Social interaction method, device and equipment and computer readable storage medium

Abstract

The invention discloses a social interaction method, device and equipment and a computer readable storage medium, and belongs to the technical field of Internet. The method comprises the steps of displaying a chat interface between a first object and at least one second object; in response to a triggering operation of a chat function, displaying at least one interaction text corresponding to a first character character according to the first character character of the first object facing the at least one second object; and in response to a trigger operation for a first interaction text in the at least one interaction text, sending the first interaction text to a terminal device corresponding to the at least one second object. According to the method, the social interaction efficiency is improved, the social interaction mode is more flexible, and the interestingness of social interaction is higher.

Description

Technical Field

[0001] The embodiments of the present application relate to the field of Internet technology, and in particular to a social interaction method, device, equipment and computer-readable storage medium. Background Art

[0002] With the rapid development of Internet technology, various social applications are emerging one after another. Users from all over the world can interact socially through social applications, providing users with opportunities for online social interaction.

[0003] In related social applications, users perform social interaction by inputting text content in a text input box and sending the input text content. This social interaction method is relatively simple and has poor flexibility, which makes the efficiency of social interaction low. Summary of the invention

[0004] The embodiments of the present application provide a social interaction method, device, equipment and computer-readable storage medium, which can be used to solve the problems in the related art. The technical solution is as follows:

[0005] On the one hand, an embodiment of the present application provides a social interaction method, the method comprising:

[0006] displaying a chat interface between the first object and at least one second object;

[0007] In response to a triggering operation of the chat function, displaying at least one interactive text corresponding to the first character personality according to the first character personality of the first object when facing the at least one second object;

[0008] In response to a triggering operation on a first interactive text among the at least one interactive text, the first interactive text is sent to a terminal device corresponding to the at least one second object.

[0009] On the other hand, an embodiment of the present application provides a social interaction device, the device comprising:

[0010] A display module, configured to display a chat interface between a first object and at least one second object;

[0011] The display module is further configured to, in response to a triggering operation of the chat function, display at least one interactive text corresponding to the first character personality according to the first character personality of the first object when facing the at least one second object;

[0012] A sending module is used to send the first interactive text to a terminal device corresponding to the at least one second object in response to a triggering operation on the first interactive text in the at least one interactive text.

[0013] In a possible implementation manner, the device further includes:

[0014] An acquisition module, configured to acquire a first virtual image of the first object in response to a triggering operation on a first interactive text in the at least one interactive text;

[0015] A generating module, configured to generate a first expression package according to the first virtual image and the first interactive text, wherein the first expression package corresponds to the first interactive text and includes the first virtual image;

[0016] The sending module is further used to send the first emoticon package to the terminal device corresponding to the at least one second object.

[0017] In a possible implementation, the display module is also used to display the first interactive text and the first emoticon package in the chat interface.

[0018] In a possible implementation, the acquisition module is used to display a character personality page, in which resources corresponding to the initial character personality of the first object are displayed; in response to a trigger operation of a picture upload function, a character picture of the first object is acquired; and based on the character picture of the first object and the resources corresponding to the initial character personality, a first virtual image of the first object is acquired.

[0019] In a possible implementation, the acquisition module is used to display a first personality test page, in which at least one first personality test question is displayed, and the first personality test question is used to test and obtain the initial character of the first object; based on the at least one first personality test question, a first test result page is displayed, in which the personality test result of the first object is displayed; in response to a triggering operation of a personality generation function, an initial character personality of the first object is generated; and according to the initial character personality of the first object, the character personality page is displayed.

[0020] In one possible implementation, the display module is used to obtain a first character of the first object in response to a triggering operation of a chat function; based on at least one interactive content displayed in the chat interface, determine a first interactive content in the at least one interactive content, the first interactive content being an interactive content whose corresponding interaction time in the at least one interactive content is before a first time and adjacent to the first time, the first time being the time when the chat function is triggered; generate at least one interactive text based on the first interactive content and the first character, the at least one interactive text being the reply content of the first object to the first interactive content; and display the at least one interactive text.

[0021] In one possible implementation, the display module is used to obtain a character of a third object and an object identity of the third object relative to the first object; obtain a first character of the first object based on the character of the third object and the object identity of the third object relative to the first object, where the third object is any second object among the at least one second object; or obtain a keyword; and obtain the first character of the first object based on the keyword.

[0022] In a possible implementation, the display module is used to obtain the character description content of the third object, determine the character of the third object according to the character description content of the third object, and the character description content of the third object is the description content of the character of the third object by the first object; or display a second personality test page, which displays at least one second personality test question, and generates the character of the third object based on the at least one second personality test question, and the second personality test question is used to test and obtain the character of the third object.

[0023] In one possible implementation, the display module is used to obtain a first character of the first object in response to a triggering operation of a chat function; based on the absence of interactive content in the chat interface, generate at least one interactive text according to a first time and the first character, the first time being the time when the chat function is triggered, and the at least one interactive text being the interactive text of the first object at the first time; and display the at least one interactive text.

[0024] In a possible implementation, a text input box is displayed in the chat interface;

[0025] The device also includes:

[0026] An acquisition module, used for acquiring the text content inputted in the text input box in response to a triggering operation of the text optimization function;

[0027] An optimization module, used for optimizing the text content input in the text input box to obtain at least one optimized text content;

[0028] The sending module is further used to send any optimized text content to a terminal device corresponding to the at least one second object in response to a trigger operation for any optimized text content.

[0029] In a possible implementation, the acquisition module is further configured to acquire a first virtual image of the first object in response to a trigger operation on any optimized text content;

[0030] The device also includes:

[0031] A generating module, configured to generate a second emoticon package according to the first virtual image and any of the optimized text contents, wherein the second emoticon package corresponds to any of the optimized text contents and includes the first virtual image;

[0032] The sending module is further used to send the second emoticon package to the terminal device corresponding to the at least one second object.

[0033] In a possible implementation, the display module is also used to display any optimized text content and the second emoticon package in the chat interface.

[0034] In a possible implementation, the sending module is also used to generate a third emoticon package based on the interactive content located at the reference position in the chat interface being the interactive content sent by the first object, in response to a triggering operation of a single-player comic generation function, according to the interactive content at the reference position and the first virtual image of the first object, and send the third emoticon package to a terminal device corresponding to the at least one second object, wherein the third emoticon package corresponds to the interactive content at the reference position, and the third emoticon package includes the first virtual image; based on the interactive content located at the reference position in the chat interface being not the interactive content sent by the first object, in response to a triggering operation of a single-player comic generation function, generate reply content for the interactive content at the reference position according to the interactive content at the reference position and the personality of the first character, generate a fourth emoticon package based on the reply content and the first virtual image, and send the fourth emoticon package to a terminal device corresponding to the at least one second object, wherein the fourth emoticon package corresponds to the reply content, and the fourth emoticon package includes the first virtual image.

[0035] In a possible implementation, the display module is further used to display the third emoticon package in the chat interface; and display the fourth emoticon package in the chat interface.

[0036] In a possible implementation manner, the device further includes:

[0037] A determination module, configured to determine, based on a plurality of interactive contents displayed in the chat interface, a second interactive content whose interaction time is within a target time period in response to a triggering operation of a multi-person comic generation function, from among the plurality of interactive contents, wherein the target time period is determined based on the triggering time of the multi-person comic generation function;

[0038] A generating module, configured to generate a fifth emoticon package according to the second interactive content, wherein the fifth emoticon package corresponds to the second interactive content and includes a virtual image of an object of each second interactive content;

[0039] The sending module is further used to send the fifth emoticon package to the terminal device of the at least one second object.

[0040] In a possible implementation, the generating module is used to obtain a virtual image of an object from which each second interactive content is emitted; and to generate the fifth emoticon package according to each second interactive content and the virtual image of the object from which each second interactive content is emitted.

[0041] In a possible implementation, a plurality of interactive contents are displayed in the chat interface, and the device further includes:

[0042] A generating module, configured to generate multimedia resources according to the reference interactive content in response to a triggering operation on the reference interactive content in the plurality of interactive contents, wherein the multimedia resources include the reference interactive content;

[0043] The sharing module is used to share the multimedia resources.

[0044] On the other hand, an embodiment of the present application provides a computer device, which includes a processor and a memory, wherein the memory stores at least one program code, and the at least one program code is loaded and executed by the processor to enable the computer device to implement any of the above-mentioned social interaction methods.

[0045] On the other hand, a computer-readable storage medium is provided, in which at least one program code is stored. The at least one program code is loaded and executed by a processor so that a computer implements any of the above-mentioned social interaction methods.

[0046] On the other hand, a computer program or a computer program product is also provided, wherein at least one computer instruction is stored in the computer program or the computer program product, and the at least one computer instruction is loaded and executed by a processor so that the computer implements any one of the above-mentioned social interaction methods.

[0047] The technical solution provided by the embodiments of the present application brings at least the following beneficial effects:

[0048] The technical solution provided by the embodiment of the present application is that in the chat interface between the first object and at least one second object, when the chat function is triggered, at least one interactive text corresponding to the first character personality is generated according to the first character personality of the first object when facing at least one second object, and any interactive text is selected in the at least one interactive text and sent to at least one second object. This method does not require the first object to manually enter the text content in the text input box and then send it, which can save time for social interaction and improve the efficiency of social interaction. Moreover, the first object can have different characters in different chat interfaces, that is, the first object can have different characters when facing different objects, so that the interactive texts in different chat interfaces can be different, which makes the social interaction more flexible and improves the fun of social interaction, thereby improving the interaction rate of social interaction and improving the user experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0050] Figure 1 It is a schematic diagram of an implementation environment of a social interaction method provided in an embodiment of the present application;

[0051] Figure 2 is a flow chart of a social interaction method provided by an embodiment of the present application;

[0052] Figure 3 This is a schematic diagram of the display of a home page of a social application provided in an embodiment of the present application;

[0053] Figure 4 It is a display schematic diagram of a chat interface provided in an embodiment of the present application;

[0054] Figure 5 It is a display schematic diagram of another chat interface provided in an embodiment of the present application;

[0055] Figure 6 This is a display schematic diagram of a personality analysis page provided by an embodiment of the present application;

[0056] Figure 7 is a display schematic diagram of a second personality test page provided in an embodiment of the present application;

[0057] Figure 8 is a display schematic diagram of a second test result page provided in an embodiment of the present application;

[0058] Fig. 9 It is a schematic diagram showing the personality of a candidate character provided in an embodiment of the present application;

[0059] Fig.10 is a flow chart of a model training process provided by an embodiment of the present application;

[0060] Fig.11 is a schematic diagram of displaying at least one interactive text provided by an embodiment of the present application;

[0061] Fig.12 is another schematic diagram of displaying at least one interactive text provided in an embodiment of the present application;

[0062] Fig.13 is a display schematic diagram of a first personality test page provided in an embodiment of the present application;

[0063] Fig.14 is a display schematic diagram of a first test result page provided in an embodiment of the present application;

[0064] Fig.15 This is a display diagram of a character personality page provided by an embodiment of the present application;

[0065] Fig.16 is a schematic diagram of displaying multiple candidate virtual images provided in an embodiment of the present application;

[0066] Fig.17 It is a schematic diagram of the use process of an emoticon package generation model provided in an embodiment of the present application;

[0067] Fig.18 It is a display schematic diagram of another chat interface provided in an embodiment of the present application;

[0068] Fig.19 It is a display schematic diagram of another chat interface provided in an embodiment of the present application;

[0069] Fig. 20 It is a display schematic diagram of another chat interface provided in an embodiment of the present application;

[0070] Fig.21 It is a display schematic diagram of another chat interface provided in an embodiment of the present application;

[0071] Fig. 22 It is a display schematic diagram of another chat interface provided in an embodiment of the present application;

[0072] Fig.23 is a schematic diagram of a multimedia resource sharing process provided by an embodiment of the present application;

[0073] Fig.24is a structural schematic diagram of a social interaction device provided in an embodiment of the present application;

[0074] Fig.25 It is a structural diagram of a terminal device provided in an embodiment of the present application;

[0075] Fig.26 It is a structural diagram of a server provided in an embodiment of the present application. DETAILED DESCRIPTION

[0076] In order to make the objectives, technical solutions and advantages of the present application clearer, the implementation methods of the present application will be further described in detail below with reference to the accompanying drawings.

