113 results about "Behavioral traits" patented technology

The invention discloses an intelligent psychological intervention system based on multi-modal fusion, which is characterized in that a three-dimensional evaluation system is constructed by integrating speech sentiment analysis, keyboard dynamics monitoring and physiological signal acquisition, and time sequence alignment and feature weighted fusion of multi-source data are realized by adopting a cross-modal Transform model. The core of the system comprises an adaptive intervention engine which defines a multi-dimensional state space based on a hierarchical reinforcement learning architecture, optimizes an intervention strategy through a PPO algorithm, and realizes dynamic emotion interaction in AR and VR scenes in combination with a digital twin training module; according to the clinical decision support system, physiological behavior characteristics and psychological assessment trends are integrated by using a multi-time scale risk prediction model, and a personalized early warning threshold system is constructed, so that the psychological state recognition accuracy is improved, the intervention intensity self-adaptive adjustment response time is shortened, and the high-risk signal early warning timeliness reaches the minute level; and the problems of evaluation hysteresis and strategy stiffness of traditional psychological intervention are obviously improved.

The invention discloses a prejudice illusion detection method based on hidden layer activation. The method comprises the steps that a belief state is evaluated according to behavior characteristics of answers of a language model, a belief state evaluation result is obtained, and the belief state reflects the uncertainty degree of the answers of the language model; based on the belief state evaluation result, a training set is constructed, a belief state classifier is trained, and the training set reflects the corresponding relation between the belief state of the language model and hidden layer activation; acquiring hidden layer activation in a target language model generation process in real time, and judging a belief state by utilizing the trained belief state classifier according to the hidden layer activation; and for the detected illusion, in combination with the output correctness of the target language model and the belief state judged by the belief state classifier, judging the type of the illusion. According to the invention, belief state determination is carried out based on model hidden layer activation, and the accuracy of prejudice hallucination detection is improved.

The invention relates to the field of intelligent detection, in particular to an induction range setting method and device, equipment and a program product. The method comprises the following steps: collecting behavior characteristics of active personnel in a detection range of a sensor; determining the behavior type of the active person according to the corresponding relation between the value range of the preset behavior characteristics and the behavior type; counting the track distribution of the moving personnel entering the monitoring area according to the behavior category; and setting the induction radius of the monitoring area according to the track distribution, and performing induction monitoring on the monitoring area according to the induction radius. The whole process does not need manual debugging, can automatically adapt to a complex environment, is favorable for improving the sensor deployment efficiency, and reduces the manual debugging cost.

According to the embodiments of the present disclosure, provided are a method for object recommendation, and a device, a storage medium and a program product. The method comprises: obtaining behavior information related to a behavior sequence which is executed by a target user on objects, and scenario information related to a target scenario used for recommending a target object; using each of a plurality of first feature generation layers, which respectively correspond to a plurality of behaviors, in a trained recommendation model to respectively determine, on the basis of the scenario information, processing parameter values specific to the behaviors, and on the basis of the processing parameter values specific to the behaviors and a shared processing parameter value among the plurality of behaviors, extracting behavior feature representations of the behaviors from the behavior information related to the behavior sequence; using a second feature generation layer in the recommendation model to extract an object feature representation from the scenario information and object information of the target object; and at least on the basis of the respective behavior feature representations of the plurality of behaviors and the object feature representation, determining a prediction result of the target user executing a specified behavior on the target object.

The invention relates to the technical field of language barrier evaluation, and discloses a deep learning-based language barrier executive intervention effect evaluation method. The method comprises the following steps: acquiring real-time voice data and facial expression data of a language barrier patient in intervention training through a multi-modal data acquisition device to form an original behavior feature set; performing acoustic feature hierarchical analysis on the voice data by adopting a time sequence feature extraction network to generate a voice time sequence feature vector; performing micro-expression dynamic capture on the expression data through a three-dimensional convolutional neural network to generate an expression state feature vector; inputting the two types of vectors into a multi-modal feature fusion layer to carry out cross-modal correlation analysis, and generating a comprehensive behavior evaluation matrix; on the basis of the matrix, an intervention effect analysis model driven by an attention mechanism is adopted, a behavior improvement degree index of the current intervention stage is calculated, accurate evaluation of the intervention effect is achieved, and support is provided for dynamic adjustment of language barrier rehabilitation intervention.

