30 results about "Expressive communication ability" patented technology

The invention discloses an expression ability dimension evaluation method and device for intelligent interview, and the method comprises the steps: collecting an interview video, extracting a video frame and audio data, firstly inputting the video frame into a CNN-based hand detection model to obtain a bottom-layer hand posture feature, and inputting the audio data into an audio processing module based on natural language processing to obtain a bottom-layer voice expression feature; respectively inputting the two underlying features into two LSTM codes to form time sequence features; extracting abstract high-level semantic features, including hand expression, expression fluency, infectivity, orderliness and conciseness information, from the two low-level features through a priori knowledge rule; standardizing the time sequence features and the high-level semantic features and then inputtingthe standardized time sequence features and the standardized high-level semantic features into a full-connection neural network, and predicting the expression ability level. The system uses distributed function calculation service construction to form an expression ability evaluation system. According to the method, the efficiency problems of subjective deviation and time cost of expression ability scoring in interviews are solved, and rapid and accurate expression ability evaluation of a large number of interview videos is realized.

The invention discloses an emotional dialogue generation method and system based on interactive fusion. The method comprises the following steps: S100: receiving a dialogue statement text; S200, an emotion classifier identifying an emotion category contained in the dialogue statement text and representing the emotion category as a vector; S300, encoding the dialogue statement text into a context vector by an encoder; S400, a fine-grained interaction module fusing the emotion category representation vector and the context vector of the dialogue statement text to generate an interactive vector; S500, the decoder performing decoding by using the interactive vector to generate a reply; and S600, outputting a reply. The problems that an existing man-machine conversation system is weak in emotion perception ability and insufficient in emotion expression ability can be solved.

The invention provides a multi-modal analysis-based video interview evaluation method. The method comprises the following steps: receiving a short video of an interviewer applying to a specific post during interview; extracting audio data and video data in the short video; extracting the Mel-frequency cepstrum coefficient of the audio data as the input of the expression ability evaluation model based on voice analysis to obtain an expression ability evaluation score based on voice analysis; analyzing the video data to serve as input of an occupational matching model of the personal basic attributes, an image occupational degree evaluation model and a personality evaluation model of action analysis, and respectively obtaining an occupational matching degree score based on the personal basic attributes, an image occupational degree score and a personality evaluation score based on action analysis; and obtaining a comprehensive post matching degree score through summation and summation. According to the invention, rapid screening in massive video resumes can be realized, and the recruitment efficiency is improved.

The present invention provides a data processing method, device, device, and storage medium for evaluating test drive experience. The method includes: acquiring voice information in the car during the test drive, and seat information corresponding to the voice information, The seat information is used to characterize the seat of the person who generated the voice information; identifying the emotion in the voice information to obtain initial emotional evaluation data; according to the initial emotional evaluation data of each voice information and the seat information, determine The final emotional assessment data for this test drive experience. In the present invention, since the accuracy of the evaluation result is not affected by people's ability to remember and understand, and is not easily affected by the ability to express, the accuracy of the evaluation can be guaranteed to a certain extent. The present invention also fully considers the specific conditions of people in different seats, so as to more accurately reflect the overall experience effect when multiple people participate in the test drive.

The invention discloses a speech and language function impairment grade converter based on an ICF framework, which includes the following function evaluation indicators: auditory comprehension (%); visual comprehension (%); right brain function (%); Subdivided into word naming (%), simple paraphrase (%), word paraphrase (%), two-syllable word duration 2cvT (s), two-syllable word fundamental frequency 2cvF0 (Hz), sentence paraphrase (%), Sentence duration (s), sentence fundamental frequency (Hz), serial speech (%), oral description (%), and reading (%); writing (%); body language (%), enabling precise language function for patients assessment to facilitate subsequent treatment of the patient.

The invention discloses a method for extracting key frames of gesture images based on deep learning. First read the input gesture video, convert the input gesture video into a video frame image; use the Mobilenet-SSD target detection model to detect gestures in the video frame image, and segment the detected gestures; use VGG16 training model training The image is segmented by hand gestures to obtain the corresponding abstract features, and the spatial gradient is calculated. According to the gradient difference between two adjacent frames of pictures, an appropriate threshold is set to determine the key frame. The present invention proposes to use the Mobilenet-SSD target detection model to detect and segment the hand area, remove the noise in the background area, and use VGG-16 to accurately extract the abstract features of the hand, which not only greatly enhances the expressive ability of the picture, but also reduces the amount of parameters. The complexity of the model is reduced, which is suitable for this kind of video key frame extraction with small changes.

The invention discloses a compression method and platform of a pre-trained language model based on knowledge distillation. The method first designs a universal knowledge distillation strategy for feature transfer, and in the process of distilling the knowledge of the teacher model to the student model, the The feature map of each layer of the student model is close to the characteristics of the teacher, focusing on the expressive ability of small samples in the middle layer of the teacher model, and using these features to guide the student model; then using the self-attention distribution of the teacher model to detect the semantic and The syntactic ability builds a cross-knowledge distillation method based on self-attention; finally, in order to improve the learning quality of the learning model in the early stage of training and the generalization ability in the later stage of training, a linear migration strategy based on the Bernoulli probability distribution is designed and gradually completed from Knowledge transfer with teacher-to-student feature maps and self-attention distributions. Through the present invention, the multi-task-oriented pre-training language model is automatically compressed, and the compression efficiency of the language model is improved.

