Virtual call processing method and device, storage medium and electronic equipment

Abstract

The invention discloses a virtual call processing method and device, a storage medium and electronic equipment, and the method comprises the steps: controlling a virtual digital object to output a dialogue input prompt voice in response to a call operation of a target user for the virtual digital object, obtaining a user input dialogue input by the target user, and carrying out the processing of the user input dialogue. And performing virtual dialogue generation processing based on the dialogue input by the user by adopting the virtual dialogue large model to obtain a virtual digital object dialogue text, and controlling the virtual digital object to perform a virtual call by using the virtual digital object dialogue text. The virtual dialogue large model provided by the invention is constructed based on a deep learning technology, natural and smooth dialogue texts can be understood and generated through training of massive real dialogue data, and by introducing the virtual dialogue large model, the real dialogue text can be understood and generated. According to the invention, the dialogue text used by the virtual digital object during the virtual conversation is closer to the dialogue effect in real life, and the humanization degree of the virtual digital object during the virtual conversation is improved.

Description

Technical Field

[0001] The present application relates to the field of artificial intelligence technology, and in particular to a virtual call processing method, device, storage medium and electronic device. Background Art

[0002] In computer technology and the virtual world, virtual digital objects usually refer to three-dimensional graphic entities generated by computers. These entities exist in a three-dimensional virtual world and can be simulations of real physical objects (such as virtual humans, animals, plants, buildings, etc.), or they can be objects created based on the creator's imagination (such as dragons in three-dimensional animations, monsters in games, etc.).

[0003] As people's requirements for human-computer interaction experience continue to improve, the market demand for voice communication technology with virtual digital objects is also growing. However, in related technologies, it is difficult to achieve the natural and smooth voice communication with virtual digital objects like face-to-face communication between people, making the interaction with virtual digital objects less humanized. Summary of the invention

[0004] The embodiments of the present application provide a virtual call processing method, device, storage medium and electronic device, which can make the interaction between the user and the virtual digital object more natural and smooth, and improve the humanization of the interaction with the virtual digital object.

[0005] In a first aspect, an embodiment of the present application provides a virtual call processing method, including:

[0006] In response to a call operation of the target user on the virtual digital object, controlling the virtual digital object to output a dialogue input prompt voice;

[0007] Obtaining a user input dialogue input by the target user, and using a virtual dialogue macromodel to generate a virtual dialogue based on the user input dialogue to obtain a virtual digital object dialogue text;

[0008] The virtual digital object is controlled to make a virtual call using the virtual digital object conversation text.

[0009] In a possible implementation, controlling the virtual digital object to use the virtual digital object conversation text to conduct a virtual call includes:

[0010] Generate a response animation script based on the virtual digital object dialogue text through the virtual dialogue model;

[0011] According to the above answering animation script, the above virtual digital object is driven to conduct a virtual call.

[0012] In a possible implementation, the above-mentioned virtual dialogue macro model is used to generate a response animation script based on the above-mentioned virtual digital object dialogue text, including:

[0013] Determine the call expression information, call posture information and call background information of the virtual digital object based on the virtual digital object dialogue text;

[0014] The above-mentioned answering animation script is generated based on the above-mentioned call expression information, call posture information, call background information and the above-mentioned answering text.

[0015] In a possible implementation, the step of driving the virtual digital object to make a virtual call according to the answering animation script includes:

[0016] obtaining an object-driven model for a virtual digital object;

[0017] The above-mentioned answering animation script is input into the object-driven model, and the above-mentioned virtual digital object is driven by the above-mentioned object-driven model to conduct a virtual call.

[0018] In a possible implementation, before controlling the virtual digital object to use the virtual digital object conversation text to make a virtual call, the method further includes:

[0019] By means of the virtual dialogue model, a target thinking animation script is determined based on the user input dialogue;

[0020] Based on the above target thinking animation script, the above virtual digital object is driven to output a reply thinking animation.

[0021] In a possible implementation, the above-mentioned determining the target thinking animation script based on the above-mentioned user input dialogue includes:

[0022] Determine the conversation intention and conversation domain in the above user input conversation;

[0023] Determine the emotional thinking factor, difficulty thinking factor, and scenario thinking factor based on the conversation intention and conversation domain;

[0024] According to the above-mentioned thinking emotion factors, the above-mentioned thinking difficulty factors and the thinking scene factors, the above-mentioned target thinking animation script is queried from the factor thinking script mapping relationship.

[0025] In a possible implementation, after controlling the virtual digital object to output the dialogue input prompt voice, the method further includes:

[0026] If the user input dialogue input by the target user is not detected within the preset first time period, determining the interactive reminder information for the virtual digital object;

[0027] Output the above interactive reminder information.

[0028] In a possible implementation, after controlling the virtual digital object to output the dialogue input prompt voice, the method further includes:

[0029] If a user input dialogue input by the target user is detected within a preset second time period, then determining voice reception prompt information for the virtual digital object;

[0030] Output the above voice reception prompt information.

[0031] In a second aspect, an embodiment of the present application further provides a virtual call processing device, including:

[0032] A prompt module, configured to control the virtual digital object to output a dialogue input prompt voice in response to a call operation of the target user on the virtual digital object;

[0033] A generation module, used for obtaining the user input dialogue input by the target user, and using a virtual dialogue macro model to perform virtual dialogue generation processing based on the user input dialogue to obtain a virtual digital object dialogue text;

[0034] The control module is used to control the virtual digital object to make a virtual call using the virtual digital object conversation text.

[0035] In a third aspect, an embodiment of the present application further provides a computer-readable storage medium on which a computer program is stored. When the computer program is run on a computer, the computer executes a virtual call processing method as provided in any embodiment of the present application.

[0036] In a fourth aspect, an embodiment of the present application further provides an electronic device, comprising a processor and a memory, wherein the memory has a computer program, and the processor is used to execute a virtual call processing method provided in any embodiment of the present application by calling the computer program.

