Chat message reading method and device, electronic equipment and storage medium

Abstract

The invention relates to the technical field of Internet, in particular to a chat message reading method and device, electronic equipment and a storage medium. The method comprises the following steps: presenting a chat interface of a target dialogue group, the chat interface being used for displaying chat messages published in the target dialogue group; in response to a selection operation triggered based on the chat interface, obtaining at least one selected target chat message; in response to a message deduction operation triggered for the target dialogue group, playing a message deduction video generated based on the at least one target chat message, the message deduction video including a chat scene generated based on virtual objects associated with release objects of the at least one target chat message; the chat content involved in the chat scene is generated based on the at least one target chat message. According to the method, the message deduction video can be generated based on object selection and the target chat message, and the chat message reading efficiency can be improved on the premise of effectively reading the chat message.

Description

Background Art

[0002] Group chat is a basic function of social products. For example, some instant messaging software can be used for group chat among acquaintances, and some instant messaging software can be used for making friends with strangers.

[0003] As the social needs of most people are constantly expanding, each person has joined one or more social groups in various instant messaging software, and various new messages are generated in social groups every day. When a person views group messages, since each social group has a lot of historical messages, and there is a lot of useless information in these historical messages, the person cannot quickly view each message one by one, nor can he quickly skip or ignore them, resulting in missing some information that he is interested in, related to his personal interests, or related to people he pays special attention to, etc.

[0004] In summary, how to improve the reading efficiency of chat messages under the premise of effectively reading chat messages is an urgent problem to be solved. Summary of the invention

[0005] The embodiments of the present application provide a chat message reading method, device, electronic device and storage medium, which are used to improve the reading efficiency of chat messages while effectively reading the chat messages.

[0006] A method for reading a chat message provided by an embodiment of the present application includes:

[0007] Presenting a chat interface of a target conversation group, wherein the chat interface is used to display chat messages posted in the target conversation group;

[0008] In response to a selection operation triggered based on the chat interface, obtaining at least one selected target chat message;

[0009] In response to a message interpretation operation triggered for the target conversation group, a message interpretation video generated based on the at least one target chat message is played, the message interpretation video comprising: a chat scene generated based on virtual objects associated with each of the publishing objects of the at least one target chat message; and chat content involved in the chat scene generated based on the at least one target chat message.

[0010] Another chat message reading method provided by an embodiment of the present application includes:

[0011] Acquire at least one target chat message, and a timestamp and a publishing object corresponding to each of the at least one target chat message, wherein the at least one target chat message is obtained by the client in response to a selection operation triggered by a chat interface based on a target conversation group, and is selected from chat messages displayed on the chat interface;

[0012] Based on the at least one target chat message, and the obtained at least one timestamp and publishing object, obtaining a message interpretation video including a chat scene generated based on a virtual object associated with each of the at least one publishing object;

[0013] The message interpretation video is fed back to the client, so that the client plays the message interpretation video after responding to the message interpretation operation triggered for the target conversation group.

[0014] An embodiment of the present application provides a chat message reading device, comprising:

[0015] A presenting unit, used for presenting a chat interface of a target conversation group, wherein the chat interface is used for displaying chat messages posted in the target conversation group;

[0016] A selection unit, configured to obtain at least one selected target chat message in response to a selection operation triggered based on the chat interface;

[0017] An interpretation unit is used to play a message interpretation video generated based on the at least one target chat message in response to a message interpretation operation triggered for the target conversation group, wherein the message interpretation video includes: a chat scene generated based on virtual objects associated with respective publishing objects of the at least one target chat message; and chat content involved in the chat scene is generated based on the at least one target chat message.

[0018] Optionally, the at least one target chat message belongs to at least one topic content, and virtual objects corresponding to each topic content are gathered in the same interactive area in the chat scene.

[0019] Optionally, each interactive area corresponds to a chat scene background related to the topic content; then the device further includes:

[0020] An adjustment unit, configured to change the chat scene background of the interactive area corresponding to the first topic content in the at least one topic content in response to a background change operation triggered by the first topic content in the at least one topic content;

[0021] Among them, the replaced chat scene background is: selected from the preset scene backgrounds, or generated based on the input key information.

[0022] Optionally, each interactive area corresponds to a related audio control; the device further includes:

[0023] An audio control unit, used to play the audio corresponding to the second topic content in the at least one topic content in response to an audio playback operation triggered by an audio control for the second topic content; the audio is a chat voice generated based on a target chat message related to the second topic content.

[0024] Optionally, the device further comprises:

[0025] A screen updating unit, configured to update a display screen corresponding to the interactive area in the message interpretation video in response to an interactive operation on the interactive area corresponding to the third topic content in the at least one topic content;

[0026] The interactive operation includes at least one of a zooming operation and a sliding switching operation.

[0027] Optionally, the chat content involved in the chat scene is presented as an animation element corresponding to a message type of the at least one target chat message;

[0028] If the interactive operation is a zoom operation in a scaling operation, then before performing the zoom operation, the animation element includes only at least one of the following:

[0029] Subtitle elements corresponding to text messages, speech bubble elements corresponding to text messages converted into speech, speech bubble elements corresponding to voice messages, and subtitle elements corresponding to voice messages converted into text.

[0030] Optionally, the message interpretation video also includes animation effects that characterize the chat atmosphere of the virtual object, and the animation effects are animation effects for the virtual object or the interactive area.

[0031] Optionally, the chat interface further includes a message interpretation control; the message interpretation control is in a non-playable state;

[0032] Then the selection unit is specifically used for:

[0033] In response to a selection operation triggered by the message interpretation control, determining the at least one target chat message selected in the message selection state, and updating the message interpretation control to a playable state;

[0034] Then the deduction unit is specifically used for:

[0035] In response to a message interpretation operation triggered by the message interpretation control, the chat interface jumps to a message interpretation interface, and a message interpretation video generated based on the at least one target chat message is played on the message interpretation interface.

[0036] Optionally, the selection unit is specifically used to:

[0037] In response to a selection operation triggered based on the message interpretation control, presenting the number of selectable chat messages and a select all control, as well as a selection control corresponding to each selectable chat message;

[0038] In response to a selection operation triggered based on the select all control or the selection control, determining the at least one target chat message selected in the message selection state.

[0039] Optionally, the device further comprises:

[0040] A first response unit, configured to respond to a small window display operation triggered for the message interpretation interface, and present the message interpretation interface through a small window in the chat interface;

[0041] The message interpretation video is played through the message interpretation interface.

[0042] Optionally, the device further comprises:

[0043] The second response unit is used to present a historical video list in response to a historical video viewing operation triggered based on the chat interface, and the historical video list includes: each message interpretation video currently generated for the target dialogue group.

[0044] Optionally, the device further comprises:

[0045] A third response unit, configured to respond to a target operation triggered on the message interpretation video and control the playing of the message interpretation video based on the target operation;

[0046] The target operation includes at least one of a pause operation and a double-speed operation.

[0047] Optionally, the body movements of each virtual object in the message interpretation video are obtained by performing content recognition on a target chat message corresponding to the corresponding virtual object.

[0048] Optionally, the message interpretation video is a video that simulates a chat scene between corresponding publishing objects based on virtual objects in a three-dimensional metaverse space.

[0049] Optionally, the device further comprises:

[0050] A first setting unit, configured to present a message setting interface of the target conversation group in response to a viewing operation on the message setting interface of the target conversation group before the selection unit responds to a selection operation triggered based on the chat interface;

[0051] In response to an interpretation start operation triggered based on the message setting interface, an interpretation function for the chat message in the target dialogue group is started, and the interpretation function supports generating a corresponding message interpretation video based on the chat message.

[0052] Optionally, the device further comprises:

[0053] A second setting unit, configured to present a message setting interface for the target conversation group in response to a viewing operation on the message setting interface for the target conversation group;

[0054] In response to an image setting operation triggered by the target object based on the message setting interface, jumping from the message setting interface to the image setting interface;

[0055] The target object is determined based on a virtual image set in the image setting interface, and the virtual image is used as a virtual object associated with the target object.

[0056] An embodiment of the present application provides a chat message reading device, comprising:

[0057] an acquisition unit, configured to acquire at least one target chat message, and a timestamp and a publishing object corresponding to each of the at least one target chat message, wherein the at least one target chat message is obtained by the client in response to a selection operation triggered by a chat interface based on a target conversation group, and is selected from chat messages displayed on the chat interface;

[0058] A generating unit, configured to obtain, based on the at least one target chat message, and the obtained at least one timestamp and publishing object, a message interpretation video including a chat scene generated based on a virtual object associated with each of the at least one publishing object;

[0059] A feedback unit is used to feed back the message interpretation video to the client, so that the client plays the message interpretation video after responding to the message interpretation operation triggered for the target dialogue group.

[0060] Optionally, if the message interpretation video is a video that simulates a chat scene between corresponding publishing objects based on virtual objects in a three-dimensional metaverse space, the generating unit is further used to:

[0061] Encoding the message deduction video into a data format supported by the Metaverse platform;

[0062] The encoded message interpretation video is imported into the Metaverse platform and associated with the scene elements in the Metaverse platform to present the message interpretation video as a video that simulates the chat scene between corresponding publishing objects based on virtual objects in a three-dimensional Metaverse space. The scene elements are: elements created in a three-dimensional Metaverse space based on the Metaverse platform for displaying the message interpretation video.

[0063] Optionally, the at least one target chat message belongs to at least one topic content;

[0064] Then the generating unit is specifically used for:

[0065] Determining the topic content to which each target chat message belongs by performing topic classification on the at least one target chat message;

[0066] Based on each target chat message belonging to the same topic content and the corresponding timestamp, generating video screen content representing the chat scene corresponding to the topic content;

[0067] In each of the video screen contents, a virtual object associated with the publishing object of the corresponding target chat message is added to integrate and generate the message interpretation video. In the message interpretation video, the virtual objects corresponding to each topic content are gathered in the same interactive area in the chat scene.

[0068] Optionally, the generating unit is specifically used for:

[0069] For each virtual object, determining the body movement of the virtual object by performing content recognition on the target chat message corresponding to the virtual object;

[0070] In each of the video screen contents, a virtual object associated with the publisher of the corresponding target chat message is added in combination with the determined body movements, and the message interpretation video is integrated to generate the message interpretation video.

[0071] Optionally, the generating unit is specifically used for:

[0072] For each virtual object, determining an animation effect for the virtual object or the interactive area by performing content recognition on a target chat message corresponding to the virtual object;

[0073] In each of the video screen contents, a virtual object associated with the publisher of the corresponding target chat message is added in combination with a determined animation effect, and the message interpretation video is integrated and generated.

[0074] An electronic device provided by an embodiment of the present application includes a processor and a memory, wherein the memory stores a computer program, and when the computer program is executed by the processor, the processor executes the steps of any one of the above-mentioned chat message reading methods.

[0075] An embodiment of the present application provides a computer-readable storage medium, which includes a computer program. When the computer program is run on an electronic device, the computer program is used to enable the electronic device to execute the steps of any one of the above-mentioned chat message reading methods.

[0076] An embodiment of the present application provides a computer program product, which includes a computer program, and the computer program is stored in a computer-readable storage medium; when a processor of an electronic device reads the computer program from the computer-readable storage medium, the processor executes the computer program, so that the electronic device performs the steps of any one of the above-mentioned chat message reading methods.

[0077] The beneficial effects of this application are as follows:

[0078] The embodiment of the present application provides a method, device, electronic device and storage medium for reading chat messages. In the embodiment of the present application, when the subject wants to quickly read the chat messages posted in the target conversation group, there is no need to browse them one by one. Just select the target chat message that you want to carefully view, and trigger the message interpretation operation to visualize the selected target chat message for dynamic interpretation, and automatically interpret and play the historical messages in the target conversation group, which not only increases the fun, but also focuses on the topic content that the subject is concerned about, or information related to his own interests or people he pays special attention to, etc., to avoid wasting too much time on topics that are not of interest, and on the premise of ensuring that the subject effectively reads the chat message, the reading efficiency of the subject for the chat message can be improved. In addition, this convenient experience and interesting expression can also increase the object's usage viscosity and dissemination rate to a certain extent.

[0079] Other features and advantages of the present application will be described in the following description, and partly become apparent from the description, or be understood by practicing the present application. The purpose and other advantages of the present application can be realized and obtained by the structures specifically pointed out in the written description, claims, and drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0080] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0081] Figure 1An optional schematic diagram of an application scenario in an embodiment of the present application;

[0082] Figure 2 A schematic diagram of an implementation flow of a chat message reading method in an embodiment of the present application;

[0083] Figure 3 A schematic diagram of a message setting interface in an embodiment of the present application;

[0084] Figure 4 A schematic diagram of a chat interface in an embodiment of the present application;

[0085] Figure 5 A schematic diagram of another chat interface in an embodiment of the present application;

[0086] Figure 6 A schematic diagram of a virtual image setting process in an embodiment of the present application;

[0087] Figure 7 A schematic diagram of a message interpretation interface in an embodiment of the present application;

[0088] Figure 8 A schematic diagram of a scene change setting interface in an embodiment of the present application;

[0089] Fig. 9 Schematic diagram of three preset scene backgrounds listed in the embodiments of the present application;

[0090] Fig.10 A schematic diagram of another message interpretation interface in an embodiment of the present application;

[0091] Fig.11 This is a schematic diagram of display screen changes before and after an interactive operation is performed in an embodiment of the present application;

[0092] Fig.12 A schematic diagram of playing a video at a multiple speed in an embodiment of the present application;

[0093] Fig.13 A schematic diagram of focusing on video content in an embodiment of the present application;

[0094] Fig.14 A schematic diagram of a display style of a video element in an embodiment of the present application;

[0095] Fig.15 A schematic diagram of an animation special effect for a single virtual object in an embodiment of the present application;

[0096] Fig.16 A schematic diagram of an animation special effect for a single interactive area in an embodiment of the present application;

[0097] Fig.17 A schematic diagram of a body movement in an embodiment of the present application;

[0098] Fig.18 is a schematic diagram of another body movement in an embodiment of the present application;

[0099] Fig.19 A schematic diagram of a small window display in an embodiment of the present application;

[0100] Fig. 20 A schematic diagram of a historical video list in an embodiment of the present application;

[0101] Fig.21 This is a schematic diagram of an implementation flow of another method for reading chat messages in an embodiment of the present application;

[0102] Fig. 22 A schematic diagram of a timing flow of interaction between a server and a client in an embodiment of the present application;

[0103] Fig.23 A schematic diagram of the structure of a chat message reading device in an embodiment of the present application;

[0104] Fig.24 A schematic diagram of the structure of another chat message reading device in an embodiment of the present application;

[0105] Fig.25 A schematic diagram of a hardware structure of an electronic device to which an embodiment of the present application is applied;

[0106] Fig.26 The present invention is a schematic diagram of the hardware structure of another electronic device to which the embodiments of the present application are applied. DETAILED DESCRIPTION

[0107] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the technical solution of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the technical solution of the present application, rather than all of the embodiments. Based on the embodiments recorded in the application documents, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the technical solution of the present application.

