21 results about "Emoticon" patented technology

This invention relates to the field of artificial intelligence processing, specifically to a method for generating non-functional interactive personalized random input, comprising the following steps: S1, basic data collection; S2, personalized random input generation; S3, output of generated content and reception of interactive feedback; S4, emotional feature fusion and extraction, obtaining surface emotional features and scene emotional features and performing emotional feature fusion; S5, lightweight emotional classification and multimodal response scheduling; S6, emotional response output, simultaneously outputting text, emoticons, and voice resources to the user; S7, quantitative analysis of user interaction willingness; S8, dynamic threshold iteration and adjustment of interaction intensity; S9, cross-stage data reuse and full-link reverse iteration, solving the problems of insufficient content generation adaptability, insufficient accuracy and real-time performance of emotional responses, and inefficient interaction links and adjustment mechanisms in traditional technologies in terms of underlying algorithms, model architecture, and technical mechanisms.

The invention discloses an interactive audience participation feedback method based on sentiment analysis and behavior prediction. User behavior data and text sentiment information are collected in real time through an audience terminal, behavior analysis and sentiment recognition are executed in parallel on a cloud server, and behavior tags and multi-level sentiment scores are generated; in combination with the historical portrait of the user, personalized interactive feedback content including an expression package, a knowledge point card, a microphone connection invitation or a voting entry is dynamically generated through a weighted scoring mechanism, and the pushing frequency is controlled to be not more than once every three minutes to avoid interference; meanwhile, when the individual continuously carries out negative feedback or the overall negative emotion ratio of the live broadcast room exceeds a threshold value, an instruction is automatically sent to the live broadcast stream pushing end, and real-time content adjustment is achieved. The method effectively solves the problems that traditional live broadcast interaction lags behind, is single in form and lacks emotional response, remarkably improves the audience immersion, participation and platform retention rate, and is suitable for various live broadcast scenes such as education, entertainment and e-commerce.

The application relates to an Internet community-based emoticon package identification method and device and a storage medium. The method comprises the following steps: acquiring an image in an Internet community, and using a pre-trained image classification model to classify the image to determine whether the image belongs to an emoticon package category; when the image does not belong to the emoticon package category, using an OCR model to acquire a text detection result in the image; determining whether the text detection result contains a keyword in a preset keyword library; when the text detection result contains the keyword, determining whether the text detection result meets a preset filtering condition; when the text detection result meets the preset filtering condition, determining that the image belongs to the emoticon package category, and adding the image to an emoticon package recommendation pool. Through the technical scheme, the accuracy of emoticon package identification is improved.

The invention discloses a virtual human generation method and a related device, and relates to the technical field of virtual humans, emoticons are adopted as bridges between text replies and emotions, emoticons with different intensities are expressed by different emoticons, and the emoticons have different emotion category labels relative to an existing emotion recognition model. Therefore, when the virtual human is generated, the emoticon is utilized to render the expression of the virtual human, the expression expression naturalness and the emotion expression accuracy of the generated virtual human can be guaranteed, the expression generation effect of the virtual human is improved, and then the interaction experience of the user and the interactive virtual human is improved.

This disclosure relates to a sentiment classification method and apparatus, belonging to the field of natural language processing technology. The method includes: extracting comment text data containing character text and emoticon text; inputting the comment text data into a preset language model to obtain a first feature vector of the character text and a second feature vector of the emoticon text; the preset language model being a language representation model pre-trained using unlabeled first sample comment text data and fine-tuned using labeled second sample comment text data; performing sentiment enhancement processing on the first feature vector according to a preset sentiment dictionary to obtain a third feature vector of the character text; and inputting a concatenated feature vector of the third and second feature vectors into a fully connected layer in the preset language model to obtain the sentiment classification result corresponding to the comment text data. This method reduces reliance on labeled data during sentiment classification and performs sentiment prediction from multiple feature dimensions, improving prediction accuracy.