[0037] The technical solution provided in the embodiment of the present application controls the virtual digital object to output a dialogue input prompt voice in response to the call operation of the target user on the virtual digital object, obtains the user input dialogue input by the target user, uses the virtual dialogue macro model to generate and process the virtual dialogue based on the user input dialogue to obtain the virtual digital object dialogue text, and controls the virtual digital object to use the virtual digital object dialogue text to make a virtual call. The virtual dialogue macro model provided in the present application is a complex model built based on deep learning technology. It is trained with a large amount of real dialogue data and can understand and generate natural and fluent dialogue text. Therefore, the present application generates the virtual digital object dialogue text for the user input dialogue by introducing the virtual dialogue macro model, which can make the virtual digital object dialogue text used by the virtual digital object in the virtual call closer to the dialogue effect in real life, and improve the humanization of the virtual digital object in the virtual dialogue. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For those skilled in the art, other drawings can be obtained based on these drawings without creative work.

[0039] Figure 1 A first flow chart of a virtual call processing method provided in an embodiment of the present application.

[0040] Figure 2 A schematic diagram of a first call interface of the virtual call processing method provided in an embodiment of the present application.

[0041] Figure 3 A schematic diagram of a second call interface of the virtual call processing method provided in an embodiment of the present application.

[0042] Figure 4 A schematic diagram of a third call interface of the virtual call processing method provided in an embodiment of the present application.

[0043] Figure 5 A fourth call interface schematic diagram of the virtual call processing method provided in an embodiment of the present application.

[0044] Figure 6 A fifth call interface schematic diagram of the virtual call processing method provided in an embodiment of the present application.

[0045] Figure 7 A sixth call interface schematic diagram of the virtual call processing method provided in an embodiment of the present application.

[0046] Figure 8A seventh call interface schematic diagram of the virtual call processing method provided in an embodiment of the present application.

[0047] Fig. 9 A second flow chart of the virtual call processing method provided in an embodiment of the present application.

[0048] Fig.10 A schematic diagram of the structure of a virtual call processing device provided in an embodiment of the present application.

[0049] Fig.11 A first structural schematic diagram of an electronic device provided in an embodiment of the present application.

[0050] Fig.12 A second structural schematic diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0051] The technical solutions in the embodiments of the present application will be described clearly and completely below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present application.

[0052] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0053] The embodiment of the present application provides a virtual call processing method, and the execution subject of the virtual call processing method can be a virtual call processing device provided in the embodiment of the present application, or an electronic device integrated with the virtual call processing device, wherein the virtual call processing device can be implemented in hardware or software. The electronic device can be a smart watch, a smart phone, a tablet computer, a PDA, a laptop computer, or a desktop computer.

[0054] Virtual human technology can provide users with a communication experience that is closer to face-to-face communication by constructing realistic three-dimensional virtual images and combining them with advanced interactive technology.

[0055] See also Figure 1 , Figure 1 This is a schematic diagram of a first flow chart of a virtual call processing method provided in an embodiment of the present application. The specific flow chart of the virtual call processing method provided in an embodiment of the present application may be as follows:

[0056] S110 . In response to a call operation of a target user on a virtual digital object, control the virtual digital object to output a conversation input prompt voice.

[0057] Among them, the target user refers to the specific user who is performing the operation, that is, the person who interacts with the virtual digital object in the current environment.

[0058] Among them, the target user's call operation on the virtual digital object can be a click operation performed by the target user through the virtual call button on the virtual call interface, or it can be a preset virtual gesture performed by the target user, such as air gesture, multi-finger gesture, specific sliding pattern gesture, long press gesture, etc. Among them, air gesture can be a gesture of the user moving the wrist downward without touching the screen, making a "V" sign with one hand, making a fist with one hand, etc. Multi-finger gesture can be a gesture of the user sliding the screen with three fingers down or up. Specific sliding pattern gestures can be a gesture of the user sliding the screen to slide out circle patterns, triangle patterns, rectangular patterns, etc. A long press gesture can be a user pressing the screen for a certain period of time to call out the call operation, such as pressing and holding the home button for two seconds to wake up the phone. Figure 2 It should be noted that the call operation of the target user on the virtual digital object in the virtual call processing method provided in this specification is not limited to the above examples, and may also include other call operations in the specific implementation, which is not limited in this embodiment of the specification.

[0059] For example, see Figure 2 , Figure 2 The character corresponding to the virtual digital object illustrated in the figure is "Badilong", and the virtual call button on the call interface can be a dial key. The target user can conduct a virtual call with the virtual digital object by clicking the dial key.

[0060] Among them, virtual digital objects usually refer to three-dimensional graphic entities generated by computers. These entities exist in a three-dimensional virtual world and can be simulations of real physical objects in reality (such as virtual humans, animals, plants, buildings, etc.), or they can be object images created based on the creator's imagination (such as dragons in three-dimensional animations, monsters in games, etc.). There can be multiple characters corresponding to the virtual digital objects in this application, and users can choose different characters as the images of virtual digital objects.

[0061] The dialogue input prompt voice refers to the sound prompt issued by the system to guide the user to input or operate during the human-computer interaction process. For example, the virtual digital object can issue a voice such as "Hello, I am Badilon, what do you want to ask me?", "I am listening, please speak" and so on.

[0062] For example, see Figure 3 , Figure 3 The character corresponding to the virtual digital object shown in the figure is "Brother Xiaozhi". Figure 3 When the character of "Brother Xiaozhi" is used, the dialogue input prompt voice can be "I'm listening, please speak", and the text corresponding to the output input prompt voice can be displayed on the call interface at the same time.

[0063] In the embodiment of the present application, the electronic device can control the virtual digital object to output a conversation input prompt voice in response to the target user's call operation on the virtual digital object.

[0064] S120, obtaining a user input dialogue input by a target user, and using a virtual dialogue macro model to perform virtual dialogue generation processing based on the user input dialogue to obtain a virtual digital object dialogue text.

[0065] The user input dialogue refers to the voice input by the user when performing human-computer interaction with the electronic device.

[0066] The virtual digital object dialogue text refers to the reply dialogue text of the virtual digital object to the user input dialogue.

[0067] Among them, the virtual dialogue model is configured to generate virtual dialogue based on user input dialogue to obtain virtual digital object dialogue text.

[0068] In the embodiment of the present application, the electronic device obtains a user input dialogue input by a target user, and uses a virtual dialogue macro model to perform virtual dialogue generation processing based on the user input dialogue to obtain a virtual digital object dialogue text.