[0077] It should be noted that the terms "first", "second", etc. in this application are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the terms used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present application. On the contrary, they are merely examples of devices and methods consistent with some aspects of the present application as detailed in the appended claims.

[0078] First, the abbreviations and key terms involved in the embodiments of the present application are defined.

[0079] Artificial Intelligence (AI) is the theory, method, technology and application system that uses digital computers or machines controlled by digital computers to simulate, extend and expand intelligence, perceive the environment, acquire knowledge and use knowledge to obtain the best results. In other words, artificial intelligence is a comprehensive technology in computer science that attempts to understand the essence of intelligence and produce a new intelligent machine that can respond in a similar way to human intelligence. Artificial intelligence is to study the design principles and implementation methods of various intelligent machines so that machines have the functions of perception, reasoning and decision-making.

[0080] Artificial intelligence technology is a comprehensive discipline that covers a wide range of fields, including both hardware-level and software-level technologies. Basic artificial intelligence technologies generally include sensors, dedicated artificial intelligence chips, cloud computing, distributed storage, big data processing technology, pre-trained model technology, operation / interaction systems, mechatronics, etc. Among them, pre-trained models are also called large models and basic models. After fine-tuning, they can be widely used in downstream tasks in various major directions of artificial intelligence. Artificial intelligence software technology mainly includes computer vision technology, speech processing technology, natural language processing technology, and machine learning / deep learning.

[0081] Pre-training model (PTM), also known as cornerstone model or big model, refers to a deep neural network (DNN) with large parameters. It is trained on massive unlabeled data, and uses the function approximation ability of large-parameter DNN to extract common features from the data. After fine tuning, parameter efficient fine tuning (PEFT), prompt-tuning and other technologies, it is suitable for downstream tasks. Therefore, the pre-training model can achieve ideal results in few-shot or zero-shot scenarios. PTM can be divided into language models (ELMO, BERT, GPT), visual models (swin-transformer, ViT, V-MOE), speech models (VALL-E), multimodal models (ViBERT, CLIP, Flamingo, Gato), etc. according to the data modality processed. Among them, the multimodal model refers to a model that establishes two or more data modality feature representations. The pre-training model is an important tool for outputting artificial intelligence generated content (AIGC), and can also be used as a general interface to connect multiple specific task models.

[0082] Deep learning: is a machine learning method in the field of artificial intelligence, which is based on artificial neural network models. Deep learning processes data in layers, from simple feature extraction to complex representation, and uses large amounts of data for training to achieve efficient learning and prediction. Deep learning has achieved remarkable results in many fields, such as computer vision, natural language processing, speech recognition, etc.

[0083] AI (Artificial Intelligence) model: A software system that uses artificial intelligence technology to learn from data and predict new data. It is usually based on mathematical methods such as linear regression, decision trees, support vector machines, neural networks, etc. AI models adapt to data characteristics through training (learning) and predict the output of unknown data through reasoning. AI models can be used in a variety of applications, such as image classification, speech recognition, natural language processing, predictive analysis, etc.

[0084] AI training: is a process of instructing AI models on how to learn from data, which usually includes steps 1 to 6.

[0085] Step 1: Prepare training data, such as images, speech, text, etc.

[0086] Step 2. Select a machine learning algorithm, such as neural network, support vector machine, etc.

[0087] Step 3: Configure the parameters of the AI ​​model, such as learning rate, number of hidden layers, etc.

[0088] Step 4: Run training to allow the AI ​​model to learn patterns in the training data.

[0089] Step 5: Evaluate model performance and verify whether the model can accurately predict through test data.

[0090] Step 6: Adjust parameters and repeat training to improve model performance.

[0091] AI training is a cyclic process that continues until the model can predict data with satisfactory accuracy. The trained model can be used in practical applications and continue to improve its performance by learning on new data.

[0092] Model fine-tuning: It is a transfer learning technique that is used to make minor adjustments to a pre-trained neural network model (such as a deep learning model) to adapt it to a new task. The advantage of this method is that it can leverage the knowledge learned by the pre-trained model on a large amount of data to achieve faster convergence and better performance on new tasks.

[0093] Specifically, model fine-tuning usually includes the following steps 1 to 4.

[0094] Step 1. Choose a pre-trained model: First, you need to choose a pre-trained neural network model that has been trained on a large amount of data (for example, an image classification model trained on the ImageNet dataset (a dataset) or a natural language processing model trained on a large text corpus).

[0095] Step 2: Modify the model structure: According to the requirements of the new task, modify the structure of the model to a certain extent. This usually includes removing the last layer (for example, the fully connected layer or the classification layer) and adding a new output layer to adapt to the number of categories or output requirements of the new task.

[0096] Step 3. Freeze some model layers: In order to retain the knowledge of the pre-trained model, some layers of the model (such as the previous convolutional layers or Transformer (a model that uses an attention mechanism to increase the speed of model training) layers) are usually frozen, which means that the weights of these layers will not change during fine-tuning.

[0097] Fine-tuning training: Train the modified model on the dataset of the new task. Since most of the layers of the model have been pre-trained, only the unfrozen layers need to be trained. This will make the model converge faster and achieve better performance on the new task.

[0098] Step 4, Evaluation and Adjustment: After fine-tuning training is completed, evaluate the performance of the model on the new task. If the performance is poor, you can try to adjust the fine-tuning strategy, for example, adjust the learning rate, change the number of frozen layers, or increase the number of training iterations.

[0099] In summary, model fine-tuning is a method of leveraging the knowledge of a pre-trained neural network model to solve new tasks. By making appropriate modifications to the model, freezing some layers, and training it on data from the new task, faster convergence and better performance can be achieved.

[0100] Transformer model: It is a neural network model with a self-attention mechanism, which has achieved great success in language translation systems. The principle is as follows: The Transformer model mainly consists of two parts: encoder and decoder. The encoder is used to convert sentences in the source language into a series of hidden representations, while the decoder converts these hidden representations into sentences in the target language.

[0101] Self-attention mechanism: It is the core of the Transformer model. In traditional recurrent neural networks, information can only flow in one direction, while the self-attention mechanism allows information to flow freely within the sentence, thereby better capturing the contextual information of the text. In the Transformer model, each input vector is mapped into three vectors: query vector, key vector, and value vector. For each query vector, its similarity with all other vectors is calculated, and the value vector is weighted averaged based on these similarities.

[0102] Multi-Head Attention: It is an extended form of the self-attention mechanism, which enables the model to learn multiple different representations to better express different aspects of the sentence. Specifically, the multi-head attention mechanism divides the input vector into multiple heads, performs self-attention on each head, and finally concatenates the results to form the final output.

[0103] Feedforward Neural Network: It is another important component of the Transformer model, which is used to perform further nonlinear transformations on the hidden representations obtained by the self-attention mechanism. Specifically, the feedforward neural network consists of two fully connected layers, and each layer is transformed by an activation function.

[0104] Through the above mechanism, the Transformer model can better capture the contextual information of the text and achieve very good results in tasks such as translation.

[0105] Image annotation: It is usually necessary to annotate objects, scenes, attributes, etc. in an image. Manual annotation is one of the most commonly used methods in image annotation. The manual annotation process includes: determining the annotation task, preparing annotation tools, training annotators, annotating images, and annotation quality control.

[0106] Among them, determining the labeling task refers to determining what types of labeling are required for the image, such as object classification, object detection, semantic segmentation, etc.

[0107] Preparing annotation tools means selecting annotation tools suitable for the task, such as drawing frames, drawing lines, coloring, etc. Commonly used image annotation tools include LabelImg (a visual image annotation tool), VGG Image Annotator (an image annotation tool), COCO Annotator (an image segmentation tool), etc.

[0108] Training annotators means that for tasks that require a large amount of labeling, annotators need to be professionally trained so that they understand the standards and processes of labeling.

[0109] Labeling images means that for each image, the labeler needs to label the label image according to the labeling task. For example, for object classification tasks, the labeler needs to label the category of the object in each image; for object detection tasks, the labeler needs to label the location and category of the object in each image; for semantic segmentation tasks, the labeler needs to fill different areas in each image with colors to label different semantic areas.

[0110] Labeling quality control means that after labeling is completed, the labeling results need to be quality controlled to ensure the accuracy and consistency of the labeling results. Common methods include cross-checking, data cleaning, labeling error correction, etc.

[0111] Semi-automatic annotation refers to improving the efficiency and accuracy of annotation by using some auxiliary tools or algorithms on the basis of manual annotation. The process of semi-automatic annotation includes: data preprocessing, initial annotation, and interactive annotation.

[0112] Among them, data preprocessing refers to the preprocessing of raw data, such as adjusting image size, color space conversion, etc., to improve the efficiency and accuracy of annotation.

[0113] Initial labeling refers to using the results of manual labeling to train an initial model or labeler to automatically label the original data.

[0114] Interactive annotation: Based on the initial annotation, the annotation results are manually modified and corrected using interactive annotation methods. Interactive annotation can be achieved through some tools and algorithms, such as region segmentation and semantic segmentation.

[0115] Annotation quality control refers to the quality control of annotation results to ensure the accuracy and consistency of annotation results.

[0116] Algorithmic large model: refers to a model with a large number of model parameters, usually between tens of millions and billions. The advantage of a large model is that the model has stronger expressiveness and generalization capabilities, and can handle more complex and abstract tasks, such as natural language understanding, image generation, etc. At the same time, large models usually have better precision and accuracy, and can achieve better results. However, the training and inference speed of large models is slower, requiring more computing resources and time, and the cost is higher.

[0117] Attention Mechanism: It is a model that simulates the human attention mechanism and can help the model better process sequence data.

[0118] In natural language processing, the attention mechanism can be used for tasks such as machine translation and text summarization. The core principle is to assign different attention weights to different parts of the input sequence so as to better focus on important information when outputting the sequence.

[0119] Specifically, the attention mechanism converts the similarity calculation between the input sequence and the output sequence into a set of attention weights to guide the generation of the output sequence. Generally speaking, the attention mechanism includes the following steps:

[0120] Calculate attention scores: Convert the similarity calculation between the input sequence and the current output state into a set of attention scores. For example, the attention scores can be calculated using dot product attention, bilinear attention, etc.

[0121] Calculate attention weights: For each input sequence position, calculate the corresponding attention weight based on the attention score. For example, use the softmax function (a mathematical function) to convert the attention score into a probability distribution to obtain the attention weight.

[0122] Calculate weighted input: sum the input sequence according to the attention weights to obtain a weighted input representation.

[0123] Output sequence generation: The weighted input representation and the current output state are jointly represented to generate the next output sequence.

[0124] By introducing the attention mechanism, the model can better focus on the important information in the input sequence and make dynamic adjustments when outputting the sequence, thereby improving the performance and expression of the model.

[0125] Avatar: An anthropomorphic image created through CG (Computer Graphics) technology, which is given a distinct character setting and runs on a computer device in the form of code and data. For example, virtual human, digital human, virtual digital human, etc.

[0126] Figure 1 is a schematic diagram of an implementation environment of a social interaction method provided in an embodiment of the present application, such as Figure 1 As shown, the implementation environment includes: a terminal device 101 and a server 102 .

[0127] Among them, a social client capable of social interaction is installed and running in the terminal device 101, and the terminal device 101 is used to execute the social interaction method provided in the embodiment of the present application.

[0128] The server 102 is used to provide background services for the social client capable of social interaction installed on the terminal device 101. In a possible implementation, the server 102 undertakes the main computing work, and the terminal device 101 undertakes the secondary computing work. Alternatively, the server 102 undertakes the secondary computing work, and the terminal device 101 undertakes the main computing work. Alternatively, the terminal device 101 and the server 102 use a distributed computing architecture for collaborative computing.

[0129] Optionally, the terminal device 101 may be any electronic device product that can perform human-computer interaction with a user through one or more methods such as a keyboard, a touchpad, a remote controller, voice interaction, or a handwriting device. For example, the terminal device 101 may be a smart phone, a tablet computer, a laptop computer, a desktop computer, a smart speaker, a smart watch, a PC (Personal Computer), a mobile phone, a PDA (Personal Digital Assistant), a wearable device, a PPC (Pocket PC), a smart car machine, a smart TV, etc.

