Virtual character generation method and device, electronic equipment and storage medium

Abstract

The invention provides a virtual character generation method and device, electronic equipment and a storage medium, the method is applied to the field of artificial intelligence, and the method comprises the following steps: monitoring a virtual character creation option triggered by a user, obtaining feature description information for a virtual character, the feature description information comprises image description information and sound description information of the virtual character; calling a character generation model and generating a virtual character based on the feature description information; and acquiring input user communication data in an interaction interface interacting with the user, displaying reply data corresponding to the user communication data based on the character image of the virtual character, and outputting the reply data according to the sound characteristics of the virtual character. According to the method, the virtual character can be created through the feature description information, input by the user, of the virtual character, the created virtual character is related to the feature description information input by the user, and the personalized requirement of the user is met.

Description

Technical Field

[0001] The present application relates to the field of artificial intelligence, and more specifically, to a method, device, electronic device and storage medium for generating a virtual character in the field of artificial intelligence. Background Art

[0002] With the rapid development of artificial intelligence, intelligent interactions between people and various types of devices are becoming more and more popular. For example, people can use voice assistants to complete daily tasks, query information, control smart home devices, and even have complex conversations and entertainment interactions, which greatly improves the convenience and fun of life.

[0003] However, in the process of interaction between people and devices, the images used are often single and cannot meet the personalized needs of users. Summary of the invention

[0004] The present application provides a method, device, electronic device and storage medium for generating a virtual character. The method can create a virtual character through feature description information of the virtual character input by a user. The created virtual character is related to the feature description information input by the user to meet the user's personalized needs.

[0005] In a first aspect, a method for generating a virtual character is provided, the method comprising: monitoring a user triggering an option to create a virtual character, obtaining feature description information for the virtual character, the feature description information comprising image description information and sound description information of the virtual character; calling a character generation model and generating a virtual character based on the feature description information; obtaining input user communication data in an interactive interface for interacting with the user, displaying reply data corresponding to the user communication data based on the image of the virtual character, and outputting the reply data based on the sound characteristics of the virtual character.

[0006] In an embodiment of the present application, when it is detected that a user has triggered an option to create a virtual character, a virtual character is generated based on the acquired feature description information of the virtual character, the image of the virtual character is used to display reply data corresponding to the user communication data, and the voice characteristics of the virtual character are used to output the reply data. Since the virtual character is created based on the feature description information of the virtual character input by the user, the created virtual character is related to the feature description information input by the user, thereby meeting the personalized needs of the user, and using the virtual character to reply to the reply data of the interaction with the user during the interaction process can improve the interactive experience of the user during the interaction process with the electronic device.

[0007] In combination with the first aspect, in some possible implementations, before displaying reply data corresponding to the user communication data based on the image of the virtual character, the method further includes: calling an interaction model to generate reply data based on the user communication data.

[0008] By adopting the above scheme, when receiving user communication data input by the user, reply data corresponding to the user communication data is generated through the exchange model, thereby realizing interaction with the user based on generating reply data corresponding to the user communication data input by the user.

[0009] In combination with the first aspect, in some possible implementations, obtaining feature description information for a virtual character includes: obtaining voice description information of a user, performing voice recognition on the voice description information to obtain text description information corresponding to the voice description information; extracting keyword information contained in the text description information, and determining the feature description information of the virtual character in the keyword information.

[0010] By adopting the above scheme, when the text description information is obtained, the keyword information in the text description information is extracted, and then the feature description information of the virtual character is determined in the keyword information, so that when the user inputs the voice description information, the feature description information of the virtual character is obtained from the voice description information.

[0011] In combination with the first aspect, in some possible implementations, after determining the characteristic description information of the virtual character in the keyword information, it also includes: obtaining the user's identity information, and obtaining the user's personal information based on the user's identity information; and supplementing the image description information based on the personal information.

[0012] By adopting the above scheme, the user's personal information is obtained through the user's identity information, and then the image description information is supplemented based on the personal information. Since the image description information input by the user is supplemented by the personal information, the content of the image description information is expanded and the accuracy of the generated character image is improved.