[0108] The following is an introduction to some concepts involved in the embodiments of the present application.

[0109] Message interpretation: refers to interpreting the chat messages posted between objects in the chat interface based on dynamic video. For example, by dynamically interpreting the conversation between virtual objects, historical chat messages in the conversation group can be simulated. Furthermore, in the process of interpreting the conversation, subtitle prompts, chat scene backgrounds, body movements for virtual objects, and animation effects that represent the chat atmosphere can be added to enhance the fun of the video.

[0110] Content recognition: refers to the recognition, judgment, and classification of information content obtained on the Internet. The objects of recognition mainly include text, images, audio, video, etc. The purpose of recognition is to determine whether it is the target content required.

[0111] Artificial Intelligence Generated Content (AIGC): refers to the use of artificial intelligence technology to generate content. AIGC is also considered to be a new content production method after User-created Content (UGC) and Professional Generated Content (PGC). Artificial Intelligence (AI) painting, AI writing, etc. are all branches of AIGC.

[0112] Virtual object: It can be understood as a virtual image used to simulate a chat conversation between publishing objects. In the message interpretation video, a virtual object represents a result of anthropomorphizing a publishing object. The virtual object can be static or dynamic (can perform certain body movements). In the embodiment of the present application, the virtual object can specifically be a virtual person, virtual animal, virtual plant, etc., which can be set by the corresponding publishing object, or it can be a default virtual object, which is not specifically limited in this article.

[0113] Metaverse: A virtual world constructed by humans using digital technology that maps or transcends the real world and can interact with the real world. It is a digital living space with a new social system. The metaverse can be cross-defined from four aspects: time and space, authenticity, independence, and connectivity.

[0114] Small window display: the window of a certain interface will be reduced and appear on the screen as a smaller window. It can be presented together with other interfaces to avoid switching back and forth, which can greatly improve usage efficiency.

[0115] Topics and tags: Both are obtained by classifying the content of chat messages. Tags are more fine-grained classifications than topics. For example, tags can be A stars, B movies, etc., C travel locations, D travel locations, self-driving tours, group tours, etc., while topics can be entertainment, travel, etc.

[0116] The embodiments of the present application relate to AI and machine learning technology (Machine Learning, ML), and are designed based on computer vision technology and machine learning in artificial intelligence.

[0117] Artificial intelligence technology mainly includes computer vision technology, natural language processing (NLP) technology, and machine learning / deep learning, autonomous driving, smart transportation and other major directions. With the research and progress of artificial intelligence technology, artificial intelligence has been studied and applied in many fields, such as common smart homes, smart customer service, virtual assistants, smart speakers, smart marketing, unmanned driving, autonomous driving, robots, smart medical care, etc. It is believed that with the development of technology, artificial intelligence will be applied in more fields and play an increasingly important role. The reading method of the chat message in the embodiment of the present application can combine artificial intelligence with the generation task of the message interpretation video in these fields to intelligently generate a message interpretation video that can dynamically interpret the content of the chat dialogue between objects.

[0118] Deep learning is a machine learning method in the field of artificial intelligence, which is based on an artificial neural network model. Deep learning processes data in layers, from simple feature extraction to complex representation, and uses a large amount 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. For example, when the target chat message is classified into topics in the embodiment of the present application, it further involves the processing of information such as pictures, videos, and voices. The processing of this information can be combined with the above-mentioned computer video, natural language processing, speech recognition and other technologies to improve the efficiency of message processing.

[0119] Optionally, in an embodiment of the present application, the generation of message interpretation videos can be achieved based on artificial intelligence generated content (AI Generated Content, AIGC) technology, that is, using artificial intelligence technology to generate content. The basic principle is to use "natural language processing", "speech recognition", "machine learning", "deep learning" and other technologies in artificial intelligence technology to analyze, learn and simulate large amounts of language data, thereby realizing the understanding and generation of natural language.

[0120] The following is a brief introduction to the design ideas in the embodiments of the present application:

[0121] Groups have become an important form of existence in social networks and one of the main places for many departments, organizations and groups to issue notices. On this basis, whether it is socializing with acquaintances or making friends with strangers, it can be achieved through group chats.

[0122] As the social needs of most people are constantly expanding, each person has joined one or more social groups in various instant messaging software, and various new messages are generated in social groups every day. When a person views group messages, since each social group has a lot of historical messages, and there is a lot of useless information in these historical messages, the person cannot quickly view each message one by one, nor can he quickly skip or ignore them, resulting in missing some information that he is interested in, related to his personal interests, or related to people he pays special attention to, etc.

[0123] For example, many people in the group share videos, and some share articles. There are many types of content and topics. For example, 20 people in the group discussed multiple topics at the same time (21:00-23:00 on Friday night), such as Topic 1: Discussion on team-building activities on Saturday afternoon. Some said that they could do frisbee, barbecue, camping, etc., and they needed to prepare some props, etc.; Topic 2: About the selection of Father's Day gifts, everyone discussed the selection of gifts for old fathers; Topic 3: Discussion on hot gossip topics, such as the xx incident, and each expressed some personal opinions; Topic 4: About a certain disease, some classmates in the group were infected with the disease, which triggered some discussions on the causes and symptoms of the disease; there may even be interspersed topics 5, 6, etc.; and some classmates joined different topics and discussed them at the same time. Everyone was discussing three or four different topics at the same time. For those who did not participate in the discussion and did not have time to read the historical messages, there were dozens or hundreds of historical messages, which put a lot of reading pressure, and also brought some possibilities of wasting time. After reading, they found that it had nothing to do with them, and they were not interested in it and it was not valuable.

[0124] In summary, how to improve the reading efficiency of chat messages under the premise of effectively reading chat messages is an urgent problem to be solved.

[0125] In view of this, the embodiment of the present application proposes a method, device, electronic device and storage medium for reading chat messages. In the embodiment of the present application, when the object wants to quickly read the chat messages posted in the target dialogue group, there is no need to browse them one by one. It only needs to select the target chat message that it wants to view carefully, and by triggering the message interpretation operation, the selected target chat message can be classified according to the topic, and a visual dynamic interpretation is performed. The historical messages in the target dialogue group are automatically interpreted and played, which not only increases the fun, but also focuses on the topic content that the object is concerned about, or information related to one's own vital interests or people who are of particular concern to oneself, etc., to avoid wasting too much time on topics that are not of interest, and on the premise of ensuring that the object effectively reads the chat message, the object's reading efficiency for the chat message can be improved. In addition, this convenient experience and interesting expression can also increase the object's usage viscosity and dissemination rate to a certain extent. In addition, the present application can also be combined with metaverse digital technology to present an interactive three-dimensional scene.

[0126] The preferred embodiments of the present application are described below in conjunction with the drawings in the specification. It should be understood that the preferred embodiments described herein are only used to illustrate and explain the present application, and are not used to limit the present application. In addition, the embodiments and features in the embodiments of the present application may be combined with each other if there is no conflict.

[0127] like Figure 1 As shown, it is a schematic diagram of an application scenario of an embodiment of the present application. The application scenario diagram includes two terminal devices 110 and a server 120.

[0128] In the embodiment of the present application, the terminal device 110 includes but is not limited to mobile phones, tablet computers, laptop computers, desktop computers, e-book readers, intelligent voice interaction devices, smart home appliances, vehicle-mounted terminals and other devices; a client with a chat function can be installed on the terminal device, and the client can be a software (such as a browser, chat software, short video software, or any software with a chat function), or a web page, a small program, etc. The server 120 is a background server corresponding to the software or web page, small program, etc., or a server specifically used for reading and processing chat messages, which is not specifically limited in the present application. The server 120 can be an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content delivery networks (CDN), and basic cloud computing services such as big data and artificial intelligence platforms.

[0129] It should be noted that the chat message reading method in each embodiment of the present application can be executed by an electronic device, and the electronic device can be a terminal device 110 or a server 120, that is, the method can be executed by the terminal device 110 or the server 120 alone, or can be executed by the terminal device 110 and the server 120 together. For example, when the terminal device 110 and the server 120 are executed together, assuming that an instant messaging client is installed on the terminal device 110, the object can view the chat interface of the target conversation group through the instant messaging client, and the chat interface can display the chat messages posted in the target conversation group. When the object wants to read these chat messages quickly and efficiently, the object can first select the target chat message that he wants to read carefully, and then trigger the message interpretation operation. The instant messaging client sends a request to the server 120 through the terminal device 110. After the server 120 obtains the target chat message selected by the object, and the timestamps and publishing objects corresponding to each of the target chat messages, based on this information, a message interpretation video containing a chat scene generated based on the virtual objects associated with each publishing object is obtained, and the message interpretation video is fed back to the instant messaging client through the terminal device 110. On the instant messaging client side, the message interpretation video is played to the object.

[0130] In an optional implementation, the terminal device 110 and the server 120 may communicate with each other via a communication network.

[0131] In an optional implementation, the communication network is a wired network or a wireless network.

[0132] It should be noted that Figure 1 The figure is only an example. In fact, the number of terminal devices and servers is not limited and is not specifically limited in the embodiments of the present application.

[0133] In an embodiment of the present application, when there are multiple servers, the multiple servers can form a blockchain, and the servers are nodes on the blockchain; as in the chat message reading method disclosed in the embodiment of the present application, the data involved in reading the chat messages can be saved on the blockchain, for example, chat messages, message interpretation videos, etc.

[0134] In addition, the embodiments of the present application can be applied to various scenarios, including but not limited to cloud technology, artificial intelligence, smart transportation, assisted driving and other scenarios.

[0135] It can be understood that in the specific implementation of the present application, user data is involved, such as chat messages between objects, the objects to which chat messages are published, virtual objects and other related data. When the above embodiments of the present application are applied to specific products or technologies, user permission or consent is required, and the collection, use and processing of relevant data need to comply with relevant laws, regulations and standards of relevant countries and regions.

[0136] The following describes the chat message reading method provided by the exemplary embodiment of the present application in combination with the application scenarios described above and with reference to the accompanying drawings. It should be noted that the above application scenarios are only shown to facilitate understanding of the spirit and principles of the present application, and the implementation of the present application is not limited in this regard.

[0137] See also Figure 2 As shown, it is an implementation flow chart of a chat message reading method provided in an embodiment of the present application. Taking the client as the execution subject as an example, the specific implementation process of the method is as follows:

[0138] S21: The client presents a chat interface of the target conversation group, where the chat interface is used to display chat messages posted in the target conversation group.

[0139] In the embodiment of the present application, the target conversation group may be a group including at least two objects, or may be a conversation group consisting of two objects in a one-to-one chat, which is not specifically limited herein. When the target conversation group is a group, the chat interface of the target conversation group is a group chat interface; when the target conversation group is a one-to-one chat group of object A and object B, the chat interface of the target conversation group is a one-to-one chat interface between object A and object B.

[0140] The following uses the target conversation group as an example to illustrate the method for reading chat information in the embodiment of the present application.

[0141] In the embodiment of the present application, the client side may be set to enable the interpretation function by default. After enabling the function, the corresponding message interpretation video may be generated based on the chat messages between the objects. Alternatively, the target object may set it for the conversation group. For example, if the target object wants to generate a message interpretation video based on the chat messages in the target conversation group, the interpretation function for the target conversation group must be enabled before selecting the target chat message.

[0142] The target object is any member of the target dialogue group.

[0143] In an optional implementation, the target object can enable the deduction function based on the message setting interface, and the implementation is as follows:

[0144] First, in response to the target object's viewing operation on the message setting interface of the target conversation group, the client presents the message setting interface of the target conversation group.

[0145] Furthermore, the client responds to the interpretation start operation triggered by the target object based on the message setting interface, and starts the interpretation function for the chat message in the target dialogue group. The interpretation function supports the generation of corresponding message interpretation videos based on the chat message.

[0146] In an embodiment of the present application, a message interpretation control may be set in the message setting interface, and the object may turn on or off the interpretation function through the message interpretation control.

[0147] Take the target conversation group as "xxx communication group" and the message interpretation control as the AI ​​interpretation button as an example. Figure 3 As shown, it is a schematic diagram of a message setting interface in an embodiment of the present application. Figure 3 S31 shown on the left and S32 shown on the right are examples of an AI interpretation button in an embodiment of the present application, wherein S31 indicates that the interpretation function is in an off state, and S32 indicates that the interpretation function is in an on state.

[0148] When the interpretation function is turned on, the target object can perform message interpretation operations on the chat messages posted in the target conversation group.

[0149] In the above implementation, after the AI ​​interpretation function is turned on, content recognition can be performed by default, and intelligent video display can be started by default. On this basis, historical messages can be interpreted by one-click intelligent video to improve the message reading efficiency of the object.

[0150] S22: The client obtains at least one selected target chat message in response to a selection operation triggered based on the chat interface.

[0151] S23: In response to the message interpretation operation triggered for the target conversation group, the client plays a message interpretation video generated based on at least one target chat message, wherein the message interpretation video includes: a chat scene generated based on virtual objects associated with the respective publishing objects of the at least one target chat message; and chat content involved in the chat scene, which is generated based on the at least one target chat message.

[0152] In an embodiment of the present application, when the message interpretation function is turned on, the target object can select the target chat message for which the message interpretation is desired from the chat interface.

[0153] It should be noted that in the embodiment of the present application, the target object does not need to carefully or read the content of the message itself one by one when selecting a message, and the selection process does not consume too much time. Specifically, when the target object selects a message, it can be quickly selected by gestures, and can also be quickly selected by other methods, which are not specifically limited in this article.

[0154] Specifically, when the target object turns on the interpretation function, a message interpretation control can be presented in the chat interface to prompt the target object to select the target chat message for message interpretation based on the message interpretation control.

[0155] Alternatively, in addition to the above-mentioned prompting methods, prompts may also be provided in the form of text, text + controls, etc., such as a prompt in the chat interface that "the interpretation function has been turned on, and chat messages can be selected and interpreted in xx manner", etc., which is not specifically limited in this article. Among them, "xx manner" refers to the method in which the target object selects the target chat message from the chat interface, such as a tap-and-swipe gesture: that is, swiping down or up from a certain chat message, and the chat messages contained in the swiped area can be used as the target chat message; another example is two-finger swiping; another example is presenting a selection control before each chat message, and selecting based on the selection control, etc., which is not specifically limited in this article.