The invention discloses an intelligent bird repelling device and method based on multi-modal recognition, and relates to the technical field of power grid operation, a microphone array is arranged in a target monitoring area, and sound signals of birds are monitored in real time; setting a camera in the target monitoring area, and acquiring an image of the bird in the target monitoring area; according to the images of the birds in the target monitoring area and the sound signals of the birds, the initial emission state of a laser and the initial sound production state of an audio generator are determined, and the birds in the target monitoring area are repelled; acquiring behavior state information that the birds are driven, and adjusting the emission state of the laser and the sound production state of the audio generator according to the behavior state information; in this way, birds can be repelled in various modes of sound and images, behavior characteristics of different birds and actual requirements of a power grid can be flexibly met, the adaptability in different environments is good, the effective bird repelling effect is ensured, and safe operation of the power grid is guaranteed.

The invention discloses an AI accompanying system and method based on general artificial intelligence, and the method comprises the following steps: S1, collecting and preprocessing user data, and generating a standardized data set; s2, performing dimension reduction by adopting diffusion mapping, extracting voice and behavior characteristics, and retaining a state change trend; s3, constructing a behavior knowledge graph based on symbol logical reasoning, and recording symbol state changes; s4, similar states and coping strategies are retrieved by using sparse distributed memory storage symbol representation; s5, combining manifold embedding, historical matching and symbolic reasoning, updating a user state and generating a personalized accompanying strategy; s6, analyzing the voice rhythm and the word frequency, constructing an emotion evaluation model, and generating a personalized emotion intervention scheme; s7, optimizing the knowledge graph by adopting incremental memory, and improving the companion strategy adaptability; and S8, recording feedback, continuously optimizing emotion intervention, and realizing intelligent accompanying. The AI accompanying system improves intelligence, personalization and long-term adaptability of AI accompanying, and is suitable for the fields of old-age care, mental health management and the like.

The present invention discloses a method and device for campus anti-bullying alarm, which collects image information and voice information in a certain period of time in the campus environment, compares and assigns behavior features, facial expression features and voice features extracted from the image information and voice information with information in a database, and calculates whether the current state is bullying through a specific algorithm. The beneficial effect of the present invention is that it can accurately identify whether the current state is bullying, avoid false alarms, and alarm in time.

The invention relates to a self-adaptive excitation method for maintaining healthy behaviors. The method comprises the following steps: acquiring environmental data in a target area and physical signs and behavior data of a person; extracting behavior characteristics of the person according to the physiological indexes and the behavior data; constructing a short-term dynamic behavior and a long-term trend behavior according to the behavior characteristics; fusing the short-term dynamic behavior and the long-term trend behavior by using a cross attention mechanism and a gating fusion formula; establishing a health behavior thinking map; generating personalized incentive content; matching the character features with the excitation content through a multi-dimensional depth similarity algorithm, and generating excitation feedback in a text, voice or video form; and iteratively updating the excitation triggering condition and the content generation strategy according to the character behavior corresponding data. Through the technical scheme of the invention, not only can the probability of behavior change be improved, but also the interpretability of the excitation method can be effectively improved.

The invention relates to the technical field of examination cheating prevention, and discloses an online examination cheating prevention real-time early warning system based on behavior recognition, and the system comprises a real-time monitoring module which employs multi-mode biological feature recognition, carries out the confirmation of the identity and registration information of an examinee through face recognition before an examination, and carries out the real-time monitoring of an examination behavior; the test module is used for identifying examinee information and providing examination questions and an answer interface; the AI algorithm recognition module monitors behavior characteristics of the examinee in the examination process, recognizes abnormal behaviors by analyzing the stability of the behavior characteristics and judges whether the behaviors are cheating behaviors, and a voiceprint recognition module is arranged in the AI algorithm recognition module to monitor environmental noise and record voice. According to the invention, through synchronous acquisition of three paths of videos, a monitoring blind area is further eliminated, multiple paths of videos complement each other, misjudgment of a single view angle is reduced, behaviors of examinees can be automatically identified and analyzed through an AI algorithm, risk prompting and early warning are carried out, and the monitoring efficiency is improved.

