining the sentiment classification of the target sentence, the present disclosure fully considers the influence of the local distance information and the global distance information of each word in the sentence on the sentiment classification thereof, thereby improving the accuracy of the sentiment classification of the text to be classified.

The application discloses a voice emotion recognition method and system, the method collects voice sample data through a recording device, pre-processes voice sample data and to-be-recognized voice data, extracts voice features of pre-processed voice sample data and to-be-recognized voice data, and establishes an emotion classifier model based on the extracted voice features of the voice sample data; the voice feature data of the to-be-recognized voice data is input into the emotion classifier model, the emotion classifier model compares and analyzes the input feature data to determine the most possible emotion category, and outputs the analysis result after processing. The method provides a voice emotion recognition method with high accuracy, effectively analyzes and understands the emotional state contained in the voice, thereby providing accurate emotional feedback or analysis results, can run in a real-time or near real-time environment, quickly processes and analyzes the voice, and meets the demand of an application scene with high speed requirement.

This invention claims protection for a speech emotion recognition method based on attention-based MCNN combined with gender information. The method includes the following steps: S1, obtaining three-dimensional dynamic Mel-frequency cepstral coefficients (MFCCs) from the preprocessed speech signal as input to a gender recognition network; S2, using MCNN for gender recognition and classifying the speech signal into male and female categories; S3, based on the output of the gender classification, extracting three-dimensional dynamic MFCC features from the male and female speech signals as input to the emotion recognition model. To focus on channel and spatial location information and address long-term dependency issues, a coordinated attention mechanism is introduced into the original MCNN model to establish the speech emotion recognition model; S4, to better capture emotional features and temporal information, A_GRUs are added to the emotion recognition model, and finally, a softmax function is used for emotion classification, providing emotion recognition results for different genders. This invention effectively solves the problems of low recognition rate and weak generalization ability of emotion recognition models caused by differences in male and female acoustic features, improving the accuracy and robustness of emotion recognition.

This invention proposes a multimodal satirical sentiment classification method based on data augmentation and model ensemble, comprising: extracting text from sample fragments to obtain text samples; performing text data augmentation on the text samples using a large language model based on thought chain reasoning; constructing cross-attention fusion features of video samples with the features of the text samples as the main driver, generating multimodal fusion features for model reasoning; training a multimodal fusion model and a text modal model to determine whether audio, video, and text belong to satire, and integrating the multimodal fusion model and the text modal model through a hard voting mechanism to obtain an ensemble model; inputting the video to be classified into the ensemble model with the highest performance index to obtain the classification result of whether it has satirical sentiment.

The application discloses an emotion recognition method based on fusion field analysis and mind theory, and the core process comprises four steps: multi-modal frequency domain enhanced feature extraction, reliable low-rank multi-modal fusion, LIMP multi-agent cognitive reasoning and integrated evaluation and verification. The three-level architecture of "frequency domain transformation, pre-training enhancement and attention de-redundancy" is used to purify features, the T-LMF network is constructed based on low-rank decomposition and MoNIG algorithm to solve the dimension disaster and uncertainty problem of modal fusion, the cognitive leap from emotion recognition to intention understanding is realized by means of the LIMP model, and finally the effect is verified by a standardized evaluation system. Under the premise that the parameter quantity is reduced by more than 90%, the emotion classification accuracy is improved by 2.8% to 4.2% compared with the existing model, the F1 value of social target reasoning reaches 89.7%, the robustness and generalization ability are significantly enhanced, and the application can be widely applied to the fields of human-computer interaction, social robots, intelligent assistants and the like, and provides technical support for multi-modal emotion cognition in complex scenes.

This application relates to the field of emotion recognition technology and discloses a few-sample multimodal emotion classification method based on cue optimization and contrastive decoding. The method includes: optimizing cuees for trainable text tokens and image tokens using a pre-trained visual-language model; constructing basic cuees for image-text pairs to be classified using the trained text and image tokens; retrieving emotion classification examples from a multimodal emotion classification sample set to enhance the basic cuees, generating example-enhanced cuees; inputting the basic cuees and example-enhanced cuees into the pre-trained visual-language model respectively to obtain corresponding emotion classification prediction results; comparing the emotion classification prediction results corresponding to the basic cuees and example-enhanced cuees respectively to obtain the final emotion classification prediction result. This method can improve the accuracy of multimodal emotion analysis with a limited number of samples while maintaining generalization.