[0069] In a possible implementation, the model training process of the virtual dialogue model may be as follows:

[0070] (1) obtaining a speech-to-text model and a basic large language model, and creating an initial virtual dialogue large model for a call interaction scenario with a virtual digital object based on the speech-to-text model and the basic large language model;

[0071] Among them, the basic large language model includes but is not limited to large models in the field of natural language processing (NLP), such as GPT-3, GPT-4, ChatGPT, BERT, and RoBERTa. The speech-to-text model can be Deep Speech, Baidu Speech, Google Cloud Speech-to-Text, and OpenAI Whisper.

[0072] (2) obtaining sample user input dialogues and labeling the sample user input dialogues with virtual digital object dialogue text labels;

[0073] (3) using sample user input dialogues to perform at least one round of model training on the initial virtual dialogue model;

[0074] (4) During the model forward propagation training process, the initial virtual dialogue model is used to determine the predicted virtual digital object dialogue text based on the sample user input dialogue;

[0075] (5) During the model back-propagation training process, the dialogue text prediction loss is determined based on the predicted virtual digital object dialogue text and the virtual digital object dialogue text label, and the dialogue text prediction loss is used to adjust the model parameters of the initial virtual dialogue large model until the initial virtual dialogue large model completes model training and obtains the virtual dialogue large model.

[0076] Specifically, based on the predicted virtual digital object dialogue text and the virtual digital object dialogue text label, the dialogue text prediction loss is calculated using a first preset model loss calculation formula. The first preset model loss calculation formula can be a comparison loss calculation formula, a cross entropy loss calculation formula, a hinge loss calculation formula, or one or more fittings in the related art.

[0077] Optionally, the model training termination conditions of the initial virtual dialogue large model may include, for example, the value of the loss function is less than or equal to a preset loss function threshold, the number of iterations reaches a preset number threshold, etc. The specific model training termination conditions can be determined based on actual conditions and are not specifically limited here.

[0078] In one possible implementation, before controlling the virtual digital object to conduct a virtual call using the virtual digital object dialogue text, the virtual dialogue model can also be used to determine a target thinking animation script based on the user input dialogue, and drive the virtual digital object to output a reply thinking animation based on the target thinking animation script.

[0079] Among them, the virtual dialogue model is also configured to determine the target thinking animation text based on the user input dialogue.

[0080] Among them, the thinking animation script, that is, the action script of the animation character's thinking, is a crucial part of the animation production process. It describes in detail all the key elements of the animation work, such as the content, plot development, character behavior, dialogue, scene transition, and visual effects. Animation characters refer to virtual digital objects. The action script of the animation character's thinking can include the following aspects:

[0081] (1) Scene description: First, the script will describe the environment and atmosphere of the current scene to provide a suitable background for the animated characters. This includes time (day, night, dusk, etc.), location (indoors, outdoors, specific places, etc.) and environmental elements (light, color, sound effects, etc.) to create the atmosphere required for thinking.

[0082] (2) Character state: Next, the script will describe in detail the body language, facial expressions, and inner thoughts of the animated character when thinking. Body language may include frowning, scratching the head, staring into the distance, or looking down in thought; facial expressions may show confusion, doubt, concentration, or a flash of inspiration; inner thoughts can be expressed through narration or inner monologue to show the character's thinking process.

[0083] (3) Action sequence: The script will connect a series of actions during the character’s thinking process in chronological order to form a coherent sequence. These actions may be small body movements or large body rotations or position changes, aiming to show the depth and breadth of the character’s thinking through changes in action.

[0084] (4) Dialogue and narration: If there is dialogue or narration during the thinking process, the script will also record it accordingly. Dialogue may be the communication between the character and others, used to discuss problems or seek answers; narration may be the inner voice of the character, directly expressing his or her thoughts or emotional state.

[0085] (5) Visual and sound effects: The script may also include visual and sound effects. For example, when a character thinks about a key point, there may be special effects such as flashing lights or sparks of thought; at the same time, there may be corresponding sound effects to enhance the expressiveness of the picture, such as light music when thinking or sound effects processing of inner monologue.

[0086] In an embodiment of the present application, through the above-mentioned thinking animation script for the virtual digital object, a thinking animation can be presented when the virtual digital object conducts voice interaction with the target user, thereby making the virtual call process closer to a natural voice conversation and closer to the conversation effect in real life, thereby improving the humanization of the virtual digital object during virtual conversations.

[0087] Specifically, when determining the target thinking animation script based on the user input dialogue, the dialogue intention and dialogue domain in the user input dialogue can be determined, and the thinking emotion elements, thinking difficulty elements and thinking scene elements can be determined based on the dialogue intention and dialogue domain. According to the thinking emotion elements, thinking difficulty elements and thinking scene elements, the target thinking animation script is queried from the element thinking script mapping relationship.

[0088] The conversation intention refers to the core needs, goals, or expectations expressed by the user (or speaker) during the conversation. It is an important basis for judging the user's next actions and the key for the dialogue system to understand and respond to user requests. Specifically, the conversation intention can include the following aspects:

[0089] (1) Core needs: the purpose or information that users want to achieve through conversations. For example, in scenarios such as checking the weather, booking a restaurant, or asking for directions, the user’s intention is to obtain relevant weather information, restaurant reservation services, or route guidance.

[0090] (2) Behavioral motivation: The motivation or reason behind a user initiating a conversation. This may be related to the user’s interests, needs, emotions, or psychological state. For example, a user may initiate a conversation because of curiosity, the need to solve a problem, to express an opinion, or to seek help.

[0091] (3) Expected response: The user's expectation of the response that the dialogue system may give. This includes the expected type of information, format, level of detail, etc. For example, the user may expect the system to provide answers in a concise and clear manner, or to provide multiple options for selection.

[0092] The dialogue domain refers to the scope and specific scenarios involved in the content of the user input dialogue. For example, when the user inputs the dialogue "Do you know the black holes in the universe", the corresponding dialogue domain is the astronomical science field. For another example, when the user inputs the dialogue "Will it rain today?", the corresponding dialogue domain is the weather forecast field.