[0130] The terminal device 101 may generally refer to one of a plurality of terminal devices, and this embodiment is only illustrated by taking the terminal device 101 as an example. Those skilled in the art may know that the number of the terminal devices 101 may be more or less. For example, the terminal device 101 may be only one, or the terminal devices 101 may be dozens or hundreds, or more. The embodiment of the present application does not limit the number and device type of the terminal devices 101.

[0131] The server 102 is a single server, or a server cluster consisting of multiple servers, or any one of a cloud computing platform and a virtualization center, which is not limited in the embodiments of the present application. The server 102 is directly or indirectly connected to the terminal device 101 via a wired or wireless communication method. The server 102 has a data receiving function, a data processing function, and a data sending function. Of course, the server 102 may also have other functions, which are not limited in the embodiments of the present application.

[0132] Those skilled in the art should understand that the above-mentioned terminal device 101 and server 102 are only for illustration, and other existing or future terminal devices or servers, if applicable to the present application, should also be included in the scope of protection of the present application and are included here by reference.

[0133] The present application embodiment provides a social interaction method, which can be applied to the above Figure 1 The implementation environment shown is Figure 2 As an example, the flowchart of a social interaction method provided in the embodiment of the present application is shown in FIG. Figure 1 The terminal device 101 in the embodiment is executed. Figure 2 As shown, the method includes the following steps 201 to 203.

[0134] In step 201, a chat interface between a first object and at least one second object is displayed.

[0135] In an exemplary embodiment of the present application, a social application for social interaction is installed and run in a terminal device. The social application may refer to an application that needs to be downloaded and installed, or may refer to an embedded program that relies on a host program to run, including but not limited to applets. The embodiment of the present application does not limit the type of social application. Based on the fact that the social application is an embedded program, an embedded program is an application that is developed based on a programming language and relies on a host program to run. An embedded program does not need to be downloaded and installed, it only needs to be dynamically loaded in the host program to run. Users can find the embedded program they need by searching, scanning, etc., and can run it by clicking it. After closing it after use, it will not occupy the memory of the terminal device, which is very convenient.

[0136] The display interface of the terminal device displays relevant information of the social application. The relevant information of the social application may be an icon of the social application, a name of the social application, or other information of the social application. The embodiment of the present application does not limit the relevant information of the social application.

[0137] The first object is an object using a terminal device. When the first object wants to run the social application, the first object selects the relevant information of the social application. The terminal device receives a trigger operation for the relevant information of the social application and displays the homepage of the social application. The homepage of the social application displays at least one dialog box, and any dialog box is a dialog box between the first object and other objects. Any dialog box can be a dialog box between the first object and one other object, or a dialog box between the first object and multiple other objects, which is not limited in the embodiments of the present application.

[0138] Among them, the relevant information of the social application selected by the first object may be the relevant information of the social application clicked by the first object, or the relevant information of the social application selected by the first object by voice, or the relevant information of the social application selected by the first object by other means. The embodiment of the present application does not limit the method of selecting the relevant information of the social application.

[0139] like Figure 3 is a schematic diagram showing the display of a home page of a social application provided in an embodiment of the present application. Figure 3 The homepage of the social application shown in FIG. 1 shows six dialog boxes. The first dialog box is a dialog box between the first object and object A. The last message in the first dialog box is sent at 12:07 and the last message in the first dialog box is “xxxxxxxxx”. The contents of other dialog boxes are shown in FIG. Figure 3 As shown, no further description will be given here.

[0140] It should be noted that more or fewer dialog boxes may be displayed on the homepage of the social application, and the present application embodiment does not limit this. Optionally, the dialog box displayed in the display interface may be updated by sliding the display screen of the terminal device up and down.

[0141] In response to a trigger operation on any of the at least one dialog box, a chat interface is displayed, where the chat interface is a chat interface between a first object and at least one second object. Figure 3 The first dialog box in the list is displayed as the chat interface between the first object and object A; based on any selected dialog box Figure 3 In the fourth dialog box, the chat interface displayed is the chat interface between the first object and other objects included in group one except the first object.

[0142] If the first object has not chatted with the second object, there is no interactive content in the chat interface. Figure 4 is a display diagram of a chat interface provided by an embodiment of the present application. Figure 4There is no interactive content in the chat interface shown.

[0143] If the first object and the second object have chatted, there is interactive content in the chat interface. Figure 5 is a display diagram of another chat interface provided by an embodiment of the present application. Figure 5 There is interactive content 501 in the chat interface shown, and the interactive content 501 is not the interactive content sent by the first object.

[0144] In step 202, in response to a triggering operation of the chat function, at least one interactive text corresponding to the first character personality is displayed according to the first character personality of the first object when facing at least one second object.

[0145] In a possible implementation, a chat control is displayed in the chat interface, such as Figure 4 401 in the figure is a chat control. When the first object selects the chat control, the chat function is triggered. In response to the triggering operation of the chat function, at least one interactive text corresponding to the first character personality is displayed according to the first character personality of the first object when facing at least one second object. The first character personality is determined according to the character personality of any second object in at least one second object, or the first character personality is the character personality that the first object wants to have when facing at least one second object. The character personality of the first object is different in different chat interfaces, that is, the character personality of the first object is different when facing different objects.

[0146] At least one interactive text can be displayed on the chat interface or on a new page. The embodiment of the present application does not limit the display method of at least one interactive text.

[0147] Optionally, in response to a trigger operation of a chat function, according to the first character of the first object when facing at least one second object, a process of displaying at least one interactive text corresponding to the first character includes: in response to a trigger operation of the chat function, obtaining the first character of the first object; based on at least one interactive content displayed in the chat interface, determining a first interactive content in the at least one interactive content, the first interactive content being an interactive content whose corresponding interaction time in the at least one interactive content is before a first time and adjacent to the first time, the first time being the time when the chat function is triggered; generating at least one interactive text according to the first interactive content and the first character, the at least one interactive text being the reply content of the first object to the first interactive content; and displaying at least one interactive text.

[0148] Among them, in response to the triggering operation of the chat function, the methods of obtaining the first character personality of the first object include the following two.

[0149] Method 1: Obtain the character of the third object and the object identity of the third object relative to the first object; obtain the first character of the first object according to the character of the third object and the object identity of the third object relative to the first object.

[0150] The third object is any second object among the at least one second object. If there is only one second object, the third object is the second object; if there are multiple second objects, the third object is any second object.

[0151] Optionally, the method of obtaining the character of the third object includes the following two methods.

[0152] The first method is to obtain a character description of the third object, and determine the character of the third object according to the character description of the third object.

[0153] The character description content of the third object is the character description content of the third object by the first object. Optionally, a character analysis page of the other party is displayed, a description control is displayed in the character analysis page of the other party, a description box is displayed in response to a trigger operation on the description control, and based on the input operation of the first object in the description box, the content input by the first object in the description box is obtained, and the character description of the third object is obtained according to the content input by the first object in the description box.

[0154] Exemplarily, the content entered by the first object in the description box is used as the character description content of the third object. For another example, the content corresponding to the content entered by the first object in the description box is used as the character description content of the third object.

[0155] Optionally, the triggering operation for the description control may be a click operation on the description control, or may be triggering the description control by voice, or may be triggering the description control by other means, which is not limited in the embodiments of the present application.

[0156] like Figure 6 Schematic diagram of a display of a personality analysis page provided by an embodiment of the present application. Figure 6 In (1), a description control 601 is displayed. In response to a trigger operation on the description control, the description control is displayed. Figure 6 (2), Figure 6 In (2), a description box 602 is displayed. According to the content input by the first object in the description box 602, the character description content of the third object is obtained.

[0157] After the terminal device obtains the character description content of the third object, the character of the third object is determined according to the character description content of the third object. The embodiment of the present application does not limit the process of determining the character of the third object according to the character description content of the third object. Optionally, the process includes: the terminal device includes multiple candidate character personalities, and obtains the first feature vector corresponding to the character description content of the third object; obtains the second feature vector corresponding to each candidate character personality; determines the matching degree between the character description content of the third object and each candidate character personality according to each second feature vector and the first feature vector; and uses the candidate character personality that meets the matching requirements as the character of the third object. For example, the candidate character personality with the highest matching degree is used as the character of the third object.

[0158] Exemplarily, 16 candidate character personalities are stored in the terminal device, namely, logistician type character (ISTJ), guardian type character (ISFJ), advocate type character (INFJ), architect type character (INTJ), connoisseur type character (ISTP), explorer type character (ISFP), mediator type character (INFP), logician type character (INTP), entrepreneur type character (ESTP), performer type character (ESFP), campaigner type character (ENFP), debater type character (ENTP), general manager type character (ESTJ), archon type character (ESFJ), protagonist type character (ENFJ), commander type character (ENTJ).

[0159] The process of determining the degree of match between the character description content of the third object and each candidate character's personality based on each second eigenvector and the first eigenvector includes: for any candidate character's personality among a plurality of candidate character's personalities, taking the dot product between the second eigenvector and the first eigenvector corresponding to any candidate character's personality as the degree of match between the character description content of the third object and any candidate character's personality.

[0160] Exemplarily, if the character description content of the third object has the highest matching degree with the general manager type character, the character of the third object is determined to be the general manager type character.

[0161] The character of the third object is obtained by using the character description of the third object by the first object, so that the obtained character of the third object has a high degree of matching with the first object's impression of the third object.

[0162] The second method is to display a second personality test page, wherein the second personality test page displays at least one second personality test question; and generate the personality of the third object based on the at least one second personality test question.

[0163] The second personality test question is used to test the personality of the third subject. At least one second personality test question displayed in the second personality test page is a question that the first subject answers from the perspective of the third subject, standing in the position of the third subject.

[0164] Optionally, the other party's personality analysis page also displays a test control, such as Figure 6 603 is a test control. In response to the triggering operation on the test control, a second personality test page is displayed. The second personality test page displays at least one second personality test question. The at least one second personality test question can be an MBTI (Myers-Briggs Type Indicator, personality test) personality test question, or a test question in any scenario, which is not limited in the embodiment of the present application.

[0165] like Figure 7 It is a display schematic diagram of a second personality test page provided in an embodiment of the present application. Figure 7 The second personality test questions displayed in the second personality test page shown in (1) are test questions in any scenario; Figure 7 The second personality test questions displayed in the second personality test page shown in (2) are MBTI personality test questions.

[0166] Based on the fact that the second personality test question displayed on the second personality test page is an MBTI personality test question, the first subject is asked to answer from the perspective of the third subject, and the third subject's words, chat habits, and emoticon preferences are identified and deeply learned based on the answer content, and the character displayed by the third subject during social chats with the first subject is analyzed to obtain a more accurate character of the third subject.

[0167] Based on the second personality test questions displayed on the second personality test page as test questions in any scenario, the first subject is asked to answer from the perspective of the third subject, and the third subject's words, chat habits, and emoticon preferences in the scenario are identified and deeply learned based on the answer content to better restore the third subject's character, thereby obtaining a more accurate third subject's character.

[0168] It should be noted that any of the above methods can be selected to obtain the character of the third object, and the embodiment of the present application does not limit the method for obtaining the character of the third object.

[0169] Optionally, after the character of the third object is generated, a second test result page may be displayed, in which the character test result of the third object is displayed. Figure 8 is a display diagram of a second test result page provided in an embodiment of the present application. Figure 8 The personality test result of the third subject shown in the second test result page is: personality type is architect-type personality (INTJ), personality characteristics: extroversion-44%, intuition-58%, logic-67%, prospective-70%, determination-85%.

[0170] The second test result page shows a reanalysis control. Figure 8 801 is a re-analysis control. When the first subject is not satisfied with the personality test result of the third subject, that is, when the first subject believes that the personality of the third subject is not the personality of the third subject indicated by the personality test result, the first subject can re-test to obtain the personality of the third subject that satisfies the first subject.

[0171] After obtaining the character of the third object, the character of the third object is stored correspondingly to the object identifier of the third object. In this way, when the chat function is triggered in the chat interface next time, there is no need to perform the process of obtaining the character of the third object again, thereby saving time for social interaction and improving the efficiency of social interaction.

