501 results about "Mood" patented technology

Aiming at the problems of insufficient language understanding depth, weak personalized dialogue generation ability, lack of continuous learning and long-term user state modeling and the like in the current emotion recognition and psychological intervention technology, the invention provides a user emotion recognition and psychological intervention method combined with a large language model (LLM). According to the method, the potential emotional state is identified by analyzing free text information input by a user by utilizing the powerful capabilities of a large language model in the aspects of natural language understanding, emotional modeling and text generation; constructing a multi-round dialogue context, and reasoning a psychological change trend of the user; in combination with a psychological knowledge base, personalized and mild psychological intervention dialogue content with a dredging effect is generated. The system supports recognition and classification of various emotional states such as depression, anxiety and alonity, is suitable for various interaction scenes (such as APPs, webpages and social robots), and can greatly improve the precision of emotion recognition and the timeliness and effectiveness of psychological intervention. The emotion recognition and psychological intervention method based on the large language model provides solid technical support for constructing an intelligent, continuous and personalized psychological health management system, and has wide application prospects and profound social significance.

A system for real-time analysis of emotional feedback during motivational speeches, consisting of: a series of multimodal sensors, including at least one visual sensor configured to capture facial expressions of spectators, at least one directional microphone configured to capture the audio responses of the audience, and optionally one or more physiological sensors configured to capture biometric signals from spectators; an edge-based processing unit that is communicatively coupled to the arrangement of multimodal sensors, wherein the edge-based processing unit comprises the following: (a) a feature extraction module configured to extract visual features from captured facial images, acoustic features from voice responses, and physiological features from biometric signals; (b) an emotion inference machine configured to process the features using a deep learning-based emotion recognition model comprising a convolutional neural network (CNN) for classifying facial expressions, a recurrent neural network (RNN) for classifying voice emotions, and a multimodal late fusion layer configured to compute a composite emotion state vector representing the aggregated emotions of the audience; (c) a timestamp and speech alignment module configured to correlate the calculated composite emotion state vector with segmented portions of a live motivational speech based on real-time speech-to-text transcription and semantic analysis; and (d) a session-based storage unit configured to log time-indexed emotional state vectors and corresponding speech segments for post-event analysis; A speaker feedback interface comprising a portable display or a podium-mounted visualization panel, wherein the interface is configured to display visual indicators of emotional feedback in real time, the indicators being derived from the emotional state vector and including at least emotional trend graphs, threshold alerts, or engagement indices.

The invention relates to the technical field of health management, in particular to a psychological risk early warning method and system based on multi-dimensional emotion data of a user. The method comprises the following steps: acquiring user multi-dimensional emotion data corresponding to a user emotion expression image, a user emotion voice signal and a user emotion physiological index, and performing multi-source time sequence alignment processing on the user multi-dimensional emotion data to obtain user multi-dimensional time sequence synchronous emotion data; an emotion three-level feature extraction framework is constructed, modal emotion feature extraction and cross-modal fusion are carried out, and cross-modal fusion psychological features of the user are obtained; and obtaining user environment data and user social network data, and performing emotional psychological dynamic graph reasoning and psychological risk early warning on the user cross-modal fusion psychological features based on the user environment data and the user social network data to generate corresponding user emotional psychological risk early warning response measures. According to the invention, early recognition and intervention of psychological health problems can be realized.

The invention relates to the field of data processing, and particularly discloses a user emotion recognition method based on AI and voice data, which obtains passive data of a user through natural language dialogue or voice interaction, and dynamically analyzes an emotion state in combination with an emotion recognition model. When the model detects that the emotion does not reach a discrimination threshold value, three levels of emotion induction mechanisms are triggered in sequence: in the primary stage, basic emotion data are supplemented by adopting a general guide verbal skill; in the intermediate stage, a personalized induction strategy is adapted based on user portrait features; and in the advanced stage, multi-modal auxiliary analysis is started. According to the technology, recessive emotions are effectively mined through a progressive data enhancement strategy, the proportion of effective emotion samples in customer service, psychological counseling and other scenes is increased, the emotion recognition accuracy is improved through a three-layer data compensation mechanism especially for the scene that a user actively hides the emotions, and deep emotion interaction and accurate recognition are achieved.