[0156] See also Figure 4 As shown, it is a schematic diagram of a chat interface in an embodiment of the present application. When the interpretation function is turned on, the following can be presented: Figure 4 The message interpretation control shown in S41 in the figure, the target object can select the target chat message and perform the message interpretation operation based on the message interpretation control.

[0157] An optional implementation is that the chat interface further includes a message interpretation control; the message interpretation control is in a non-playable state; at this time, S22 can be implemented according to the following process:

[0158] The client determines at least one selected target chat message in the message selection state in response to the selection operation triggered by the target object based on the message interpretation control, and updates the message interpretation control to a playable state.

[0159] Still Figure 4 As shown in the example, Figure 4 The message interpretation control shown in S41 is gray, indicating a non-playable state. In the embodiment of the present application, before the target object selects the target chat message, the message interpretation control can remain in a non-playable state, indicating that the target chat message can be selected based on the message interpretation control and a message interpretation video can be generated.

[0160] After the target object selects the target chat message, or after the target object triggers a selection operation based on the message interpretation control, the message interpretation control can be updated to a playable state, such as Figure 4 As shown in S42, in this case, the target object can continue to trigger the message interpretation operation based on the message interpretation control.

[0161] That is, S23 may be implemented according to the process shown below:

[0162] The client responds to the message interpretation operation triggered by the target object through the message interpretation control, jumps from the chat interface to the message interpretation interface, and plays a message interpretation video generated based on at least one target chat message on the message interpretation interface.

[0163] In the embodiment of the present application, the message selection state means: the state in which the object is supported to select the target chat message. There are many ways to present the message selection state, for example, presenting a selection control before the chat message, presenting a text prompt, a voice prompt, etc., which are not specifically limited in this article.

[0164] Taking the method of presenting a selection control as an example, an optional implementation of S22 is:

[0165] In response to the selection operation triggered by the target object based on the message interpretation control, the client presents the number of selectable chat messages and the select all control, as well as the selection control corresponding to each selectable chat message. Furthermore, in response to the selection operation triggered by the target object based on the select all control or the selection control, the client determines at least one selected target chat message in the message selection state.

[0166] The target object can browse the chat interface and select a chat message from it. On this basis, the selectable chat messages are all messages starting from and after the chat message. Alternatively, the target object can slide the chat interface and select all messages after a certain area in the chat interface as selectable chat messages, etc., which are not specifically limited in this article.

[0167] In an embodiment of the present application, after the target object clicks (or other operations such as long pressing, which are not specifically limited in this article) the message interpretation control, the message selection state can be entered, and the selection control will be presented before each chat message (it can also be presented in other locations, such as after the chat message, which is not specifically limited in this article).

[0168] When the target object selects a chat message as a target chat message, the number of the target chat message and subsequent chat messages can be counted and presented in the relevant position of the select all control.

[0169] Still Figure 4 As shown in the example, the target object clicks Figure 4 The message interpretation control shown in S41 on the left side of the middle is expanded to present the message selection state. The target object can adjust the content presented in the chat interface by sliding (or dragging, etc.), such as adjusting to Figure 4 In the interface shown on the right side, the chat messages located below the expanded position of the rectangular area shown in S42 are all selectable chat messages, and the number of these chat messages is the number of messages to be selected. Figure 4 In the interface shown on the right, the number of items to be selected is 198. The 198 shown here refers to the total number of messages after "It has indeed been displayed for more than a year", including the message "It has indeed been displayed for more than a year", but does not include the messages that are not fully displayed at the top of the chat interface, such as image message 2.

[0170] In the embodiment of the present application, the selectable chat messages located below the rectangular area S42 can be adjusted by sliding or the like, and when adjusted to meet one's own needs, click "Select All" (i.e., a select all control in the present application) to select multiple chat messages as target chat messages at one time. This operation method is simple and can effectively improve the efficiency of the target object in selecting the target chat message.

[0171] See also Figure 5 As shown, it is a schematic diagram of another chat interface in the embodiment of the present application. If the target object clicks "Select All", the 198 chat messages located below the S50 area can be selected at one time as the target chat messages.

[0172] After selecting the target chat message, the target object clicks the message interpretation control in the playable state to automatically generate and play the corresponding message interpretation video based on the target chat message.

[0173] like Figure 5 As shown, after the object clicks the AI ​​interpretation button, Figure 5 The chat interface shown in the figure jumps to the message interpretation interface, and plays the message interpretation video in the message interpretation interface. Figure 7 As shown, this is an example of a message interpretation interface listed in an embodiment of the present application, which will be described in detail below and will not be repeated here.

[0174] In an embodiment of the present application, the target object can select unread information content through convenient gesture interaction, and based on content recognition technology and AIGC content generation technology, a visual video interpretation of the message content is presented to the object on the current interface, providing the object with a more intuitive, efficient and interesting way to obtain messages, thereby reducing the object's reading pressure.

[0175] In an embodiment of the present application, the message interpretation interface is used to play a message interpretation video, which includes: a chat scene generated based on virtual objects associated with each of the publishing objects of at least one target chat message, which is used to simulate a conversation between the corresponding publishing objects. The chat content involved in the chat scene is generated based on the message content of at least one target chat message.

[0176] That is, the message interpretation video in the embodiment of the present application at least includes a virtual object for representing the publishing object, which is a virtual image set by the publishing object itself, or a default virtual image, which is not specifically limited in this article. In the message interpretation video, these virtual objects represent the publishing object of the target chat message, and the message content of each target chat message will be reflected in the message interpretation video in a certain form (such as text, voice, image, video, etc.), providing the target object with a dynamic interpretation of the dialogue between the publishing objects. The experience, which not only increases the fun, but also focuses on the topic content that the target object is concerned about, or information related to their own interests or people they pay special attention to, etc., avoids wasting too much time on topics that are not of interest, and ensures that the target object effectively reads the chat message. The premise can improve the target object's reading efficiency for the chat message. In addition, this convenient experience and interesting expression can also increase the object's usage viscosity and dissemination rate to a certain extent.

[0177] It should be noted that in the embodiment of the present application, each publishing object corresponds to at least one virtual object. The virtual object can be understood as a virtual image used to simulate a chat dialogue between publishing objects. Specifically, it can be a virtual character, virtual animal, virtual plant, etc., which is not specifically limited in this article.

[0178] For each object, its own virtual image can be set in the following ways. Taking the target object in the target dialogue group as an example, an optional setting method is as follows:

[0179] The client responds to the target object's viewing operation on the message setting interface of the target conversation group by presenting the message setting interface of the target conversation group. Furthermore, the client responds to the target object's image setting operation triggered by the message setting interface by jumping from the message setting interface to the image setting interface. Finally, the client determines the virtual image set by the target object based on the image setting interface, and uses the virtual image as the virtual object associated with the target object.

[0180] In the embodiment of the present application, an image setting control can be set in the message setting interface, and the object can perform operations such as clicking and long pressing on the image setting control to trigger the image setting operation. In addition, the object can also trigger a preset gesture (such as pinching with two fingers, drawing a circle, etc.) or a voice command in the message setting interface to trigger the image setting operation, which is not specifically limited herein.

[0181] The following is an example based on control triggering:

[0182] See also Figure 6 As shown, it is a schematic diagram of a virtual image setting process in an embodiment of the present application. The target object can be clicked Figure 6The image setting control "My Group Image" shown in S61 on the left side of the image setting control is used to enter the image setting interface shown on the right side. In the image setting interface, the target object can set the virtual image by himself. Specifically, some template library resources can be provided in the image setting interface, such as virtual characters (as shown in S62) and some dressing objects that can dress up the virtual characters, such as clothing, jewelry, etc. (as shown in S63), which are not specifically limited in this article. The target object can customize his personal image in the group, and challenge himself by combining according to the template library resources to generate his own three-dimensional image.

[0183] Among them, only one virtual character is currently presented, and the target object can click the left arrow or the right arrow to view other virtual characters. In addition, the virtual characters can be further distinguished by gender, etc., which is not specifically limited in this article.

[0184] In the embodiment of the present application, each object can set its own corresponding virtual object in the target dialogue group in the above manner. The virtual objects set for the same object in different dialogue groups can be the same or different, and this document does not make any specific limitations.

[0185] In addition, when a virtual object is not set for an object, a predefined default image may be used as the virtual object corresponding to the object.

[0186] In the above implementation, each object can set its own corresponding virtual object, which can be used to simulate the object's participation in the chat in the message interpretation video, giving the object a more intuitive feeling, which helps to improve the object's stickiness while enhancing the fun.

[0187] It should be noted that the above is only a simple example of how an object triggers the process of generating a message interpretation video. The following is an example of the specific content of the message interpretation video in the embodiment of the present application and the operations related to the message interpretation video:

[0188] In an embodiment of the present application, after the target object triggers the message interpretation operation, the message interpretation interface can be entered, which can be used for AI to interpret visual chat scenes, and reorganize and classify the chat content according to the theme. The reorganized content includes text content, voice content, image content, video content, and external link sharing content of one or more publishing objects, etc. Based on content semantic recognition, it is converted into visual chat scenes of multiple single topic contents.

[0189] An optional implementation is: at least one target chat message belongs to at least one topic content, and the virtual objects corresponding to each topic content are gathered in the same interactive area in the chat scene.

[0190] In the embodiment of the present application, after the target object selects the target chat message and triggers the message interpretation operation, the client can send a video generation request to the server, requesting the server to generate a message interpretation video based on the target chat message selected by the target object and feedback it to the client. After the client receives the message interpretation video feedback from the server, it presents the video to the target object through the message interpretation interface.

[0191] See also Figure 7 As shown, it is a schematic diagram of a message interpretation interface in an embodiment of the present application. Figure 7 Four interactive areas are displayed, corresponding to four topic contents. These interactive areas have no obvious boundary distinction in the message interpretation interface. Of course, in order to more clearly reflect the interactive area, the boundary of the interactive area can also be reflected. This article does not make specific restrictions.

[0192] Specifically, the position of the interactive area corresponding to the topic content in the message interpretation video is not specifically limited in this article. It can be set randomly or based on the correlation between the topic content. For example, the interactive areas corresponding to the topic content with a higher correlation can be closer.

[0193] In addition, in the embodiment of the present application, virtual objects discussing the same topic content are gathered in the same interactive area. If the publishing object corresponding to the same virtual object has both referred to the discussion of topic 1 and participated in the discussion of topic 2, then the virtual object can exist in the interactive areas corresponding to the two topics at the same time. Alternatively, there may be a certain overlap between the two interactive areas, and the overlapping area includes the virtual objects corresponding to the publishing objects that participate in the discussion of the two topics at the same time, etc., which is not specifically limited in this article.

[0194] In the above implementation, by dividing the topic content and the corresponding interactive area, the topic content being discussed in the target discussion group can be conveyed to the target object more intuitively and efficiently.

[0195] In an optional implementation, each interactive area corresponds to a chat scene background related to the topic content; the present application also supports the object to change the chat scene background of the interactive area by itself:

[0196] The client responds to a background replacement operation triggered by a target object for a first topic content in at least one topic content, and replaces the chat scene background of the interactive area corresponding to the first topic content in the message interpretation video; wherein the replaced chat scene background is selected from preset scene backgrounds, or generated based on input key information.

[0197] For example, the target object clicks Figure 7The icon shown in S71 can present a scene change setting interface, which can be in the form of a pop-up window, a floating layer, etc., or can be directly presented in a certain area of ​​the message interpretation interface shown in Figure 7.

[0198] like Figure 8 As shown, it is a schematic diagram of a scene change setting interface in an embodiment of the present application. In addition to being able to change the overall chat scene background of the message interpretation interface, the target object can also set a chat scene background that matches the topic theme for each topic content based on the topic content. Specifically, the target object can choose to change the area, such as: Figure 8 The whole in the text represents the overall chat scene background; Figure 8 Topic 1 in , which means the interactive area corresponding to topic 1; Figure 8 Topic 2 in the figure refers to the interactive area corresponding to topic 2; similarly, topics 3 and 4 are also similar, and repeated support will not be repeated.

[0199] In addition, there are many ways to change the chat scene background in the embodiment of the present application, such as Figure 8 The preset in means that the target object is supported to select the chat scene background from the preset scene backgrounds provided by the system material library for replacement; or Figure 8 The key information in the intelligent generation means that the target object can also input key information (such as keywords, scene description information, etc.), and the chat scene background that matches the keyword is automatically generated based on the key information combined with AI technology. This article does not make specific restrictions.

[0200] like Fig. 9 As shown, it is a schematic diagram of three preset scene backgrounds listed in the embodiment of the present application, namely: amusement park theme, conference theme and game hall theme. The target object can select a preset scene background with a suitable theme according to the theme of the current first topic content. For example, if the currently selected first topic content is related to the amusement park, it can be replaced with a preset scene background with an amusement park theme.

[0201] In the above implementation, the target object can be selected according to the theme of the material library, or it can be recognized by default based on the theme content, and AIGC content can be used to automatically generate random chat scene backgrounds, etc., to enhance interest and improve object stickiness.

[0202] Optionally, the chat content involved in the chat scene is expressed as: an animation element corresponding to the message type of at least one target chat message. Specifically, the form of the animation element corresponds to the message type of the target chat message. The messages in the embodiment of the present application include but are not limited to the following message types: text, voice, image, video, article, etc.

[0203] The image may be a dynamic image (i.e., an animated image), a static image, or an expression image (such as a yellow face expression), which is not specifically limited in this article.

[0204] Accordingly, the animation elements include but are not limited to some or all of the following: subtitle elements corresponding to text messages, speech bubble elements corresponding to text messages converted into speech, speech bubble elements corresponding to voice messages, subtitle elements corresponding to voice messages converted into text, image elements, video elements, and article link elements.

[0205] Among them, the image element refers to an animation element corresponding to an image-type message. In addition, if the image message is an emoticon image, the corresponding animation element can be embodied in the form of a subtitle element, that is, it is presented in the image bubble of the corresponding virtual object in the form of a subtitle. In this case, the subtitle element corresponding to the image message can also be presented together with the animation element corresponding to the text or voice message before the target object is zoomed in, and this article does not make specific restrictions.

[0206] In addition, the video element can be a video posted by the publisher, a shared external link video, or a video integrated from images and / or video messages posted by the publisher, etc., which is not specifically limited in this article.

