111 results about "Emoji" patented technology

The present disclosure provides a semantic understanding based emoji input method and device, and relates to the input method technology field. The method includes: obtaining a text content according to an input sequence; performing word segmentation on the text content, and extracting text features based on the word segmentation result; constructing an input vector using the text features, performing classification using an emotion classification model to determine an emotion label of the text content; based on a correspondence relationship between the emotion label and emojis of various themes, respectively obtaining an emoji corresponding to the emotion label from each of the various themes; sorting the obtained emojis of the various themes, and displaying the sorted emojis as candidate options in a client. The disclosed invention facilitates users to input an emoji, enhances emoji input efficiency, and provides users with rich and wide scope of emoji resources.

The present disclosure generally relates to systems and processes for emoji word sense disambiguation. In one example process, a word sequence is received. A word-level feature representation is determined for each word of the word sequence and a global semantic representation for the word sequence is determined. For a first word of the word sequence, an attention coefficient is determined based on a congruence between the word-level feature representation of the first word and the global semantic representation for the word sequence. The word-level feature representation of the first word is adjusted based on the attention coefficient. An emoji likelihood is determined based on the adjusted word-level feature representation of the first word. In accordance with the emoji likelihood satisfying one or more criteria, an emoji character corresponding to the first word is presented for display.

Systems and methods of generating personified emoji include a digital image of a user. Facial features identified in the digital image are represented by facial data generated from the digital image. An emoji template is accessed and modified with the facial data to create a personified emoji which contains embedded information about the user's face, as represented in the digital image.

Providing interactive communication between a plurality of members includes providing a routing and redistribution module that communicatively connects each of the members with each of the other members and allows the members to receive at least real-time audio data from other ones of the members. Providing the interactive communication also includes receiving content from at least one of the members, selectively distributing the content to at least some of the members in real-time, selectively storing at least some of the content, and visually indicating temporal relationships between different types of the content to at least one of the members. The content includes text messages, images, documents, graphical emojis, stickers, animated gifs, audio emojis, recorded audio, recorded video, real-time audio, and/or real-time video. Distribution of the content to a particular one of the members varies according to a listening state of the particular one of the members.

A method and system are provided for assisting a user with Emoji in communication content. The method includes receiving, by a user interface, an input string that includes one or more Emoji characters for interpretation based on a user profile. The method further includes verifying and recovering, by a processor-based Emoji semantic verification and recovery system, an intended meaning of the one or more Emoji characters in the input string, by applying rules based on the user profile and natural language processing to analyze the input string for semantic context, interpret the one or more Emoji characters based on the semantic context, and replace at least one of the one or more Emoji characters with one or more other characters to form a modified input string.

Implementations of the present disclosure are directed to a method, a system, and an article for suggesting emoji for insertion into a communication having text or other content. A plurality of features corresponding to the communication are obtained and provided to a plurality of emoji detection modules. A set of emoji and first confidence scores are received from each emoji detection module andprovided to at least one classifier. A proposed set of candidate emoji and second confidence scores are received from the at least one classifier. A candidate emoji is inserted into the communication.

The invention discloses an emoji recommending method and system for a chat tool. When a user chats on a social software, the method and system monitor input text content by a user in real time; according to input text content length to judge whether or not the emoji is recommended, if emoji matching recommendation is carried out, the input text content is accurately matched with an emoji database,if the accurate matching is successful, a series of emojis are recommended for the user who can choose whether or not the recommended emojis replace the text content to be sent; if the accurate matching fails, fuzzy matching recommendation is carried out. The emoji recommending method and system for the chat tool can carry out multi-level matching, the emoji recommendation efficiency for the chattool is improved, referring to different users, the personalized emoji recommendation is provided and is more suitable, and it is convenient for the user to choose the emojis.