The invention discloses a multi-dimensional personality evaluation method for dynamic emotion changes, and relates to the technical field of personality evaluation, the system is composed of a plurality of functional modules, and the method comprises the following steps: step 1, recording physiological data in real time through a wearable device, capturing micro-reactions by using a computer vision technology, and determining whether the micro-reactions exist or not; the micro-reactions comprise facial micro-expressions, limb actions and voice and intonation changes; based on a preset dynamic simulation social scene, observing an emotion regulation strategy of the subject in pressure; step 2, using an LSTM model to carry out time sequence modeling on the multi-modal acquisition data, capturing dynamic evolution of emotions, and combining an attention mechanism to dynamically adjust the weight of each modal; based on six basic emotions and nine mental disorder tendencies, establishing a classification model, and capturing association between emotions and personalities; reinforcement learning is introduced, and model parameters are dynamically optimized according to feedback of a subject; and predicting the emotion trend of the subject in a period of time in the future through an autoregressive integral moving average model.

The invention relates to the technical field of service robots, and discloses an elderly care service robot based on an emotion adjustment system, and the robot comprises a multi-mode emotion recognition module which is used for carrying out the comprehensive perception of the emotional state of the elderly through combining various emotion signals of voice, facial expression and limb movement; the personalized emotion adjusting module is used for generating personalized emotion responses meeting the requirements of the old people; the emotion memory module is used for recording emotion changes, important life events and personal preferences of the elderly; the scene self-adaption module is used for sensing the living environment of the old people in real time and adjusting the emotional expression mode of the robot according to the environment information; the health intervention module is used for generating a health management scheme through long-term monitoring of the emotional state and health of the old people; and a safety monitoring module. According to the invention, the emotion state of the elderly is analyzed through the multi-modal fusion network, the emotion misjudgment probability is reduced, and the man-machine interaction experience and the emotion support effect of the elderly are remarkably improved.

The invention relates to the technical field of intelligent assessment of psychological states, and discloses an intelligent dynamic assessment method for psychological states of teenagers based on multi-modal data. The method comprises the steps that multi-modal psychological data of a target assessment object is acquired, the multi-modal psychological data comprises voice emotion information and expression behavior relations, and dynamic features are extracted from the multi-modal psychological data; performing feature fusion processing on the psychological data by adopting a trained machine learning model to generate a multi-modal feature set containing a mapping relation between modal type identifiers and time sequence codes; based on the multi-modal feature set, performing time sequence correlation analysis on the dynamic features through a state analysis network to obtain a fusion result containing emotion dimension features and cognitive mode features; and inputting a fusion result into an evaluation model for dynamic state deduction processing, and outputting psychological state evaluation elements. According to the invention, comprehensive and dynamic assessment of the psychological state can be realized.

The invention relates to the technical field of emotion regulation and control, in particular to an emotion regulation and control system based on a self-adaptive virtual reality scene, which comprises an emotion monitoring module, a virtual reality device, a self-adaptive regulation and control module, a feedback module, an emotion guiding module and an effect evaluation module, the emotion category and the emotion intensity are analyzed and judged; the virtual reality equipment is used for providing virtual reality experience for a user; the self-adaptive regulation and control module is used for adjusting elements and parameters of the virtual scene; the feedback module is used for collecting evaluation on the emotion regulation effect, analyzing the evaluation and generating a feedback report; the emotion guiding module is used for providing emotion guiding suggestions; and the effect evaluation module is used for quantifying the effect of emotion regulation and control and evaluating the effect of emotion regulation and control. According to the invention, real-time monitoring and dynamic regulation and control of the emotion of the user can be realized, personalized virtual reality experience is provided, and more effective mental health support is provided for the user.

The invention provides an intelligent virtuality and reality combined psychological health service device based on digital elements, and aims to improve the accuracy and individuation level of psychological health management. The device firstly obtains the physiological indexes, behavior data, environmental factor data and social economic data of an individual, and carries out multi-modal fusion to form comprehensive feature data. Based on this, a psychological health environment factor model is constructed to quantify the influence of the external environment on the individual psychological state, and the calculation weight and prediction logic of the negative emotion large model are optimized. And the optimized negative emotion large model is used for identifying an individual emotion state, analyzing factors such as social environment, economic pressure and life events in combination with the mental health environment factor model, and generating an individual mental health assessment result. And according to an evaluation result, the virtual digital doctor provides intelligent pre-inquiry and other services. Through data-driven intelligent analysis and virtual-real combined intervention means, the accessibility, accuracy and intervention effect of psychological health services are improved.