[0093] In the embodiment of the present application, the target user's conversation intention and conversation scope are analyzed through the user's input dialogue, and a corresponding response is generated accordingly. This helps to improve the intelligence level of the virtual call, so that the virtual call function can more accurately understand the user's needs and provide more intimate and personalized services.

[0094] The mapping relationship between the element thinking script records the corresponding relationship between the element information and the thinking script. The element information may include the thinking emotion element, the thinking difficulty element, the thinking scene element, and the like.

[0095] The thinking emotion element refers to the emotion or emotional state associated with the cognitive activity of thinking. In order to make the subsequently generated thinking animation script more humanized, the display of thinking emotions is added to the virtual digital object. For example, the emotion can be manifested through the state of deep thinking, the state of calm thinking, the state of excited thinking, the state of confused thinking, etc.

[0096] The difficulty factor of thinking can determine the difficulty of replying according to the content of the user input dialogue, and thus determine the difficulty factor of thinking according to the difficulty level. For example, the time of thinking and the thinking action in the target animation script can be determined according to the difficulty factor of thinking.

[0097] The thinking scene element can be determined based on the scene and field involved in the user input dialogue. For example, if the user input dialogue is in the field of astronomical science, then the thinking scene element can be to add a scene image of the astronomical science field to the screen that displays the virtual digital object, such as an image of the universe, etc., and the virtual digital object can also be given a doctoral hat prop, etc.

[0098] It should be noted that the above-mentioned element information cited in this specification is not limited to the above-mentioned examples, and other element information may also be included in the specific implementation, and the embodiments of this specification are not limited to this.

[0099] Specifically, in an embodiment of the present application, thinking emotion elements, thinking difficulty elements and thinking scene elements are determined based on the dialogue intention and dialogue domain, and the target thinking animation script is queried from the element thinking script mapping relationship based on the thinking emotion elements, thinking difficulty elements and thinking scene elements.

[0100] For example, see Figure 4 , Figure 4 The character corresponding to the virtual digital object shown in the figure is "Brother Xiaozhi". The display screen of the virtual digital object corresponding to the target thinking animation script can be as follows Figure 4 As shown, a thinking bubble is displayed in the upper right corner of the virtual digital object. The effect of the thinking bubble is to enlarge from small to large, and the text "thinking" of the current status can be displayed at the same time.

[0101] S130: Control the virtual digital object to conduct a virtual call using the virtual digital object conversation text.

[0102] In the embodiment of the present application, after the virtual digital object dialogue text is obtained through the virtual dialogue macro model, the virtual digital object is controlled to use the virtual digital object dialogue text to conduct a virtual call.

[0103] Specifically, the conversation text of the virtual digital object can be converted into audio for the character corresponding to the virtual digital object through text-to-speech technology, and the audio is output, so as to realize the conversation interaction between the virtual digital object and the target user.

[0104] In a possible implementation, after controlling the virtual digital object to output the dialogue input prompt voice, the following steps may also be included:

[0105] If the user input dialogue input by the target user is not detected within the preset first time period, interaction reminder information for the virtual digital object is determined and the interaction reminder information is output.

[0106] The interactive reminder information refers to the notification and reminder-related information sent by the virtual digital object to the user to remind the user to perform interactive input when the virtual digital object interacts with the user.

[0107] The preset first duration is a duration set by technicians in this field according to actual conditions.

[0108] For example, the preset first duration can be set to 5 seconds, that is, if the user input dialogue input by the target user is not detected within five seconds, an interactive prompt message such as "You don't seem to be speaking" can be output. For example, please refer to Figure 5 , Figure 5 The character corresponding to the virtual digital object illustrated in the figure is "Buddy Dragon". When no voice input of the target user is detected within 5 seconds, an audio of "You don't seem to be speaking" can be issued through Buddy Dragon, and the text corresponding to the audio can be displayed at the same time.

[0109] For another example, the preset second duration can be set to 60 seconds. Figure 6 , Figure 6 The character corresponding to the virtual digital object shown in the figure is "Badilong". If the user input dialogue input by the target user is not detected within 60 seconds, an interactive prompt message such as "click the screen to continue chatting" can be output. When the user input dialogue cannot be detected within the 60 seconds, the audio collection function of the electronic device is turned off to save power. The interactive prompt message prompts the user to confirm that the user currently wants to make a call by performing a specific operation, and then the audio collection function is turned on. The specific operation requires the user to click the screen to continue chatting, as shown in the above prompt.

[0110] The interactive reminder information set in this application can stimulate the user's enthusiasm for participation and promote communication and interaction between users by sending interactive reminder information in a timely manner.

[0111] In a possible implementation, after controlling the virtual digital object to output the dialogue input prompt voice, the following steps may also be included:

[0112] If a user input dialogue input by the target user is detected within the preset second time period, voice reception prompt information for the virtual digital object is determined and the voice reception prompt information is output.

[0113] Among them, voice reception prompt information refers to a function in which, when receiving a user input dialogue, the device or application reminds the user that it is listening through sound, vibration, pattern or other means.

[0114] Among them, the preset second time length is smaller than the above-mentioned preset first time length, and the preset second time length is a time length set by technical personnel in this field according to actual conditions. For example, the preset second time length may be 1 second, that is, if the input dialogue of the target user is detected within 1 second, a voice reception prompt message such as "listening" is output.

[0115] For example, see Figure 7 , Figure 7 The virtual digital object shown in the figure corresponds to the character "Badilong". When the user performs voice input, the call interface may display the following Figure 7 As shown, the four dynamically enlarged and reduced rectangular patterns at the bottom of the Badilon can remind the user that the electronic device is currently in a listening state, that is, it is currently collecting the user's voice. In addition, when the user wants to end the call, he can also hang up the call through the dial key to end the call interaction. After the call ends, the chat text record between the user and the virtual digital object can be displayed through the call interface.

[0116] In addition, when the user and the virtual digital object are interacting through a call, subtitles can be turned on to display the content of the interaction between the user and the virtual digital object. For example, please refer to Figure 8 The subtitle display effect shown. Figure 8 The character corresponding to the virtual digital object illustrated in the figure is "Brother Xiaozhi".

[0117] The purpose of setting the voice reception prompt information in this application is to improve the user experience and efficiency.

[0118] In specific implementation, the present application is not limited by the execution order of the various steps described. If no conflict occurs, some steps can be performed in other orders or simultaneously.