A SaaS service recommendation procedure based on global multi-behavior dependencies, in which one first analyzes the service interaction data to obtain the behavior perception sequences and service classification sets, then uses the behavior perception sequences and service classification sets to construct behavior perception hypergraphs, and combines the hypergraph self-monitoring mechanism to measure the difference in meaning of multi-behavior interactions between users and API services, then designs the hypergraph convolution process on the behavior-oriented hypergraph, which is based on the theory of spectral decomposition, and uses the hypergraph signals to represent the global multi-behavior dependencies, finally combining the global sequence features and the service embedding vectors to obtain the recommendation scores of the API services for service recommendations.The present invention effectively models the complex and heterogeneous behavioral characteristics of users and can better measure the difference in meaning of interactions between multiple behaviors, thereby making the results of service recommendations highly relevant.

The invention discloses a simulation method and system for students with different cognitive levels based on a large language model. According to the method, the cognitive prototype is constructed based on the past learning records of the students, and the mastering degrees of the students on different knowledge concepts are clearly expressed through the knowledge graph. The cognitive prototype can be used for accurately predicting the performance of the student in a new task, including whether the problem can be solved or not and specific errors possibly caused. Meanwhile, a self-evaluation-self-optimization loop process based on beam search is introduced, and a student answer consistent with a prediction behavior is iteratively generated, so that student simulation which is more real, natural and consistent in cognition is realized on the premise that additional training is not needed. Related results show that the staged and cognitive prototype-driven student simulation framework provided by the invention is superior to the existing mainstream method in multiple dimensions, and behavior characteristics of students with different cognitive levels can be reproduced more truly.

The invention discloses a quantitative evaluation method for an interference effect of trombone playing training on suppression control ability, which comprises the following steps of: acquiring pulse wave signals in various states when a subject performs trombone playing training, denoising, and extracting physiological features from the pulse wave signals; the method comprises the following steps: collecting behavior data when a subject executes playing training, including a playing airflow signal and position control data, and extracting behavior characteristics from the behavior data; when the correct rate and the response of executing the inhibition control test task by the subject are recorded, calculating the score of the test task through probability distribution fitting; and constructing a data set by taking the physiological features and behavior features of the subject as explanatory variables and taking the test task score as a target variable, training a regression model and screening an optimal feature subset to construct a quantitative formula, and obtaining a quantitative evaluation result of the intervention effect. According to the invention, a quantitative analysis method is provided for research on the intervention effect of the music therapy on the suppression control ability by relying on trombone playing training.

The invention discloses a behavior data analysis method and system based on intelligent perception. The method and system are used for improving the reliability of child behavior analysis. The method comprises the following steps: acquiring multi-dimensional monitoring data of a plurality of children in a monitoring environment, wherein the multi-dimensional monitoring data comprises visual information, auditory information and physiological information of each child; performing multi-source fusion on the visual information, the auditory information and the physiological information of each child to generate a behavior feature set; inputting the behavior feature set into a preset behavior and emotion classification model for classification to obtain a behavior mode and an emotion state of each child; on the basis of individual information of different children, the behavior modes and the emotional states in combination with scene information of the monitoring environment, knowledge graph construction on a time sequence is carried out, a children behavior graph is obtained, and the children behavior graph is used for displaying behavior events of the children in a preset time period.

The embodiment of the invention belongs to the technical field of psychological state detection, and discloses a psychological state assessment interaction system and device, and the corresponding system comprises an AI interaction module which is used for interacting with a user and obtaining feedback information of the user in the interaction process, and the feedback information comprises voice reply data, text reply data and physiological data of a question; the deep learning model is used for extracting feature data of the feedback information; the support vector machine model is used for evaluating the psychological state of the user according to the feedback information; input data of a kernel function of the support vector machine model is feature data; and the VR video generation module is used for generating a corresponding VR video according to the psychological state and pushing the VR video to the user, and the VR video has an interaction function with the user so as to further determine a lower state of the psychological state of the user and autonomously modify the VR video according to the lower state. The emotion, cognition and behavior characteristics can be extracted from the dialogue of the user, and the psychological state is quantified.

