48 results about "Emotional Changes" patented technology

The present invention is a method and system for measuring human emotional response to visual stimulus, based on the person's facial expressions. Given a detected and tracked human face, it is accurately localized so that the facial features are correctly identified and localized. Face and facial features are localized using the geometrically specialized learning machines. Then the emotion-sensitive features, such as the shapes of the facial features or facial wrinkles, are extracted. The facial muscle actions are estimated using a learning machine trained on the emotion-sensitive features. The instantaneous facial muscle actions are projected to a point in affect space, using the relation between the facial muscle actions and the affective state (arousal, valence, and stance). The series of estimated emotional changes renders a trajectory in affect space, which is further analyzed in relation to the temporal changes in visual stimulus, to determine the response.

Systems and methods for estimating emotional states, moods, affects of an individual and providing feedback to the individual or others are disclosed. Systems and methods that provide real time detection and monitoring of physical aspects of an individual and / or aspects of the individual's activity and means of estimating that person's emotional state or affect and change to those are also disclosed. Real time feedback to the individual about the person's emotional change, change or potential change is provided to the user, helping the user cope, adjust or appropriately act on their emotions.

System and method capable of reducing the effects of negative emotional states by performing physiological measurements of a user with wearable sensors (1), detecting an emotional state of said user according to the performed measurements, preferably using an autoassociative memory, and generating commands or instructions for external devices (3) whenever an emotional change is detected, in order to compensate or alleviate said emotional change.

Systems and methods for estimating emotional states, moods, affects of an individual and providing feedback to the individual or others are disclosed. Systems and methods that provide real time detection and monitoring of physical aspects of an individual and / or aspects of the individual's activity and means of estimating that person's emotional state or affect and change to those are also disclosed. Real time feedback to the individual about the person's emotional change, change or potential change is provided to the user, helping the user cope, adjust or appropriately act on their emotions.

The present invention relates to a method for constructing human-machine interface by utilizing human emotion and emotional change information, in particular, it is a method utilizing human physiological change information produced after the man is stimulated by external factor or internal factor to implement human / machine interaction and implement automatic control of external equipment. Said construction method mainly includes the following steps: defining detected object, starting emotional information collecting system, feeding the collected signal into collector synchronization and control system, making characteristic extraction and identification, judging emotional signal and analyzing said signal, and outputting said respose signal, etc.

The invention relates to a virtual reality interaction method and device based on eye movement tracking, being characterized in that eyeball movement is tracked in real time by measuring the positionsof visual attention focuses of eyes; and an infrared light source and an infrared camera are adopted for collecting eye movement information, and the positions of pupils are measured by tracking andcalculating the center positions of the pupils in an eye image, and the movement track of the pupils is established. Furthermore, the virtual reality interaction device based on eye movement trackingcan monitor the physiological or cognitive state and emotional changes, such as frightening and stimulation, of a user in real time by monitoring the changes of pupils, and can monitor eye movement tracks and the changes, such as the corresponding degree of dilation or reduction, of the pupils and feed the changes back to the main control module.

The embodiment of the invention provides a method and a device for predicting an evolution trend of an internet public opinion. The method comprises the following steps: collecting data from a network, generating a statistical ratio f<pos>(t) between the number of posts employing a supportive attitude as an emotional trend aiming at the same theme in various time intervals and the total post number according to the obtained data; building a viewpoint interaction model driven by user behaviors according to the characteristics of individual behaviors; generating an optimal value of a system parameter of the viewpoint interaction model according to the statistical ratio f<pos>(t) and the viewpoint interaction model; generating a long-term change curve of the viewpoint interaction model according to the optimal value of the system parameter; carrying out fitting on the long-term change curve and generating an emotional change curve function y(t); generating the optimal value of a factor of the emotional change curve function y(t) by the value of the statistical ratio f<pos>(t) in a time interval [0, T]; and generating a stable value of the emotional change curve function y(t) under the optimal value of the factor as a prediction value of the evolution trend of the same theme.