Embodiments of this disclosure provide a method, system, electronic device, computer-readable medium, and computer program product for displaying emoticons in a conversation. The method includes: displaying a conversation interface, the conversation interface including a conversation display area and an emoticon display area, the emoticon display area displaying at least one emoticon image, the at least one emoticon image including a first emoticon image; causing the conversation display area to enter a point-and-draw state according to a first selection operation on the first emoticon image in the emoticon display area; and displaying the first emoticon image in the first selected area according to a first target operation on the first selected area in the conversation display area. The method, system, electronic device, computer-readable medium, and computer program product for displaying emoticons in a conversation provided by embodiments of this disclosure can achieve efficient user communication based on operations on emoticons.

1. The name of the design product: the main body of the expression input graphical user interface for electronic devices. 2. The use of the design product: an electronic device. 3. The design points of the design product: the part in the graphical user interface, the part outside the dotted line is the claimed part. 4. The picture or photo that best shows the design points: design 1 front view. 5. Design 1 is designated as the basic design. 6. The use of the graphical user interface: the overall interface is used for expression input and sending; the claimed part of the interface is used for expression assembly and switching. 7. The human-computer interaction mode of the graphical user interface: in design 1 front view, the user can click the "complete" control to enter the current expression combination into the input box, long press the rounded rectangle expression card control to expand the preview switching window of the corresponding expression library, click the "structure" control to switch the card structure, and click the "random" control to randomly switch the expression combination under the current card structure. The human-computer interaction modes of design 2 and design 3 are the same as those of design 1. In design 4 front view, the user can click the "complete" control to enter the current expression combination into an input box, long press the rounded rectangle expression card control to expand the preview switching window of the appropriate expression library, click the "structure" control to switch the card structure, click the "random" control to randomly switch the expression combination under the current card structure, and click the color disc control at the bottom of the interface to select the color combination to randomly generate the expression combination with the corresponding color. In design 5 front view, when the user clicks the "+ expression combination" control, it enters design 5 interface change state diagram 1; when the user clicks the "complete" control, it enters design 5 interface change state diagram 2. In design 6 front view, when the user clicks the "+ expression combination" control, it enters design 6 interface change state diagram 1; when the user clicks the "structure" control, it randomly switches the expression card structure and enters design 6 interface change state diagram 2. In design 7 front view, when the user clicks the "+ expression combination" control, it enters design 7 interface change state diagram 1; when the user clicks the "random" control, it randomly switches the expression combination and enters design 7 interface change state diagram 2. In design 8 front view, when the user clicks the "+ expression combination" control, it enters design 8 interface change state diagram 1; when the user long presses the leftmost expression card control, it enters design 8 interface change state diagram 2. In the design 9 main view, when the user clicks the "+ emotion combination" control, enter the design 9 interface change state diagram 1; when the user long-presses the middle expression card control, enter the design 9 interface change state diagram 2. In the design 10 main view, when the user clicks the expression combination control at the lower right of the "+ emotion combination" button twice, enter the design 10 interface change state diagram 1; when the user clicks the "send" control, enter the design 10 interface change state diagram 2.

The invention provides an expression package generation method and device based on a large model, electronic equipment, a readable storage medium and a computer program product, and relates to the field of artificial intelligence, in particular to the field of intelligent generation. According to the implementation scheme, first feature information of a user is determined based on a first conversation between the user and an intelligent agent, and the first feature information at least comprises intention description information about the user; acquiring second feature information of the intelligent agent, wherein the second feature information at least comprises role setting information about the intelligent agent; on the basis of the first feature information and the second feature information, a cue word corresponding to the first dialogue is determined by utilizing a predefined cue word template, and the cue word template at least comprises description information for guiding a large model to map the intention description information and the role setting information into an expression package; and determining an expression package corresponding to the first dialogue by using a large model based on the cue word.

The application discloses an expression package generation method, which comprises the following steps: obtaining a target picture and identifying the target picture; analyzing the identification result of the target picture; selecting a target expression according to the identification result; and generating an expression package based on the target expression. The application further discloses an expression package generation device, equipment and computer readable storage medium. The application combines the target expression with the target picture according to the target expression selected by a user and the target expression selected by the user by obtaining the target picture selected by the user, identifying the target picture, and generating an expression package according to the identification result of the target picture. The application realizes high expression package production efficiency, makes the generated expression package more diversified, and meets the customized needs of users.