[0172] In a possible implementation, the process of obtaining the object identity of the third object relative to the first object includes: the other party's personality analysis page also displays multiple candidate identities, such as Figure 6 There are 12 candidate identities shown in Figure 6 As shown, no further description is given here. In response to a selection instruction for any candidate identity, any candidate identity is used as the object identity of the third object relative to the first object. Exemplarily, the object identity of the third object relative to the first object is a supervisor. The selection instruction for any candidate identity can be clicking on any candidate identity.

[0173] Optionally, the second test result page also displays a generation control, such as Figure 8 802 is a generation control. In response to a trigger operation on the generation control, multiple candidate character personalities are generated according to the character of the third object and the object identity of the third object relative to the first object, and the generated candidate character personalities are displayed. In response to a trigger operation on any candidate character personality, any candidate character personality is used as the first character personality of the first object.

[0174] like Fig. 9 is a schematic diagram showing the personality of a candidate character provided in an embodiment of the present application. Fig. 9There is a candidate character personality (INTJ) in the screen, and other candidate character personalities can be displayed by sliding the screen left or right. Fig. 9 It also displays descriptive information about the personality of various candidate characters, such as Fig. 9 The description of the candidate character INTJ is "The same courageous character as the boss, which can help you communicate more directly." When you swipe left or right to display other candidate character personalities, you can also display descriptions of other candidate character personalities.

[0175] In one possible implementation, Fig. 9 Confirmation controls are also displayed, such as Fig. 9 901 is a confirmation control. After the first subject slides the screen left and right to view the generated candidate character personality, in response to a trigger operation for any candidate character personality and a trigger operation for the confirmation control, any candidate character personality is used as the first character personality of the first subject. The trigger operation for the confirmation control can be a click operation for the confirmation control, or can be other operations for the confirmation control, which is not limited in the embodiment of the present application.

[0176] Method 2: Obtain keywords, and obtain the first character of the first object based on the keywords.

[0177] Optionally, a keyword input box may be displayed, and keywords may be acquired in response to content input by the first subject in the keyword input box; and the first character personality of the first subject may be acquired based on the keywords.

[0178] The content entered by the first subject in the keyword input box is used as the keyword. Alternatively, the content entered by the first subject in the keyword input box is simplified to obtain the keyword. For example, if the content entered by the first subject in the keyword input box is "capable and calm", the keyword is "capable and calm". For another example, if the content entered by the first subject in the keyword input box is "he is very serious and cautious in doing things", the content entered by the first subject in the keyword input box is simplified to obtain the keyword "serious and cautious".

[0179] The process of obtaining the first character personality of the first object according to the keyword includes: a plurality of candidate character personalities are stored in the terminal device, a third feature vector corresponding to the keyword is obtained, and a second feature vector corresponding to each candidate character personality is obtained; based on the third feature vector and the second feature vector corresponding to each candidate character personality, the degree of match between the keyword and each candidate character personality is determined, and the candidate character personality with the highest degree of match with the keyword is used as the first character personality of the first object.

[0180] For example, the keyword may be capable and calm, and the candidate character personality with the highest degree of match between the keyword is a logistician-type character personality, and the first character personality of the first object is a logistician-type character personality. Alternatively, if the keyword is introverted and casual, the candidate character personality with the highest degree of match between the keyword is a mediator-type character personality, and the first character personality of the first object is a mediator-type character personality. Alternatively, if the keyword is happy puppy, the candidate character personality with the highest degree of match between the keyword is a campaigner-type character personality, and the first character personality of the first object is a campaigner-type character personality.

[0181] It should be noted that any of the above methods can be selected to obtain the first character of the first object, and the embodiments of the present application are not limited to this. When the first object interacts socially with different objects, the character of the first object is different. For example, when the first object interacts socially with object A, the character of the first object is type A character, and when the first object interacts socially with object B, the character of the first object is type B character.

[0182] After obtaining the first character of the first object, the first character of the first object and the identifier corresponding to the chat interface are stored in correspondence. In this way, when the chat function is triggered in the chat interface next time, there is no need to perform the process of obtaining the first character of the first object in the chat interface again, thereby saving time for social interaction and improving the efficiency of social interaction.

[0183] After obtaining the first character of the first object, based on at least one interactive content displayed in the chat interface, the process of determining the first interactive content in the at least one interactive content includes: based on only one interactive content displayed in the chat interface, the interactive content is used as the first interactive content. Based on multiple interactive contents displayed in the chat interface, each interactive content corresponds to an interaction time, and the interactive content whose corresponding interaction time in the multiple interactive contents is before the first time and adjacent to the first time is used as the first interactive content.

[0184] The process of generating at least one interactive text according to the first interactive content and the first character personality includes: inputting the first interactive content and the first character personality into an interactive text generation model, and using the content output by the interactive text generation model as the interactive text.

[0185] Optionally, before inputting the first interactive content and the first character personality into the interactive text generation model, it is necessary to first obtain the interactive text generation model, and the acquisition process of the interactive text generation model includes the training process of the interactive text generation model and the parameter fine-tuning process of the interactive text generation model. The training process of the interactive text generation model includes the following steps: data collection, data preprocessing, model selection, parameter initialization, model training, model tuning and model evaluation.

[0186] Data collection is used to collect text data. Text data includes but is not limited to news text, book text, forum text, conversation text, etc. The text data covers multiple topics, multiple fields and multiple styles, so that the trained interactive text generation model has a wide range of knowledge understanding capabilities.

[0187] Data preprocessing is used to preprocess the collected text data. The preprocessing includes but is not limited to removing special characters, correcting spelling errors, unifying capitalization, data segmentation, part-of-speech tagging, named entity recognition, etc., so that the trained interactive text generation model can better understand the text structure and semantics.

[0188] Model selection is used to select a suitable large language model as the infrastructure, such as the BERT model (Bidirectional Encoder Representation from Transformers, a pre-trained language representation model). Large prediction models usually have a multi-layer Transformer structure that can capture long-distance dependencies and complex semantics in text.

[0189] Parameter initialization is used to initialize the parameters of the interactive text generation model. You can choose to initialize randomly or load parameters from a pre-trained model. The pre-trained model has usually been trained on a large amount of data, which can accelerate the convergence speed of the interactive text generation model.

[0190] Model training is used to feed the preprocessed text data into the interactive text generation model for training. During the training process, the interactive text generation model generates corresponding outputs based on the input text, compares it with the actual label of the input text, and calculates the loss function. Then, the parameters of the model are updated through optimization algorithms (such as gradient descent) to minimize the loss function. The training process of the interactive text generation model requires a large amount of computing resources, such as GPU (Graphics Processing Unit), TPU (Tensor Processing Unit), etc.

[0191] Model tuning is used to adjust the hyperparameters of the interactive text generation model during the training process. Hyperparameters include but are not limited to learning rate, batch size, number of training rounds, etc. By continuously adjusting hyperparameters, the performance and generalization ability of the interactive text generation model can be improved.

[0192] Model evaluation is used to evaluate the performance of the interactive text generation model on the validation set and test set. The performance includes but is not limited to accuracy, recall, F1 score (F1-score, a measurement indicator for classification problems), etc. If the interactive text generation model achieves the expected results on these indicators, the next step of fine-tuning the parameters of the interactive text generation model can be carried out.

[0193] like Fig.10 This is a flow chart of a model training process provided by an embodiment of the present application. Fig.10 In the process, a question is first extracted from the question bank (What is a banana?), and the labeler writes the expected response to the question (Banana is a fruit...). The question is input into the model, the output of the model is obtained (Banana...), the loss value between the expected response and the output is determined, and the parameters of the model are updated according to the loss value.

[0194] The parameters of the trained interactive text generation model are fine-tuned so that one of the 16 MBTI personalities can be used to organize sentences for replies. The parameter fine-tuning of the interactive text generation model is basically equivalent to a retraining, which is to strengthen specific functions. The parameter fine-tuning process of the interactive text generation model includes the following steps: data collection, data expansion, data preprocessing, data labeling, and fine-tuning training.

[0195] Data collection is used to collect text data related to MBTI personality types, including personality descriptions, personality traits, behaviors, etc. The text data includes conversation data related to each personality type so that the interactive text generation model can learn how to respond according to specific personality types.

[0196] Model expansion is used to create some synthetic data in order to enable the interactive text generation model to better understand the characteristics of each personality type. For example, you can write some sentences that describe personality characteristics, or generate some dialogues that meet specific personality types based on existing dialogue data.

[0197] Model preprocessing is used to preprocess the collected text data. Preprocessing includes but is not limited to removing special characters, correcting spelling errors, unifying capitalization, word segmentation, part-of-speech tagging, named entity recognition, etc., so that the interactive text generation model can better understand the text structure and semantics.

[0198] Data annotation is used to add corresponding MBTI personality type labels to each text data. These labels will be used as target outputs during model training.

[0199] Fine-tuning training is used to adapt the trained interactive text generation model. It usually includes adding a task-specific output layer, such as a fully connected layer, to predict the MBTI personality type. The interactive text generation model is fine-tuned using the collected annotated data. During the training process, some parameters of the pre-trained model (such as the underlying word embeddings) are fixed, and only the task-specific output layer parameters are updated. This can improve the performance of the interactive text generation model on specific tasks while retaining the semantic expression ability of the interactive text generation training model.

[0200] After fine-tuning the parameters, the interactive text generation model can use one of the 16 MBTI personalities to organize sentence responses based on the context, or it can use rich user chat feature survey questionnaire data to continue training and fine-tuning, and train a model that combines the current user's personal characteristics with one of the 16 MBTI personalities to provide more appropriate answers.

[0201] Optionally, the interactive text generation model may store chat scripts of objects with different personalities. Exemplarily, the chat scripts of objects with debater-type personalities include: Look at it this way..., we can do this, it is indeed the case, what's wrong with me, I am so awesome. The chat scripts of objects with logician-type personalities include: Let me check it out, let's do it this way today, it depends on you. The chat scripts of objects with architect-type personalities include: Then I will go by myself, let's talk about the matter, I won't go and you will go by yourself, what's the point. The chat scripts of objects with other personalities will not be elaborated here.

[0202] Optionally, after generating at least one interactive text in the above manner, at least one interactive text is displayed. Fig.11 is a schematic diagram of displaying at least one interactive text provided by an embodiment of the present application. Fig.11 The chat interface in (1) displays interactive content 1101 and chat widget 1102. In response to a trigger operation on the chat widget 1102, the chat interface displays Fig.11 (2) Fig.11 There are four interactive texts in (2). Fig.11 The four interactive texts displayed in (2) are the first object's reply content to the interactive content 1101.

[0203] In one possible implementation, in response to a triggering operation of a chat function, a first character of a first object is obtained; based on the absence of interactive content in the chat interface, at least one interactive text is generated according to a first time and the first character, the first time being the time when the chat function is triggered, and the at least one interactive text is the interactive text of the first object at the first time; and at least one interactive text is displayed.

[0204] Optionally, the process of generating at least one interactive text based on the first time and the first character personality is similar to the above-mentioned process of generating at least one interactive text based on the first interactive content and the first character personality, and will not be repeated here.

[0205] like Fig.12 is another display schematic diagram of at least one interactive text provided by an embodiment of the present application. Fig.12 In the chat interface in (1), no interactive content is displayed, but a chat control 1201 is displayed. In response to the trigger operation on the chat control 1201, the chat interface 1201 is displayed. Fig.12 (2) Fig.12 There are four interactive texts in (2). Fig.12 The four interaction texts shown in (2) are the interaction texts of the first character's object at the first time.

[0206] In step 203, in response to a triggering operation on a first interactive text in at least one interactive text, the first interactive text is sent to a terminal device corresponding to at least one second object.

[0207] In one possible implementation, after at least one interactive text is displayed in the above step 202, in response to a trigger operation on a first interactive text in the at least one interactive text, indicating that the first object wishes to send the first interactive text, the first interactive text is sent to a terminal device corresponding to at least one second object.

[0208] In response to a trigger operation on a first interactive text in at least one interactive text, the first interactive text can be sent to a terminal device corresponding to at least one second object and can also be displayed in a chat interface.