The application discloses a training method of an emotion classification model, an opinion monitoring method and related equipment. The training method comprises: performing a deletion operation on a single word in a key sentence of a first text respectively to obtain a plurality of candidate sentences; performing emotion classification on the key sentence and the plurality of candidate sentences respectively by using an emotion classification model to obtain an emotion classification result of the key sentence and emotion classification results of the candidate sentences; determining a key word in the key sentence based on the emotion classification result of the key sentence and the emotion classification results of the candidate sentences; performing word replacement on the key word in the key sentence to obtain an enhanced key sentence corresponding to the key sentence; and performing optimization training on the emotion classification model based on the key sentence and the enhanced key sentence corresponding to the key sentence.

This invention relates to the field of artificial intelligence technology, specifically to a multimodal dialogue emotion recognition method based on an identity-aware network. It maps multimodal features such as text, speech, and vision to a unified space, then uses a recursive network to jointly model the dialogue context and speaker identity information. Features are enhanced through multi-path residual fusion, and a global-local cross-modal attention network is used to achieve hierarchical fusion of multimodal features. Furthermore, label-guided identity transfer is introduced to assist modeling, and a main-slave loss optimization model is used. Finally, the trained model is used for multimodal information fusion and emotion classification. This invention mitigates interference from multiple speaker emotions by explicitly modeling speaker identity changes and fully exploits the complementarity of multimodal emotional cues. Verification shows that this invention outperforms existing state-of-the-art methods in both recognition accuracy and weighted F1 score on public datasets, significantly improving model robustness and generalization ability.

This invention discloses an interactive risk warning system, method, device, and medium based on speech recognition and a large language model, relating to the field of artificial intelligence technology. Specifically, it can be applied to the financial and medical fields, combining emotion and context to accurately grasp the complex and ever-changing emotions and true intentions of customers or patients, thereby improving the accuracy of risk identification. The interactive risk warning system includes a speech recognition module, a semantic analysis module, a risk prediction module, and a feedback module: the speech recognition module collects user-input speech information in real time and converts it into text information; the semantic analysis module performs emotion and context classification on the text information to obtain semantic analysis results; the risk prediction module obtains risk prediction results based on the semantic analysis results and user historical data; the feedback module obtains risk warning strategies generated based on a large language model and pushes the risk prediction results and risk warning strategies to the risk handling party for risk processing.

This invention belongs to the field of artificial intelligence model training and optimization technology, specifically a sentiment classification optimization method and system based on geometric constraints of predicted distribution. The method includes: extracting feature vectors from text samples to be classified; inputting the feature vectors into a sentiment classification model to obtain a predicted probability distribution; wherein the model is trained by minimizing a joint loss function, which includes a discriminative loss term and a geometric constraint term; the geometric constraint term is constructed based on the geometric distance between the predicted probability distributions of sample pairs, used to reduce the distance between predicted distributions of similar samples and increase the distance between predicted distributions of dissimilar samples during training; finally, the predicted probability distribution is output as the classification result. This invention, by imposing geometric constraints on the predicted probability distribution, enables the model to improve the prediction stability and generalization ability for boundary samples and noisy samples while ensuring classification accuracy.

The application provides a training method and device of a mental attention tendency hierarchical emotion classification model, relates to the technical field of natural language processing, and aims to solve the problems of low efficiency, insufficient generalization and weak interpretability of traditional mental attention tendency analysis methods. The method comprises the following steps: obtaining parent-child dialogue text carrying hierarchical labels, connecting multiple classification heads to be trained according to the hierarchical relationship represented by the hierarchical labels, and constructing a hierarchical task classification module to be trained; processing the parent-child dialogue text through a pre-trained large language model and the hierarchical task classification module to be trained to obtain hierarchical task classification prediction results of the parent-child dialogue text; updating the model parameters of the hierarchical task classification module to be trained according to the hierarchical task classification prediction results of the parent-child dialogue text and the hierarchical labels carried thereby, and obtaining the trained hierarchical task classification module.