A spoken language evaluation method and device, comprising: obtaining a speech material to be evaluated and obtaining an evaluation dimension from a plurality of evaluation dimensions, and extracting evaluation features of the speech material to be evaluated according to the evaluation dimension; Score, get the spoken language evaluation value, and score the evaluation features according to the pre-stored oral language norm model, and get the public average level value for the speech material to be evaluated; output the evaluation result of the speech material to be evaluated according to the spoken language evaluation value and the public average level value . The spoken language evaluation method and device provided by the present invention use the seven dimensions of pronunciation and intonation ability, vocabulary use ability, grammar use ability, language logic ability, as well as the degree of theme concentration, the degree of expressiveness in a single sentence and the degree of completeness of expression to evaluate the learners' actual oral ability. Comprehensive evaluation and precise guidance provide comprehensive, practical and effective help for learners to improve their oral expression ability in various real situations.

The invention discloses a gait recognition system and method based on deep learning of a self-attention mechanism, belonging to the field of gait recognition. The present invention proposes to use the attention mechanism on the original feature map. By learning a matrix between 0 and 1 with the same size as the original feature, the original feature is denoised, and the salient features in the picture are selected to reduce the noise in the feature map. The noise of the classification loss and the comparison verification loss are organically combined to punish the features in combination with the loss function, which not only uses the identity information of the target, but also uses the different relationships between the targets to increase the discrimination between different features; The most important limb features in gait are added to the original depth features as prior knowledge. This combination can not only use the target global body shape features, but also correct the features that are not conducive to classification brought about by the clothes transformation learned by the global features, and enhance the original depth features. The expressive ability of deep features enhances the expressive ability of features from different dimensions.

The invention discloses an intelligent moral quality online interactive education system and method, and belongs to the technical field of education systems. According to the system, a video course is set, so that students complete course learning and establish a correct moral quality view; through a community law module, students analyze and express hot events from different angles, on one hand, the ability of the students to learn to use knowledge points learned from books is exercised, on the other hand, the oral expression ability and thinking logic of users are exercised, and the comprehensive ability of the users is improved; and through a character community module, students deeply experience different effects generated by executing decisions and better understand the content learned by video courses, intelligent operation is realized, the operating cost of the system is reduced, the students exercise their comprehensive quality and ability while playing and learning, audiences of moral quality education are expanded, and a cultural atmosphere of lifelong moral quality-oriented education is formed.

The invention provides an intelligent robot oriented multimodal emotion data interaction method. The method comprises a step of receiving and analyzing multimodal interactive input information so as to obtain an intention parameter and a user emotional parameter inputted by a user, a step of generating text reply information corresponding to the multimodal interactive input information with the combination with the intention parameter and the emotional parameter and generating a speech emotional parameter with the combination of the text reply information, context interaction data and the user emotional parameter, and a step of carrying out synthesis to obtain speech information according to the text reply information and the speech emotional parameter and outputting the speech information. Through the intelligent robot oriented multimodal emotion data interaction method of the embodiment of the invention, when an intelligent robot interacts with the user, the sound effects of outputted TTS speech are different in different emotional states, the emotional expression ability of the robot is improved greatly, and thus the intelligent degree of the robot is improved greatly.

The present application discloses a method for constructing natural language word segmentation. The method includes: obtaining Ngram word segmentation of natural language, and discontinuously combining the Ngram word segmentation according to the sequence of positions to obtain the combined word segmentation. It can be seen that on the basis of the original Ngram word segmentation, the obtained Ngram word segmentation is combined according to the order of the position sequence. Through this method, the expressive ability of natural language is increased, and the classification accuracy of natural language is improved. Moreover, in this solution, the window size is further set for the combined word segmentation, so as to avoid generating too many combined word segmentation feature quantities, and improve the classification speed of natural language. Correspondingly, the present invention also discloses a natural language word segmentation construction system, a natural language classification method and system, which also have the above beneficial effects.

The present invention provides a video human behavior recognition method based on salient trajectory space information, which redefines the salience of the trajectory in the video, effectively removes the background and the trajectory of the non-moving parts of the human body in the video, and leaves the foreground with significant motion. These trajectories have smaller error and stronger expressive ability; in addition, this method distinguishes the moving parts and interactive objects of different human body parts, and uses the spatial and semantic relationship between them through multi-core learning to improve The recognition effect of the algorithm.

The invention discloses an emotional dialogue generation method and system based on interactive fusion, comprising: S100: receiving dialogue sentence text; S200: an emotion classifier identifying the emotion category contained in the dialogue sentence text and expressing it as a vector; S300: an encoder Encode the dialogue sentence text into a context vector; S400: the fine-grained interaction module fuses the emotion category representation vector and the context vector of the dialogue sentence text to generate an interactive vector; S500: the decoder uses the interactive vector to decode and generate a reply; S600: output reply. The invention can solve the problems of weak emotion perception ability and insufficient emotion expression ability of the existing man-machine dialogue system.

The present application provides a method for generating POI copy, which belongs to the field of computer technology, and is used to solve the problems in the POI copy generation method in the prior art that the copy does not have a strong ability to express POI and the expression accuracy is not high. The method includes: acquiring POI information for generating copy; predicting the subject tendency of the POI information, and determining the subject heading of the POI information; generating the copy of the POI to which the POI information belongs according to the determined subject heading. The POI copy generation method disclosed in the present application first predicts the subject tendency of the POI information, obtains the subject words, and uses the subject words as the input text for generating the copy, narrows the data range of the input text for generating the copy, and makes the generated copy The input text is more targeted, which improves the accuracy and expressiveness of the generated copywriting.