[0209] Optionally, in response to a trigger operation on a first interactive text in at least one interactive text, a first virtual image of the first object can also be obtained; a first emoticon package is generated based on the first virtual image and the first interactive text, the first emoticon package corresponds to the first interactive text, and the first emoticon package includes the first virtual image; and the first emoticon package is sent to a terminal device corresponding to at least one second object.

[0210] The process of obtaining a first virtual image of a first object includes: displaying a character page, in which resources corresponding to the initial character of the first object are displayed; in response to a trigger operation of a picture upload function, obtaining a character picture of the first object; and obtaining the first virtual image of the first object based on the character picture of the first object and the resources corresponding to the initial character. The resources corresponding to the initial character can be pictures corresponding to the initial character or videos corresponding to the initial character, which is not limited in the embodiments of the present application. When the resources corresponding to the initial character are pictures corresponding to the initial character, they can be static pictures corresponding to the initial character or dynamic pictures corresponding to the initial character, which is not limited in the embodiments of the present application.

[0211] Optionally, the process of displaying a character personality page includes: displaying a first personality test page, in which at least one first personality test question is displayed, and the first personality test question is used to test and obtain an initial character personality of the first object; based on the at least one first personality test question, displaying a first test result page, in which the personality test result of the first object is displayed; in response to a trigger operation of a personality generation function, generating an initial character personality of the first object; and displaying a character personality page according to the initial character personality of the first object.

[0212] The first personality test question may be an MBTI personality test question, or a test question in any scenario, which is not limited in this embodiment of the present application.

[0213] like Fig.13 It is a display schematic diagram of a first personality test page provided in an embodiment of the present application. Fig.13 The first personality test question displayed on the first personality test page shown in (1) is a test question in any scenario. Fig.13 The first personality test question displayed in the first personality test page shown in (2) is an MBTI personality test question.

[0214] After the first subject completes at least one first personality test question in the first personality test page, the first test result page is displayed. Fig.14 is a display diagram of a first test result page provided in an embodiment of the present application. Fig.14 The personality test result of the first subject shown in the first test result page is: personality type is debater-type personality (ENTP), personality characteristics: extroversion-64%, intuition-58%, logic-67%, prospective-70%, determination-85%.

[0215] The first test result page shows a retest control. Fig.141401 is a retest control. When the first subject is not satisfied with the personality test result of the first subject, that is, when the first subject believes that he or she is not a debater type of person, the first subject can retest to obtain the personality test result of the first subject that satisfies the first subject.

[0216] In a possible implementation, the first test result page also displays a generation control, such as Fig.14 1402 is a generation control. In response to a trigger operation on the generation control, a personality generation function is triggered. In response to the trigger operation of the personality generation function, an initial personality of the first object is generated. According to the initial personality of the first object, a personality page is displayed. The personality page displays a picture corresponding to the initial personality of the first object. Optionally, the initial personality of the first object is also displayed on the personality page.

[0217] like Fig.15 is a display diagram of a character personality page provided by an embodiment of the present application. Fig.15 The initial character personality (ENTP) of the first subject and a picture 1501 corresponding to the initial character personality of the first subject are displayed.

[0218] Optionally, a picture upload control is displayed on the character personality page, such as Fig.15 1502 is a picture upload control. In response to a trigger operation on the picture upload control, the picture upload function is triggered. In response to the trigger operation on the picture upload function, a process of obtaining a person picture of the first object is as follows: in response to the trigger operation on the picture upload function, a picture page is displayed, and a plurality of candidate pictures are displayed on the picture page. In response to a trigger operation on any candidate picture, any candidate picture is used as the person picture of the first object.

[0219] The process of determining the first virtual image of the first object based on the character picture of the first object and the resources corresponding to the initial character personality includes: generating multiple candidate virtual images based on the character picture of the first object and the resources corresponding to the initial character personality, displaying the multiple candidate virtual images, and in response to a trigger operation for any candidate virtual image, using any candidate virtual image as the first virtual image of the first object.

[0220] like Fig.16 is a schematic diagram of displaying multiple candidate virtual images provided by an embodiment of the present application, Fig.16 A first candidate virtual image 1601, a second candidate virtual image 1602, and a third candidate virtual image 1603 are displayed. Optionally, Fig.16A confirmation control 1604 is also displayed, and in response to a trigger operation on any candidate virtual image and the trigger operation on the confirmation control 1604, any candidate virtual image is used as the first virtual image of the first object. Exemplarily, in response to a trigger operation on the first candidate virtual image 1601 and the trigger operation on the confirmation control 1604, the first candidate virtual image 1601 is used as the first virtual image of the first object.

[0221] In one possible implementation, after obtaining the first virtual image of the first object, the process of generating a first emoticon package according to the first virtual image and the first interactive text includes: inputting the first virtual image and the first interactive text into an emoticon package generation model, and using the content output by the emoticon package generation model as the first emoticon package.

[0222] Optionally, before inputting the first virtual image and the first interactive text into the emoticon package generation model, it is necessary to first obtain the emoticon package generation model, and the acquisition process of the emoticon package generation model includes the training process of the emoticon package generation model and the parameter fine-tuning process of the emoticon package generation model. The training process of the emoticon package generation model includes the following steps: data collection, data preprocessing, selecting a model architecture, training a model, hyperparameter tuning, model evaluation, and model deployment.

[0223] Data collection is used to collect image data, which can include various types of artworks, such as oil paintings, sketches, watercolors, etc. The richer and more diverse the collected image data, the more powerful the ability of the trained emoji generation model will be.

[0224] Data preprocessing is used to preprocess the collected image data after it is collected. The preprocessing includes but is not limited to operations such as cropping, scaling, and rotating. The purpose of preprocessing is to convert these images into a format suitable for the emoticon generation model.

[0225] Select the model architecture to select a suitable neural network model architecture, usually using generative models such as Generative Adversarial Networks (GAN) or Variational Auto-Encoders (VAE), which can learn the underlying representation of images and generate new images under given input conditions.

[0226] Training model, used to train the selected model using the collected image data. During the training process, the model will learn how to generate images with similar style and content based on the input conditions. The training process may require a lot of computing resources and time, so it may be necessary to use GPU or other acceleration hardware.

[0227] Hyperparameter tuning is used to adjust hyperparameters during model training to optimize model performance. By trying different hyperparameter combinations, we can find the best configuration that can generate high-quality images. Hyperparameters include but are not limited to learning rate, batch size, number of iterations, etc.

[0228] Model evaluation is used to evaluate the trained model and use some quantitative indicators such as Peak Signal to Noise Ratio (PSNR) and Structural Similarity Index measure (SSIM) to observe the quality of the generated images.

[0229] Model deployment, which is used to deploy the trained emoji generation model into a drawing tool through which users can interact with the emoji generation model to create new images. The emoji generation model can be deployed to a cloud server or embedded into a desktop or mobile application.

[0230] like Fig.17 This is a schematic diagram of the use process of an emoticon package generation model provided in an embodiment of the present application. The text "paradise, beach, universe" is input into the emoticon package generation model, encoded by the text encoder, and the encoded content is input into the image generator to obtain an image corresponding to the text.

[0231] The process of fine-tuning the parameters of the emoticon generation model is similar to the process of fine-tuning the parameters of the interactive text generation model mentioned above. It is also a re-training with the addition of MBTI personality. The process of fine-tuning the parameters of the emoticon generation model includes the following steps: data collection, data labeling, data preprocessing, and fine-tuning strategy.

[0232] Among them, data collection is used to collect image data. The collected image data contains characters of various MBTI personality types and their related scenes, expressions and interactions. Some images can be collected from the Internet, or some original images can be created by users themselves.

[0233] Data annotation is used to add labels to the collected image data. The label refers to the MBTI personality type corresponding to the image data, which helps the model learn features related to MBTI personality during fine-tuning.

[0234] Data preprocessing is used to preprocess the collected image data, such as cropping, scaling, rotating, etc., so that the format of the preprocessed image data is consistent with the input data format of the model.

[0235] Fine-tuning strategy, used to select the appropriate fine-tuning strategy to fine-tune the model. Since emojis are quite different from ordinary works of art in terms of style and content, it is recommended to fine-tune the entire model to adapt it to specific tasks, and then generate MBTI personality emojis based on specific tags. The fine-tuned emoji generation model can generate corresponding emojis based on various keywords in the interactive text.

[0236] Optionally, after generating a first emoticon package according to the first virtual image and the first interactive text, the first emoticon package is sent to a terminal device corresponding to at least one second object.

[0237] In a possible implementation, the first interactive text and the first emoticon package may also be displayed in the chat interface, and the display position of the first interactive text is before the display position of the first emoticon package. Fig.18 is a display diagram of another chat interface provided by an embodiment of the present application. Fig.18 A first interactive text 1801 and a first emoticon package 1802 are displayed, and the first emoticon package includes a first virtual image 1803. The first interactive text 1801 is displayed above the first emoticon package 1802.

[0238] In a possible implementation, a text input box is displayed in the chat interface, such as Figure 4 402 is a text input box. The first object can input text content in the text input box, and in response to a trigger operation of the text optimization function, obtain the text content input in the text input box; optimize the text content input in the text input box to obtain at least one optimized text content; in response to a trigger operation for any optimized text content, send any optimized text content to a terminal device corresponding to at least one second object.

[0239] Optionally, a text optimization control is also displayed in the chat interface, such as Figure 4 403 in the text optimization control is a text optimization control. In response to the triggering operation on the text optimization control, the text optimization function is triggered.

[0240] In response to a trigger operation for any optimized text content, a first virtual image of the first object can also be obtained, and a second emoticon package can be generated based on the first virtual image and any optimized text content, the second emoticon package corresponding to any optimized text content, and the second emoticon package includes the first virtual image; the second emoticon package is sent to a terminal device corresponding to at least one second object.

[0241] Among them, the process of generating the second emoticon package based on the first virtual image and any optimized text content is similar to the process of generating the first emoticon package based on the first virtual image and the first interactive text, and will not be repeated here.

[0242] Any optimized text content and the second emoticon package can also be displayed in the chat interface, and the display position of any optimized text content is before the display position of the second emoticon package.

[0243] like Fig.19 is a display diagram of another chat interface provided by an embodiment of the present application. Fig.19 The text content "It's really boring" is entered into the text input box 1901 in (1), and the text optimization control 1902 is triggered, which then displays Fig.19 (2), Fig.19 In (2), four optimized text contents are displayed. All four optimized text contents are text contents after optimizing the text content "It's really boring". In response to the trigger operation for the second optimized text content, the display Fig.19 (3), Fig.19 (3) shows the second optimized text content 1903 and the second emoticon package 1904, and the second emoticon package 1904 includes the first virtual image 1905, and the display position of the second optimized text content 1903 is before the display position of the second emoticon package 1904.

[0244] In a possible implementation, based on the interactive content displayed in the chat interface, and the interactive content at the reference position in the chat interface is the interactive content sent by the first object, in response to the triggering operation of the single-player comic generation function, a third emoticon package is generated according to the interactive content at the reference position and the first virtual image of the first object, and the third emoticon package is sent to a terminal device corresponding to at least one second object, the third emoticon package corresponds to the interactive content at the reference position, and the third emoticon package includes the first virtual image. The interactive content at the reference position may be the last interactive content.

[0245] Optionally, a single-player comic generation control is also displayed in the chat interface, such as Figure 4 404 is a single-player comic generation control. In response to a trigger operation on the single-player comic generation control, a single-player comic generation function is triggered.

[0246] Among them, the process of generating the third emoticon package based on the interactive content of the reference position and the first virtual image of the first object is similar to the process of generating the first emoticon package based on the first interactive text and the first virtual image, and will not be repeated here.

[0247] Optionally, after the third emoticon package is generated according to the interactive content at the reference position and the first virtual image of the first object, the third emoticon package can also be displayed in the chat interface. The third emoticon package is displayed below the last interactive content.

[0248] like Fig. 20 is a display diagram of another chat interface provided by an embodiment of the present application. Fig. 20 The chat interface shown in (1) shows interactive content 2001, and the interactive content 2001 is sent by the first object. When the first object selects the single-player comic generation control 2002, the display Fig. 20 (2), Fig. 20 In (2), a third emoticon package 2003 is displayed, and the third emoticon package 2003 includes a first virtual image 2004. The third emoticon package 2003 is displayed below the interactive content 2001.