[0119] As can be seen from the above, the virtual call processing method provided in the embodiment of the present application controls the virtual digital object to output a dialogue input prompt voice in response to the call operation of the target user on the virtual digital object, obtains the user input dialogue input by the target user, uses the virtual dialogue macro model to generate and process the virtual dialogue based on the user input dialogue to obtain the virtual digital object dialogue text, and controls the virtual digital object to use the virtual digital object dialogue text to make a virtual call. The virtual dialogue macro model provided in the present application is a complex model built based on deep learning technology. It is trained with massive real dialogue data and can understand and generate natural and fluent dialogue text. Therefore, the present application generates the virtual digital object dialogue text for the user input dialogue by introducing the virtual dialogue macro model, which can make the virtual digital object dialogue text used by the virtual digital object in the virtual call closer to the dialogue effect in real life, and improve the humanization of the virtual digital object in the virtual dialogue.

[0120] The method described in the above embodiments is further described in detail below with examples.

[0121] See also Fig. 9 , Fig. 9 A second flow chart of the virtual call processing method provided in the embodiment of the present application. The specific flow of the virtual call processing method provided in the embodiment of the present application may be as follows:

[0122] S210: In response to the target user's call operation on the virtual digital object, control the virtual digital object to output a conversation input prompt voice.

[0123] For example, the target user triggers a call operation on the virtual digital object through a preset air gesture, and the electronic device controls the virtual digital object to output a dialogue prompt voice "Hello, I am Badilon, what do you want to ask me?"

[0124] For another example, the target user triggers a call operation on the virtual digital object through a preset specific sliding pattern gesture, and the electronic device controls the virtual digital object to output a dialogue prompt voice "Hello, I am Brother Xiaozhi, what do you want to ask me?"

[0125] S220, obtaining a user input dialogue input by a target user, and using a virtual dialogue macromodel to perform virtual dialogue generation processing based on the user input dialogue to obtain a virtual digital object dialogue text.

[0126] For example, if the user inputs a dialogue "Badilong, do you know about black holes in the universe?", then the virtual digital object dialogue text obtained by using the virtual dialogue macro model to generate virtual dialogues based on the user input dialogue can be "A black hole is a celestial body that exists in the universe in modern general relativity. Its gravity is so strong that any matter and radiation, including light, will be swallowed up by the black hole's strong gravity when it approaches the event horizon of the black hole and cannot escape its boundary. The boundary of a black hole is called the "event horizon", which is a one-way boundary. Once matter or information crosses this boundary, it can no longer return or escape the gravity of the black hole..."

[0127] For another example, if the user inputs a dialogue like "Brother Xiaozhi, I don't like vegetables, can I not eat vegetables?", then the virtual dialogue big model is used to generate a virtual dialogue based on the user input dialogue to obtain a virtual digital object dialogue text such as "Although you may not like to eat vegetables, the role of vegetables in the diet is irreplaceable. Vegetables are rich in various vitamins, minerals, dietary fiber and antioxidants, which are essential for maintaining human health and preventing diseases, so you still have to eat a moderate amount of vegetables..."

[0128] S230, generating a response animation script based on the virtual digital object dialogue text through the virtual dialogue macro model.

[0129] Among them, the virtual dialogue model is also configured to generate a response animation copy script based on the virtual digital object dialogue text.

[0130] The answering animation script, that is, the action script of the animated character's answer, contains various dialogue scenarios and corresponding answering contents that the virtual digital object may encounter during the virtual call. These answering contents are not only text, but may also include descriptions of expressions, actions, postures and other information, so that the virtual digital object can interact in a more vivid and natural way. The animated character refers to the virtual digital object. For example, the action script of the animated character's answer may include the following aspects:

[0131] (1) Scene description: First, the script will describe the environment and atmosphere of the current scene to provide a suitable background for the animated character. This includes time (day, night, dusk, etc.), location (indoors, outdoors, specific places, etc.) and environmental elements (light, color, sound effects, etc.) to create the atmosphere required for the response.

[0132] (2) Character status: Next, the script will describe in detail the body language and facial expressions of the animated character when responding. For example, when the user inputs a dialogue related to popular science, the body language can be to keep the body straight, relax the shoulders, show a confident and professional image, and the facial expression can be serious and meticulous.

[0133] (3) Action sequence: The script will connect the series of actions of the animated character in the response process in chronological order to form a coherent sequence. These actions may be small body movements or large body rotations or position changes.

[0134] (4) Dialogue: Dialogue is the audio of the interaction between the virtual digital object and the target user.

[0135] (5) Visual and audio prompts: For example, when a virtual digital object answers a question, a scene image related to the virtual digital object’s dialogue text can be displayed, along with sound effects that match the scene.

[0136] Specifically, when generating a response animation script based on the virtual digital object dialogue text through the virtual dialogue model, the call expression information, call posture information and call background information of the virtual digital object can be determined based on the virtual digital object dialogue text, and the response animation script can be generated based on the call expression information, call posture information, call background information and the response text.

[0137] S240: driving the virtual digital object to conduct a virtual call according to the answering animation script.

[0138] In an embodiment of the present application, after generating a response animation script through a virtual dialogue model, the electronic device drives the virtual digital object to conduct a virtual call according to the response animation script.

[0139] In one possible implementation, when a virtual digital object is driven to make a virtual call according to a response animation script, an object driving model for the virtual digital object can be obtained, the response animation script can be input into the object driving model, and the virtual digital object can be driven to make a virtual call through the object driving model.

[0140] Among them, the object-driven model is configured to drive the virtual digital object to conduct a virtual call through a response animation copy script.

[0141] The object-driven model, also known as the virtual digital object-driven model, is one of the core technologies for building and driving virtual digital humans (i.e., virtual digital objects). The virtual digital object-driven model can transform input data (such as text, voice, action, etc.) into a model of the output behavior (such as voice, expression, action, etc.) of the virtual digital human through a series of technical means. The virtual digital object-driven model can parse and respond to instructions in the animation copywriting script and generate corresponding control signals accordingly. These control signals can drive multiple aspects of the virtual digital object, such as facial expressions, body movements, and voice output, to achieve real-time interaction with users.