[0207] In an embodiment of the present application, if the target chat message is a text message, corresponding subtitle elements, such as text bubbles, can be added to the message interpretation video. In addition, the text message can also be converted into a voice message, and then the corresponding voice bubble elements can be added to the message interpretation video.

[0208] Similarly, if the target chat message is a voice message, a corresponding voice bubble element can be added to the message interpretation video. In addition, the voice message can also be converted into a text message, and then a corresponding subtitle element can be added to the message interpretation video.

[0209] In addition, it should be noted that in order to facilitate the target object to quickly and clearly understand the main chat information, it can also be set that only subtitle elements and / or speech bubble elements are presented in the initially presented message interpretation video, and image elements or video elements are not displayed for the time being. When the display screen of the target object's message interpretation video is enlarged and focused on a certain area in the message interpretation video, the image elements, video elements, etc. corresponding to the area are presented.

[0210] It should be noted that Figure 7 There are many virtual objects listed. In order to ensure the clarity of the attached figure, Figure 7 The presentation of subtitle elements and speech bubble elements is omitted. In essence, the initially presented message interpretation video includes subtitle elements and / or speech bubble elements.

[0211] In addition, in order to help the target object understand the information of the virtual object more clearly, the identity information of the corresponding publishing object, such as nickname, gender, etc., can also be presented at the relevant position of the virtual object (such as the left side of the head).

[0212] In the case where the target chat message selected by the target object belongs to multiple topic contents, each topic content may have its own corresponding audio, which is the chat voice generated based on the target chat message related to the topic content. This application takes into account that when multiple audios are played at the same time, the actual listening effect of the object is poor, so an audio control can be set for each interactive area to control the opening or closing of the audio corresponding to the interactive area.

[0213] An optional implementation manner is: the client plays the audio corresponding to the second topic content in response to the audio play operation triggered by the target object's audio control for the second topic content in the at least one topic content.

[0214] Still Figure 7 As shown in the example, Figure 7 The icon shown in S72 is an example of an audio control in an embodiment of the present application. The target object can set the audio that he currently wants to listen to based on the audio control.

[0215] If the target object selects topic 1 as the second topic content that he wants to listen to, the audio can be turned on based on the corresponding audio control, and the following is presented: Fig.10 The message interpretation interface shown plays the corresponding chat voice of topic 1.

[0216] It should be noted that in order to ensure that the target object can clearly hear the chat voice of the virtual object, Figure 7 When no interactive operation is performed in the message interpretation interface shown, only the audio corresponding to one topic content can be opened at the same time.

[0217] For interactive areas where audio is not enabled, the chat content can be presented through subtitle elements, such as Fig.10 The text bubbles in the Topic 2 and Topic 3 areas are shown. Meanwhile, for the interactive area with audio turned on, only the chat voice can be played and the corresponding speech bubble elements can be presented, such as Fig.10 The small voice microphone on the virtual object's head shown in the topic 1 area. In addition, the subtitle elements obtained by voice-to-text conversion can be presented while playing the chat voice ( Fig.10 not shown).

[0218] In addition, if the content in the current message interpretation interface corresponds to only one topic, the audio of the topic will be turned on by default; or if no topic division is performed, the audio will be turned on by default.

[0219] In the above implementation, interference and influence between multiple audios can be effectively avoided through the control of audio playback; in addition, messages that originally consist of voice content can generate subtitles and play them simultaneously, and messages that originally consist of text content can generate voice and audio content for synchronous playback, further enhancing the viewing and audio-visual experience of the target and improving the efficiency of message reading.

[0220] In an embodiment of the present application, the object can also perform further zooming and interaction based on the content of interest to it, and the current scene can also perform further interaction at the same time. The object can zoom in and out or slide to switch the subject content according to gesture operations, focusing on the current topic scene, so as to pay more attention to the current topic content.

[0221] An optional implementation is: the client updates the display screen corresponding to the interactive area in the message interpretation video in response to the target object's interactive operation on the interactive area corresponding to the third topic content in at least one topic content; wherein the interactive operation includes at least one of a zoom operation and a sliding switching operation.

[0222] In the embodiment of the present application, the target object can focus the screen on the interactive area corresponding to the third topic content through zooming operations, sliding switching operations, etc., to pay more attention to the current third topic content in detail.

[0223] The updating of the display screen includes but is not limited to: zooming and switching of the interactive area.

[0224] In the embodiment of the present application, when the interactive area is enlarged, more screen details can be further displayed. For example, if the target chat message of virtual object A mentions eating breakfast at a breakfast shop, only virtual object A can be presented before the enlargement operation is performed, and when the enlargement operation is performed, it is updated to a screen of virtual object A eating breakfast at the breakfast shop. Alternatively, only virtual object A and the action of eating breakfast are presented before the enlargement operation is performed, and when the enlargement operation is performed, it is updated to a screen of virtual object A eating breakfast at the breakfast shop. Regardless of the presentation method, it can be determined that after the enlargement operation is performed, more interactive details can be presented for the interactive area of ​​the third topic content.

[0225] In addition, if the interactive operation is a zoom operation in a scaling operation, then before performing the zoom operation, the animation element only includes at least one of a subtitle element and a speech bubble element, that is, when the target object does not perform a zoom operation on the message interpretation video, the animation element used to represent the chat may be at least one of a subtitle element and a speech bubble element, but does not include other animation elements except subtitle elements and speech bubble elements, such as video elements.

[0226] Specifically, before the zoom-in operation is performed, only the animation elements corresponding to at least one of the two message types of text messages and voice messages are presented, that is, the animation elements only include at least one of the following:

[0227] Subtitle elements corresponding to text messages, speech bubble elements corresponding to text messages converted into speech, speech bubble elements corresponding to voice messages, and subtitle elements corresponding to voice messages converted into text.

[0228] After performing the zoom-in operation, if the target chat message involved in the interactive area also includes images, videos, articles and other content, the corresponding image elements, video elements, article link elements, etc. can be further presented in the updated video, reflecting richer chat content.

[0229] For example, the target object manually slides to focus on topic 3. The content related to this topic includes group voice, text, video resources, sharing resources, etc. Through content recognition and AIGC content production, they can all be intuitively presented in the chat scene for intuitive interpretation. In addition, based on the emotional fluctuations or speech speed recognition of the language between the publishers of the target chat message, some interactive animation scenes can be presented, such as virtual object A saying "xxx" to virtual object B, virtual object B replies to virtual object A saying "xxx", and so on.

[0230] See also Fig.11 As shown, it is a schematic diagram of the display screen changes before and after executing an interactive operation in an embodiment of the present application. Among them, the target object can select topic 3 as the third topic content, using Fig.11 The gesture shown in the figure performs a sliding switching operation on topic 3, and displays topic 3 in the center of the video display screen. On this basis, a zoom operation can be further performed to focus on the current topic content, thereby presenting Fig.11 The second message interpretation interface pointed by the arrow in the middle. Obviously, the message interpretation interface focuses on presenting the interactive area corresponding to topic 3. In the updated display screen, in addition to the subtitle element and the speech bubble element, the video element is further presented, as shown in S111. In addition, more picture details are further presented, such as the street lamp shown in S112, etc.

[0231] Moreover, after the target object performs the above-mentioned amplification operation on the third topic content, it can be adjusted to play the audio corresponding to the third topic content, as shown in the S113 icon, which means that the audio of topic 3 is turned on. If the audio of other topics has been set to be turned on before, it can be turned off in this case, and only the audio of topic 3 can be played.

[0232] Optionally, the target object may also perform some playback control on the current message interpretation video based on its own needs or interests. The client responds to the target operation triggered on the message interpretation video and controls the playback of the message interpretation video based on the target operation.

[0233] The target operation includes at least one of a pause operation and a double-speed operation.

[0234] Still Figure 7 As an example, in Figure 7 In the message interpretation interface shown, there is an AI interpretation button shown in S73. In the message interpretation interface, this button can play the role of pausing the play, that is, the AI ​​interpretation button in the message interpretation interface is a play pause button. The target object can use this button to control the message interpretation video to pause or continue playing.

[0235] Another example Fig.11 As shown, in an embodiment of the present application, the video element shown in S112 can also be played and paused by the target object to avoid conflicts or influences between the voice in the video and the chat voice between virtual objects, and to avoid playing various audios at the same time to interfere with the target object's acquisition of information.

[0236] In addition, the target object can also play the video content at double the speed, providing corresponding capabilities for objects that need to speed up.

[0237] like Fig.12 As shown, it is a schematic diagram of a video played at a double speed in an embodiment of the present application. The target object can play the content at a double speed by long pressing (or other methods), so as to further improve the message reading efficiency.

[0238] Furthermore, when focusing on the third topic content, the target object may further focus on the details in the interactive area of ​​the topic content, such as Fig.13 As shown, it is a schematic diagram of focusing video content in an embodiment of the present application. The target object can be Fig.13 The gestures shown further magnify and push, focus on the current video content, etc., which are not specifically limited in this document.

[0239] In addition, when there are multiple videos, images, etc. for the same topic content, these video elements, image elements, etc. can be superimposed and displayed in a sub-area of ​​the current interactive area. Fig.14 As shown, it is a schematic diagram of a display style of a video element in an embodiment of the present application. Fig.14 On the right side of the interactive area in the topic shown, three videos are overlapped and displayed, namely Video 1, Video 2 and Video 3.

[0240] Among them, the upper and lower display order of Video 1, Video 2 and Video 3 can be determined according to the corresponding release time, such as the earlier the release time, the higher the display order, or the later the release time, the higher the display order, and so on.

[0241] Alternatively, if the events described in these videos occur in a certain chronological order, the order in which these videos are displayed can be determined based on the understanding of the interpretation of the events and in accordance with the context of the events, e.g., the earlier the event occurs, the higher the display order, and so on.

[0242] In the above implementation, the object is provided with the ability to control the video playback by itself, so that the object can flexibly adjust the playback of the message interpretation video according to its own video viewing habits and needs.

[0243] Optionally, the message interpretation video also includes an animation effect that represents the chat atmosphere of the virtual object, and the animation effect is an animation effect for the virtual object or the interactive area. The animation effect is obtained by performing content recognition and analysis on the target chat message corresponding to the corresponding virtual object.

[0244] Specifically, for example, in a certain interactive area, if the chat atmosphere between virtual object A and virtual object B is very heated, animation effects related to the fire element may be added above the heads of virtual object A and virtual object B (or other relevant positions of the virtual objects, which are not specifically limited herein).

[0245] When the number of virtual objects with a very hot chat atmosphere in a certain interactive area exceeds a certain percentage, for example, 80% of the virtual objects in the interactive area have a very hot chat atmosphere, animation effects related to the fire element can be presented in the entire interactive area.

[0246] Alternatively, in addition to the chat atmosphere being expressed as the chat's hotness, the chat atmosphere may also be expressed through the weather, mood, etc. involved in the target chat message. For example, if virtual object C currently mentions rainy days, an animation effect of rainy day elements may be presented above the head of virtual object C. For another example, if virtual object D currently mentions being in a good mood, an animation effect indicating a good mood, such as a happy expression effect, may be presented above the head of virtual object D.

[0247] See also Fig.15 As shown, it is a schematic diagram of an animation special effect for a single virtual object in an embodiment of the present application, which can present an animation special effect of the fire element above the head of the virtual object. The special effect can be static or dynamic, and is not specifically limited in this article.

[0248] See also Fig.16As shown, it is a schematic diagram of an animation special effect for a single interactive area in an embodiment of the present application. The animation special effect of snow elements can be presented in the entire interactive area. The special effect can be static or dynamic, and this article does not make specific limitations.

[0249] It should be noted that the above-mentioned methods of adding animation special effects are just simple examples and are not specifically limited in this article.

[0250] In the above implementation, by presenting the animation effects of the chat atmosphere, the target object can timely understand the discussion degree of each virtual object or each topic content, so as to more quickly locate the content that he wants to focus on.

[0251] Optionally, the body movements of each virtual object in the message interpretation video are obtained by performing content recognition and analysis on the target chat message corresponding to the corresponding virtual object.

[0252] For example, in an embodiment of the present application, the body movements of each virtual object can be obtained through semantic recognition, speech rate recognition, emotion recognition, etc. of the target chat message, and the body movements are generated by the AIGC system and displayed in the video.

[0253] Specifically, the body movements directed at the virtual object can be directly displayed in the initially presented message interpretation video, or the target object can perform an interactive operation on a certain interactive area and focus on a certain interactive area, and then the body movements of the virtual object in the interactive area can be presented as details, etc. This article does not make specific limitations.

[0254] See also Fig.17 As shown, it is a schematic diagram of a body movement in an embodiment of the present application. If the virtual object has no body movement, it can be presented Fig.17 The state on the left in the middle, when it is found through semantic recognition that the virtual object has mentioned the heart shape, the body movement shown on the right can be presented, that is, the state of making a heart shape can be presented.

[0255] See also Fig.18 As shown, it is a schematic diagram of another body movement in the embodiment of the present application. For example, when the virtual object has no body movement, it can be presented Fig.18 The state on the left side of the middle, and when it is found through semantic recognition that the virtual object mentions dancing, the body movements shown on the right can be presented, that is, the state of dancing.

[0256] In the above implementation, the presentation of body movements can further enhance the interest of the video and more vividly interpret the target chat message.

[0257] Optionally, the message interpretation video in the embodiment of the present application may also be a video generated based on the metaverse platform, that is, the video is a video that simulates the chat scene between corresponding publishing objects based on virtual objects in a three-dimensional metaverse space.

[0258] Specifically, compared with ordinary videos, videos generated based on Metaverse digital technology can reflect a more immersive sense of interaction and more concrete content. For example, the video elements in ordinary videos may only use Figure 12 to Figure 14 By combining the digital technology of Metaverse, ordinary video can be combined with Metaverse space, such as Figure 12 to Figure 14 The video elements listed in the video are displayed on the advertising screen of the building, on the TV in the living room, etc. For another example, in an ordinary message interpretation video, only a virtual object running can be presented, while in a three-dimensional metaverse space, the virtual object can be presented as running on a track operated by the school, etc. The virtual object can also be a three-dimensional object.

[0259] Based on the above implementation, more concrete video content can be generated and presented to the target object, thereby enhancing the target object's sense of immersion and interactivity when watching the video.

[0260] Optionally, the message interpretation video in this application also supports small window display. An optional implementation is as follows:

[0261] The client responds to the small window display operation triggered by the target object on the message interpretation interface, presents the message interpretation interface through a small window in the chat interface, and plays the message interpretation video through the message interpretation interface.

[0262] In an embodiment of the present application, there are many ways for a target object to trigger a small window display operation. For example, the target object can trigger a small window display operation for the message interpretation interface through small window controls, returns, etc.