The invention provides a multi-modal emotion analysis method for an emoji package of a social platform, and the method comprises the following steps: S1, crawling an emoji package image from the social platform through a crawler tool, carrying out the emotion labeling of the emoji package image, and then carrying out the preprocessing; S2, obtaining semantic information of the emoji package images crawled in the step S1, and obtaining text information feature vector representation corresponding to each emoji package image; S3, obtaining visual features of the emoji package imageS crawled in the step S1, and obtaining visual feature vector representation corresponding to each emoji package image; S4, performing multi-modal fusion on the text information feature vector representation and the visual feature vector representation to obtain multi-modal fusion feature vector representation; and S5, enabling the multi-modal fusion feature vector to represent that an emotion recognition result is obtained through a classifier, selecting the emotion recognition result with the highest confidence coefficient as a predicted emotion, and introducing text semantic features of the image, so that implicit semantic information in the expression package can be better captured.

The embodiment of the invention provides a method and device for determining copywriting of an emoji package and electronic equipment. The method comprises the steps of obtaining a to-be-matched copywriting picture; determining feature information for indicating a category object in the to-be-matched document picture, wherein the indication category object comprises an object representing the content contained in the to-be-matched document picture; calculating the similarity between the feature information of the indicated category object in the to-be-matched document picture and the feature information of the indicated category object in each template expression package; selecting target feature information, wherein the target feature information is the feature information with the highest similarity with the feature information of the indication category object in the to-be-matched document picture; and acquiring characters in the template expression package corresponding to the target feature information, and taking the characters as the copywriting of the to-be-matched copywriting picture. Through the method and device for determining copywriting of an emoji package and the electronic equipment provided by the embodiment of the invention, the efficiency of determining the copywriting corresponding to the emoji package can be improved.

A method for generating a real-time context-based emoticon may include receiving conversation information associated with a conversation between a set of users. The method may include identifying an attribute associated with the conversation. The method may include generating a base emoticon. The method may include generating an output shape based on a fiducial point of the base emoticon. The method may include transforming the output shape of the base emoticon with an accessory. The method may include generating the real-time context-based emoticon for the conversation, based on transforming the output shape of the base emoticon with the accessory.

The invention provides a text emotion recognition method, a device, a storage medium and electronic equipment, and relates to the technical field of text emotion analysis. The text emotion recognitionmethod comprises the following steps of obtaining target data information for a specified event; wherein the target data information comprises text data and emoticons; respectively determining a wordvector of each target segmented word of the text data and an emoji vector of the emoji; and determining an emotion category to which the target data information belongs in combination with the word vector of each target segmented word and the emoji vector of the emoji. According to the method, text data and emotion features expressed by emoticons are comprehensively considered, so that the emotion analysis accuracy can be effectively improved.

The embodiment of the invention discloses an intelligent expression recommendation method and device based on user chat habits. The method comprises the steps of obtaining the dialogue content inputted by the user in social software; obtaining at least one expression package corresponding to the dialogue content according to a user expression package prediction model, wherein the user emoji package prediction model is established according to the chat habit of a user and comprises a corresponding relation between user chat corpora in a user chat corpus package library and emoji packages in anemoji package library; and recommending the at least one expression package to a user for the user to select and use.

The invention is suitable for the technical field of visual application. The invention provides an emoji package generation method. The method comprises the steps of obtaining at least one portrait image from a to-be-processed figure video, wherein the portrait image comprises a face image; calculating expression similarity between a face image in the portrait image and an expression package imagein a preset expression package image library, determining a target emoji package image and an emoji package material based on the emoji similarity, wherein the target emoji package image belongs to the emoji package image library, and the emoji package material belongs to the portrait image, extracting text information of the target emoji package image, and integrating the text information with the emoji package material to generate a target emoji package. The invention further provides an emoji package generation device and terminal equipment, and the emoji package generation efficiency andthe text information matching accuracy are improved.

The invention relates to a case microblog comment emotion classification method fusing emotion knowledge, and belongs to the technical field of natural language processing. According to the method, anemotion knowledge base containing a case microblog emotion dictionary, emoticons, network flow languages, a negative dictionary and a degree adverb dictionary is constructed; and constructing an attributive feature representation. Finally, semantic representation and attribute feature representation of comments are fused based on a convolutional neural network, an emotion classification model isconstructed, deep semantic features and serialized emotion knowledge features are extracted, and emotion classification is achieved. Experimental results based on case microblog comment corpora show that compared with a reference method INIT-CNN, the method has the advantage that two indexes of Macro _ F1 and Micro _ F1 are improved by 1.88% and 1.94% respectively.