The application provides a sentiment classification method, a model training method, a system and a storage medium. The initial sentiment classification model is trained by using a training sample set to obtain a sentiment classification model. Each sample includes text data, audio data and visual data and takes a sentiment classification result true value as a label. Feature fusion is performed based on a cross-modal attention mechanism. A first feature fusion module obtains text audio features from text features extracted by a text feature extraction module and audio features extracted by an audio feature extraction module, and inputs the text audio features and visual features extracted by a visual feature extraction module into a second feature fusion module to obtain fusion features. A classification module outputs a sentiment classification result prediction value after fusing the fusion features and global audio features. A joint loss function is constructed by combining a comparison loss function obtained from the fusion features and the global audio features and a classification loss function obtained from the sentiment classification prediction value and the true value, and the initial sentiment classification model is iteratively updated based on the parameters of the joint loss function.

The application provides a task-level and sample-level double-layer fusion cross-domain multi-modal sentiment recognition method and system based on meta learning. The method is aimed at the domain difference and annotation cost problem between different sentiment data sets, adopts a model-independent meta learning (MAML) framework to realize rapid domain adaptation, and specifically includes multi-modal feature coding, double-layer adaptive fusion, meta learning adaptation and sentiment classification. The double-layer adaptive fusion includes a task-level fusion mechanism and a sample-level fusion mechanism. The former generates domain-level modal weights through an attention mechanism, and the latter dynamically adjusts the weights according to the characteristics of each sample through a gating mechanism. The meta learning adaptation learns the initialization parameters through inner and outer double-layer optimization. The leave-one-domain test protocol is adopted to verify the method on four public data sets. The method realizes high-precision cross-domain sentiment recognition under the condition of 20 samples, has a sample efficiency improvement of 2-4 times compared with traditional supervised learning, and significantly improves the cross-domain generalization ability of the model.

The application discloses a kind of multi-modal sentiment analysis methods based on variational capsule gate and three modal interactive attention mechanism, comprising: extracting the text modal feature, visual modal feature and audio modal feature corresponding to the sample to be analyzed;Visual modal feature is generated sparse gating weight by visual gating and variational capsule uncertainty modeling, weighted summation is carried out to the output of multiple candidate expert networks, and visual enhancement representation is obtained, and early fusion feature is obtained by splicing with text modal feature;Each modal feature is calculated by bidirectional cross attention and updated within the mode to output three modal deep fusion feature;Cross-modal consistency alignment is carried out to three modal deep fusion feature;Based on the constructed joint optimization objective function, the optimized three modal alignment fusion feature is trained, input into sentiment classifier for sentiment classification prediction, and multi-modal sentiment classification result is output.The application can improve the accuracy, stability and generalization ability of cross-modal feature fusion in multi-modal sentiment analysis.

The application discloses an emotion analysis method and device, a machine readable storage medium and an electronic device. The emotion analysis method comprises the following steps: determining electroencephalogram fusion features based on electroencephalogram signals of multiple channels, wherein the determined electroencephalogram fusion features fuse time domain information, frequency domain information and spatial information of the electroencephalogram signals; determining text semantic features based on a read text; and determining emotion classification based on the determined electroencephalogram fusion features and the determined text semantic features to perform emotion analysis. In this way, the accuracy of emotion analysis is improved.

This application proposes an aspect-level sentiment analysis method based on dependency trees and structure trees, relating to the field of computer technology. The method includes: inputting preprocessed text into a neural network; jointly extracting explicit and implicit terms from the text to obtain aspect-viewpoint pairs; and performing category-sentiment classification based on the aspect-viewpoint pairs to obtain the aspect-viewpoint-category-sentiment quadruple of the text. This application, by jointly extracting explicit and implicit terms from the text, delves deeper into the hidden sentiment information behind the text, improving the comprehensiveness and accuracy of sentiment analysis; and further enhances the accuracy and reliability of sentiment analysis through a fusion encoding method.

The application discloses a kind of based on mixed information mining's review text sentiment classification method and system, comprising: determining the user and commodity of review text, obtain the latent feature vector of user and commodity;According to latent feature vector and review text, determine the semantic information of review text;Get the goods and sentiment category that have interaction with user, the user of review text, the goods and sentiment category that have interaction with user are handled, obtain user behavior characteristics;Get the user and sentiment category that have interaction with commodity, the commodity of review text, the user and sentiment category that have interaction with commodity are handled, obtain commodity attribute characteristics;User behavior characteristics and commodity attribute characteristics are handled, obtain high-order interaction information;Fusion semantic information and high-order interaction information, determine the sentiment category of review text.The application can realize the sufficient mining fusion of review text semantic information and the interaction information of user commodity, improve the performance and precision of review text sentiment classification.