[0263] Taking the control trigger as an example, in the embodiment of the present application, a "small window control" may be presented in the message interpretation interface, such as Figure 7 S74 in FIG. 1 is an example of a small window control in an embodiment of the present application. The target object can click on the small window control to trigger the small window display operation triggered by the message interpretation interface. The client responds to the operation, returns from the message interpretation interface to the chat interface, and presents the message interpretation interface through a small window in the chat interface, and plays the message interpretation video through the message interpretation interface.

[0264] Another example Figure 7As shown in S75, it is a "return" icon in the message interpretation interface. The target object can click "return" in the message interpretation interface, and can also trigger a small window display operation triggered for the message interpretation interface. The client responds to the operation, returns from the message interpretation interface to the chat interface, and presents the message interpretation interface through a small window in the chat interface, and plays the message interpretation video through the message interpretation interface.

[0265] It should be noted that, if no new messages are received, the chat messages presented after the chat interface is returned are the chat messages presented when the message interpretation operation is triggered. If a new message is received, the chat messages presented after the chat interface is returned include the latest new message received, and may also include several messages before the new message, depending on the content and number of new messages to be presented and the size of the chat interface, which is not specifically limited in this article.

[0266] See also Fig.19 As shown, it is a schematic diagram of a small window display in an embodiment of the present application. Fig.19 In the chat interface, a message interpretation interface is presented in the form of a small window, and the message interpretation video is played through the message interpretation interface. In the chat interface in this case, the message interpretation control is restored to the initial non-playable state, as shown in S191, supporting the target object to continue to select a new target chat message and continue to generate a new message interpretation video.

[0267] Optionally, the target object can restore the message interpretation interface displayed in the small window through the icon shown in S192, that is, switch from the chat interface to the message interpretation interface again. In addition, the target object can also close the message interpretation video through the icon shown in S193.

[0268] In an embodiment of the present application, after the target object triggers the small window display operation, it can return to the chat interface to watch the historical interpretation while interacting with the group, which helps to improve the efficiency of message reading.

[0269] In the embodiment of the present application, no matter whether the target object closes the currently viewed message interpretation video, the historical video list can still be viewed. The historical video list may only present the message interpretation videos generated by the target object based on the chat messages in the target conversation group, or may present the message interpretation videos generated by each object in the target conversation group based on the chat messages in the target conversation group, which is not specifically limited herein.

[0270] An optional implementation is as follows:

[0271] The client responds to the historical video viewing operation triggered by the target object based on the chat interface and presents a historical video list, wherein the historical video list includes: each message interpretation video currently generated for the target conversation group.

[0272] Among them, a history viewing control can be set in the chat interface, and the target object can trigger the history video viewing operation based on the control; or the target object can also trigger the history video viewing operation through a preset gesture or voice command, etc., which is not specifically limited in this article. The history video list can be in the form of a pop-up window, floating layer, etc., or it can be directly presented in a certain area of ​​the chat interface, which is not specifically limited in this article.

[0273] See also Fig. 20 As shown, it is a schematic diagram of a historical video list in an embodiment of the present application. As shown in S201, it is an example of a historical viewing control in an embodiment of the present application. The target object can click the control shown in S201 to view the historical video list, as shown in S202. Specifically, when presenting each message interpretation video that has been generated, the corresponding generation time and generation object can be further displayed. The generation object is the object that triggers the message interpretation operation corresponding to the message interpretation video, and the generation time is the trigger time of the message interpretation operation, etc., which are not specifically limited in this article.

[0274] Based on the above implementation, the target object can view more message interpretation videos for the target conversation group based on the historical video list, thereby further improving the message reading efficiency for the target conversation group.

[0275] The above is an explanation of the method for reading a chat message in an embodiment of the present application from the client side. The following is a further explanation of the method for reading a chat message in an embodiment of the present application from the server side:

[0276] See also Fig.21 As shown, it is an implementation flow chart of another chat message reading method provided in an embodiment of the present application. Taking the server as the execution subject as an example, the specific implementation process of the method is as follows:

[0277] S211: The server obtains at least one target chat message, and a timestamp and a publishing object corresponding to each of the at least one target chat message.

[0278] Among them, at least one target chat message is obtained by the client in response to a selection operation triggered by a chat interface based on the target dialogue group, and is at least one target chat message selected from the chat messages displayed on the chat interface.

[0279] In the embodiment of the present application, the target object can view the chat interface of the target conversation group and select the target chat message for which the target object wants to perform message interpretation based on the chat interface. After the target object selects the target chat message and triggers the message interpretation operation, the target object can send a video generation request to the server through the client, requesting the server to generate a message interpretation video based on the target chat message selected by the target object and feed it back to the client. After the client receives the message interpretation video fed back by the server, it presents the video to the target object through the message interpretation interface.

[0280] In an embodiment of the present application, after receiving a video generation request, the server can obtain at least one target chat message selected by the target object, and the timestamp and publishing object corresponding to each of the at least one target chat message.

[0281] Specifically, these data can be included in the video generation request, counted by the client and sent to the server, or only the identification information of these target chat messages can be carried in the video generation request. After the server receives the video generation request, it queries the specific content, timestamp, and publishing object of these target chat messages based on the identification information.

[0282] Taking client statistics as an example, the client needs to collect and prepare the above data. Specifically, the client collects and organizes the data of historical chat messages of the target dialogue group, extracts the message content, timestamp and publishing object information of the target chat message selected by the target object, etc.

[0283] Optionally, the client can also perform data preprocessing on these target chat messages. The target chat messages may contain entity information such as locations, names, and organizations. Therefore, entity recognition technology can be used to extract these entities from text messages and mark their types. Specifically, this can be done using the entity recognition tool provided by the NLP library.

[0284] In addition, the client can also perform other language processing and standardization operations on the above data according to specific needs, such as language translation, spelling correction, part-of-speech tagging, etc., to improve the consistency and accuracy of the data.

[0285] In an embodiment of the present application, after the server obtains these data, it can intelligently generate a message interpretation video based on these data.

[0286] S212: Based on at least one target chat message, and at least one timestamp and publishing object obtained, the server obtains a message interpretation video including a chat scene generated based on a virtual object associated with each of the at least one publishing object.

[0287] This application takes into account that the historical chat messages in the target dialogue group may involve multiple topics. Therefore, before generating the message interpretation video, they can be split according to the subject content of the topic and reorganized according to the coherence of the content.

[0288] In an optional implementation, at least one target chat message belongs to at least one topic content; then an optional implementation of S212 is as follows, including S2121~S2123 ( Fig.21 not shown):

[0289] S2121: Determine the topic content to which each target chat message belongs by classifying the topic of at least one target chat message.

[0290] S2122: Based on each target chat message belonging to the same topic content and the corresponding timestamp, generate video screen content representing the chat scene corresponding to the topic content.

[0291] S2123: In each video screen content, add the virtual object associated with the publisher of the corresponding target chat message, integrate and generate a message interpretation video, and in the message interpretation video, the virtual objects corresponding to each topic content are gathered in the same interactive area in the chat scene.

[0292] In the embodiment of the present application, when the server generates a message interpretation video based on the target chat message, it first needs to perform content recognition on the target chat message, such as using NLP technology to perform content recognition on the target chat message, including but not limited to: text information classification, voice information classification, publishing object recognition, object text, tone and emotion and other emotional analysis and recognition processing. In addition, feature extraction and analysis of various target chat messages such as images, audio, and video are performed, and label classification and topic content extraction and classification are performed.

[0293] Optionally, when the server performs content recognition and topic classification on the target chat message, it can be implemented based on a trained topic model. Specifically, a topic model algorithm (such as Latent Dirichlet Allocation, LDA) is used to perform topic modeling on the text messages in the target chat message, and potential topics are extracted from these text messages based on the trained topic model, and a topic distribution is assigned to each text message.

[0294] Furthermore, based on the results of the topic model, clustering analysis algorithms (such as K-means, hierarchical clustering, etc.) can be used to cluster various types of target chat messages, and similar messages can be grouped into the same category based on the clustering algorithm, so as to be clearly divided into multiple topic groups.

[0295] In the embodiment of the present application, the topic model may be a classification model. When training the topic model, the labeled data may be used to train a classification model, such as naive Bayes, support vector machine, decision tree, deep learning model, etc. These models can predict the topic classification of new messages and help to clearly divide multiple topics into different topic groups.

[0296] Specifically, a large number of group historical chat messages can be collected as training data sets, and the topics to which the group historical chat messages belong can be labeled to ensure that the data set is large enough and representative, so as to improve the accuracy of subsequent content recognition and generation. Among them, messages that are not clearly classified can be manually labeled. Manual labeling can further improve the accuracy of topic classification, and these labeled data can be used to train supervised learning models.

[0297] Furthermore, the topic classification of the group historical chat messages in the training data set is carried out based on the classification model to be trained, the accuracy of the classification results is evaluated, and the classification model and algorithm are improved as needed. Different preprocessing techniques, feature representation methods, clustering algorithms or classification models can be tried, and the performance of topic classification can be improved by adjusting parameters and optimizing models.

[0298] It should be noted that before classifying the target chat message by topic, the following preprocessing may be performed:

[0299] 1) Data preparation: Collect the target chat message data and ensure that the data is available and accessible. Text messages can be extracted from the target chat messages and appropriate data cleaning can be performed, such as removing unnecessary, repeated, incomplete, inaccurate, incomprehensible or irrelevant text content.

[0300] 2) Text preprocessing: Preprocess the text messages, such as removing stop words, punctuation marks and special characters, and performing operations such as stemming or lemmatization. This helps reduce noise and improve the accuracy of subsequent analysis.

[0301] 3) Text representation: Represent each text message in a numerical form that can be processed by the algorithm.

[0302] In the embodiments of the present application, the algorithms that can be used include but are not limited to: Bag-of-Words, TF-IDF (Term Frequency-Inverse Document Frequency) vectors and word embeddings, etc., which are not specifically limited in this article.

[0303] It should be noted that the selection of an appropriate representation method depends on the size of the dataset and the task requirements, and this article does not make any specific restrictions.

[0304] In the embodiments of the present application, content identification and topic classification of chat messages is a complex task that requires the integration of multiple technologies and algorithms for processing. The specific implementation details and effects will be affected by data characteristics, task requirements and available resources. The above are just simple examples. The specific situation may be determined according to actual needs, and this article does not make specific limitations.

[0305] Based on the above, AI creation or generation (AICG) technology can be used to generate visual message interpretation video content.

[0306] In an embodiment of the present application, the generation of message interpretation video can be achieved using a generative adversarial network (GAN), automated text summarization, image or video generation models, etc. Based on the identified content prompts, the AICG system can generate corresponding images, animations or video clips, which in this embodiment of the present application can be collectively referred to as video screen content.

[0307] Simply put, based on the processed data, AIGC technology is used to generate video content. Taking the topic category as a unit, the text, image, audio, video, etc. of the topic content are generated using AIGC technologies such as text generation, image generation, audio generation, and video generation to generate corresponding video content. The AIGC model can build relevant video scenes and backgrounds based on the locations, object roles, events, etc. mentioned in the target chat message, and at the same time add virtual objects of the publishing object to integrate and generate a visual message interpretation video.

[0308] Specifically, based on the collected and summarized text, audio, image, and video contents in the target chat message, the following steps can be followed when using AIGC technology to generate a visual message interpretation video:

[0309] 1) Data preparation: Organize and prepare the text, audio, image, and video content in the target chat messages of each topic to ensure that the data is available and accessible.

[0310] 2) Data analysis: For each topic, data analysis is performed on the corresponding target chat messages to understand the distribution, characteristics, and relevance of various media content (text, audio, images, videos, etc.). This helps determine how to integrate content of different media types.

[0311] 3) Content generation model selection: Select an AIGC model suitable for generating video content, such as a GAN model based on deep learning, such as pix2pix, CycleGAN, Deep Convolutional Generative Adversarial Networks (DCGAN), or a Transformer model.

[0312] It should be noted that choosing an appropriate AIGC model requires considering the data type and generation effect requirements, which are not specifically limited in this article.

[0313] 4) Data preprocessing: According to the requirements of the selected AIGC model, various types of target chat message data are preprocessed accordingly.

[0314] For example, for text messages, natural language processing technology can be used to perform word segmentation, remove stop words, etc. For audio, image and video data, format conversion, noise reduction, size adjustment and other processing can be performed.

[0315] 5) Model training and generation: According to the requirements of the selected AIGC model, the above-processed target chat message is input to generate new video screen content.

[0316] It should be noted that the AIGC model used here is a trained AIGC model. During the training process, the model is trained using a prepared training data set, and the model parameters can be adjusted according to the quality and effect of the generated video to obtain a trained AIGC model.

[0317] 6) Video synthesis and editing: synthesize the generated video content with other elements.

[0318] Specifically, in addition to adding corresponding virtual objects to the video content according to the location, object role, event, etc. mentioned in the target chat message, video editing software can also be used for further processing and editing, such as adding background music, subtitles, transition effects, etc. This can make the generated video more visual and enjoyable.

[0319] 7) Evaluation and optimization: Evaluate and optimize based on the quality and effect of the generated video. If the result is not satisfactory, you can try to adjust the model parameters, modify the data preprocessing steps, or choose other AIGC models to improve the generated video content.

[0320] It should be noted that AIGC technology is a relatively new field in generating video content. The quality of the results will be affected by factors such as data quality, model selection, and training. Therefore, in practical applications, appropriate adjustments and trade-offs can be made based on task requirements and technical limitations. This article does not make specific restrictions.

[0321] The following is a brief description of the specific technology of generating video content (including images and animations, etc.) corresponding to each topic based on the AIGC system, which mainly includes the following aspects:

[0322] 1) Generate dialogue and plot: The AIGC system can use natural language processing technology to generate appropriate dialogue and plot based on the text content in the target chat message. In this process, a language model can be used to understand the message content and generate corresponding dialogue and plot based on its semantics and context.

[0323] 2) Character animation: In order to generate realistic character animation, the AIGC system can use human pose estimation and skeleton following technology. These technologies can automatically generate corresponding animations based on the character's motion trajectory and posture data. For example, deep learning methods are used to estimate human poses, and then the estimated pose data is applied to the character model to achieve automatic character animation generation.

[0324] On the basis of the above, when implementing step S2122, it is also necessary to determine the body movements of each virtual object by performing content recognition on the target chat message corresponding to the virtual object; then, when implementing step S2123, in the content of each video screen, the virtual object associated with the publisher of the corresponding target chat message is added in combination with the determined body movements to integrate and generate a message interpretation video.