The invention provides a psychological tutoring system based on a digital human technology, and relates to the technical field of psychological health. The system captures the emotional state of a user in real time in a multi-modal interaction mode, generates a real-time emotional state group of the user by combining multi-dimensional data fusion of facial micro-expressions, voice spectrums and dialogue texts, and maps the real-time emotional state group to a three-dimensional emotional space for accurate emotion recognition. Based on an emotion-behavior mapping rule, the system dynamically adjusts the digital person and provides an intervention scheme. And when the emotion fluctuation of the user is detected to exceed a preset threshold value, the system automatically triggers a digital human hiding mechanism, gradually weakens visual, auditory and action stimulation, and provides psychological pacification and guidance. According to the method, the accuracy of psychological state recognition and the pertinence of intervention are remarkably improved, real-time and continuous psychological health support is provided for the user, and the method is suitable for psychological health assistance and emotional state analysis.

The invention discloses a three-dimensional emotion resonance interaction system fused with multi-modal perception, and belongs to the field of artificial intelligence. The emotion micro-expression fine-grained recognition module is used for extracting facial local muscle micro-motion features and amplifying and enhancing micro-expression detail changes through sub-pixel-level motion; the voice emotion spectrum dynamic modeling module is used for analyzing an audio emotion change trend; the individual emotional process depth tracking module is used for modeling an individual emotional state evolution track according to historical interaction records; the three-dimensional emotion situation synchronous rendering module is used for inputting and synchronously displaying emotion changes in a virtual environment; the self-adaptive personalized emotion modeling module dynamically learns an individual emotion response mode and constructs an emotion preference map; the interactive memory evolution module evolves and updates the individual emotion model; and the emotion resonance enhancement regulation and control module is used for dynamically regulating interaction contents and expression modes based on resonance intensity. The method has the beneficial effects that fine-grained perception, accurate understanding and natural expression of three-dimensional emotion resonance interaction are realized.

The present invention proposes an AI dynamic emotion recognition multi-dimensional targeted training system, which relates to the fields of computer vision technology and artificial intelligence technology. It includes multiple emotion collection and training terminals at the front end and a background server. The emotion collection and training terminals are used to detect the emotions of the tested personnel. The terminals analyze the face images to obtain the multi-dimensional emotion data of the tested personnel. The multi-dimensional emotion data is uploaded to the background server. The background server analyzes the current emotion state of the tested personnel according to the received multi-dimensional emotion data, and pushes different targeted training tasks to the corresponding emotion collection and training terminals for the tested personnel in different states. After receiving the targeted training tasks, the emotion collection and training terminals, the tested personnel complete the corresponding training content according to the guidance. The present invention can specifically improve the psychological quality of the tested personnel or improve the bad emotion state.

The invention discloses an elderly emotion evaluation system based on multi-modal physiological and behavior signals. The elderly emotion evaluation system is composed of a multi-modal signal acquisition module, an emotion induction task design module and a multi-modal feature processing module. By collecting multi-mode signals such as electroencephalogram, electrocardio, voice and facial expressions, the system can synchronously record physiological and behavior changes of a user in a specific situation. The emotion induction task adopts scientifically designed audio and video contents, and six typical emotions such as happiness, tension, boring, anger, calm and sadness are guided. Then, the system extracts emotion related features from the multi-modal signals by using a deep learning method, models a cooperative relationship among the multi-modal signals by using an attention mechanism fusion technology, and generates unified emotion feature representation; by comprehensively analyzing and identifying the emotional state of the elderly user, the system provides important reference for early monitoring of emotional health of the elderly, psychological state evaluation and personalized intervention, and has social and clinical values.

The invention discloses a cognitive training emotion interaction method and system based on a large model. The method comprises the following steps: acquiring a cognitive evaluation result of a patient, and pushing a corresponding cognitive training scheme to the patient; before cognitive training, acquiring the current emotional psychological state of the user to judge whether the cognitive training requirement is met or not, and if not, performing emotion regulation until the cognitive training requirement is met; during cognitive training, acquiring multi-modal data of the patient and inputting the multi-modal data into a preset large model to perform emotion calculation, so as to identify the current emotional psychological state of the patient again; and based on the current emotional psychological state of the patient, carrying out interaction feedback of a corresponding mode on the patient so as to carry out personalized emotional interaction with the patient. According to the method, the emotional state of the user is recognized in advance before cognitive training, emotion feedback of different modes can be performed according to the current emotional psychological state of the patient in the cognitive training, so that the training compliance of the patient is improved, and the cognitive training effect is improved.