[0249] In one possible implementation, based on the interactive content displayed in the chat interface and the interactive content located at the reference position in the chat interface is not the interactive content sent by the first object, in response to the triggering operation of the single-player comic generation function, reply content of the interactive content at the reference position is generated according to the interactive content at the reference position and the personality of the first character; a fourth emoticon package is generated according to the reply content and the first virtual image, and the fourth emoticon package is sent to a terminal device corresponding to at least one second object, the fourth emoticon package corresponds to the reply content, and the fourth emoticon package includes the first virtual image, and the reply content is the reply content of the first object to the interactive content at the reference position.

[0250] Among them, the process of generating reply content of the interactive content of the reference position according to the interactive content of the reference position and the personality of the first character is similar to the above-mentioned process of generating at least one interactive text according to the first interactive content and the first character personality, and the process of generating the fourth emoticon package according to the reply content and the first virtual image is similar to the above-mentioned process of generating the first emoticon package according to the first interactive text and the first virtual image, and they will not be repeated here.

[0251] Optionally, after the fourth emoticon package is generated according to the reply content and the first virtual image, the fourth emoticon package can also be displayed in the chat interface. The fourth emoticon package is displayed below the last interactive content.

[0252] like Fig.21 is a display diagram of another chat interface provided by an embodiment of the present application. Fig.21 The chat interface shown in (1) shows interactive content 2101, and the interactive content 2101 is not sent by the first object. When the first object selects the single-player comic generation control 2102, the display Fig.21 (2), Fig.21 In (2), a fourth emoticon package 2103 is displayed, and the fourth emoticon package 2103 includes a first virtual image 2104. And the fourth emoticon package 2103 is displayed below the interactive content 2101.

[0253] In a possible implementation, based on the display of multiple interactive contents in the chat interface, in response to the triggering operation of the multi-person comic generation function, a second interactive content whose interaction time is within a target time period is determined in the multiple interactive contents, a fifth emoticon package is generated according to the second interactive content, and the fifth emoticon package is sent to a terminal device of at least one second object. The target time period is determined based on the triggering time of the multi-person comic generation function; the fifth emoticon package corresponds to the second interactive content, and the fifth emoticon package includes a virtual image corresponding to each second interactive content.

[0254] Optionally, the end time of the target time period is the trigger time of the multi-person comic generation function, and the duration of the target time period is the reference duration. The reference duration is set based on experience, or adjusted according to the implementation environment, and the embodiment of the present application does not limit this. Exemplarily, the reference duration is 3 minutes, and the trigger time of the multi-person comic generation function is 17:44:43 on November 7, 2023, then the target time period is from 17:41:43 on November 7, 2023 to 17:44:43 on November 7, 2023.

[0255] The chat interface also displays a multiplayer comic generation control, such as Figure 4 405 is a multi-person comic generation control. In response to a trigger operation on the multi-person comic generation control, a multi-person comic generation function is triggered.

[0256] The process of generating the fifth emoticon package according to the second interactive content includes: obtaining the virtual image of the sending object of each second interactive content; generating the fifth emoticon package according to each second interactive content and the virtual image of the sending object of each second interactive content.

[0257] The server stores virtual images of various objects, and the terminal device obtains the virtual images of the objects that send out the second interactive content through interaction with the server. The process of generating the fifth emoticon package based on the second interactive content and the virtual images of the objects that send out the second interactive content is similar to the process of generating the first emoticon package based on the first interactive text and the first virtual image, and will not be repeated here.

[0258] In a possible implementation, after the fifth emoticon package is generated according to the second interactive content, the fifth emoticon package can also be displayed in the chat interface.

[0259] like Fig. 22 This is a display diagram of another chat interface provided in an embodiment of the present application. Fig. 22In (1), three interactive contents are displayed, namely, interactive content 2201, interactive content 2202 and interactive content 2203. When the first object selects the multi-person comic generation control 2204, the interactive content 2202 and the interactive content 2203 are used as the second interactive content, and the fifth emoticon package is generated according to the second interactive content, and displayed. Fig. 22 (2), Fig. 22 (2) shows a fifth emoticon package 2205. The fifth emoticon package 2205 shows a first avatar 2206 of the first object that sends out the interactive content 2202 and a avatar 2207 of the object that sends out the interactive content 2203.

[0260] In one possible implementation, based on multiple interactive contents displayed in a chat interface, in response to a trigger operation on reference interactive contents among the multiple interactive contents, multimedia resources are generated and shared according to the reference interactive contents, and the multimedia resources include the reference interactive contents.

[0261] Optionally, in response to a long press operation on any interactive content, a selection control is displayed at a target position of each interactive content, and in response to a triggering operation of the selection control on at least one interactive content among the multiple interactive contents, the selected at least one interactive content is used as a reference interactive content. The target position of the interactive content can be the left side of the interactive content or other positions of the interactive content, which is not limited in the embodiments of the present application.

[0262] In response to a long press operation on any interactive content, a confirmation control is also displayed. After responding to a trigger operation of a selection control on at least one of the multiple interactive contents, in response to a trigger operation on the confirmation control, a multimedia resource is generated based on the reference interactive content. The multimedia resource can be a picture or a video, which is not limited in the embodiment of the present application.

[0263] After the multimedia resources are generated according to the reference interactive content, the multimedia resources may be displayed. Optionally, after the multimedia resources are generated, a display page is displayed, and the multimedia resources are displayed on the display page.

[0264] Optionally, a sharing control is also displayed in the presentation page. In response to a trigger operation on the sharing control, at least one sharing channel is displayed. In response to a trigger operation on any sharing channel, the multimedia resource is shared through any sharing channel.

[0265] like Fig.23 Schematic diagram of a multimedia resource sharing process provided by an embodiment of the present application. Fig.23 The chat interface shown in (1) shows multiple interactive contents. When the first object long presses any interactive content, it is displayed Fig.23 (2), Fig.23 In (2), a selection control is displayed in front of each interactive content, such as Fig.23 In (2), the selection control 2300 corresponding to the first interactive content is displayed in front of the first interactive content, and the selection controls displayed in front of other interactive contents are shown in FIG. Fig.23 As shown in (2), Fig.23 In (2), a confirmation control 2301 is displayed. The first object can select the selection control in front of the interactive content of the multimedia resource to be generated, and then display Fig.23 (3), Fig.23 In (3), the selection control for generating interactive content of multimedia resources is in a selected state. Fig.23 When the confirmation control in (3) is selected, multimedia resources are generated and displayed according to the interactive content in the selected state. Fig.23 (4), Fig.23 In (4), multimedia resources 2302 and sharing controls 2303 are displayed. When the first object selects the sharing control, Fig.23 (5), Fig.23 (5) shows sharing channel 1, sharing channel 2, sharing channel 3, and sharing channel 4. When the first object selects any sharing channel, the multimedia resource is shared through any sharing channel.

[0266] Optionally, in response to a trigger operation on any sharing channel, a sharing page is displayed, in which the object identifier of the object included in any sharing channel is displayed; in response to a trigger operation on any object identifier, multimedia resources are sent to a terminal device of an object corresponding to any object identifier, so as to achieve the purpose of sharing multimedia resources with the object corresponding to any object identifier.

[0267] In a possible implementation, a switching control is also displayed in the chat interface, and the switching control is used to switch the character of the first object, such as Figure 4 406 in is a switching control. In response to a trigger operation on the switching control, a switching page is displayed, in which a first character and multiple optional characters are displayed, wherein the display state of the first character is a first state, and the display state of each optional character is a second state, the first state is used to indicate that the character of the first object in the current chat interface is the first character, and the second state is used to indicate that the character of the first object in the current chat interface is not an optional character. Optionally, displaying in white indicates that the display state is the first state, and displaying in gray indicates that the display state is the second state. The display state of the first state and the display state of the second state may also be in other forms, which are not limited in the embodiments of the present application.

[0268] In response to a trigger operation for any optional character, the display state of the first character is adjusted to the second state, and the display state of any optional character is adjusted to the first state, that is, the character of the first object in the current chat interface is adjusted from the first character to any optional character. In response to a trigger operation for the chat function, at least one reference interaction text is displayed, and any reference interaction text is an interaction text related to any optional character. The process of obtaining at least one reference interaction text is similar to the process of obtaining at least one interaction text described above, and the embodiments of the present application will not be repeated here.

[0269] In the above method, in the chat interface between the first object and at least one second object, when the chat function is triggered, at least one interactive text corresponding to the first character personality is generated according to the first character personality of the first object when facing at least one second object, and any interactive text is selected in the at least one interactive text and sent to at least one second object. This method does not require the first object to manually enter the text content in the text input box and then send it, which can save time for social interaction and improve the efficiency of social interaction. Moreover, the first object can have different characters in different chat interfaces, that is, the first object can have different characters when facing different objects, so that the interactive texts in different chat interfaces can be different, which makes the social interaction more flexible and improves the fun of social interaction, thereby improving the interaction rate of social interaction and enhancing the user experience.

[0270] Fig.24 FIG. 1 is a schematic diagram of a social interaction device provided in an embodiment of the present application. Fig.24 As shown, the device comprises:

[0271] Display module 2401, used to display a chat interface between a first object and at least one second object;

[0272] The display module 2401 is further configured to display at least one interactive text corresponding to the first character personality according to the first character personality of the first object when facing at least one second object in response to a triggering operation of the chat function;

[0273] The sending module 2402 is used to send the first interactive text to a terminal device corresponding to at least one second object in response to a triggering operation on a first interactive text in at least one interactive text.

[0274] In a possible implementation, the device further includes:

[0275] An acquisition module, configured to acquire a first virtual image of a first object in response to a trigger operation on a first interactive text in at least one interactive text;

[0276] A generating module, configured to generate a first emoticon package according to the first virtual image and the first interactive text, wherein the first emoticon package corresponds to the first interactive text and includes the first virtual image;

[0277] The sending module 2402 is further configured to send the first emoticon package to a terminal device corresponding to at least one second object.

[0278] In a possible implementation, the display module 2401 is also used to display the first interactive text and the first emoticon package in the chat interface.

[0279] In one possible implementation, an acquisition module is used to display a character personality page, in which resources corresponding to the initial character personality of a first object are displayed; in response to a trigger operation of a picture upload function, a character picture of the first object is acquired; and based on the character picture of the first object and the resources corresponding to the initial character personality, a first virtual image of the first object is acquired.

[0280] In a possible implementation, the acquisition module is used to display a first personality test page, in which at least one first personality test question is displayed, and the first personality test question is used to test and obtain the initial character personality of the first object; based on the at least one first personality test question, a first test result page is displayed, in which the personality test result of the first object is displayed; in response to a triggering operation of a personality generation function, an initial character personality of the first object is generated; and according to the initial character personality of the first object, a character personality page is displayed.

[0281] In one possible implementation, display module 2401 is used to obtain a first character of a first object in response to a triggering operation of a chat function; based on at least one interactive content displayed in the chat interface, determine a first interactive content in the at least one interactive content, the first interactive content being the interactive content whose corresponding interaction time in the at least one interactive content is before a first time and adjacent to the first time, and the first time is the time when the chat function is triggered; generate at least one interactive text based on the first interactive content and the first character, the at least one interactive text being the reply content of the first object to the first interactive content; and display at least one interactive text.

[0282] In one possible implementation, display module 2401 is used to obtain the character of a third object and the object identity of the third object relative to the first object; obtain the first character of the first object based on the character of the third object and the object identity of the third object relative to the first object, where the third object is any second object among at least one second object; or obtain keywords; and obtain the first character of the first object based on the keywords.

[0283] In a possible implementation, the display module 2401 is used to obtain the character description content of the third object, determine the character of the third object according to the character description content of the third object, where the character description content of the third object is the description content of the character of the third object by the first object; or, display a second character test page, where at least one second character test question is displayed on the second character test page, and the character of the third object is generated based on the at least one second character test question, where the second character test question is used to test and obtain the character of the third object.