The invention discloses a dolphin behavior analysis method, device and equipment based on multi-modal characteristics and a medium, and the method comprises the steps: carrying out the framing of an acoustic waveform signal of a dolphin, so as to construct a three-dimensional acoustic tensor; performing feature coding on the original video slice of the dolphin to obtain a global behavior feature vector, and performing behavior clustering on the global behavior feature vector through a preset clustering algorithm to obtain a behavior center vector; the method comprises the following steps: obtaining an audio embedding vector of a preset dimension through a preset time sequence modeling network, and obtaining a video embedding vector of the same dimension as the audio embedding vector through a preset multi-layer perceptron; generating a plurality of groups of sound-line embedding pairs according to the time alignment index table and a preset dynamic time warping algorithm; and through a preset graph convolutional network, carrying out propagation and aggregation on the sound line graph structure constructed according to the plurality of groups of sound-line embedding pairs to obtain a dolphin behavior analysis result. The dolphin behavior analysis method can improve the accuracy of dolphin behavior analysis results.

The invention relates to the technical field of intelligent pet behavior correction based on image recognition, and particularly discloses a pet dog behavior correction method based on training image feedback recognition, which comprises the following steps: capturing activity image data of a pet dog by using a camera, and extracting behavior characteristics such as social interaction distance and energy release level; analyzing the time sequence data of the social interaction distance by using a multi-scale convolutional neural network, and calculating an abnormal feature value of the social interaction distance; performing dimension reduction processing and clustering analysis on the energy release level through a manifold learning algorithm, calculating energy release abnormal feature values, constructing a comprehensive feature vector by the two abnormal feature values, inputting the comprehensive feature vector into a random forest model to predict an abnormal behavior score of the pet dog, and when the score exceeds a preset threshold value, judging that the pet dog shows an abnormal behavior. Based on the behavior correction value calculated by the fuzzy logic system, the intensity of the correction measure is dynamically adjusted.

The invention belongs to the technical field of natural language processing, and discloses an AI voice rate adjustment method and system for an AI platform, and the method comprises the steps: firstly obtaining historical data, including user behavior data and user feedback data; performing feature extraction on the user behavior data to obtain corresponding behavior features; screening out data subsets with excellent and good user feedback from historical data, and extracting corresponding behavior features to form a standard feature group; standard behavior characteristics are obtained based on the calculation; extracting real-time behavior characteristics in a real-time dialogue process of the AI and the user; calculating a characteristic deviation value between the real-time behavior characteristics and the standard behavior characteristics; and finally, adjusting the voice rate of the A I according to the real-time voice rate and the characteristic deviation value. The AI voice rate is automatically adjusted by analyzing the interaction habit of the user, so that the cumbersome process that the user needs to manually set is avoided, and the naturalness of AI voice interaction and the user satisfaction are improved.

The invention relates to an SVM-based fatigue driving state detection method and system, and the method comprises the following steps: collecting behavior feature data of a driver, and constructing a multi-modal behavior feature vector; classifying the multi-modal behavior feature vectors through a mixed kernel function SVM model to obtain behavior state classification, wherein the mixed kernel function SVM model comprises a dual-kernel function pool of a radial basis kernel and a polynomial kernel and an online incremental learning framework; the behavior state classification is judged according to a judgment threshold value, a driver fatigue driving state detection result is obtained, and the judgment threshold value is obtained through dynamic adjustment of a dynamic threshold value adjustment module according to the multi-mode behavior characteristic data. Compared with the prior art, the fatigue driving state detection method has the advantages that the conditions of misjudgment and missed judgment are effectively reduced, and the accuracy and reliability of fatigue driving state detection are improved.

The invention provides an explanation strategy adjusting method and device, and the method comprises the steps: obtaining the behavior characteristics of a user and a current subject, adjusting the explanation strategy of the current subject based on the behavior characteristics of the user, determining the learning effect, efficiency and cognitive load of the user under the explanation strategy, and obtaining the learning effect, efficiency and cognitive load of the user under the explanation strategy. And obtaining a score according to the learning effect, efficiency and cognitive load of the user under the explanation strategy, and if the score is higher than a preset score, adjusting the explanation strategy of the current subject based on a knowledge graph. By comprehensively capturing the learning behavior and the emotional state of the user, the explanation strategy is adjusted, so that a more personalized explanation strategy is provided for the user.