The invention provides an emotional fluctuation event recording method, an emotional fluctuation event recording device and a computer readable storage medium. The emotional fluctuation event recording method comprises the following steps: acquiring an electroencephalogram signal of a user to be recorded; according to the electroencephalogram signal, determining a probability value used for representing that the emotion of the to-be-recorded user originates from a virtual event; in response to the fact that the probability value is smaller than a preset first threshold value, it is judged that the emotion fluctuation of the user to be recorded is caused by a real event, and event content of the real event is recorded. The emotion fluctuation caused by the virtual event and the real event can be distinguished by judging the emotion source of the user, and the emotion intensity of the user is dynamically calculated through the multi-modal signal and is used for recording the event content of the real event causing the emotion fluctuation of the user, so that the authenticity of the recorded content in the emotion recognition process is ensured, and the user experience is improved. In this way, erroneous records related to emotional fluctuations caused by virtual events are eliminated.

The invention discloses a psychological health education auxiliary system based on big data, and relates to the technical field of psychological health education, the psychological health education auxiliary system uses a camera to collect eye movement data, combines CNN to extract static features and LSTM to capture time sequence changes, improves anxiety detection objectivity, combines embedded online learning, short video watching or classroom scenes, and improves anxiety detection accuracy. Daily data collection is carried out, the anxiety trend is continuously tracked by adopting a dynamic analysis method, and the change of the psychological state is monitored and evaluated in real time; the psychological intervention content can be dynamically adjusted based on anxiety scores and personalized feedback strategies, for example, relaxation training, psychological adjustment videos or emotion evaluation questionnaires are pushed, so that psychological health education is more personalized, and invalid or generalized psychological education information is reduced; in addition, a reinforcement learning algorithm is introduced, recommendation content is continuously optimized through interaction data of a tested object, the intervention effect is improved, and psychological education resources can adapt to dynamic changes of individual psychological states.

The embodiment of the invention provides an emotion processing method and device based on multi-modal data, equipment and a computer readable storage medium. The method comprises the following steps: acquiring multi-modal data information; performing feature extraction on the data information to obtain a plurality of features; inputting the plurality of characteristics into a trained emotion analysis model to obtain a target emotion including a plurality of emotion classifications; analyzing the target emotion through a preset emotion analysis strategy, and determining a main emotion category; and executing a corresponding emotion intervention strategy according to the main emotion category. In this way, on the basis that the emotion recognition accuracy is greatly improved, the user experience is enhanced, and the method can be widely applied to multiple fields such as medical treatment and health.

The invention provides a multi-modal emotion recognition fusion method based on a multi-head attention mechanism, and the method comprises the steps: carrying out the feature extraction and fusion of various data, capturing the internal relation of a modal through the multi-head attention mechanism, achieving the information complementation between modals through cross-modal interaction, and dynamically adjusting the weight according to the quality of the modals. And a self-built database containing a large amount of Chinese data is constructed, and a culture adaptation optimization strategy is combined, so that the generalization performance and culture adaptability of the model in Chinese user groups are improved. The system is deployed on a cloud server, optimized hardware and software configuration is adopted, efficient model reasoning and multi-user concurrent processing are achieved, and the large-scale real-time application requirement is met. The emotion of the user can be monitored in real time and early warning can be provided in scenes such as psychological counseling and group emotion monitoring, professionals are assisted in better understanding the emotion state of the user, and the service effect is improved.

The invention relates to an emotional infection method based on parameterized reinforcement learning, and the method comprises the steps: obtaining a real crowd video with a social identity attribute, and carrying out the recognition processing of the real crowd video, so as to obtain all groups forming a real crowd and the social identity of each individual; calculating the emotion intensity of each individual and behavior weights of behaviors corresponding to the individual under different emotion intensities on the basis of the influence of an emergency event source in the surrounding environment and the emotion influence of surrounding neighbor individuals on the individual; and obtaining evacuation behaviors of each individual under different emotion intensities and environment conditions based on the same reward function and each behavior weight of all individuals. Thus, the reality that individual emotions are affected by emergency event sources in the environment where the individual emotions are located and surrounding neighbor individual emotions is considered, the dynamic adaptability of the individual to the crowd environment where the individual emotions are located is achieved, complex behavior decisions of the individual under emotion driving are fully captured, and the method adapts to complex scene changes of high-density crowds.