[0325] In the embodiment of the present application, the body movements of each virtual object can be obtained by performing semantic recognition, speech rate recognition, emotion recognition, etc. on the target chat message. Then, the AIGC system uses human posture estimation and skeleton following technology to apply these body movements to the character model of the corresponding virtual object to realize automatic character animation generation, for example Fig.17 or Fig.18 As shown, it is an example of a virtual object with added body movements listed in the embodiments of the present application.

[0326] In the embodiment of the present application, the presentation of body movements can further enhance the interest of the video and interpret the target chat message more vividly.

[0327] 3) Scene rendering: AIGC systems can use computer graphics and rendering technology to generate realistic scenes. This includes technologies in lighting models, material design, texture mapping, etc.

[0328] Furthermore, by generating a corresponding virtual scene according to the scene description or keywords and placing characters and objects therein, the background and context related to the target chat message can be presented.

[0329] Still Figure 8As shown in the figure, the target object can input key information (such as keywords, scene description information, etc.), and then the AIGC system can use computer graphics and rendering technology to generate realistic scenes. In addition, characters (such as virtual objects) and objects (objects associated with the target chat message, such as restaurants and breakfasts mentioned in the message) can be placed in it to present the background and context related to the target chat message.

[0330] 4) Special effects generation: In order to enhance the expressiveness of images and animations, the AIGC system can use special effects generation technology. This includes the implementation of particle systems, physical simulations, and post-production special effects. By adding animation special effects such as flames, smoke, and light effects, the generated images and animations can be made more vivid and eye-catching.

[0331] On the basis of the above, when implementing step S2122, it is also necessary to determine the animation effects for each virtual object or interactive area by performing content recognition on the target chat message corresponding to the virtual object; then, when implementing step S2123, in the content of each video screen, the virtual object associated with the publisher of the corresponding target chat message is added in combination with the determined animation effects to integrate and generate a message interpretation video.

[0332] Specifically, after the target chat message corresponding to the corresponding virtual object is identified and analyzed to determine the special effect type (such as snow element or fire element, etc.), the corresponding animation special effects can be generated based on the particle system, physical simulation and post-production special effects, such as Fig.15 or Fig.16 As shown, it is a schematic diagram of several animation special effects listed in the embodiments of the present application.

[0333] In the embodiment of the present application, by presenting the animation special effects of the chat atmosphere, the target object can timely understand the discussion degree of each virtual object or each topic content, so as to more quickly locate the content that he wants to focus on.

[0334] The above technology can be implemented by combining methods and algorithms in the fields of machine learning, deep learning, computer vision and computer graphics. By using large-scale training data, advanced models and algorithms, and high-performance computing resources, the AIGC system can achieve the ability to generate appropriate images and animations to present the dialogue, plot or emotion in the object chat message.

[0335] After generating the images and animations corresponding to each topic, they need to be integrated into a coherent video content. The specific process is as follows:

[0336] 5) Video synthesis and rendering: The generated images and animations need to be synthesized and rendered to create a coherent, visual video image.

[0337] 6) Video editing and clipping: The generated images and animations need to be organized and arranged according to the timeline.

[0338] Specifically, the order of images and animations generated based on the target chat messages can be determined based on the timestamps of the target chat messages, and then, based on video editing and clipping techniques, the video sequences can be cropped, spliced, mixed, and processed for transition effects to combine different images and animations in a determined order to generate continuous video images.

[0339] 7) Temporal interpolation and inter-frame compensation: During the video generation process, images and animations can also be temporally interpolated to smooth the transitions and movements of the animations.

[0340] Specifically, the temporal interpolation technology can automatically generate intermediate frames based on the differences between consecutive frames, making the animation transition smoother. The inter-frame compensation technology can automatically generate missing frames by analyzing and predicting the motion between different frames, thereby improving the smoothness of the animation. The above are just simple examples and are not specifically limited in this article.

[0341] 8) Video transitions and special effects: To enrich the presentation of the video, various transition and special effects techniques can be applied.

[0342] In the embodiments of the present application, transition techniques include but are not limited to fade in and fade out, wipe, switch, etc., which are used to smoothly transition different scenes and animation elements. Special effects technology can change the appearance and expression of images and animations by applying filters, transformation effects, color correction, etc.

[0343] 9) Rendering Engine: Video rendering requires converting the generated images and animations into the final video format. The rendering engine is the key component responsible for synthesizing images and animations into video frames. It can process each image frame with rendering, lighting, shadows, texture mapping, etc., and finally output realistic and coherent video images.

[0344] In the embodiments of the present application, the above processing can be implemented using algorithms and tools in the fields of computer graphics, image processing, and video encoding and decoding. By combining advanced rendering engines, optimized video encoders, and fast computing hardware, high-quality and efficient video synthesis and rendering processes can be achieved to create a satisfying visual experience.

[0345] On the above basis, the virtual object of the release object is integrated into the realistic and coherent video picture content to obtain the message interpretation video.

[0346] The present application takes into account that in order to further enhance the sense of interactivity of the message interpretation video, it is also possible to generate a video based on virtual objects simulating the chat scene between the corresponding publishing objects in a three-dimensional metaverse space based on the metaverse digital technology.

[0347] An optional implementation is that the message interpretation video can also be a video generated based on the Metaverse digital technology, which simulates the chat scene between the corresponding publishing objects based on virtual objects in the three-dimensional Metaverse space. In this case, after implementing S212 and before implementing S213, the following operations need to be performed to obtain the three-dimensional message interpretation video generated based on the Metaverse digital technology:

[0348] First, encode the message deduction video into a data format supported by the Metaverse platform.

[0349] Furthermore, the encoded message interpretation video is imported into the Metaverse platform and associated with the scene elements in the Metaverse platform to present the message interpretation video as a video that simulates the chat scene between the corresponding publishing objects based on virtual objects in the three-dimensional Metaverse space, wherein the scene elements here are: elements created in the three-dimensional Metaverse space based on the Metaverse platform for displaying the message interpretation video.

[0350] That is, the target chat message is subject to content recognition, AICG content generation, and presented in the metaverse visualization video. In the embodiment of the present application, the tools and editors of the metaverse platform or engine can be used to create a metaverse visualization scene, and the generated images, animations, or video clips can be embedded into the metaverse visualization scene to display the content of the target chat message to ensure that the video content can be correctly displayed and interacted in the metaverse. By interacting with other elements and publishing objects in the metaverse, the immersion and interactivity of the video are enhanced.

[0351] In the embodiment of the present application, when the generated video screen is embedded into the metaverse for presentation, it can be achieved through the following technologies and steps:

[0352] 1) Metaverse platform or engine integration: That is, first of all, it needs to be integrated with the Metaverse platform or engine.

[0353] This process requires working with Metaverse developers or platform providers to understand their development environments, APIs, and tools, and through integration, to seamlessly insert the generated video content into the Metaverse scene and enable interaction with other elements.

[0354] 2) Video encoding and decoding: Encode the generated video images to meet the requirements and format of the Metaverse platform or engine.

[0355] In the embodiments of the present application, it is generally involved to compress and encode the video using a video coding standard, such as H.264 or H.265. When playing in the metaverse, the platform or engine will decode and render the video accordingly so that users can watch and interact with it.

[0356] 3) Metaverse scene creation and layout: Create a scene in the metaverse to display the generated video content.

[0357] Specifically, the process requires selecting a suitable environment, background, and placement of other elements to best display the video. The scene can be created and arranged using the tools and editors provided by the Metaverse platform or engine according to its requirements. For example, some buildings with advertising screens can be arranged to present video elements, or a school playground can be arranged.

[0358] 4) Video media import: Import the generated video media files into the Metaverse platform or engine, and associate them with specific areas or objects in the scene. For example, associate video elements with the advertising screen of a building, associate virtual objects that need to run with the school playground, etc.

[0359] Specifically, this process can be implemented through the media library, resource manager, or application programming interface (API) provided by the platform, and the actual technology and methods vary depending on the Metaverse platform and application. Different Metaverse platforms may use different development tools, APIs, and interaction methods, which are not specifically limited in this article.

[0360] Based on the above implementation method, the visualization elements, effects and interactive functions provided by the Metaverse platform library can make the final generated video richer and more interesting.

[0361] S213: The server feeds back the message interpretation video to the client, so that the client plays the message interpretation video after responding to the message interpretation operation triggered for the target conversation group.

[0362] In the embodiment of the present application, when the subject wants to quickly read the chat messages posted in the target conversation group, there is no need to browse them one by one. The subject only needs to select the target chat message that he wants to carefully view, and by triggering the message interpretation operation, the selected target chat message can be visually and dynamically interpreted, and the historical messages in the target conversation group can be automatically interpreted and played, which not only increases the fun, but also focuses on the topic content that the subject is concerned about, or information related to his own interests or people he pays special attention to, etc., avoiding wasting too much time on topics that are not of interest. Under the premise of ensuring that the subject effectively reads the chat message, the reading efficiency of the subject for the chat message can be improved. In addition, this convenient experience and interesting expression can also increase the object's usage viscosity and dissemination rate to a certain extent.

[0363] Optionally, the present application further considers video presentation and interactivity, and plays and presents videos in the metaverse scene. The target object can watch the video as needed, and can also interact with the video, such as playing, pausing, adjusting the volume, full screen, etc. This may be achieved through user interface elements, gestures, voice commands, etc. provided by the platform. For details, please refer to the above embodiments, such as Figure 7 The related descriptions of etc. will not be repeated here.

[0364] Furthermore, to ensure that there is reasonable synchronization between the generated content and the target chat message, the image or video clip generated by a specific text can be matched with the corresponding target chat message based on the timestamp and semantic interpretation. Fig.12 When text bubbles, speech bubble elements, etc. are presented in the picture shown, it can be implemented based on the above technology to present an orderly and coherent visual effect.

[0365] On this basis, in order to enhance the interactivity of the Metaverse visualization video as much as possible, this application also adds some user interface functional elements, animation effects, reminders or feedback, etc. to interact with the audience, allowing them to better browse and understand the content of historical chat messages.

[0366] The object can zoom in, out, drag and other operations according to the different topic contents presented in the interface content. Long press the current content to play the content at double speed, which is convenient for improving efficiency. At the same time, the video and audio content in the interface can be paused or muted, and can also be played in a small window, so that the object can better browse and understand the content of historical chat messages. For details, please refer to the above embodiments, such as Fig.12 , Fig.13 The related descriptions of etc. will not be repeated any more.

[0367] It should be noted that the specific implementation of each of the above steps depends on the technology and Metaverse platform used. In actual operation, it is necessary to deeply study and use the corresponding NLP and AICG tools, libraries or frameworks, and develop and integrate them accordingly according to the requirements and functions of the Metaverse platform. Through the above technologies and steps, the chat message content between objects can be converted into a visual video screen and presented in the Metaverse, providing objects with rich visual experience and interaction possibilities.

[0368] Combine the following Fig. 22 , the specific generation process of the message interpretation video in the embodiment of the present application is briefly summarized as follows:

[0369] See also Fig. 22 As shown, it is a timing flow chart of the interaction between a server and a client in an embodiment of the present application.

[0370] First, the target object sets up to turn on the AI ​​interpretation function of the target dialogue group, selects the target chat message in the chat interface of the target dialogue group, and then clicks the AI ​​interpretation button to trigger the message interpretation operation.

[0371] The client responds to the message deduction operation triggered by the target object, collects data and organizes the data of the group's historical chat messages:

[0372] Specifically, it involves extracting the message content (text, audio, video, external link information, etc.), timestamp and publishing object information of the target chat message, ensuring the accuracy of the data set to improve the accuracy of subsequent content recognition and generation. The specific process can be found in the above embodiment, and the repeated parts will not be repeated.

[0373] After collecting and organizing the data, the client transmits the above information content to the server, which processes the data to generate a message interpretation video and feeds it back to the client.

[0374] When the server processes data, it uses natural language processing technology to identify the content of the target chat message. This can include text information classification, voice information classification, publishing object identification, object text, tone and emotion analysis and identification processing, as well as feature extraction and analysis of various target chat messages such as images, audio, and video, label classification, topic content extraction classification: topic 1, topic 2, topic 3, etc. The specific process can be referred to the above embodiment, and the repeated parts will not be repeated.

[0375] Furthermore, the server generates video content through AIGC technology based on the processed data, and takes the topic category as the unit, and uses AIGC technologies such as text generation, image generation, audio generation, and video generation to generate corresponding video content for the text, image, audio, and video of the topic content. The AIGC model can construct relevant video scenes and backgrounds based on the locations, object roles, events, etc. mentioned in the target chat message, and at the same time add virtual objects of the publishing object to integrate and generate a visual message interpretation video.

[0376] Metaverse visualization video creation: Use the tools and editors of the Metaverse platform or engine to create a Metaverse visualization scene, and embed the generated images, animations, or video clips into the Metaverse visualization scene to display the content of the target chat message. Use the visualization elements, effects, and interactive functions provided by the Metaverse platform library to make the video richer and more interesting.

[0377] Based on the above, the server can generate a three-dimensional message interpretation video based on the metaverse space, and feed it back to the client, which then presents it to the target object, as follows:

[0378] When presenting the message interpretation video, the client side needs to ensure data synchronization with visual presentation: ensure that there is reasonable synchronization between the generated content and the target chat message. For example, the image or video clip generated by a specific text can be matched with the corresponding target chat message based on the timestamp and semantic interpretation to present an orderly and coherent visual effect. The specific implementation method can be referred to the above embodiment, and the repeated parts will not be repeated.

[0379] At the same time, it provides certain interactivity: the target object can zoom in, zoom out, drag and other operations according to the different topic contents presented in the message interpretation interface. Long press the current content to play the content at double speed, which is convenient for improving efficiency. At the same time, the video and audio content in the message interpretation interface can be paused or muted, and can also be played in a small window, so that the target object can better browse and understand the content of the target chat message. The specific implementation method can be referred to the above embodiment, and the repeated parts will not be repeated.

[0380] In summary, the present application sets up a quick switching mode in the chat interface, which supports one-click operation of the object, and can convert the selected chat message into a visual animation scene, automatically interpret and play the historical messages in the dialogue group, and reorganize and classify them according to the theme of the chat content. The reorganized content includes text content, voice content, video content and external link sharing content of multiple objects, etc., which are converted into visual metaverse scenes of multiple single topic contents based on content semantic recognition, and presented in the chat interface at the same time, so as to convey the topic content discussed in the group to the object more intuitively and efficiently. In addition, the object can also further zoom and interact based on the content of his interest, and the current scene can be further interacted at the same time. The subject content can be zoomed in and out or slid to switch according to gesture operations, focusing on the current topic scene, so as to pay more attention to the current topic content in detail, ensuring that the object can effectively read the chat message while improving the object's reading efficiency of the chat message.