Disclosed is a method for changing emotion of a software robot (sobot) in a sobot terminal. The sobot terminal includes a short-term memory unit and a long-term memory unit. When an emotional change occurs during the operation of the short-term memory unit, the sobot terminal stores a short-term reference emotion value of the corresponding emotion in the long-term reference memory. When the operation time of the long-term memory unit elapses, the sobot terminal resets the long-term reference emotion value using the short-term reference emotion values stored in the long-term memory unit. The sobot terminal can change the emotion of the sobot more naturally through the above process.

The invention provides a multi-layer emotion calculating method based on a mood index. The method comprises the steps of calculating the mood index at a current moment according to input stimulation; calculating the emotional intensity at the current moment according to the input stimulation and the mood index; calculating an emotional probability after state transition according to the emotional intensity and a state transition probability matrix, and outputting the emotional state with a maximum probability value. The method defines the mood index, quantifies a relation among mood, characters and emotion again, effectively fuses the influences of external stimulation, mood states, personality characteristics, emotion decay and emotion interactions on emotional change, can reflect the characteristics of human emotional change well and realizes personalized calculation for the emotional state of a robot.

The invention provides a method for robot emotion cognition based on depth learning, which comprises the following steps: obtaining multimodal information, and obtaining emotional state through a multimodal information fusion algorithm; obtaining emotional state through the multimodal information fusion algorithm; inputting emotional state into an interactive decision model for processing to obtain decision information, and outputting the decision information to a satisfaction degree model; satisfaction degree model being used to detect whether the decision information outputted from interactive decision model accords with the current user's preference. If so, it enters into long-term memory, updates the data, and outputs the obtained decision information to behavior selector to obtain robot behavior output. Otherwise, the recorded fragments and the corresponding emotional changes of the user are retrieved from the short-term memory, the user characteristics are extracted from the long-term memory, the decision information is calculated by using the LSTM depth learning model, and the obtained decision information is output to the behavior selector to obtain the robot behavior output. The invention improves the cognitive ability of the robot and better performs human-computer interaction through an interactive decision model.

The invention discloses a vehicle-mounted personalized audio and video content pushing method and device. The pushing method comprises an emotion recognition stage, a traffic jam recognition stage andpersonalized content pushing, and the personalized content pushing is started when an abnormal emotion is recognized based on the emotion recognition stage or traffic jam is recognized based on the traffic jam recognition stage. The pushing device comprises a core processing module, and an external power supply, an in-vehicle camera, an out-vehicle camera, a Bluetooth BT, a communication module,a multi-channel sound pickup, an audio output module and an FM emission module which are electrically connected with the core processing module. The emotion of the driver can be recognized in the driving process. According to the emotional change of the driver, interaction with the driver is carried out. Abnormal emotions such as fatigue, anger, depression and hyperactivity of the driver are relieved, the driving attention of the driver is improved, interaction with the driver is oriented according to different emotions of the driver, accurate content is pushed to the driver, and driving safety and driving fun are improved.

The invention discloses a convolutional neural network-based wireless rechargeable smart watch capable of detecting emotional changes. The smart watch is composed of two major parts, namely, a spectacles frame and a watch body; the spectacles frame is internally provided with a coil antenna, a power source module, a physiological parameter sensing type sensor, a signal processing part and a wireless communication module; the smart watch body is internally provided with a power source module, an MCU module, an ADC module, a wireless communication module, a Bluetooth module and an audio output module; the exterior of the smart watch body is connected with a watch chain through an embedded coil antenna which can capture the energy of a surrounding magnetic field to realize wireless charging;a resistive touch screen is adopted as a watch screen; the touch sensitivity of the resistive touch screen is weak, and can be touched by any item such as nails and styluses without being easily broken; a spectrogram is drawn through the signal processing part; and the spectrogram is transmitted to an intelligent terminal through using the wireless communication module; analog signals are converted into digital signals through the ADC module; the digital signals are transmitted to the MCU module for real-time data processing; and finally a speech prompt is outputted through the audio output module.