The invention relates to an emoji-based cross-language emotion analysis method and device. The method includes: 1) creating a word vector based on a large number of untagged texts of a collected source language and a target language; 2) selecting a text containing emoji in an unlabeled text base on a word vector, and establishing an emoji prediction task through that text containing emoji, therebyobtaining a sentence representation model; 3) translate that source language corpus marked with affective polarity into the target language, obtain the document representation of the original text and the translated text by using the sentence representation model, and then training the affective classification model by use the document representation; 4) utilizing the trained emotion classification model to classify the new text of the target language to obtain the emotion polarity. The invention uses the emoji text which is easily climbed on the social platform to realize the cross-languageemotion analysis, and can alleviate the problems of scarce marker resources and unbalanced marker resources in different languages.

The invention discloses an emoji package processing method and a terminal. The emoji package processing method and the terminal solve a fact that the emoji package in the prior art has limitation. The emoji package processing method is applied to a social application system and comprises steps of obtaining first characteristic information of a first emoji package; obtaining second corresponding characteristic information of the first emoji package in a target application scene when the first characteristic information is not matched with the target application scene of the first emoji package, wherein the target application scene is a social application scene matched with the first emoji package; updating the first emoji package to a second emoji package according to the second characteristic information; and displaying the second emoji package on a terminal display interface.

The embodiment of the invention discloses an emoji package generation method, device and equipment and a medium, and relates to the field of image processing, in particular to the Internet technology.The specific implementation scheme is as follows: determining an associated text of an emoji and/or a similar emoji package of the emojis, wherein the associated text of the emojis comprises at leastone of main body information, scene information, emotion information, action information and connotation information; determining a target matching text from the associated text of the emoji and/or the associated text of the similar emoji package; and superposing the target matching text in an emoticon to generate a new emoticon package. The embodiment of the invention provides the emoji packagegeneration method and device, equipment and the medium, so as to realize automatic and accurate generation of the emoji package.

A face image de-identification apparatus and method are disclosed. The face image de-identification apparatus may include an emoji generator configured to generate a first emoji image including facial feature information corresponding to a face image using the face image stored in a database, and an image inserter configured to insert the first emoji image into the database by replacing the first emoji image with the face image.

The invention discloses a sensitive emoji package detection method and a device, and electronic equipment. The method and the device are high in robustness, accurate and efficient. The method comprises the steps of performing image-text separation processing on a to-be-tested expression package to obtain a to-be-tested text and a to-be-tested picture; constructing a periodically updated sensitiveword bank; performing matching detection on the to-be-detected text and the sensitive word bank, and determining a sensitivity value of the to-be-detected text according to a matching detection result; constructing a periodically updated training picture library, establishing an optimized support vector machine classification model according to the periodically updated training picture library, and classifying the to-be-tested pictures to obtain a picture classification result; and detecting and filtering the expression package to be detected. The device comprises an image-text separation module, a sensitive word bank module, a text sensitive value module, an image classification module and a detection filtering module. The electronic equipment includes a memory, a processor, and a computer program stored on the memory and operable on the processor to implement the sensitive emoji package detection method.

The invention relates to a multi-dimensional emotion intensity value calculation method fusing emoticons and short texts. The method comprises the following steps: (1) constructing an emoticon dictionary; (2) extracting emoji features, and calculating a multi-dimensional emotion intensity value; calculating a multi-dimensional emotion intensity value of the text and Emoji combined part; and calculating a multi-dimensional emotion intensity value of the network comment statement: for the emotion intensity of the social network comment statement, considering the multi-dimensional emotion intensity values of the two parts, and obtaining the multi-dimensional emotion intensity value of the statement by weighting the emotion intensity of the two parts.

Accordingly, systems and methods for purchasing, securing, and maintaining emoji sequences is presented herein. In one or more examples, an enterprise or user can generate or purchase an emoji sequence, which can include a sequence of emojis that can be used to uniquely identify an enterprise. Once the emoji sequence has been acquired, in one or more examples, the emoji sequence can have a digital token associated with it, wherein the digital token can be derived from the emoji sequence string, in a manner that is unique and deterministic.