The embodiment of the invention discloses a background Alpha rhythm-based audio-visual perception ability evaluation method, which comprises the following steps of: acquiring an individual Alpha peak frequency of each subject, and setting various background rhythm stimuli for each subject; enabling each subject to execute various audio-visual perception tasks while the various background rhythms are stimulated, so as to collect electroencephalogram data and behavior data of each subject when the various audio-visual perception tasks are executed under the stimulation of the various background rhythms; performing feature extraction on the electroencephalogram data of each subject to obtain electroencephalogram features; performing feature extraction on the behavior data of each subject to obtain behavior features; screening electroencephalogram features related to improvement of the behavior features from the electroencephalogram features to obtain effective electroencephalogram features; and based on the effective electroencephalogram characteristics of each subject under the individual Alpha rhythm stimulation and the effective electroencephalogram characteristics of each subject under each contrast rhythm stimulation, calculating the modulation index of each subject so as to quantitatively evaluate the adjustment effect of the individual Alpha rhythm stimulation on the audiovisual perception ability of each subject.

A system and method for processing third party behavioral assessments that receives data for a first and second behavioral assessment, the first behavioral assessment assessing a first behavioral characteristic of a first person and the second behavioral assessment assessing a second behavioral characteristic of the first person; utilizes the first and second behavioral characteristics to calculate a behavioral parameter for the first person; compares the behavioral parameter against corresponding behavioral parameters for respective persons for a team; provides a user interface to a user device that is configured to receive a team dynamic selection; receives a hypothetical scenario dataset that describes how the first person would work with the respective persons of the team; determines an impact of including the first person in the team, based on the desired dynamic for the team and the hypothetical scenario dataset; and displays the impact via the user interface.

The invention provides an automatic evaluation system for enterprise risk management, and relates to the technical field of automatic evaluation, and the system carries out the desensitization of obtained enterprise evaluation data, and obtains desensitization evaluation data; constructing a behavior feature difference matrix, determining the behavior feature anomaly degree of the target enterprise in the interaction process according to the behavior feature difference matrix, and determining the behavior characterization of each interaction behavior in the target enterprise based on the behavior feature anomaly degree and the behavior feature difference matrix; determining the behavior diversity of each interaction behavior in the target enterprise according to the evaluation data training set, and updating the evaluation data training set into an interaction behavior training set according to the behavior characterization and the behavior diversity of each interaction behavior; according to the technical scheme of the invention, the representativeness and diversity of the training data can be improved when the automatic evaluation model is trained, so that the evaluation capability of the automatic evaluation model is enhanced.

The invention relates to an intelligent security and protection method and an early warning system based on behavior detection, and the method comprises the steps: obtaining video data in a monitoring region through a camera; performing real-time analysis on the video data, and extracting human body behavior characteristics; performing abnormal behavior detection based on the behavior characteristics; when an abnormal behavior is detected, an early warning mechanism is triggered, and alarm information is sent; according to the invention, by analyzing the video data in the monitoring area, the human body behavior characteristics are extracted, and abnormal behavior detection is carried out based on the behavior characteristics, so that intelligent safety monitoring and early warning are realized.

The invention relates to the technical field of picture processing, and particularly discloses an image-text question and answer and person swimming detection method and system, and the method comprises the following steps: collecting a swimming scene image, a scene historical record and a reasoning chain of the scene historical record, and collecting a question input by a user; generating associated behavior characteristics; judging whether the associated behavior characteristics are the same as the behavior characteristics recorded in the historical scene, if it is found that no historical scene record cannot be judged, generating a to-be-confirmed behavior characteristic problem for the behavior characteristics which cannot be judged, searching for related behavior characteristics in the swimming scene image, reasoning the to-be-confirmed behavior characteristic problem, generating a to-be-confirmed reasoning chain, and sending the to-be-confirmed reasoning chain to the swimming scene image; the inference chain of the scene history record with the maximum overlap ratio of the inference chain to be confirmed and the scene calendar is output to an inference chain result; and feeding back the reasoning chain and the reasoning chain result to the user. According to the method, complex behavior analysis can be dealt with, automatic monitoring, intelligent question and answer and anomaly detection in a swimming scene are realized, and the accuracy and flexibility of the system are remarkably improved.

