144 results about "Emotion detection" patented technology

The subject matter discloses a computerized method for real time emotion detection in audio interactions comprising: receiving at a computer server a portion of an audio interaction between a customer and an organization representative, the portion of the audio interaction comprises a speech signal; extracting feature vectors from the speech signal; obtaining a statistical model; producing adapted statistical data by adapting the statistical model according to the speech signal using the feature vectors extracted from the speech signal; obtaining an emotion classification model; and producing an emotion score based on the adapted statistical data and the emotion classification model, said emotion score represents the probability that the speaker that produced the speech signal is in an emotional state.

A system for analyzing a sentence emotion is provided. The system comprises a case repository, an input module, a sentence structure analyzing module, a similarity analyzing module and an emotion detection module. The case repository stores several case sentences and each case sentence comprises at least one major term and is corresponding to at least one emotion annotation. The input module receives an input sentence and the sentence structure analyzing module analyzes a sentence structure of the input sentence. The similarity analyzing module performs a semantic analysis and a syntax analysis according to the sentence structure to obtain a similarity level between the input sentence and each of the case sentences. The emotion detection module detects at least one emotion of the input sentence according to the similarity level between the input sentence and each of the case sentences.

A method and apparatus for controlling a vehicle are disclosed in embodiment of that present application. A method for controlling a vehicle includes acquiring face perception information, wherein theface perception information comprises at least one of face emotion detection information, face recognition information, face living detection information and face attribute detection information; thevehicle setting parameters include at least one of a control parameter of a vehicle hardware, a control parameter of an interior environment of the vehicle, and a vehicle intelligent service parameter. This embodiment adjusts the setting of the vehicle based on the face perception information, the intelligent adjustment of vehicle setting parameters can provide more targeted services to drivers and/or occupants, meet the needs of drivers and/or occupants in an all-round way, and improve the control efficiency of drivers and/or occupants in the vehicle use process.

The invention discloses a cross-inducing-mode emotion electroencephalogram recognition and modeling method which comprises the following steps: designing inducing tests with different stimulation modes; collecting and preprocessing electroencephalogram data; extracting emotion electroencephalogram characteristics from the preprocessed electroencephalogram data; taking a part of video and picture inducing samples as a training set and the other part of the samples as a test set, and performing classification and recognition on emotion electroencephalogram characteristics corresponding to the training set by a support vector machine classifier based on recursive characteristic screening, wherein samples in the training set and the test set are from different material sources. According to the method, emotion electroencephalogram samples of different inducing modes are all tested, thus better conforming to practical application scenarios; the objective and moderate emotion recognition method can provide technical support for emotion detection on on-orbit astronauts, or enables a computer in a man-machine interaction field to have capabilities of sensing, recognizing and understanding human emotions so as to make a sensitive and friendly response to the emotion of a user and build a really intelligent and humanized man-machine environment.

The invention relates to a crowd emotion anomaly detection and positioning method based on a deep neural network. Video data is obtained through a monitoring device. Video key frame data is extracted from the video data. Data of each face image is obtained from the video key frame data. Alignment, grouping and sorting preprocessing are carried out. The data is input into a trained face emotion identification model based on a convolutional neural network. Crowd emotion anomaly detection and positioning results in monitored video data is obtained and is fed back to a worker of the monitoring device through a trained crowd emotion detection and positioning model. The method is reasonable in design; a relationship between a crowd emotion anomaly and a crowd anomaly can be obtained through the model, the detection limitation problem resulting from associating the crowd anomaly with a specific anomaly event is avoided, and moreover, the model is a hybrid deep neural network structure model, so the video crowd emotion anomaly detection and positioning efficiency is further improved.