The invention discloses a cognitive heuristic multi-modal reasoning method for Chinese harmful expression package detection. The method comprises the following steps of 1, obtaining a Chinese harmful data set; 2, scene-based narrative generation is carried out; 3, multi-granularity visual feature fusion is carried out; step 4, carrying out progressive multi-mode reasoning; and 5, performing model uncertainty weighted multi-loss framework training. According to the invention, by simulating a human cognitive mechanism, a multi-modal recognition framework integrating scene narration, multi-granularity visual perception and progressive reasoning is constructed, and accurate detection of Chinese harmful expression packages is realized.

1. Name of the product in this design: Graphical User Interface for Displaying an Expression Clock on an Electronic Device. 2. Purpose of this design: An electronic device. 3. The key design feature of this product is its graphical user interface. 4. The picture or photo that best illustrates the key design points: Design 1 front view. 5. Design 1 is designated as the basic design. 6. Purpose of the graphical user interface: To display a clock interface with emoticons. 7. Human-computer interaction method of graphical user interface: The main view of Design 1 to Design 5 is the emoticon interface. Clicking on the emoticon pattern in the top layer of the interface will switch to the change state diagram of Design 1 to Design 5 respectively, displaying a clock with the emoticon pattern in the top layer, and the color of the second hand is the same as the color scheme of the emoticon pattern.

1. Name of the product in this design: Graphical User Interface for Emoticon Bullet Screen on Electronic Devices. 2. Application of this design: This design is intended for use in electronic devices. 3. The key design features of this product are the graphical user interface portion of the electronic device for which protection is sought. 4. Images or photos that best illustrate the design points: Interface change state diagram 4. 5. For electronic devices, the rear view, left view, right view, top view, and bottom view are omitted due to conventional design. 6. Purpose of the graphical user interface: This product design is used for sending selfie emojis via bullet comments. 7. Human-computer interaction method of graphical user interface: Clicking the "Face Expression" icon in the lower left corner of the main view will enter the interface change state diagram 1. Clicking the "Shoot" icon in the interface change state diagram 1 will enter the interface change state diagram 2. After confirming that the expression is captured correctly in the interface change state diagram 2, clicking the "Done" button will enter the interface change state diagram 3. Clicking the "Send Expression" button in the interface change state diagram 3 will enter the interface change state diagram 4.

Systems and methods are described herein for inserting emoticons within a media asset based on an audio portion of the media asset. Each audio portion of a media asset is associated with a respective part of speech, and an emotion corresponding to the audio portion for the media asset is determined. A corresponding emoticon is identified based on the determined emotion in the audio portion and presented in the subtitles.

The present disclosure provides an expression package generation method, device, electronic equipment, storage medium and product. The method comprises: obtaining event content data of a current event and user portrait data of a user; generating an initial expression package set matched with the user and the current event based on the event content data and the user portrait data; identifying an emotion type and an emotion intensity of the user during watching of a live broadcast of the event; and adjusting display parameters of corresponding expression packages in the initial expression package set according to the emotion type and the emotion intensity, to generate a dynamic expression package adapted to a current emotion state. The expression package can dynamically change with real-time emotions of the user, accurately convey the emotion intensity and real reaction of the user in the current event, and thus meet the demand of the user for more accurate emotion expression.

The invention relates to the field of artificial intelligence processing, in particular to a non-functional interactive personalized random input generation method, which comprises the following steps of S1, acquiring basic data; s2, generating personalized random input; s3, generating content output and interaction feedback receiving; s4, emotion feature fusion extraction: obtaining surface emotion features and scene emotion features, and performing emotion feature fusion; s5, lightweight sentiment classification and multi-modal response scheduling are carried out; s6, outputting emotional response, and synchronously outputting three types of resources including texts, emoticons and voices to the user; s7, user interaction willingness quantitative analysis is carried out; s8, iteration and adjustment of the dynamic threshold value of the interaction intensity; and S9, performing cross-link data multiplexing and full-link reverse iteration. The problems of insufficient content generation adaptability, insufficient emotion response accuracy and real-time performance and low efficiency of an interactive link and an adjustment mechanism in the aspects of an underlying algorithm, a model architecture and a technical mechanism in the traditional technology are solved.