[0284] In one possible implementation, display module 2401 is used to obtain the first character personality of the first object in response to the triggering operation of the chat function; based on the absence of interactive content in the chat interface, generate at least one interactive text according to the first time and the first character personality, the first time is the time when the chat function is triggered, and the at least one interactive text is the interactive text of the first object at the first time; and display at least one interactive text.

[0285] In a possible implementation, a text input box is displayed in the chat interface;

[0286] The device also includes:

[0287] An acquisition module, used for acquiring text content inputted in the text input box in response to a triggering operation of the text optimization function;

[0288] An optimization module, used for optimizing the text content input in the text input box to obtain at least one optimized text content;

[0289] The sending module 2402 is further configured to send any optimized text content to a terminal device corresponding to at least one second object in response to a trigger operation for any optimized text content.

[0290] In a possible implementation, the acquisition module is further configured to acquire a first virtual image of the first object in response to a trigger operation on any optimized text content;

[0291] The device also includes:

[0292] A generating module, used for generating a second emoticon package according to the first virtual image and any optimized text content, wherein the second emoticon package corresponds to any optimized text content and includes the first virtual image;

[0293] The sending module 2402 is further configured to send a second emoticon package to a terminal device corresponding to at least one second object.

[0294] In a possible implementation, the display module 2401 is also used to display any optimized text content and the second emoticon package in the chat interface.

[0295] In one possible implementation, the sending module 2402 is also used to generate a third emoticon package based on the interactive content located at the reference position in the chat interface being the interactive content sent by the first object, in response to the triggering operation of the single-player comic generation function, according to the interactive content at the reference position and the first virtual image of the first object, and send the third emoticon package to a terminal device corresponding to at least one second object, where the third emoticon package corresponds to the interactive content at the reference position, and the third emoticon package includes the first virtual image; based on the interactive content located at the reference position in the chat interface being not the interactive content sent by the first object, in response to the triggering operation of the single-player comic generation function, according to the interactive content at the reference position and the personality of the first character, generate reply content for the interactive content at the reference position, generate a fourth emoticon package based on the reply content and the first virtual image, and send the fourth emoticon package to a terminal device corresponding to at least one second object, where the fourth emoticon package corresponds to the reply content, and the fourth emoticon package includes the first virtual image.

[0296] In a possible implementation, the display module 2401 is further used to display the third emoticon package in the chat interface; and to display the fourth emoticon package in the chat interface.

[0297] In a possible implementation, the device further includes:

[0298] A determination module, configured to determine, based on a plurality of interactive contents displayed in the chat interface, a second interactive content whose interaction time is within a target time period in response to a triggering operation of a multi-person comic generation function, from among the plurality of interactive contents, wherein the target time period is determined based on the triggering time of the multi-person comic generation function;

[0299] A generating module, configured to generate a fifth emoticon package according to the second interactive content, wherein the fifth emoticon package corresponds to the second interactive content and includes a virtual image of an object of each second interactive content;

[0300] The sending module 2402 is further configured to send a fifth emoticon package to a terminal device of at least one second object.

[0301] In a possible implementation, the generating module is used to obtain a virtual image of an object from which each second interactive content is emitted; and to generate a fifth emoticon package according to each second interactive content and the virtual image of the object from which each second interactive content is emitted.

[0302] In a possible implementation, a plurality of interactive contents are displayed in the chat interface, and the device further includes:

[0303] A generating module, configured to generate multimedia resources according to the reference interactive content in response to a triggering operation on the reference interactive content in the plurality of interactive contents, wherein the multimedia resources include the reference interactive content;

[0304] Sharing module, used to share multimedia resources.

[0305] In the chat interface between the first object and at least one second object, when the chat function is triggered, the above-mentioned device generates at least one interactive text corresponding to the first character's personality according to the first character's personality of the first object when facing at least one second object, and selects any interactive text in the at least one interactive text and sends it to at least one second object. Since the first object does not need to manually input the text content in the text input box before sending it, it can save time for social interaction and improve the efficiency of social interaction. Moreover, the first object can have different personalities in different chat interfaces, that is, the first object can have different personalities when facing different objects, so that the interactive texts in different chat interfaces can be different, which makes social interaction more flexible and improves the fun of social interaction, thereby improving the interaction rate of social interaction and enhancing the user experience.

[0306] It should be understood that the above-mentioned device only uses the division of the above-mentioned functional modules as an example to illustrate when implementing its functions. In actual applications, the above-mentioned functions can be assigned to different functional modules as needed, that is, the internal structure of the device is divided into different functional modules to complete all or part of the functions described above. In addition, the device and method embodiments provided in the above embodiments belong to the same concept, and their specific implementation process is detailed in the method embodiment, which will not be repeated here.

[0307] Fig.25 The structural block diagram of a terminal device 2500 provided by an exemplary embodiment of the present application is shown. The terminal device 2500 may be any electronic device product that can interact with a user through one or more methods such as a keyboard, a touchpad, a remote controller, voice interaction, or a handwriting device. For example, a PC (Personal Computer), a mobile phone, a smart phone, a PDA (Personal Digital Assistant), a wearable device, a PPC (Pocket PC), a tablet computer, a smart car machine, a smart TV, a smart speaker, a smart watch, etc.

[0308] Typically, the terminal device 2500 includes: a processor 2501 and a memory 2502 .

[0309] The processor 2501 may include one or more processing cores, such as a 4-core processor, an 8-core processor, etc. The processor 2501 may be implemented in at least one hardware form of DSP (Digital Signal Processing), FPGA (Field-Programmable Gate Array), and PLA (Programmable Logic Array). The processor 2501 may also include a main processor and a coprocessor. The main processor is a processor for processing data in an awake state, also known as a CPU (Central Processing Unit); the coprocessor is a low-power processor for processing data in a standby state. In some embodiments, the processor 2501 may be integrated with a GPU (Graphics Processing Unit), which is responsible for rendering and drawing the content to be displayed on the display screen. In some embodiments, the processor 2501 may also include an AI (Artificial Intelligence) processor, which is used to process computing operations related to machine learning.

[0310] The memory 2502 may include one or more computer-readable storage media, which may be non-transitory. The memory 2502 may also include a high-speed random access memory, and a non-volatile memory, such as one or more disk storage devices, flash memory storage devices. In some embodiments, the non-transitory computer-readable storage medium in the memory 2502 is used to store at least one instruction, which is used to be executed by the processor 2501 to implement the social interaction method provided in the method embodiment of the present application.

[0311] In some embodiments, the terminal device 2500 may also optionally include: a peripheral device interface 2503 and at least one peripheral device. The processor 2501, the memory 2502 and the peripheral device interface 2503 may be connected via a bus or a signal line. Each peripheral device may be connected to the peripheral device interface 2503 via a bus, a signal line or a circuit board. Specifically, the peripheral device includes: at least one of a radio frequency circuit 2504, a display screen 2505, a camera assembly 2506, an audio circuit 2507 and a power supply 2509.

[0312] The peripheral device interface 2503 may be used to connect at least one peripheral device related to I / O (Input / Output) to the processor 2501 and the memory 2502. In some embodiments, the processor 2501, the memory 2502, and the peripheral device interface 2503 are integrated on the same chip or circuit board; in some other embodiments, any one or two of the processor 2501, the memory 2502, and the peripheral device interface 2503 may be implemented on a separate chip or circuit board, which is not limited in this embodiment.

[0313] The radio frequency circuit 2504 is used to receive and transmit RF (Radio Frequency) signals, also known as electromagnetic signals. The radio frequency circuit 2504 communicates with the communication network and other communication devices through electromagnetic signals. The radio frequency circuit 2504 converts the electrical signal into an electromagnetic signal for transmission, or converts the received electromagnetic signal into an electrical signal. Optionally, the radio frequency circuit 2504 includes: an antenna system, an RF transceiver, one or more amplifiers, a tuner, an oscillator, a digital signal processor, a codec chipset, a user identity module card, and the like. The radio frequency circuit 2504 can communicate with other terminal devices through at least one wireless communication protocol. The wireless communication protocol includes, but is not limited to: the World Wide Web, a metropolitan area network, an intranet, various generations of mobile communication networks (2G, 3G, 4G and 5G), a wireless local area network and / or a WiFi (Wireless Fidelity) network. In some embodiments, the radio frequency circuit 2504 may also include circuits related to NFC (Near Field Communication), which is not limited in this application.

[0314] The display screen 2505 is used to display a UI (User Interface). The UI may include graphics, text, icons, videos, and any combination thereof. When the display screen 2505 is a touch display screen, the display screen 2505 also has the ability to collect touch signals on the surface or above the surface of the display screen 2505. The touch signal can be input to the processor 2501 as a control signal for processing. At this time, the display screen 2505 can also be used to provide virtual buttons and / or virtual keyboards, also known as soft buttons and / or soft keyboards. In some embodiments, the display screen 2505 can be one, arranged on the front panel of the terminal device 2500; in other embodiments, the display screen 2505 can be at least two, respectively arranged on different surfaces of the terminal device 2500 or in a folding design; in other embodiments, the display screen 2505 can be a flexible display screen, arranged on a curved surface or a folding surface of the terminal device 2500. Even, the display screen 2505 can also be arranged as a non-rectangular irregular figure, that is, a special-shaped screen. The display screen 2505 can be made of materials such as LCD (Liquid Crystal Display) and OLED (Organic Light-Emitting Diode).

[0315] The camera assembly 2506 is used to capture images or videos. Optionally, the camera assembly 2506 includes a front camera and a rear camera. Typically, the front camera is arranged on the front panel of the terminal device 2500, and the rear camera is arranged on the back of the terminal device 2500. In some embodiments, there are at least two rear cameras, which are any one of a main camera, a depth of field camera, a wide-angle camera, and a telephoto camera, so as to realize the fusion of the main camera and the depth of field camera to realize the background blur function, the fusion of the main camera and the wide-angle camera to realize panoramic shooting and VR (Virtual Reality) shooting function or other fusion shooting functions. In some embodiments, the camera assembly 2506 may also include a flash. The flash can be a monochrome temperature flash or a dual-color temperature flash. A dual-color temperature flash refers to a combination of a warm light flash and a cold light flash, which can be used for light compensation at different color temperatures.

[0316] The audio circuit 2507 may include a microphone and a speaker. The microphone is used to collect sound waves from the user and the environment, and convert the sound waves into electrical signals and input them into the processor 2501 for processing, or input them into the radio frequency circuit 2504 to achieve voice communication. For the purpose of stereo acquisition or noise reduction, there may be multiple microphones, which are respectively arranged at different parts of the terminal device 2500. The microphone may also be an array microphone or an omnidirectional acquisition microphone. The speaker is used to convert the electrical signal from the processor 2501 or the radio frequency circuit 2504 into sound waves. The speaker may be a traditional film speaker or a piezoelectric ceramic speaker. When the speaker is a piezoelectric ceramic speaker, it can not only convert the electrical signal into sound waves audible to humans, but also convert the electrical signal into sound waves inaudible to humans for purposes such as ranging. In some embodiments, the audio circuit 2507 may also include a headphone jack.

[0317] The power supply 2509 is used to power various components in the terminal device 2500. The power supply 2509 can be an alternating current, a direct current, a disposable battery, or a rechargeable battery. When the power supply 2509 includes a rechargeable battery, the rechargeable battery can be a wired rechargeable battery or a wireless rechargeable battery. A wired rechargeable battery is a battery charged through a wired line, and a wireless rechargeable battery is a battery charged through a wireless coil. The rechargeable battery can also be used to support fast charging technology.

[0318] In some embodiments, the terminal device 2500 further includes one or more sensors 2510 , including but not limited to: an acceleration sensor 2511 , a gyroscope sensor 2512 , a pressure sensor 2513 , an optical sensor 2515 , and a proximity sensor 2516 .

[0319] The acceleration sensor 2511 can detect the magnitude of acceleration on the three coordinate axes of the coordinate system established by the terminal device 2500. For example, the acceleration sensor 2511 can be used to detect the components of gravity acceleration on the three coordinate axes. The processor 2501 can control the display screen 2505 to display the user interface in a horizontal view or a vertical view according to the gravity acceleration signal collected by the acceleration sensor 2511. The acceleration sensor 2511 can also be used for collecting game or user motion data.