The invention relates to a sound-groove identification method based on emotion compensation. The emotion compensation includes three portions of emotion detection, character compensation and emotion expansion, comprising of calculating voice emotion factors to be according to the emotion detecting technique, compensating the voice change caused by emotion change respectively from the two layers of character and mode and finally improving robustness of the sound-groove identification technique to the emotion change. The invention has the advantages that the invention breaks through the inconsideration of sound-groove emotion change of the existing sound-groove identification technique, deals with the voice change caused by emotion change from the two layers of character and mode and strengthens resisting power to the voice emotion drift. The character layer standardizes the voice feature within the modeling ability of the training model by means of emotion degradation, normalization and barrier to reach the purpose of inhibiting the influence of the user emotion on the identification property. The mode layer obtains large scale emotion voices by employing the reverse way of synthesizing emotion voice by emotion changing rule, thereby greatly expanding the modeling information of the sound-groove model and resoling the difficulty of obtaining emotion data.

A system and method for emotion detection and more specifically to an image-capture based system and method for detecting invisible and genuine emotions felt by an individual. The system provides a remote and non-invasive approach by which to detect invisible emotion with a high confidence. The system enables monitoring of hemoglobin concentration changes by optical imaging and related detection systems.

The invention discloses an infant emotion detection method and device based on brain waves. According to the infant emotion detection method, brain wave signals are acquired at a plurality of positions of the brain of an infant; the acquired brain wave signals are processed, and a first energy ratio and a second energy ratio are calculated according to energy of the brain wave signals acquired at all the positions and energy of signals in preset frequency bands; the first energy ratio and the second energy ratio are matched in a prestored emotion sample library to obtain a final sample, so that corresponding infant emotion information is obtained. The infant emotion detection method and device based on brain waves realize real-time judgment of emotions of the infant through the brain waves, enable emotion judgment of the infant to be more accurate, and bring much convenience to a user.

The embodiment of the invention relates to the technical field of data processing, and particularly discloses a customer emotion detection method and device in telephone customer service and an electronic device. The method is applied to an application scene where a client performs voice communication with a telephone customer service, and comprises the following steps: acquiring voice informationof the client; extracting an audio feature vector in the voice information, and extracting a text feature vector corresponding to the voice information; and according to the audio feature vector andthe text feature vector, detecting the emotion of the client, and determining the emotion type of the client. Compared with a traditional emotion detection method, the emotion of the client is predicted in a multi-mode processing mode of combining the audio feature vector and the text feature vector, different mode information has complementary characteristics, and therefore the detection result of the emotion type of the client can be more accurate.

Techniques are presented for providing misinformation detection in online content. The described techniques can identify instances of misinformation in online content and pass a misinformation result to the user. A misinformation probability analysis can be performed by applying a syntactic analysis and a semantic analysis to detect misinformation with confidence by applying featurization to a URL, text of content referenced by the URL, and metadata associated with the URL using a feature set, the feature set comprising semantic-based features and syntactic-based features, wherein the semantic features and the syntactic features are selected from the group consisting of: sentiment amplifiers, sentiment continuity disruption features, lexical features, keywords, baseline features, speech act, sensicon features, emotion detection on the obtained text, exaggerated language, strong adjectives, heuristics, bag-of-words, objectivity, colloquial-ness score, and semantic difference.

The invention discloses a system for realizing emotion detection and service guidance based on an emotion detection technology, and a method thereof. The system comprises a telephone switching network and an access telephone switching network, various existing gateways and platforms for completing different functions, and an emotion detection and service guidance platform which is innovatively arranged for completing the emotion detection, counting and transmitting emotion detection reports in real time and/or periodically, transmitting an emotion regulation suggestion to a user according to emotion detection results and performing various operations favorable for emotion regulation such as requesting songs, sending multimedia messages or short messages, replacing polyphonic ringtone, replacing mobile phone wallpaper and ringing tones, presenting gifts and recommending WAP links. The service can improve the number of users and reduce the churn rate of the users, promote the development of the products such as wireless music, the short messages, the multimedia messages and the like; and the system can help service users to enrich amusement activities, timely find emotion changes of friends and assist the friends in regulating the emotion, and can help reduce the communication expenses.