A computer-implemented method, system, and computer program product for emotion recognition. A deep convolutional neural network is trained to identify an emotion from images of facial expressions. Furthermore, an application in a computing device (e.g., mobile computing device, such as a smartphone) is utilized to capture an image of an individual (e.g., individual that is neurotypical, individual on the autism spectrum). The captured image of the individual is then analyzed using the trained deep convolutional neural network. The emotional state of the individual is then classified based on the analysis of the captured image of the individual using the trained deep convolutional neural network. The classified emotional state is then conveyed to a user (e.g., neurotypical individual, autistic individual) via an emoticon (emotional icon), such that the emoticon reflects the classified emotional state.

The application relates to the technical field of computer image processing, and discloses an expression animation display method and system, the method comprising the following steps: when expression animation is displayed, a control instruction sent by a central control host is acquired, the control instruction is analyzed, and analyzed control information is obtained; whether the expression animation is upgraded is determined according to the control information; when it is determined that the expression animation is not upgraded, whether the expression animation is switched is determined according to the control information; when it is determined that the expression animation is switched, an expression resource animation in a TTF font file format is acquired from a character set; font picture switching is performed according to the expression resource animation, and screen display is adapted. The expression animation is displayed in a vector font TTF display animation picture and a Bluetooth service analysis instruction control expression animation upgrade display mode, so that the smoothness of expression animation display and the dynamic adaptation capability can be ensured, and the real-time update requirement of expression animation resources in an MCU system can be met.

1. Name of the product in this design: Dynamic graphical user interface with emoticon thumbs-up for electronic devices. 2. Application of this design: This design is intended for use in an electronic device. 3. The key design features of this product are the graphical user interface content displayed in the electronic device. 4. Images or photos that best illustrate the design points: Interface change state diagram 3. 5. Purpose of the graphical user interface: This graphical user interface is used to display the animation after a user's "like" action. 6. Human-computer interaction method of graphical user interface: Click the "Like" function icon in the lower right corner of the message list area of ​​the main view, and the interface will jump to the interface change state diagram 1, interface change state diagram 2, interface change state diagram 3, interface change state diagram 4, interface change state diagram 5, interface change state diagram 6, interface change state diagram 7 and interface change state diagram 8 in sequence.

Embodiments of the present application provide a message processing method and device, computer equipment, storage medium and program product. The message processing method comprises: displaying a social interface, the social interface comprising a message editing area and a message display area; receiving message content input in the message editing area, the message content comprising a first emoticon icon; in response to a sending event of the message content in the message editing area, displaying a target social message in the message display area, the target social message comprising a second emoticon icon, the second emoticon icon being an emoticon icon obtained by replacing the first emoticon icon. The embodiments of the present application can enrich the use mode of the emoticon icon in the social scenario and improve the interest of the social scenario.

The application provides a large model-based multi-modal multi-granularity feature fusion emoticon emotion recognition method, which comprises the following steps: inputting a picture-text data pair into a CLIP model; constructing a similarity graph representing fine-grained picture-text consistency based on cosine similarity; screening partial image block features with the highest similarity to text features; fusing image global features and image block features corresponding to sequence indexes to obtain multi-granularity image feature representation; adjusting and freezing the CLIP model; obtaining a to-be-recognized emoticon and repeatedly performing image fusion processing via the current frozen CLIP model image encoder to obtain to-be-recognized fusion image features, which are embedded into a preset prompt template and input into an LLM model for fine-tuning and emotion category prediction; adjusting the LLM model and performing iteration until the LLM model meets preset requirements in emotion recognition. Through two-stage fine-tuning, the application realizes accurate recognition and classification of emoticon emotions.