The invention relates to a method, a device and a system for feeding back a network teaching effect based on a galvanic skin response signal. The system comprises a first terminal, a network server and a second terminal, wherein the first terminal is used for acquiring the galvanic skin response signal, and sending out the acquired galvanic skin response signal through network connection; the network server is used for receiving the galvanic skin response signal through network connection, and judging an emotional state of an object generating the galvanic skin response signal, and sending out the emotional state through network connection; and the second terminal is used for receiving the emotional state through network connection, and adjusting a teaching method according to the emotional state. Thus, the method, the device and the system for feeding back the network teaching effect based on the galvanic skin response signal can monitor emotional changes of a student through the galvanic skin response signal so as to adjusting the network teaching method according to the emotional change, and have high accuracy and good user experience.

The invention provides a visual method for the dynamic view evolution of a social media event. The method comprises the following steps: the emotional membership degree and emotional classification of information in the collection of collected social media event information is determined firstly; then the geometrical layout of an emotional visual graph is built based on the emotional classification of the information, and the built geometrical layout is colored based on the emotional membership degree of the information. The method can intuitively display the emotional change of the event in an information stream, can display more emotional information in the aspects of the change and development of the invent, can help a user recognize the turning point and the bursting point of the event better, and predicts the development trend of the event.

The invention provides an emotion community classification method oriented to microblogging, which relates to the technical field of emotion analysis. The method includes: establishing naive Bayesianclassification algorithm SL based on emotion dictionary and emotion expression; SE-NB; users who build LPA-based topic models-Super topic-Sub topic- Keywords UTK; topics are classified into three emotional communities: positive, negative and neutral. The invention provides an emotional community classification method based on micro-blog, this method can not only find the affective community with high modularity, moreover, the running time is within the acceptable range. This method can not only monitor the public opinion of micro-blog users for the relevant departments, but also help businesses to reduce business losses, and can also provide psychological research institutions with the results of emotional change analysis of people on sensitive topics.

Based on a BP neural network and a GAN network, the invention provides a method for enabling computer voice to generate corresponding emotional changes according to emotional changes of users. A BP neural network is trained in two processes of information forward propagation and error back propagation. According to the voice service system based on the adversarial artificial intelligence network,the type of the voice emotional state input by the user is accurately output. The corresponding emotional voice is output through the generative adversarial process of the GAN network with the emotional state type as the reference. The voice service system based on the adversarial artificial intelligence network is designed through the method.

The invention is suitable for the technical field of electronics, and provides an intelligent interaction system. The system comprises a client and a background server, wherein the client is used foranalyzing emotional states and health states of users according to data input by the users, carrying out man-machine interaction with the users by adoption of corresponding multimedia combination manners according to the emotional states, and feeding back corresponding medical advices to the users through man-machine interaction according to the health states; and the background server is used foranalyzing and processing user demands obtained by the client through man-machine interaction. Through the intelligent interaction system, man-machine is carried out by adoption of the corresponding multimedia combination manners according to the emotional states of the users, so that mechanization of man-machine interaction is avoided, the man-machine interaction process is diversified in function and the intelligent experience of the users is improved; and meanwhile, the health states of the users are analyzed by combining emotional changes of the users, and the corresponding medical advicesare fed back to the users through multimedia man-machine interaction according to the health states of the users, so that the intelligent level of medical detection and analysis is improved.

This invention discloses a method and system for recognizing facial expression changes based on vision of intelligent robot. The intelligent robot is provided with a robot operation system. The robot operation system receives a facial expression change node command acquired by a first application, calls a visual module cycle according to the command to acquire image information and record facial expression information in the image information, judges whether the facial expression is changed or not according to the recorded facial expression information, and feeds back node information when a node of the facial expression change is recognized. The method can recognize the emotional changes of a user in time, so as to achieve self-snapshot better and improve the interactive experience of the user.

The present invention discloses an emotion analyzing method integrating eye movement technology and heart rate detection technology, which comprises the following steps: step 1: initially screening out the heart rate indexes and the eye movement indexes; step 2: recording the related heart rate data and eye movement index data during the experiencing of a product by the user and filling in a PAD emotional questionnaire; step 3: performing homogeneity-of-variance detection to all of the initially screened heart data and eye movement index data and screening them; step 4: using a one-way ANOVA method to analyze the heart rate data and the eye movement index data to select and obtain the best data index related to the emotional change; step 5: using the partial least-squares regression analysis method o establish a corresponding mathematic relationship model for the obtained best heart rate and the eye movement index and the PAD emotional value; and based on the PAD emotional value, determining the emotional state of the user. The present invention integrates two different emotion measurements, which can complement each other in the process of emotion recognition and can effectively recognize different affective states.