The invention discloses an emotion detection method and system based on human skin resistance changes. The method includes parameter initialization, acquisition of human body resistance data, data analysis, and emotional state values feedback for a user. The analysis comprises preprocessing and threshold analysis, slope analysis, slope and duration combined analysis, and slope, duration and threshold combined analysis. The system comprises a medical pole piece, a bridge resistance / conductivity measurement circuit, an amplifying circuit, an A / D conversion circuit, a CPU and a man-machine interface. According to the method and system, a self-adaptive algorithm is adopted, emotions is reflected through the resistance, slope and state duration changes, the problem of individual differences can be overcome, and the excitability of testers can be reflected more accurately.

The invention provides a speech emotion detection method. The speech emotion detection method comprises the steps of obtaining speech data to be detected; performing framing on the speech data to be detected to obtain speech frames, extracting speech features of each speed frame to form a speech feature matrix, inputting the speech feature matrix into a trained emotion state probability detectionmodel, outputting an emotion state probability matrix corresponding to the speech date to be detected, inputting the emotion state probability matrix and the voice feature matrix into a trained emotion state transition model to obtain a corresponding emotion state sequence, wherein the trained emotion state transition model comprises a trained emotion state transition probability parameter, and determining the emotion state corresponding to the speech data to be detected according to the emotion state sequence. The method provided by the invention greatly improves the accuracy of speech emotion detection. In addition, the invention further provides a speech emotion detection device, computer equipment and a storage medium.

A system for detection of noncompliance including substance abuse, driving under influence, and untruthful testimony giving under law enforcement setting, comprising optical sensors for capturing a subject's pupillary responses, blinking eye movements, point-of-gaze, facial expression, and head pose during a compliance test session. The system can also be applied in neurocognitive disorder diagnosis. The subject's affective and cognitive states estimation based on the captured sensory data during a diagnosis test is feedback to the system to drive the course of the compliance or cognitive test, adaptively change the test materials, and influence the subject's affective and cognitive states. The estimated affective and cognitive states in turn provide a more accurate reading of the subject's condition.

The invention relates to an electrocardiograph and respiratory signal synchronous characteristic based emotion detection method. The method includes: acquiring ECG (electrocardiograph) signals and respiratory signals; preprocessing; extracting characteristics including 1) time domain synchronous characteristics, 2) frequency domain synchronous characteristics and 3) phase lock valves; assessing separability of each characteristic according to a Fisher discriminant ratio, calculating to finally obtain FDR (Fisher discriminant ratio) values of five characteristics, and distributing corresponding weight value wi to each characteristic according to the FDR values; adopting a SVM (support vector machine) for establishing an emotion recognition model to recognize a current emotion state of a user. The electrocardiograph and respiratory signal synchronous characteristic based emotion detection method has the advantage that accurate real-time emotion monitoring can be realized.

The invention discloses an intelligent robot negative emotion detection method and a system. The method comprises steps that face detection and tracking operation starts; after a face is detected, face expression emotion detection is carried out; after face expression emotion is determined to be negative emotion, recording starts, and sound emotion detection is further carried out; after sound emotion is determined to be negative emotion, the multi-modal output data is generated according to the negative emotion and is outputted. Through the method, interaction experience between a user and an intelligent robot can be improved, negative emotion of the user can be accurately identified through the intelligent robot, and interaction with the user can be realized according to the negative emotion.

The invention belongs to the technical field of artificial intelligence, and relates to a voice emotion detection method and device, a storage medium and electronic equipment. The method comprises thefollowing steps: acquiring initial voice data, and performing voice recognition processing on the initial voice data to obtain a voice recognition text; determining the voice duration of the initialvoice data, and determining the number of characters of the voice recognition text; determining a voice speed grade according to the number of the characters and the voice duration, and obtaining a tone grade and a mood grade of the initial voice data; and inputting the voice speed level, the intonation level and the mood level into a pre-trained machine learning model to obtain a voice emotion category. On one hand, the subjectivity of manual voice emotion labeling is avoided, voice emotion category labeling is more objective, the error frequency of emotion category labeling is reduced, and the emotion category labeling accuracy is improved; and on the other hand, online voice recognition is avoided, the speed of voice recognition is increased, and the efficiency of voice recognition andemotion category labeling is improved.