[0142] In the embodiment of the present application, the input of the object-driven model is the text content of the response animation copy script, and the output is the action and expression parameters that the virtual digital object needs to perform.

[0143] In a possible implementation, the model training process of the object-driven model may be as follows:

[0144] (1) obtaining a basic large language model, a computer vision model, and an action generation model, and creating an initial object-driven model for a virtual call scenario based on the basic large language model, the computer vision model, and the action generation model;

[0145] Among them, the basic large language models include but are not limited to large models in the field of natural language processing (NLP), such as GPT-3, GPT-4, ChatGPT, BERT, and RoBERTa models.

[0146] Among them, computer vision model refers to an algorithm model that uses machine learning and deep learning technologies to process, analyze and understand image and video data. It can simulate the human visual system's ability to perceive, recognize, understand and reason about visual information. It is widely used in image classification, object detection, semantic segmentation, instance segmentation, target tracking, image generation, action recognition, visual question and answer and many other fields.

[0147] Among them, the action generation model is based on deep learning technology, especially recurrent neural network (RNN), long short-term memory network (LSTM), Transformer and other structures, as well as reinforcement learning, imitation learning and other algorithms. These models learn a large amount of action data, understand the relationship and rules between actions, and thus generate coherent, natural and physically consistent action sequences.

[0148] It should be noted that the basic large language model is used to parse and understand the text content in the response animation copy script; the computer vision model is used to capture and process the visual features of virtual digital objects; and the action generation model is responsible for generating corresponding actions and expressions based on the text content.

[0149] (2) obtaining a sample response animation script, and labeling the sample response animation script with virtual digital object action and expression parameter labels;

[0150] (3) using the sample response animation script to perform at least one round of model training on the initial object-driven model;

[0151] (4) During the model forward propagation training process, the initial object-driven model is used to determine the predicted virtual digital object action and expression parameters based on the sample response animation script;

[0152] (5) During the model back-propagation training process, the parameter prediction loss is determined based on the predicted virtual digital object action and expression parameters and the virtual digital object action and expression parameter labels, and the parameter prediction loss is used to adjust the model parameters of the initial object driving model until the initial object driving model completes model training to obtain the object driving model.

[0153] Specifically, based on the predicted virtual digital object action and expression parameters and the virtual digital object action and expression parameter labels, the parameter prediction loss is calculated using a second preset model loss calculation formula. The second preset model loss calculation formula can be a comparison loss calculation formula, a cross entropy loss calculation formula, a hinge loss calculation formula, or one or more fittings in the related art.

[0154] Optionally, the model training termination condition of the initial object driven model may include, for example, the value of the loss function is less than or equal to a preset loss function threshold, the number of iterations reaches a preset number threshold, etc. The specific model training termination condition may be determined based on actual conditions and is not specifically limited here.

[0155] In the embodiment of the present application, driven by the object-driven model, the virtual digital object can interact with the user in real time according to the content of the answering animation script. This interaction includes not only voice communication, but also rich visual elements such as facial expressions and body movements, thereby providing users with a more immersive and realistic virtual call experience.

[0156] As can be seen from the above, the virtual call processing method proposed in the embodiment of the present application controls the virtual digital object to output a dialogue input prompt voice in response to the call operation of the target user on the virtual digital object, obtains the user input dialogue input by the target user, uses the virtual dialogue model to generate virtual dialogue based on the user input dialogue to obtain the virtual digital object dialogue text, generates a response animation copy script based on the virtual digital object dialogue text through the virtual dialogue model, and drives the virtual digital object to make a virtual call according to the response animation copy script. The virtual dialogue model provided in the present application is a complex model built based on deep learning technology. It is trained with massive real dialogue data, can understand and generate natural and smooth dialogue text, and can generate a response animation copy script according to the generated dialogue text, and drive the virtual digital object to make a virtual call through the response animation copy script, so that the dialogue text used by the virtual digital object when making a virtual call is not only closer to the dialogue effect in life, but also the virtual digital object can display the corresponding animation effect when using the dialogue text for dialogue, further improving the humanization of the virtual digital object when making a virtual dialogue.

[0157] In one embodiment, a virtual call processing device is also provided. Fig.10 , Fig.10The structure diagram of the virtual call processing device 300 provided in the embodiment of the present application is as follows: The virtual call processing device 300 is applied to an electronic device, and the virtual call processing device 300 includes a prompt module 301, a generation module 302 and a control module 303, as follows:

[0158] Prompt module 301, used for controlling the virtual digital object to output a dialogue input prompt voice in response to a target user's call operation on the virtual digital object;

[0159] A generation module 302 is used to obtain the user input dialogue input by the target user, and use a virtual dialogue macro model to perform virtual dialogue generation processing based on the user input dialogue to obtain a virtual digital object dialogue text;

[0160] The control module 303 is used to control the virtual digital object to make a virtual call using the virtual digital object conversation text.

[0161] In a possible implementation, the control module 303 may be used to:

[0162] Generate a response animation script based on the virtual digital object dialogue text through the virtual dialogue model;

[0163] According to the above answering animation script, the above virtual digital object is driven to conduct a virtual call.

[0164] In a possible implementation, the control module 303 may be used to:

[0165] Determine the call expression information, call posture information and call background information of the virtual digital object based on the virtual digital object dialogue text;

[0166] The above-mentioned answering animation script is generated based on the above-mentioned call expression information, call posture information, call background information and the above-mentioned answering text.

[0167] In a possible implementation, the control module 303 may be used to:

[0168] obtaining an object-driven model for a virtual digital object;

[0169] The above-mentioned answering animation script is input into the object-driven model, and the above-mentioned virtual digital object is driven by the above-mentioned object-driven model to conduct a virtual call.

[0170] In a possible implementation, the control module 303 may also be used to:

[0171] By means of the virtual dialogue model, a target thinking animation script is determined based on the user input dialogue;

[0172] Based on the above target thinking animation script, the above virtual digital object is driven to output a reply thinking animation.