[0381] Based on the same inventive concept, the present application embodiment also provides a chat message reading device. Fig.23 As shown, it is a schematic diagram of the structure of a chat message reading device 2300, which may include:

[0382] A presenting unit 2301 is used to present a chat interface of a target conversation group, where the chat interface is used to display chat messages posted in the target conversation group;

[0383] A selection unit 2302, configured to obtain at least one selected target chat message in response to a selection operation triggered based on the chat interface;

[0384] The interpretation unit 2303 is used to respond to the message interpretation operation triggered for the target dialogue group, and play the message interpretation video generated based on at least one target chat message, wherein the message interpretation video includes: a chat scene generated based on virtual objects associated with the respective publishing objects of at least one target chat message; and the chat content involved in the chat scene is generated based on at least one target chat message.

[0385] Optionally, at least one target chat message belongs to at least one topic content, and virtual objects corresponding to each topic content are gathered in the same interactive area in the chat scene.

[0386] Optionally, each interactive area corresponds to a chat scene background related to the topic content; the device further includes:

[0387] The adjusting unit 2304 is configured to change the chat scene background of the interactive area corresponding to the first topic content in the message interpretation video in response to the background change operation triggered for the first topic content in the at least one topic content;

[0388] Among them, the replaced chat scene background is: selected from the preset scene backgrounds, or generated based on the input key information.

[0389] Optionally, each interactive area has a corresponding audio control; the device further includes:

[0390] The audio control unit 2305 is used to play the audio corresponding to the second topic content in response to the audio playback operation triggered by the audio control of the second topic content in at least one topic content; the audio is a chat voice generated based on the target chat message related to the second topic content.

[0391] Optionally, the device further comprises:

[0392] A screen updating unit 2306, configured to update a display screen corresponding to the interactive area in the message interpretation video in response to an interactive operation on the interactive area corresponding to the third topic content in the at least one topic content;

[0393] The interactive operation includes at least one of a zoom operation and a slide switching operation.

[0394] Optionally, the chat content involved in the chat scene is presented as an animation element corresponding to a message type of at least one target chat message;

[0395] If the interactive operation is a zoom operation in a scaling operation, then before the zoom operation is performed, the animation element includes only at least one of the following:

[0396] Subtitle elements corresponding to text messages, speech bubble elements corresponding to text messages converted into speech, speech bubble elements corresponding to voice messages, and subtitle elements corresponding to voice messages converted into text.

[0397] Optionally, the message interpretation video also includes animation effects that represent the chat atmosphere of the virtual object, and the animation effects are animation effects for the virtual object or the interactive area.

[0398] Optionally, the chat interface further includes a message interpretation control; the message interpretation control is in a non-playable state;

[0399] The selection unit 2302 is specifically used for:

[0400] In response to a selection operation triggered by a message interpretation control, determining at least one selected target chat message in a message selection state, and updating the message interpretation control to a playable state;

[0401] The deduction unit 2303 is specifically used for:

[0402] In response to a message interpretation operation triggered by a message interpretation control, the chat interface jumps to a message interpretation interface, and a message interpretation video generated based on at least one target chat message is played on the message interpretation interface.

[0403] Optionally, the selection unit 2302 is specifically configured to:

[0404] In response to a selection operation triggered based on the message interpretation control, presenting the number of selectable chat messages and a select all control, as well as a selection control corresponding to each selectable chat message;

[0405] In response to a selection operation triggered based on a select all control or a selection control, at least one target chat message selected in a message selection state is determined.

[0406] Optionally, the device further comprises:

[0407] The first responding unit 2307 is used to respond to the small window display operation triggered for the message interpretation interface, and present the message interpretation interface through a small window in the chat interface;

[0408] Play the message interpretation video through the message interpretation interface.

[0409] Optionally, the device further comprises:

[0410] The second response unit 2308 is used to present a historical video list in response to a historical video viewing operation triggered based on the chat interface, and the historical video list includes: for the target dialogue group, each message interpretation video that has been currently generated.

[0411] Optionally, the device further comprises:

[0412] The third response unit 2309 is used to respond to the target operation triggered on the message interpretation video and control the playing of the message interpretation video based on the target operation;

[0413] The target operation includes at least one of a pause operation and a double-speed operation.

[0414] Optionally, the body movements of each virtual object in the message interpretation video are obtained by performing content recognition on a target chat message corresponding to the corresponding virtual object.

[0415] Optionally, the message interpretation video is a video that simulates a chat scene between corresponding publishing objects based on virtual objects in a three-dimensional metaverse space.

[0416] Optionally, the device further comprises:

[0417] A first setting unit 2310 is configured to present a message setting interface of the target conversation group in response to a viewing operation of the message setting interface of the target conversation group before the selection unit 2302 responds to the selection operation triggered based on the chat interface;

[0418] In response to the interpretation start operation triggered by the message setting interface, the interpretation function for the chat message in the target dialogue group is started, and the interpretation function supports the generation of corresponding message interpretation videos based on the chat message.

[0419] Optionally, the device further comprises:

[0420] The second setting unit 2311 is used to present a message setting interface of the target conversation group in response to a viewing operation on the message setting interface of the target conversation group;

[0421] In response to the image setting operation triggered by the target object based on the message setting interface, jump from the message setting interface to the image setting interface;

[0422] The target object is determined based on the virtual image set in the image setting interface, and the virtual image is used as a virtual object associated with the target object.

[0423] Based on the same inventive concept, the present application embodiment also provides a chat message reading device. Fig.24 As shown, it is a structural schematic diagram of a chat message reading device 2400, which may include:

[0424] The acquisition unit 2401 is used to acquire at least one target chat message, and a timestamp and a publishing object corresponding to each of the at least one target chat message, wherein the at least one target chat message is obtained by the client in response to a selection operation triggered by a chat interface based on a target conversation group, and is selected from the chat messages displayed on the chat interface;

[0425] A generating unit 2402 is used to obtain, based on at least one target chat message, and at least one obtained timestamp and publishing object, a message interpretation video including a chat scene generated based on a virtual object associated with each of the at least one publishing object;

[0426] The feedback unit 2403 is used to feed back the message interpretation video to the client, so that the client plays the message interpretation video after responding to the message interpretation operation triggered for the target conversation group.

[0427] Optionally, if the message interpretation video is a video that simulates a chat scene between corresponding publishing objects based on virtual objects in a three-dimensional metaverse space, the generating unit 2402 is further used to:

[0428] Encode the message deduction video into a data format supported by the Metaverse platform;

[0429] The encoded message interpretation video is imported into the Metaverse platform and associated with the scene elements in the Metaverse platform to present the message interpretation video as a video that simulates the chat scene between the corresponding publishing objects based on virtual objects in the three-dimensional Metaverse space. The scene elements are: elements created in the three-dimensional Metaverse space based on the Metaverse platform for displaying the message interpretation video.

[0430] Optionally, at least one target chat message belongs to at least one topic content;

[0431] Then the generating unit 2402 is specifically used for:

[0432] Determine the topic content to which each target chat message belongs by classifying the topic of at least one target chat message;

[0433] Based on each target chat message belonging to the same topic content and the corresponding timestamp, a video screen content representing the chat scene corresponding to the topic content is generated;

[0434] In each video screen content, virtual objects associated with the publisher of the corresponding target chat message are added to integrate and generate a message interpretation video. In the message interpretation video, the virtual objects corresponding to each topic content are gathered in the same interactive area in the chat scene.

[0435] Optionally, the generating unit 2402 is specifically configured to:

[0436] For each virtual object, the body movements of the virtual object are determined by performing content recognition on the target chat message corresponding to the virtual object;

[0437] In each video screen content, a virtual object associated with the publisher of the corresponding target chat message is added in combination with the determined body movements, and the message interpretation video is integrated and generated.

[0438] Optionally, the generating unit 2402 is specifically configured to:

[0439] For each virtual object, determine the animation effect for the virtual object or interactive area by performing content recognition on the target chat message corresponding to the virtual object;

[0440] In each video screen content, a virtual object associated with the publisher of the corresponding target chat message is added in combination with a determined animation effect, and the message interpretation video is integrated and generated.

[0441] In the embodiment of the present application, when the subject wants to quickly read the chat messages posted in the target conversation group, there is no need to browse them one by one. The subject only needs to select the target chat message that he wants to carefully view, and by triggering the message interpretation operation, the selected target chat message can be visually and dynamically interpreted, and the historical messages in the target conversation group can be automatically interpreted and played, which not only increases the fun, but also focuses on the topic content that the subject is concerned about, or information related to his own interests or people he pays special attention to, etc., avoiding wasting too much time on topics that are not of interest. Under the premise of ensuring that the subject effectively reads the chat message, the reading efficiency of the subject for the chat message can be improved. In addition, this convenient experience and interesting expression can also increase the object's usage viscosity and dissemination rate to a certain extent.

[0442] For the convenience of description, the above parts are divided into modules (or units) according to their functions and described separately. Of course, when implementing this application, the functions of each module (or unit) can be implemented in the same or multiple software or hardware.

[0443] After introducing the chat message reading method and device according to an exemplary embodiment of the present application, next, an electronic device according to another exemplary embodiment of the present application is introduced.

[0444] Those skilled in the art will appreciate that various aspects of the present application may be implemented as a system, method or program product. Therefore, various aspects of the present application may be specifically implemented in the following forms, namely: a complete hardware implementation, a complete software implementation (including firmware, microcode, etc.), or a combination of hardware and software, which may be collectively referred to as "circuit", "module" or "system" herein.

[0445] Based on the same inventive concept as the above method embodiment, an electronic device is also provided in the embodiment of the present application. In one embodiment, the electronic device may be a server, such as Figure 1In this embodiment, the structure of the electronic device can be as follows: Fig.25 As shown, it includes a memory 2501, a communication module 2503 and one or more processors 2502.

[0446] The memory 2501 is used to store computer programs executed by the processor 2502. The memory 2501 may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system and programs required for running the instant messaging function, etc.; the data storage area may store various instant messaging information and operation instruction sets, etc.

[0447] The memory 2501 may be a volatile memory, such as a random-access memory (RAM); the memory 2501 may also be a non-volatile memory, such as a read-only memory, a flash memory, a hard disk drive (HDD) or a solid-state drive (SSD); or the memory 2501 may be any other medium that can be used to carry or store a desired computer program in the form of instructions or data structures and can be accessed by a computer, but is not limited thereto. The memory 2501 may be a combination of the above memories.

[0448] The processor 2502 may include one or more central processing units (CPU) or a digital processing unit, etc. The processor 2502 is used to implement the above chat message reading method when calling the computer program stored in the memory 2501.

[0449] The communication module 2503 is used to communicate with terminal devices and other servers.

[0450] The specific connection medium between the memory 2501, the communication module 2503 and the processor 2502 is not limited in the embodiment of the present application. Fig.25 In the embodiment, the memory 2501 and the processor 2502 are connected via a bus 2504. The bus 2504 is connected to the processor 2502 via a bus 2504. Fig.25 The connections between the other components are only for illustration and are not intended to be limiting. The bus 2504 can be divided into an address bus, a data bus, a control bus, etc. For ease of description, Fig.25 The diagram shows that only one thick line is used, but this does not mean that there is only one bus or only one type of bus.

[0451] The memory 2501 stores a computer storage medium, and the computer storage medium stores computer executable instructions, and the computer executable instructions are used to implement the chat message reading method of the embodiment of the present application. The processor 2502 is used to execute the above-mentioned chat message reading method, such as Fig.21 shown.

[0452] In another embodiment, the electronic device may also be other electronic devices, such as Figure 1 The terminal device 110 shown in FIG. 1 is a terminal device 110 shown in FIG. 1 . In this embodiment, the structure of the electronic device can be as follows: Fig.26 As shown, it includes: a communication component 2610, a memory 2620, a display unit 2630, a camera 2640, a sensor 2650, an audio circuit 2660, a Bluetooth module 2670, a processor 2680 and other components.

[0453] The communication component 2610 is used to communicate with the server. In some embodiments, a circuit wireless fidelity (Wireless Fidelity, WiFi) module may be included. The WiFi module belongs to a short-range wireless transmission technology. The electronic device can help the user to send and receive information through the WiFi module.

[0454] The memory 2620 can be used to store software programs and data. The processor 2680 executes various functions and data processing of the terminal device 110 by running the software programs or data stored in the memory 2620. The memory 2620 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other volatile solid-state storage device. The memory 2620 stores an operating system that enables the terminal device 110 to run. In the present application, the memory 2620 can store an operating system and various application programs, and can also store a computer program for executing the method for reading chat messages in the embodiment of the present application.

[0455] The display unit 2630 can also be used to display information input by the user or information provided to the user and a graphical user interface (GUI) of various menus of the terminal device 110. Specifically, the display unit 2630 may include a display screen 2632 disposed on the front of the terminal device 110. The display screen 2632 may be configured in the form of a liquid crystal display, a light emitting diode, etc. The display unit 2630 may be used to display a chat interface, a message interpretation interface, a message setting interface, etc. in the embodiment of the present application.

[0456] The display unit 2630 can also be used to receive input digital or character information and generate signal input related to user settings and function control of the terminal device 110. Specifically, the display unit 2630 may include a touch screen 2631 arranged on the front of the terminal device 110, which can collect user touch operations on or near it, such as clicking a button, dragging a scroll box, etc.

[0457] The touch screen 2631 can be covered on the display screen 2632, or the touch screen 2631 and the display screen 2632 can be integrated to realize the input and output functions of the terminal device 110. The integrated touch screen can be referred to as a touch display screen. In this application, the display unit 2630 can display the application and the corresponding operation steps.

[0458] Camera 2640 can be used to capture static images, and users can publish images taken by camera 2640 through the application. Camera 2640 can be one or more. The object generates an optical image through the lens and projects it onto the photosensitive element. The photosensitive element can be a charge coupled device (CCD) or a complementary metal-oxide-semiconductor (CMOS) phototransistor. The photosensitive element converts the optical signal into an electrical signal, and then passes the electrical signal to the processor 2680 to convert it into a digital image signal.

[0459] The terminal device may further include at least one sensor 2650, such as an acceleration sensor 2651, a distance sensor 2652, a fingerprint sensor 2653, and a temperature sensor 2654. The terminal device may also be configured with other sensors such as a gyroscope, a barometer, a hygrometer, a thermometer, an infrared sensor, a light sensor, and a motion sensor.