The invention discloses a multi-information based emotion recognition method and device. The method includes: acquiring human body action signals and physiological signals, and extracting multiple feature data according to the action signals and physiological signals; acquiring multiple feature weights in one-to-one correspondence to the multiple feature data, and retaining the feature data with the feature weights within a preset weight range; and recognizing the retained feature data with a trained decision tree classifier, thus obtaining corresponding emotional signals. Compared with the prior art, the method and device provided by the invention judge and classify the emotions of population with emotional uncontrollability through multi-information and multi-dimension, overcome the problem of single information representing emotional changes, and then improve the accuracy of emotional recognition.

A psychological consultation robot includes an artificial ear (1) containing a recording device, an artificial skin (2), an artificial eye (3) having a photographic function, a brain psychological consultation system (4), an artificial mouth (5) capable of speaking a human language and a button (6). When the psychological counseling robot communicates with a user, the user's facial expression is collected through the eyes (3), the biomimetic skin (2) collects the body temperature of the user at any time, the ear (1) acquires the language of the user, the collected information is transmitted tothe brain psychological consultation system (4) for comparison and analysis to thereby obtain the appropriate scheme, and then is talked out by the mouth (5). The invention utilizes two technologiesof temperature collection and facial expression recognition to observe the emotional change of a person, the result is more accurate, and by the psychological consultation network system, the judgmenterror is not caused by the subjective factor of the person according to the rationality.

The invention relates to a consultation recommendation method and a management system thereof. The method comprises the steps that voice of a customer is acquired through a voice acquisition module when a commodity service is recommended to the customer; the volume, speed and tone of the voice are analyzed in real time according to the voice of the customer, and the real-time emotional state of the customer is determined according to volume information, speed information and tone information; the interest degree of the customer is analyzed according to the real-time emotional state of the customer; customer service staff make further recommendation according to the recommendation content which the customer is interested in. The system comprises an acquisition module, a voice analysis module and a emotion analysis module, wherein the acquisition module is used for acquiring the voice emitted by the customer when consulting the customer service staff; the voice analysis module is used for analyzing the volume, speed and tone of the voice of the customer, determining the changing range of the voice of the customer, and detecting whether the voice of the customer exceeds the designatedarea or not; and the emotion analysis module is used for determining the emotional change of the customer and understanding the recommendation content which the customer is interested in. The customer service staff can understand the emotional state of the customer in real time in providing the consulting service and indirectly improving the consumption desire of the customers.

The invention aims to provide a method and device for evaluating to-be-tested application. An evaluating device generates evaluating information for the to-be-tested application by obtaining user emotion information capable of indicating users' continuous emotional changes for the to-be-tested application. Compared with the prior art, the novel evaluation method is provided. The users' experience and feeling to the to-be-tested application are displayed from a user interaction angle, so that the evaluation is diversified and personalized, the information content obtained by the users is increased, the users' efficiency in obtaining information is improved, and the user experience is improved.

The invention discloses a method for assisting teleoperation based on visual stimulation of brainwaves. During teleoperation, the emotions of an operator are continuously affected by external factors. The method aims to sense emotional changes of the operator in a real time manner, reduce the effects of human factors on a master terminal, and improve the teleoperation stability. The method provided by the invention has the advantages that the operation difficulty and fatigue degree of the teleoperation operator in the prior art are reduced, so that the operation stability of the master terminal during the teleoperation is improved; the emotional changes of the operator can be sensed in a real time manner, and brainwave signals of the operator are added into a teleoperation circuit, so that the entire teleoperation circuit can promptly formulate a corresponding strategy, which is a brand new method in the teleoperation field.