[0173] In a possible implementation, the control module 303 may also be used to:

[0174] Determine the conversation intention and conversation domain in the above user input conversation;

[0175] Determine the emotional thinking factor, difficulty thinking factor, and scenario thinking factor based on the dialogue intention and dialogue domain;

[0176] According to the above-mentioned thinking emotion factors, the above-mentioned thinking difficulty factors and the thinking scene factors, the above-mentioned target thinking animation script is queried from the factor thinking script mapping relationship.

[0177] In a possible implementation, the control module 303 may also be used to:

[0178] If no user input dialogue input by the target user is detected within the preset first time period, determining interactive reminder information for the virtual digital object;

[0179] Output the above interactive reminder information.

[0180] In one possible implementation,

[0181] If a user input dialogue input by the target user is detected within a preset second time period, then determining voice reception prompt information for the virtual digital object;

[0182] Output the above voice reception prompt information.

[0183] It should be noted that the virtual call processing device provided in the embodiment of the present application belongs to the same concept as the virtual call processing method in the above embodiment. Any method provided in the virtual call processing method embodiment can be implemented through the virtual call processing device. The specific implementation process is detailed in the virtual call processing method embodiment, which will not be repeated here.

[0184] In addition, in order to better implement the virtual call processing method in the embodiment of the present application, on the basis of the virtual call processing method, the present application also provides an electronic device, which can be a smart watch, a smart phone and other devices. Fig.11 , Fig.11 The first structural diagram of the electronic device provided in the embodiment of the present application is as follows: The electronic device 400 includes a processor 401 and a memory 402. The processor 401 is electrically connected to the memory 402.

[0185] The processor 401 is the control center of the electronic device 400. It uses various interfaces and lines to connect various parts of the entire electronic device. By running or calling the computer program stored in the memory 402, and calling the data stored in the memory 402, it executes various functions of the electronic device and processes data, thereby monitoring the electronic device as a whole. Among them, the processor 401 can be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor, etc.

[0186] The memory 402 can be used to store computer programs and data. The computer program stored in the memory 402 contains instructions that can be executed in the processor. The computer program can form various functional modules. The processor 401 executes various functional applications and data processing by calling the computer program stored in the memory 402. Among them, the memory 402 can mainly include a program storage area and a data storage area. The program storage area can store an operating system, an application required for at least one function (such as a sound playback function, an image playback function, etc.), etc.; the data storage area can store data created according to the use of the electronic device 400 (such as audio data, video data, etc.), etc. In addition, the memory can include a high-speed random access memory, and can also include a non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart memory card (Smart MediaCard, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), at least one disk storage device, a flash memory device, or other volatile solid-state storage devices.

[0187] In this embodiment, the processor 401 in the electronic device 400 loads instructions corresponding to the processes of one or more computer programs into the memory 402 according to the following steps, and the processor 401 runs the computer programs stored in the memory 402 to implement various functions:

[0188] In response to a call operation of the target user on the virtual digital object, controlling the virtual digital object to output a dialogue input prompt voice;

[0189] Obtaining a user input dialogue input by the target user, and using a virtual dialogue macromodel to generate a virtual dialogue based on the user input dialogue to obtain a virtual digital object dialogue text;

[0190] The virtual digital object is controlled to make a virtual call using the virtual digital object conversation text.

[0191] In one possible implementation, see Fig.12 , Fig.12 A second structural diagram of an electronic device provided in an embodiment of the present application. The electronic device 400 further includes: a radio frequency circuit 403, a display screen 404, a control circuit 405, an input unit 406, an audio circuit 407, a sensor 408, and a power supply 409. The processor 401 is electrically connected to the radio frequency circuit 403, the display screen 404, the control circuit 405, the input unit 406, the audio circuit 407, the sensor 408, and the power supply 409, respectively.

[0192] The radio frequency circuit 403 is used to send and receive radio frequency signals to communicate with network devices or other electronic devices through wireless communication.

[0193] The display screen 404 may be used to display information input by a user or information provided to a user and various graphical user interfaces of the electronic device. These graphical user interfaces may be composed of images, texts, icons, videos and any combination thereof.

[0194] The control circuit 405 is electrically connected to the display screen 404 and is used to control the display screen 404 to display information.

[0195] The input unit 406 can be used to receive input numbers, character information or user feature information (such as fingerprints), and generate keyboard, mouse, joystick, optical or trackball signal input related to user settings and function control. The input unit 406 can include a fingerprint recognition module.

[0196] The audio circuit 407 can provide an audio interface between the user and the electronic device through a speaker and a microphone. The audio circuit 407 includes a microphone. The microphone is electrically connected to the processor 401. The microphone is used to receive voice information input by the user.

[0197] The sensor 408 is used to collect external environment information. The sensor 408 may include one or more sensors such as an environment brightness sensor, an acceleration sensor, and a gyroscope.

[0198] The power supply 409 is used to supply power to various components of the electronic device 400. In a possible implementation, the power supply 409 may be logically connected to the processor 401 through a power management system, so that the power management system can manage charging, discharging, power consumption, and other functions.

[0199] Although not shown in the figure, the electronic device 400 may also include a camera, a Bluetooth module, etc., which will not be described in detail here.

[0200] In this embodiment, the processor 401 in the electronic device 400 loads instructions corresponding to the processes of one or more computer programs into the memory 402 according to the following steps, and the processor 401 runs the computer programs stored in the memory 402 to implement various functions:

[0201] In response to a call operation of the target user on the virtual digital object, controlling the virtual digital object to output a dialogue input prompt voice;

[0202] Obtaining a user input dialogue input by the target user, and using a virtual dialogue macromodel to generate a virtual dialogue based on the user input dialogue to obtain a virtual digital object dialogue text;

[0203] The virtual digital object is controlled to make a virtual call using the virtual digital object conversation text.

[0204] In a possible implementation, when the processor 401 controls the virtual digital object to use the virtual digital object conversation text to make a virtual call, the processor 401 may execute:

[0205] Generate a response animation script based on the virtual digital object dialogue text through the virtual dialogue model;

[0206] According to the above answering animation script, the above virtual digital object is driven to conduct a virtual call.

[0207] In a possible implementation, when the processor 401 generates a response animation script based on the virtual digital object dialogue text through the virtual dialogue macro model, it can execute:

[0208] Determine the call expression information, call posture information and call background information of the virtual digital object based on the virtual digital object dialogue text;

[0209] The above-mentioned answering animation script is generated based on the above-mentioned call expression information, call posture information, call background information and the above-mentioned answering text.