[0460] The audio circuit 2660, the speaker 2661, and the microphone 2662 can provide an audio interface between the user and the terminal device 110. The audio circuit 2660 can transmit the electrical signal converted from the received audio data to the speaker 2661, which is converted into a sound signal for output. The terminal device 110 can also be configured with a volume button for adjusting the volume of the sound signal. On the other hand, the microphone 2662 converts the collected sound signal into an electrical signal, which is received by the audio circuit 2660 and converted into audio data, and then the audio data is output to the communication component 2610 to be sent to, for example, another terminal device 110, or the audio data is output to the memory 2620 for further processing.

[0461] The Bluetooth module 2670 is used to exchange information with other Bluetooth devices having Bluetooth modules through the Bluetooth protocol. For example, the terminal device can establish a Bluetooth connection with a wearable electronic device (such as a smart watch) that also has a Bluetooth module through the Bluetooth module 2670 to exchange data.

[0462] The processor 2680 is the control center of the terminal device, which uses various interfaces and lines to connect various parts of the entire terminal, and executes various functions of the terminal device and processes data by running or executing software programs stored in the memory 2620, and calling data stored in the memory 2620. In some embodiments, the processor 2680 may include one or more processing units; the processor 2680 may also integrate an application processor and a baseband processor, wherein the application processor mainly processes the operating system, the user interface, and the application program, and the baseband processor mainly processes wireless communication. It is understandable that the above-mentioned baseband processor may not be integrated into the processor 2680. In the present application, the processor 2680 can run the operating system, the application program, the user interface display and the touch response, as well as the method for reading the chat message of the embodiment of the present application. In addition, the processor 2680 is coupled to the display unit 2630.

[0463] In some possible implementations, various aspects of the chat message reading method provided by the present application may also be implemented in the form of a program product, which includes a computer program. When the program product is run on an electronic device, the computer program is used to enable the electronic device to execute the steps of the chat message reading method according to various exemplary embodiments of the present application described above in this specification. For example, the electronic device may execute the following steps: Figure 2 or Fig.21 Follow the steps shown in .

[0464] The program product may use any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. The readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of readable storage media (a non-exhaustive list) include: an electrical connection with one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above.

[0465] The program product of the embodiment of the present application may adopt a portable compact disk read-only memory (CD-ROM) and include a computer program, and can be run on an electronic device. However, the program product of the present application is not limited thereto, and in this document, a readable storage medium may be any tangible medium containing or storing a program, which can be used by or in combination with a command execution system, apparatus, or device.

[0466] A readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, wherein a readable computer program is carried. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the foregoing. A readable signal medium may also be any readable medium other than a readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with a command execution system, apparatus, or device.

[0467] The computer program embodied on the readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.

[0468] The computer program for performing the operation of the present application can be written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Java, C++, etc., and also conventional procedural programming languages ​​such as "C" language or similar programming languages. The computer program can be executed entirely on the user electronic device, partially on the user electronic device, as a separate software package, partially on the user electronic device and partially on a remote electronic device, or entirely on a remote electronic device or server. In the case of a remote electronic device, the remote electronic device can be connected to the user electronic device through any type of network including a local area network (LAN) or a wide area network (WAN), or can be connected to an external electronic device (for example, using an Internet service provider to connect through the Internet).

[0469] It should be noted that, although several units or subunits of the device are mentioned in the above detailed description, this division is merely exemplary and not mandatory. In fact, according to the embodiments of the present application, the features and functions of two or more units described above can be embodied in one unit. Conversely, the features and functions of one unit described above can be further divided into multiple units to be embodied.

[0470] In addition, although the operations of the method of the present application are described in a specific order in the drawings, this does not require or imply that the operations must be performed in this specific order, or that all the operations shown must be performed to achieve the desired results. Additionally or alternatively, some steps may be omitted, multiple steps may be combined into one step, and / or one step may be decomposed into multiple steps.

[0471] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain a computer-usable computer program.

[0472] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program commands. These computer program commands can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the commands executed by the processor of the computer or other programmable data processing device generate commands for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0473] These computer program commands may also be stored in a computer readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the commands stored in the computer readable memory produce an article of manufacture comprising a command device, the command device implementing the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0474] These computer program commands can also be loaded onto a computer or other programmable data processing device so that a series of operation steps are executed on the computer or other programmable device to produce a computer-implemented process, so that the commands executed on the computer or other programmable device provide the instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0475] Although the preferred embodiments of the present application have been described, those skilled in the art may make additional changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications falling within the scope of the present application.

[0476] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the claims of the present application and their equivalents, the present application is also intended to include these modifications and variations.

Claims

1. A method for reading chat messages, characterized in that: The method comprises: Presenting a chat interface of a target conversation group, wherein the chat interface is used to display chat messages posted in the target conversation group; In response to a selection operation triggered based on the chat interface, obtaining at least one selected target chat message; In response to a message interpretation operation triggered for the target conversation group, a message interpretation video generated based on the at least one target chat message is played, the message interpretation video comprising: a chat scene generated based on virtual objects associated with each of the publishing objects of the at least one target chat message; and chat content involved in the chat scene generated based on the at least one target chat message.

2. The method according to claim 1, characterized in that The at least one target chat message belongs to at least one topic content, and the virtual objects corresponding to each topic content are gathered in the same interactive area in the chat scene.

3. The method according to claim 2, characterized in that Each interactive area corresponds to a chat scene background related to the topic content; the method further includes: In response to a background replacement operation triggered for a first topic content among the at least one topic content, replacing a chat scene background of an interactive area corresponding to the first topic content in the message interpretation video; Among them, the replaced chat scene background is: selected from the preset scene backgrounds, or generated based on the input key information.

4. The method according to claim 2, characterized in that Each interactive area has a corresponding audio control; the method further includes: In response to an audio playback operation triggered by an audio control for a second topic content among the at least one topic content, the audio corresponding to the second topic content is played; the audio is a chat voice generated based on a target chat message related to the second topic content.

5. The method according to claim 2, characterized in that The method further comprises: In response to an interactive operation on an interactive area corresponding to a third topic content in the at least one topic content, updating a display screen corresponding to the interactive area in the message interpretation video; The interactive operation includes at least one of a zoom operation and a slide switching operation.

6. The method according to claim 5, characterized in that The chat content involved in the chat scene is presented as an animation element corresponding to the message type of the at least one target chat message; If the interactive operation is a zoom operation in a scaling operation, then before performing the zoom operation, the animation element includes only at least one of the following: Subtitle elements corresponding to text messages, speech bubble elements corresponding to text messages converted into speech, speech bubble elements corresponding to voice messages, and subtitle elements corresponding to voice messages converted into text.

7. The method according to claim 2, characterized in that The message interpretation video also includes animation effects that characterize the chat atmosphere of the virtual object, and the animation effects are animation effects for the virtual object or the interactive area.

8. The method according to any one of claims 1 to 7, characterized in that: The chat interface also includes a message interpretation control; the message interpretation control is in a non-playable state; Then, in response to the selection operation triggered based on the chat interface, obtaining at least one selected target chat message includes: In response to a selection operation triggered by the message interpretation control, determining the at least one target chat message selected in the message selection state, and updating the message interpretation control to a playable state; Then, in response to the message interpretation operation triggered for the target conversation group, playing the message interpretation video generated based on the at least one target chat message includes: In response to a message interpretation operation triggered by the message interpretation control, the chat interface jumps to a message interpretation interface, and a message interpretation video generated based on the at least one target chat message is played on the message interpretation interface.

9. The method according to claim 8, characterized in that The step of determining, in response to the selection operation triggered by the message interpretation control, the at least one target chat message selected in the message selection state comprises: In response to a selection operation triggered based on the message interpretation control, presenting the number of selectable chat messages and a select all control, as well as a selection control corresponding to each selectable chat message; In response to a selection operation triggered based on the select all control or the selection control, determining the at least one target chat message selected in the message selection state.

10. The method according to claim 8, characterized in that The method further comprises: In response to a small window display operation triggered for the message interpretation interface, presenting the message interpretation interface through a small window in the chat interface; The message interpretation video is played through the message interpretation interface.

11. The method according to any one of claims 1 to 7, characterized in that: The method further comprises: In response to a historical video viewing operation triggered based on the chat interface, a historical video list is presented, wherein the historical video list includes: each message interpretation video currently generated for the target conversation group.

12. The method according to any one of claims 1 to 7, characterized in that: The method further comprises: In response to a target operation triggered on the message interpretation video, controlling the playing of the message interpretation video based on the target operation; The target operation includes at least one of a pause operation and a double-speed operation.

13. The method according to any one of claims 1 to 7, characterized in that: The body movements of each virtual object in the message interpretation video are obtained by performing content recognition on the target chat message corresponding to the corresponding virtual object.

14. The method according to any one of claims 1 to 7, characterized in that: Before responding to the selection operation triggered based on the chat interface, the method further includes: In response to a viewing operation on a message setting interface of the target conversation group, presenting a message setting interface of the target conversation group; In response to an interpretation start operation triggered based on the message setting interface, an interpretation function for the chat message in the target dialogue group is started, and the interpretation function supports generating a corresponding message interpretation video based on the chat message.

15. The method according to any one of claims 1 to 7, characterized in that: The method further comprises: In response to a viewing operation on a message setting interface of the target conversation group, presenting a message setting interface of the target conversation group; In response to an image setting operation triggered by the target object based on the message setting interface, jumping from the message setting interface to the image setting interface; The target object is determined based on a virtual image set in the image setting interface, and the virtual image is used as a virtual object associated with the target object.

16. A method for reading chat messages, characterized in that: The method comprises: Acquire at least one target chat message, and a timestamp and a publishing object corresponding to each of the at least one target chat message, wherein the at least one target chat message is obtained by the client in response to a selection operation triggered by a chat interface based on a target conversation group, and is selected from chat messages displayed on the chat interface; Based on the at least one target chat message, and the obtained at least one timestamp and publishing object, obtaining a message interpretation video including a chat scene generated based on a virtual object associated with each of the at least one publishing object; The message interpretation video is fed back to the client, so that the client plays the message interpretation video after responding to the message interpretation operation triggered for the target conversation group.

17. The method according to claim 16, characterized in that If the message interpretation video is a video that simulates a chat scene between corresponding publishing objects based on virtual objects in a three-dimensional metaverse space, before feeding back the message interpretation video to the client, the method further includes: Encoding the message deduction video into a data format supported by the Metaverse platform; The encoded message interpretation video is imported into the Metaverse platform and associated with the scene elements in the Metaverse platform to present the message interpretation video as a video that simulates the chat scene between corresponding publishing objects based on virtual objects in a three-dimensional Metaverse space. The scene elements are: elements created in a three-dimensional Metaverse space based on the Metaverse platform for displaying the message interpretation video.

18. The method according to claim 16 or 17, characterized in that The at least one target chat message belongs to at least one topic content; Then, based on the at least one target chat message, and the obtained at least one timestamp and publishing object, obtaining a message interpretation video including a chat scene generated based on a virtual object associated with each of the at least one publishing object comprises: Determining the topic content to which each target chat message belongs by performing topic classification on the at least one target chat message; Based on each target chat message belonging to the same topic content and the corresponding timestamp, generating video screen content representing the chat scene corresponding to the topic content; In each of the video screen contents, a virtual object associated with the publishing object of the corresponding target chat message is added to integrate and generate the message interpretation video. In the message interpretation video, the virtual objects corresponding to each topic content are gathered in the same interactive area in the chat scene.

19. The method according to claim 18, characterized in that The method of generating video screen content representing a chat scene corresponding to the topic content based on target chat messages belonging to the same topic content and corresponding timestamps also includes: For each virtual object, determining the body movement of the virtual object by performing content recognition on the target chat message corresponding to the virtual object; The step of adding a virtual object associated with the publishing object of the corresponding target chat message to each of the video screen contents, and integrating and generating the message interpretation video, includes: In each of the video screen contents, a virtual object associated with the publisher of the corresponding target chat message is added in combination with the determined body movements, and the message interpretation video is integrated to generate the message interpretation video.

20. The method of claim 18, wherein: The method of generating video screen content representing a chat scene corresponding to the topic content based on target chat messages belonging to the same topic content and corresponding timestamps also includes: For each virtual object, determining an animation effect for the virtual object or the interactive area by performing content recognition on a target chat message corresponding to the virtual object; The step of adding a virtual object associated with the publishing object of the corresponding target chat message to each of the video screen contents, and integrating and generating the message interpretation video, includes: In each of the video screen contents, a virtual object associated with the publisher of the corresponding target chat message is added in combination with a determined animation effect, and the message interpretation video is integrated and generated.

21. A chat message reading device, characterized in that: include: A presenting unit, used for presenting a chat interface of a target conversation group, wherein the chat interface is used for displaying chat messages posted in the target conversation group; A selection unit, configured to obtain at least one selected target chat message in response to a selection operation triggered based on the chat interface; An interpretation unit is used to play a message interpretation video generated based on the at least one target chat message in response to a message interpretation operation triggered for the target conversation group, wherein the message interpretation video includes: a chat scene generated based on virtual objects associated with respective publishing objects of the at least one target chat message; and chat content involved in the chat scene is generated based on the at least one target chat message.

22. A chat message reading device, characterized in that: include: an acquisition unit, configured to acquire at least one target chat message, and a timestamp and a publishing object corresponding to each of the at least one target chat message, wherein the at least one target chat message is obtained by the client in response to a selection operation triggered by a chat interface based on a target conversation group, and is selected from chat messages displayed on the chat interface; A generating unit, configured to obtain, based on the at least one target chat message, and the obtained at least one timestamp and publishing object, a message interpretation video including a chat scene generated based on a virtual object associated with each of the at least one publishing object; A feedback unit is used to feed back the message interpretation video to the client, so that the client plays the message interpretation video after responding to the message interpretation operation triggered for the target dialogue group.

23. An electronic device, characterized in that: It comprises a processor and a memory, wherein the memory stores a computer program, and when the computer program is executed by the processor, the processor executes the steps of any one of the methods of claims 1 to 15 or 16 to 20.

24. A computer-readable storage medium, characterized in that: It includes a computer program. When the computer program is run on an electronic device, the computer program is used to enable the electronic device to execute the steps of any method described in claims 1 to 15 or 16 to 20.

25. A computer program product, characterized in that It includes a computer program, which is stored in a computer-readable storage medium; when a processor of an electronic device reads the computer program from the computer-readable storage medium, the processor executes the computer program, so that the electronic device performs the steps of any method described in claims 1 to 15 or 16 to 20.

Images