The invention provides a context-based emotional dialogue method and system and a storage medium, and relates to the technical field of emotional dialogues. According to the embodiment of the invention, the method comprises the steps: firstly obtaining a dialogue context data set, extracting a theme category and an emotion category in the dialogue context data set, obtaining a theme keyword probability and an emotion keyword probability, predicting theme keywords and emotion keywords in replies, and generating preliminary replies according to the predicted theme keywords and emotion keywords;and then obtaining a weight value of the preliminary reply, and obtaining a final reply according to the preliminary reply and the weight. Therefore, according to the embodiment of the invention, thedialogue context is fully utilized, the reply generated by the machine is closer to the theme, the emotional change of the context is better judged, and the extension of the dialogue theme is mastered.

The invention relates to a method of applying music to oviposition and insemination of four major Chinese carps and belongs to the technical field of fish propagation. In the artificial propagation of the four major Chinese carps, under the condition that parent fishes generate resistance to exogenous hormone drugs year by year, the music is introduced to induce estrus and spawning. In the invention, the music which is suitable for the estrus induction of fishes is selected and edited to corresponding segments and is correspondingly played according to emotional changes of the fishes from estrus beginning to spawning, ejaculation and insemination end phases to ensure that the fishes can naturally mate, spawn and inseminate under the synergistic action of the music and the hormone. Therefore, the problems that in the traditional artificial propagation of the four major Chinese carps, the fishes generate drug resistance because only the hormone drugs are injected to induce estrus and spawning, the estrus of the fish body is insufficient, and the parent fishes are wounded and the death rate is high because of forcibly extruding sperm and ovum artificially can be solved; and the method has the advantages of increasing the spontaneous labor rate of the parent fishes, reducing the death rate of the parent fishes and increasing the propagation efficiency of the fishes.

The invention discloses a personality evaluation method and system based on emotional states and emotional changes, and the method comprises the steps: collecting a video of a testee during the current speech or report; preprocessing the video to obtain preprocessed video data, voice data and semantic data; calling trained emotion recognition model E-R-Model to test the preprocessed video data, voice data and semantic data to obtain an emotion type of the testee and a distribution result along time; calling personality recognition model P-R-Model to analyze the emotion type of the testee and the distribution result along the time to obtain a personality result of the testee. In the embodiment of the invention, the personality type of the testee is evaluated according to the emotional stateand the emotional change of the testee in the speech or report process, so that the test time can be saved, and the test objectivity is improved.

The invention discloses nutrition agent including superoxide dismutase. The invention is mainly composed of camellia chrysantha, spirulina and superoxide dismutase which all having the functions of regulating the sub-healthy state of human body, supplementing nutrient and anti-aging, but the effect is not clear, and the function is not strong when being used alone. The invention has scientific and rational ratio and preparation, in order to realize the synergistic value increment function among the materials, and thereby the bioavailability is further improved, and the specific effect is realized. The actual application confirms that the invention can enable the elderly to generally look rosy and the age spot to fade out, stabilize the blood pressure, improve the sleep, normalize the stool, improve the appetite and eliminate the fatigue. The stain and the chloasma of the middle-aged women can be mottled, the wrinkles fade out and are fined, the skin elasticity is enhanced, the fatigue is eliminated, the disease-resistant capacity is strengthened, and the emotional change state is improved. And thereby, the invention has good health caring function, and is a better nutriment to improve the sub-healthy state of human body.

The invention provides a warning method for shared car passengers, which can effectively prevent drivers from injuring the passengers and greatly improve the safety of the passengers. The method comprises the following processes: determining whether a driver, an order APP, and a car are consistent and in a same area, if so, receiving the order by the order APP; monitoring the physical signs of thedriver by a physical sign monitoring device after the order is received, and sending the physiological data obtained by the physical sign monitoring device to a processing unit continuously or periodically, determining the physical or emotional changes of the driver based on at least the physiological data by the processing unit; and reminding the passengers by a client APP or issuing an alarm signal by a server or both when the physical or emotional changes of the driver reach a dangerous level, or reminding the passengers by the client APP or issuing the alarm signal by the server or bothif the order APP is closed or uninstalled after the order is received.