The invention discloses a five-dimensional dynamic emotion visual chemotherapy healing method and system, and relates to the technical field of emotion visual chemotherapy healing, and the method comprises the steps: employing a multi-sensor fusion method to collect physiological data, psychological assessment questionnaire results and historical emotion data of a user, and obtaining a basic emotion feature vector of the user; mapping the emotional state of the user to a five-dimensional emotional space based on the basic emotional feature vector, and initializing a particle set; collecting multi-mode biological signals of electroencephalogram, heart rate variability, electrodermal response, body temperature and voice emotion recognition of the user, and processing to obtain a feature vector reflecting the current emotion state of the user; the geometric morphology and kinetic parameters in the particle set are dynamically adjusted, a visualization engine is used for rendering particles, a two-way feedback adjustment mechanism is constructed, particle behaviors are adjusted according to the emotional state of the user, and the emotional adjustment ability of the user is enhanced; and designing an interactive emotion regulation game.

The invention discloses a skin electric signal multi-task feature fusion-based mixed emotion recognition method, which comprises the following steps of: acquiring a skin electric signal in a mixed emotion state, performing preprocessing such as filtering and baseline correction, extracting time domain, frequency domain and nonlinear manual features, and extracting deep spatial-temporal features in combination with a CNN-LSTM model; a gating network is designed to realize self-adaptive fusion of manual features and deep spatial-temporal features, so that a multi-task collaborative learning framework with emotion classification as a main task and titer / wakeup degree prediction as an auxiliary task is constructed, and accurate distinguishing of positive, negative and mixed emotions is realized through joint optimization of model parameters. According to the method, classification of mixed emotions is realized, and an extensible technical reference can be provided for the fields of emotion calculation, intelligent health monitoring and the like.

The invention relates to the technical field of education, and discloses an AI-based learning weakness promotion training test question generation system, which comprises a data acquisition module used for acquiring emotional data and cognitive load data of students in real time, the emotional data comprises emotional fluctuation information of the students, and the cognitive load data comprises emotional fluctuation information of the students; the cognitive load data comprises question solving time and question answering error deviation information of the students; the emotion and cognition analysis module is used for analyzing the current emotion fluctuation and cognition load of the student based on the collected emotion data and cognition load data, and generating a corresponding emotion fluctuation value and a cognition load value; and the test question generation module is used for dynamically generating test questions suitable for the current learning state of the student according to the emotion fluctuation value and the cognitive load value of the student, and adjusting the difficulty and the type of the questions. According to the method, the difficulty and the type of the test questions are dynamically adjusted by combining emotion fluctuation and cognitive load analysis, so that cognitive overload and emotion pressure are effectively avoided, and the learning efficiency and the learning motivation are improved.

To solve the problem that it is general to generate a response on the basis of single input and an ability for continuously tracking emotions and intentions of a user is limited, and thus, it is difficult to maintain a natural dialog in a conventional AI dialog system.SOLUTION: The present invention applies a technique named dead-reckoning for estimating a current position from a position and speed in the past in navigation and aviation to a dialog with AI, extracts important information from dialog data in the past of a user, and estimates current needs and emotions. Thus, the intentions of the user are understood, directivity of the dialog is defined, the emotions and degrees of interest are grasped as speed and force of the dialog, a psychological state of the user and context of the dialog are more accurately analyzed, and a response adaptable to the analyzed psychological state and context are generated. For that purpose, the emotions of the user are estimated, and directivity of the dialog is analyzed to generate a personalized response by a response generation unit to be constituted of a user emotion analysis unit, a dynamic dialog navigation analysis unit, a personalized response generation unit, and a learning and evolution unit.SELECTED DRAWING: Figure 3

The invention relates to the technical field of psychological assessment, in particular to a psychological state assessment method, system and terminal based on an interactive terminal, and the method comprises the steps: separating voice data and text data of a user into an emotion change sequence; based on the emotion tendency of the emotion change sequence, setting an emotion change quantity, and according to a matching relationship between the emotion change quantity and a dialogue situation, calculating a user response duration; obtaining the participation degree of the user at different moments by obtaining the response frequency corresponding to the response duration of the user; combining the degree of participation, the emotional variation and the emotional change probability into an emotional feature, and deducing an emotional classification and a transition label of the current emotional feature; on the basis of the emotion proportion of each emotion classification, dialogue strategy matching is carried out according to the participation amount of the emotion classification at adjacent moments, and a dialogue strategy is set; and the accuracy and effect of emotion recognition are improved.