[0320] The gyro sensor 2512 can detect the body direction and rotation angle of the terminal device 2500, and the gyro sensor 2512 can cooperate with the acceleration sensor 2511 to collect the user's 3D actions on the terminal device 2500. The processor 2501 can implement the following functions based on the data collected by the gyro sensor 2512: motion sensing (such as changing the UI according to the user's tilt operation), image stabilization during shooting, game control, and inertial navigation.

[0321] The pressure sensor 2513 can be set on the side frame of the terminal device 2500 and / or the lower layer of the display screen 2505. When the pressure sensor 2513 is set on the side frame of the terminal device 2500, it can detect the user's holding signal of the terminal device 2500, and the processor 2501 performs left and right hand recognition or shortcut operation according to the holding signal collected by the pressure sensor 2513. When the pressure sensor 2513 is set on the lower layer of the display screen 2505, the processor 2501 controls the operability controls on the UI interface according to the user's pressure operation on the display screen 2505. The operability controls include at least one of a button control, a scroll bar control, an icon control, and a menu control.

[0322] The optical sensor 2515 is used to collect the ambient light intensity. In one embodiment, the processor 2501 can control the display brightness of the display screen 2505 according to the ambient light intensity collected by the optical sensor 2515. Specifically, when the ambient light intensity is high, the display brightness of the display screen 2505 is increased; when the ambient light intensity is low, the display brightness of the display screen 2505 is reduced. In another embodiment, the processor 2501 can also dynamically adjust the shooting parameters of the camera component 2506 according to the ambient light intensity collected by the optical sensor 2515.

[0323] The proximity sensor 2516, also called a distance sensor, is usually arranged on the front panel of the terminal device 2500. The proximity sensor 2516 is used to collect the distance between the user and the front of the terminal device 2500. In one embodiment, when the proximity sensor 2516 detects that the distance between the user and the front of the terminal device 2500 is gradually decreasing, the processor 2501 controls the display screen 2505 to switch from the screen-on state to the screen-off state; when the proximity sensor 2516 detects that the distance between the user and the front of the terminal device 2500 is gradually increasing, the processor 2501 controls the display screen 2505 to switch from the screen-off state to the screen-on state.

[0324] Those skilled in the art will understand that Fig.25 The structure shown in the figure does not constitute a limitation on the terminal device 2500, and may include more or fewer components than shown in the figure, or combine certain components, or adopt a different component arrangement.

[0325] Fig.26This is a schematic diagram of the structure of the server provided in the embodiment of the present application. The server 2600 may have relatively large differences due to different configurations or performances, and may include one or more processors (Central Processing Units, CPU) 2601 and one or more memories 2602, wherein the one or more memories 2602 store at least one program code, and the at least one program code is loaded and executed by the one or more processors 2601 to implement the social interaction methods provided by the above-mentioned various method embodiments. Of course, the server 2600 may also have components such as a wired or wireless network interface, a keyboard, and an input and output interface for input and output. The server 2600 may also include other components for implementing device functions, which will not be described in detail here.

[0326] In an exemplary embodiment, a computer-readable storage medium is further provided, in which at least one program code is stored. The at least one program code is loaded and executed by a processor to enable a computer to implement any of the above-mentioned social interaction methods.

[0327] Optionally, the computer-readable storage medium may be a read-only memory (ROM), a random access memory (RAM), a compact disc (CD-ROM), a magnetic tape, a floppy disk, an optical data storage device, etc.

[0328] In an exemplary embodiment, a computer program or a computer program product is also provided, wherein at least one computer instruction is stored in the computer program or the computer program product, and the at least one computer instruction is loaded and executed by a processor to enable a computer to implement any one of the above-mentioned social interaction methods.

[0329] It should be noted that the information (including but not limited to user device information, user personal information, etc.), data (including but not limited to data used for analysis, stored data, displayed data, etc.) and signals involved in this application are all authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with the relevant laws, regulations and standards of the relevant countries and regions. For example, the object identifiers, texts and other information involved in this application are all obtained with full authorization.

[0330] It should be understood that the "plurality" mentioned in this article refers to two or more. "And / or" describes the association relationship of the associated objects, indicating that there can be three relationships. For example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone. The character " / " generally indicates that the associated objects are in an "or" relationship.

[0331] The serial numbers of the above-mentioned embodiments of the present application are for description only and do not represent the advantages or disadvantages of the embodiments.

[0332] The above description is only an exemplary embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent substitutions, improvements, etc. made within the principles of the present application shall be included in the protection scope of the present application.

Claims

1. A method of social interaction, It is characterized in that The method comprises: displaying a chat interface between the first object and at least one second object; In response to a triggering operation of the chat function, displaying at least one interactive text corresponding to the first character personality according to the first character personality of the first object when facing the at least one second object; In response to a triggering operation on a first interactive text among the at least one interactive text, the first interactive text is sent to a terminal device corresponding to the at least one second object.

2. The method according to claim 1, It is characterized in that The method further comprises: In response to a triggering operation on a first interactive text in the at least one interactive text, acquiring a first virtual image of the first object; generating a first emoticon package according to the first virtual image and the first interactive text, wherein the first emoticon package corresponds to the first interactive text and includes the first virtual image; The first emoticon package is sent to a terminal device corresponding to the at least one second object.

3. The method according to claim 2, It is characterized in that The method further comprises: The first interactive text and the first emoticon package are displayed in the chat interface.

4. The method according to claim 2, It is characterized in that The obtaining of the first virtual image of the first object comprises: Displaying a character personality page, wherein the character personality page displays resources corresponding to the initial character personality of the first object; In response to a triggering operation of the picture upload function, obtaining a person picture of the first object; A first virtual image of the first object is obtained according to the character picture of the first object and the resources corresponding to the initial character personality.

5. The method according to claim 4, It is characterized in that The character personality display page includes: Displaying a first personality test page, wherein the first personality test page displays at least one first personality test question, wherein the first personality test question is used to test and obtain an initial personality of the first object; Based on the at least one first personality test question, displaying a first test result page, wherein the first test result page displays the personality test result of the first subject; In response to a triggering operation of the personality generation function, generating an initial personality of the first object; The character page is displayed according to the initial character of the first object.

6. The method according to any one of claims 1 to 5, It is characterized in that The method of responding to the triggering operation of the chat function, and displaying at least one interactive text corresponding to the first character personality according to the first character personality of the first object when facing the at least one second object, comprises: In response to a triggering operation of the chat function, obtaining a first character of the first object; Based on at least one interactive content displayed in the chat interface, determining a first interactive content in the at least one interactive content, the first interactive content being an interactive content whose corresponding interaction time in the at least one interactive content is before a first time and adjacent to the first time, the first time being the time when the chat function is triggered; Generate at least one interactive text according to the first interactive content and the first character's personality, where the at least one interactive text is the first object's reply to the first interactive content; The at least one interactive text is displayed.

7. The method according to claim 6, It is characterized in that The obtaining of the first character of the first object includes any of the following: Acquire a character of a third object and an object identity of the third object relative to the first object; acquire a first character of the first object according to the character of the third object and the object identity of the third object relative to the first object, wherein the third object is any second object among the at least one second object; Obtain keywords; and obtain the first character of the first object based on the keywords.

8. The method according to claim 7, It is characterized in that The obtaining of the character of the third object includes any of the following: Obtaining a character description of the third object, and determining the character of the third object according to the character description of the third object, wherein the character description of the third object is a description of the character of the third object by the first object; A second personality test page is displayed, wherein at least one second personality test question is displayed on the second personality test page, and based on the at least one second personality test question, the character of the third object is generated, and the second personality test question is used to test and obtain the character of the third object.

9. The method according to any one of claims 1 to 5, It is characterized in that The method of displaying at least one interactive text corresponding to the first character personality according to the first character personality of the first object when facing the at least one second object in response to the triggering operation of the chat function includes: In response to a triggering operation of the chat function, obtaining a first character of the first object; Based on the absence of interactive content in the chat interface, generating at least one interactive text according to a first time and the first character's personality, the first time being the time when the chat function is triggered, and the at least one interactive text being the interactive text of the first object at the first time; The at least one interactive text is displayed.

10. The method according to any one of claims 1 to 5, It is characterized in that A text input box is displayed in the chat interface; the method further includes: In response to a triggering operation of the text optimization function, obtaining text content input in the text input box; Optimizing the text content inputted into the text input box to obtain at least one optimized text content; In response to a trigger operation for any optimized text content, the optimized text content is sent to a terminal device corresponding to the at least one second object.

11. The method according to claim 10, It is characterized in that The method further comprises: In response to a triggering operation on any optimized text content, obtaining a first virtual image of the first object; generating a second emoticon package according to the first virtual image and any of the optimized text contents, wherein the second emoticon package corresponds to any of the optimized text contents and includes the first virtual image; The second emoticon package is sent to a terminal device corresponding to the at least one second object.

12. The method according to claim 11, It is characterized in that The method further comprises: Display any optimized text content and the second emoticon package in the chat interface.

13. The method according to any one of claims 1 to 5, It is characterized in that The method further comprises: Based on the interactive content at the reference position in the chat interface being the interactive content sent by the first object, in response to a triggering operation of a single-player comic generation function, a third emoticon package is generated according to the interactive content at the reference position and the first virtual image of the first object, and the third emoticon package is sent to a terminal device corresponding to the at least one second object, wherein the third emoticon package corresponds to the interactive content at the reference position and includes the first virtual image; Based on the fact that the interactive content located at the reference position in the chat interface is not the interactive content sent by the first object, in response to the triggering operation of the single-player comic generation function, reply content of the interactive content at the reference position is generated according to the interactive content at the reference position and the personality of the first character, a fourth emoticon package is generated according to the reply content and the first virtual image, and the fourth emoticon package is sent to the terminal device corresponding to the at least one second object, the fourth emoticon package corresponds to the reply content, and the fourth emoticon package includes the first virtual image.

14. The method according to claim 13, It is characterized in that After generating the third expression package according to the interactive content of the reference position and the first virtual image of the first object, the method further includes: Displaying the third emoticon package in the chat interface; After generating a fourth emoticon package according to the reply content and the first virtual image, the method further includes: The fourth emoticon package is displayed in the chat interface.

15. The method according to any one of claims 1 to 5, It is characterized in that The method further comprises: Based on the display of multiple interactive contents in the chat interface, in response to the triggering operation of the multi-person comic generation function, determining, from the multiple interactive contents, second interactive contents whose interaction time is within a target time period, wherein the target time period is determined based on the triggering time of the multi-person comic generation function; generating a fifth emoticon package according to the second interactive content, wherein the fifth emoticon package corresponds to the second interactive content and includes a virtual image of an object of each second interactive content; The fifth emoticon package is sent to a terminal device of the at least one second object.

16. The method according to claim 15, It is characterized in that The step of generating a fifth emoticon package according to the second interactive content includes: Acquire a virtual image of an object sending each second interactive content; The fifth emoticon package is generated according to each of the second interactive contents and the virtual image of the object to which the second interactive contents are sent.

17. The method according to any one of claims 1 to 5, It is characterized in that The chat interface displays multiple interactive contents, and the method further includes: In response to a triggering operation on a reference interactive content among the plurality of interactive contents, generating a multimedia resource according to the reference interactive content, the multimedia resource including the reference interactive content; The multimedia resource is shared.

18. A social interaction device, It is characterized in that The device comprises: A display module, configured to display a chat interface between a first object and at least one second object; The display module is further configured to, in response to a triggering operation of the chat function, display at least one interactive text corresponding to the first character personality according to the first character personality of the first object when facing the at least one second object; A sending module is used to send the first interactive text to a terminal device corresponding to the at least one second object in response to a triggering operation on the first interactive text in the at least one interactive text.

19. A computer device, It is characterized in that The computer device includes a processor and a memory, wherein the memory stores at least one program code, and the at least one program code is loaded and executed by the processor so that the computer device implements the social interaction method as described in any one of claims 1 to 17.

20. A computer-readable storage medium, It is characterized in that The computer-readable storage medium stores at least one program code, and the at least one program code is loaded and executed by a processor so that a computer implements the social interaction method according to any one of claims 1 to 17.

Images