[0210] In a possible implementation, when the processor 401 drives the virtual digital object to make a virtual call according to the answering animation script, the processor 401 may execute:

[0211] obtaining an object-driven model for a virtual digital object;

[0212] The above-mentioned answering animation script is input into the object-driven model, and the above-mentioned virtual digital object is driven by the above-mentioned object-driven model to conduct a virtual call.

[0213] In a possible implementation, before executing controlling the virtual digital object to use the virtual digital object conversation text to make a virtual call, the processor 401 may further execute:

[0214] By means of the virtual dialogue model, a target thinking animation script is determined based on the user input dialogue;

[0215] Based on the above target thinking animation script, the above virtual digital object is driven to output a reply thinking animation.

[0216] In a possible implementation, when executing the target thinking animation script determined based on the user input dialogue, the processor 401 may execute:

[0217] Determine the conversation intention and conversation domain in the above user input conversation;

[0218] Determine the emotional thinking factor, difficulty thinking factor, and scenario thinking factor based on the dialogue intention and dialogue domain;

[0219] According to the above-mentioned thinking emotion factors, the above-mentioned thinking difficulty factors and the thinking scene factors, the above-mentioned target thinking animation script is queried from the factor thinking script mapping relationship.

[0220] In a possible implementation, after executing the above-mentioned control of the above-mentioned virtual digital object to output the dialogue input prompt voice, the processor 401 may execute:

[0221] If no user input dialogue input by the target user is detected within the preset first time period, determining interactive reminder information for the virtual digital object;

[0222] Output the above interactive reminder information.

[0223] In a possible implementation, when the processor 401 controls the virtual digital object to output the dialogue input prompt voice, it may execute:

[0224] If a user input dialogue input by the target user is detected within a preset second time period, then determining voice reception prompt information for the virtual digital object;

[0225] Output the above voice reception prompt information.

[0226] An embodiment of the present application further provides a computer-readable storage medium, in which a computer program is stored. When the computer program runs on a computer, the computer executes the virtual call processing method described in any of the above embodiments.

[0227] It should be noted that, a person skilled in the art can understand that all or part of the steps in the various methods of the above embodiments can be completed by instructing related hardware through a computer program, and the computer program can be stored in a computer-readable storage medium, and the storage medium can include but is not limited to: read-only memory (ROM), random access memory (RAM), disk or optical disk, etc.

[0228] In addition, the terms "first", "second", and "third" in this application are used to distinguish different objects, rather than to describe a specific order. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product, or device that includes a series of steps or modules is not limited to the listed steps or modules, but some embodiments also include steps or modules that are not listed, or some embodiments also include other steps or modules inherent to these processes, methods, products, or devices.

[0229] The above is a detailed introduction to the virtual call processing method, device, storage medium and electronic device provided in the embodiments of the present application. This article uses specific examples to illustrate the principles and implementation methods of the present application. The description of the above embodiments is only used to help understand the method and core ideas of the present application; at the same time, for those skilled in the art, according to the ideas of the present application, there will be changes in the specific implementation methods and application scopes. In summary, the content of this specification should not be understood as a limitation on the present application.

Claims

1. A virtual call processing method, characterized in that: include: In response to a call operation of the target user on the virtual digital object, controlling the virtual digital object to output a dialogue input prompt voice; Acquire a user input dialogue input by the target user, and use a virtual dialogue macro model to perform virtual dialogue generation processing based on the user input dialogue to obtain a virtual digital object dialogue text; The virtual digital object is controlled to make a virtual call using the virtual digital object conversation text.

2. The method according to claim 1, characterized in that The controlling the virtual digital object to use the virtual digital object conversation text to conduct a virtual conversation includes: Generate a response animation script based on the virtual digital object dialogue text through the virtual dialogue macro model; The virtual digital object is driven to conduct a virtual call according to the answering animation script.

3. The method according to claim 2, characterized in that The method of generating a response animation script based on the virtual digital object dialogue text through the virtual dialogue macro model includes: Determining call expression information, call posture information and call background information of the virtual digital object based on the virtual digital object dialogue text; The response animation script is generated based on the call expression information, call posture information, call background information and the response text.

4. The method according to claim 2, characterized in that: The step of driving the virtual digital object to make a virtual call according to the answering animation script includes: obtaining an object-driven model for a virtual digital object; The answering animation script is input into the object-driven model, and the virtual digital object is driven by the object-driven model to conduct a virtual call.

5. The method according to claim 1, characterized in that Before controlling the virtual digital object to use the virtual digital object conversation text to make a virtual call, the method further includes: Determine the target thinking animation script based on the user input dialogue through the virtual dialogue macro model; The virtual digital object is driven to output a response thinking animation based on the target thinking animation script.

6. The method according to claim 5, characterized in that The step of determining a target thinking animation script based on the user input dialogue comprises: Determining a conversation intention and a conversation domain in the user input conversation; Determine the emotional thinking factor, difficulty thinking factor, and scenario thinking factor based on the dialogue intention and dialogue domain; The target thinking animation script is queried from the element thinking script mapping relationship according to the thinking emotion element, the thinking difficulty element and the thinking scene element.

7. The method according to claim 1, characterized in that After controlling the virtual digital object to output the dialogue input prompt voice, the method further includes: If no user input dialogue input by the target user is detected within a preset first time period, determining interactive reminder information for the virtual digital object; The interactive reminder information is output.

8. A virtual call processing device, characterized in that: include: A prompt module, configured to control the virtual digital object to output a dialogue input prompt voice in response to a call operation of the target user on the virtual digital object; A generation module, used for acquiring a user input dialogue input by the target user, and using a virtual dialogue macro model to perform virtual dialogue generation processing based on the user input dialogue to obtain a virtual digital object dialogue text; The control module is used to control the virtual digital object to make a virtual call using the virtual digital object conversation text.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed on a computer, the computer is enabled to execute the virtual call processing method according to any one of claims 1 to 7.

10. An electronic device comprising a processor and a memory, wherein the memory stores a computer program, wherein: The processor is configured to execute the virtual call processing method according to any one of claims 1 to 7 by calling the computer program.

Images