The invention discloses a multi-mode emotion resonance system with an emotion feedback closed loop, and belongs to the field of artificial intelligence and human-computer interaction. The system comprises eight modules including a multi-modal emotion acquisition module, a modal alignment and fusion module, a high-dimensional emotion modeling module, an individualized context construction module, a resonance generation and adjustment module, a behavior prediction triggering module, an interactive feedback deposition module and a strategy closed-loop evolution module. Micro expressions and acoustic and physiological features are sensed through multi-source signals, a subjectively-adjusted emotion vector field and a dynamic context map are constructed, a resonance reaction path is generated through heterogeneous map mapping and multi-layer reasoning, closed-loop linkage of sensing, reasoning, resonance, response and regeneration is finally achieved, and continuous emotional sharing and strategy self-adaptive optimization among individuals are supported. The method has the beneficial effects that closed-loop adjustment of cross-modal emotion recognition and individualized emotional response is realized, and the emotion understanding depth and response adaptability in human-computer interaction are remarkably improved.

The invention discloses a multi-modal emotion recognition method based on an attention mechanism under collaborative learning, and the method comprises the steps: obtaining a sample and a corresponding emotion state, and generating a training set, a verification set and a test set based on the sample; constructing a collaborative learning multi-modal emotion recognition model; defining a loss function of the collaborative learning multi-modal emotion recognition model; training a collaborative learning multi-modal emotion recognition model based on the training set; and inputting a to-be-predicted sample into the trained collaborative learning multi-modal emotion recognition model, and outputting a corresponding predicted emotion state. According to the feature fusion method combining the multi-head self-attention mechanism and the improved efficient additive attention module, the cross-modal global dependency relationship and the local context consistency can be effectively captured, and therefore better emotion recognition precision is achieved.

The invention relates to the technical field of robots, in particular to an accompanying robot control method and an accompanying robot. The accompanying robot control method comprises the following steps: presetting a series of mood values based on different expressions; a series of interactive behaviors are preset, and different interactive behaviors correspond to different mood values; obtaining the current performance of the target, and automatically adjusting the current mood value according to the obtained current performance; outputting a corresponding interactive behavior according to the current mood value; in the scheme, the accompanying robot can adjust the own mood value by sensing the external emotion, that is, the accompanying robot can adjust the own emotion by sensing the external emotion and make the interactive behavior corresponding to the current emotion, so that not only can the target emotion be captured, but also the own emotion can be owned, and real bidirectional emotion interaction is realized; and the deep condition sharing between the accompanying robot and the target is realized.

The invention is suitable for the field of artificial intelligence and psychological health services, and provides a multi-mode psychological counseling system based on artificial intelligence. According to the system, face image data, voice data and text data of a user are collected through a multi-modal data collection module; the psychological counseling strategy generation module determines a corresponding psychological counseling strategy according to the comprehensive emotional state of the user and personal information of the user, and the psychological counseling strategy generation module generates a psychological counseling strategy according to the psychological counseling strategy according to the psychological counseling strategy and the personal information of the user. And finally, the interaction feedback module communicates with the user according to the policy, and optimizes the policy according to feedback information in the communication. The emotional state of the user can be judged according to various information sources such as facial expressions, voice emotions and voice texts of the user. Therefore, the accuracy and comprehensiveness of emotion recognition are improved.

The invention provides a depression analysis scoring method based on knowledge distillation and retrieval enhancement generation, belongs to the field of depression medical assessment, and utilizes a large language model to convert emotion self-description data of volunteers into dialogue data between doctors and the volunteers. And using a large-scale reasoning large language model to perform emotion reasoning and scoring on the part representing the volunteer in the dialogue data according to a medical scale rule. Performing supervised fine tuning on the reasoning large language model with relatively small parameter scale by using the dialogue data and the corresponding reasoning process and scoring result, and constructing a large language model specially used for depressive emotion analysis; the method comprises the following steps: constructing a CCMD-3 diagnosis system into a vector database, and performing similarity retrieval on dialogue data in a real scene and the vector database; and combining the most relevant diagnosis standard obtained by retrieval with dialogue data in a real scene, jointly inputting into the depressive emotion big language model, and finally outputting an analysis result and a score of a depressive symptom.

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.