The invention provides a monitored wristband, monitoring wristband equipment and an abnormal emotion monitoring system and method. The monitored wristband collects real-time stress physiological parameters produced when a wristband wearer answers the question put forward by a questioner each time, an abnormal emotion evaluation machine judges whether the current emotion of the wristband wearer is abnormal according to the baseline state physiological parameters and the real-time stress physiological parameters, when it is monitored that the current emotion is abnormal, vibration prompt messages are sent to all monitoring wristbands, and all monitoring wristbands send corresponding vibration according to the vibration indication manners in the vibration prompt messages after receiving the vibration prompt messages. According to the technical scheme, an efficient abnormal emotion detection scheme is provided, vibration can be triggered when the abnormal emotion is detected, the abnormal emotion phenomenon can be reminded effectively, and the questioner can put up more effective follow-up questions.

The invention discloses smart emotion detection clothes based on the cloud computing technology and belongs to the technical field of wearable intelligent equipment. All existing medical systems are short of an effective emotion interaction mechanism, and consequently the traditional wearing technology cannot provide better medical services including physical and mental care in a satisfying mode. The smart clothes comprise a sensor, a data processing module, a storage module, a wireless communication module and an alarm module. The cloud computing technology is used for carrying out big data analysis and processing, so that the computing speed is substantially increased, and the purpose of monitoring emotion data in real time is achieved.

The invention discloses an emotion detection method and system based on map expressions. The method includes collecting text data with map expressions, preprocessing the collected data, and convertinginto a word vector data set; and inputting a data set generated by a data preprocessing unit into a trained network model, the network model outputting a corresponding emotion detection result. The emotion detection method based on map expressions can realize emotion detection of user comments and the like; further, a multiple neural network and an attention mechanism are combined, thereby improving the identification degree of map expressions related with various emotions; the model is trained through an iterator, thereby saving internal storage; and through transfer learning, parameters that can be trained are gradually unfrozen, the risk of over-fitting after transfer learning is reduced as much as possible, and the characteristics of a pre-training model are fully kept.

The invention is applicable to the technical field of machine learning and providesa text topic and emotion joint detection method and device. The method comprises the following steps of: computing an initial emotional tendency of each word in an input target text by using a preset emotion dictionary, setting word vectors of pre-acquired external corpora as initial values of word vectors of the target text, training the input target text by using a preset topic and emotion mixed model to obtain initial distribution between each emotion-topic pair and each word in the target text, scanning each document in the target text according to the initial emotional tendency of each word in the target text, the initial values of the word vectors and the initial distribution between each emotion-topic pair and each word, executing a preset topic and emotion detection step to each scanned training target word to obtain the topic and emotion involved in the target text. Thereby, the accuracy of the obtained topics and emotions of the target text is improved.

The embodiment of the invention provides a face emotion recognition method and device, a computer readable medium and electronic equipment, and relates to the technical field of computer vision of artificial intelligence. The human face emotion recognition method comprises the following steps: detecting a human face region contained in an image of a human face emotion to be recognized; recognizingan expression type of a human face according to the human face region, recognizing an action label of a target facial organ corresponding to the expression type, and recognizing an action label of the target facial organ corresponding to the expression type according to the expression type; and determining the face emotion in the image according to the expression type and the action label of thetarget facial organ. According to the technical scheme provided by the embodiment of the invention, the expression type in the face region is recognized, and the action label of the facial organ corresponding to the expression type is determined, so that comprehensive face emotion information is obtained by integrating the expression type and the action label, and the comprehensiveness and accuracy of face emotion detection are improved.