The invention discloses an interview method and device, relates to the technical field of online interview, and mainly aims to adjust interview problems in real time according to the state of an interviewer. According to the main technical scheme, the method comprises the steps of collecting audio and video data of an interviewer in an interview process; when an interview question is issued to the interviewer terminal every time, the collected audio and video data are analyzed to obtain emotion feature data, language behavior feature data and other behavior feature data except the language behavior feature data of the interviewer responding to the current interview question; selecting a next interview question based on the emotion feature data, the language behavior feature data and other behavior feature data, and issuing the next interview question to the interviewer terminal; and if it is determined that the interview process of the interviewer is finished, generating an interview report of the interviewer based on the corresponding emotional feature data, language behavior feature data, other behavior feature data and answers of the interviewer responding to each interview question in the interview process.

This technology provides ways to diversify the behavioral characteristics of non-player characters. [Solution] In the acquisition step, situation information indicating the game status of a non-player character is acquired. In the output step, control information for controlling the actions of the non-player character is output based on the situation information and predetermined reference information. The non-player character is associated with a first character or other non-player character with whom it collaborates in a virtual space. The reference information is configured to allow referencing action information about the actions of the first character or other non-player character, and situation information at the timing when the control corresponding to the action information is executed. The action information is acquired sequentially via input from the first player operating the first character, or sequentially in response to actions taken by the first character or other non-player characters, and managed in an information processing system.

This invention discloses a method and system for early warning of abnormal behavior among college students based on multi-source data fusion, relating to the technical field of image processing. The method involves real-time acquisition of video streams of individuals within a target area, extraction of behavioral features from the video streams for classification, and a determination list based on these behavioral features. Multi-source data is collected, and anomaly coefficients are calculated based on the multi-source data. If the anomaly coefficient exceeds a threshold, the target individual is identified as exhibiting abnormal behavior. Anomaly warnings are then issued based on the behavioral features corresponding to the abnormal behavior. By calculating the anomaly coefficient through multi-source data fusion, a preliminary screening of hidden risks is achieved, reducing the detection delay and computational redundancy caused by traditional full-process monitoring analysis. Furthermore, real-time video stream acquisition and cloud-based behavioral feature extraction are initiated for high-risk individuals, avoiding the limitations of audio noise interference and single visual modalities, and improving the robustness of identification and the real-time performance of warnings in complex monitoring scenarios.

This application provides a method for assessing the training ability of a target audience, applicable to the field of artificial intelligence. The method includes: obtaining a first score for the target audience based on their answers in a business training system and the knowledge points in the knowledge graph at the current moment; analyzing the behavioral characteristics of the target audience during the answering process using a time-series analysis model to obtain a second score and a guessing coefficient, where the guessing coefficient characterizes the degree of guessing in the target audience's answers; correcting the second score based on the guessing coefficient to obtain a corrected second score; obtaining a comprehensive score using a gating fusion mechanism based on the first score, the guessing coefficient, and the corrected second score; and obtaining the training ability level corresponding to the comprehensive score from a preset training ability level table, using the training ability level as the assessment result of the target audience's training ability. This application also provides a device, equipment, storage medium, and program product for assessing the training ability of a target audience.

An emotion recognition method includes the following steps: acquiring video data of a human-object interaction behavior process; performing data labeling on the positions of a person and an object and the interaction behaviors and emotions expressed by the person; constructing a feature extraction model based on deep learning, extracting features of interaction between the person and the object in a time-space dimension, and detecting the position and category of the human-object interaction behavior; mapping the detected interaction behavior category into a vector form through a word vector model; and finally, constructing a fusion model based on deep learning, fusing the interaction behavior vector and the time-space interaction behavior features, and identifying the emotion expressed by the interaction person.