[0013] In combination with the first aspect, in some possible implementations, obtaining feature description information for a virtual character includes: obtaining the trigger duration for the user to trigger the option to create a virtual character; if the trigger duration reaches a preset duration and no feature description information for the virtual character is received, displaying a preset question in the interactive interface; obtaining the user's answer information to the preset question, and obtaining the feature description information for the virtual character based on the answer information.

[0014] By adopting the above scheme, when it is determined that the triggering time of the user triggering the option of creating a virtual character reaches the preset time and no feature description information of the virtual character input by the user is received, a preset question can be displayed in the interactive interface for interacting with the user, and the feature description information of the virtual character can be determined through the user's reply information to the preset question. Therefore, when the user is not clear about how to describe the virtual character that he needs to generate, the user can be guided by the preset question, and the feature description information of the virtual character can be generated. The feature description information can be effectively input, thereby improving the accuracy of the generated virtual character.

[0015] In combination with the first aspect, in some possible implementations, before obtaining feature description information for a virtual character, it also includes: if it is determined that the creation type of the virtual character creation option triggered by the user is a template selection type, then obtaining each currently stored character template, and displaying each character template, the feature description information of each character template, and the timbre selection information in a display interface; determining a target character template in the character template based on the received trigger information, and determining a target timbre selection information in the timbre selection information, the target character template being determined based on the feature description information of each character template; and generating a virtual character based on the target character template and the target timbre selection information.

[0016] By adopting the above scheme, when the user triggers the creation type of the virtual character creation option as the template selection type, a virtual character can be generated based on the target character template and target tone selection information selected by the user. The user can select a virtual character that meets his or her personalized needs through the character template, thereby improving the convenience of generating virtual characters.

[0017] In combination with the first aspect, in some possible implementations, after inputting the feature description information into the character generation model to generate a virtual character corresponding to the character feature information, it also includes: obtaining user modification information on the virtual character; and modifying the virtual character based on the modification information.

[0018] By adopting the above scheme, the virtual character is modified based on the received modification information, and there is no need to re-enter the feature description information, thereby improving the convenience of modifying the virtual character.

[0019] In combination with the first aspect, in some possible implementations, displaying reply data corresponding to user communication data based on the character image of the virtual character includes: determining emotional characteristics of the reply data; and controlling the virtual character to perform actions corresponding to the emotional characteristics based on the character image of the virtual character.

[0020] By adopting the above scheme, the virtual character can be controlled to perform actions corresponding to the emotional characteristics according to the emotional characteristics of the reply data, so that the actions of the virtual character are associated with the reply data, thereby improving the interactive experience between the user and the virtual character.

[0021] In a second aspect, a device for generating a virtual character is provided, the device comprising:

[0022] A monitoring unit, used to monitor the user triggering the option of creating a virtual character, and obtain feature description information for the virtual character, the feature description information including image description information and sound description information of the virtual character;

[0023] A calling unit is used to call a character generation model and generate a virtual character based on feature description information; a display unit is used to obtain input user communication data in an interactive interface for interacting with the user, display reply data corresponding to the user communication data based on the character image of the virtual character, and output the reply data based on the voice characteristics of the virtual character.

[0024] In a third aspect, an electronic device is provided, comprising: a memory for storing executable program code;

[0025] The processor is used to call and run the executable program code from the memory, so that the electronic device executes the method in the above-mentioned first aspect or any possible implementation manner of the first aspect.

[0026] In a fourth aspect, a computer program product is provided, comprising: a computer program code, which, when executed on a computer, enables the computer to execute the method in the first aspect or any possible implementation of the first aspect.

[0027] In a fifth aspect, a computer-readable storage medium is provided, which stores a computer program code. When the computer program code runs on a computer, the computer executes the method in the above-mentioned first aspect or any possible implementation manner of the first aspect. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] Figure 1 It is a scene schematic diagram of a method for generating a virtual character provided in an embodiment of the present application;

[0029] Figure 2 It is a flowchart of a method for generating a virtual character provided in an embodiment of the present application;

[0030] Figure 3 It is a flowchart of a method for generating a virtual character provided in an embodiment of the present application;

[0031] Figure 4 It is a flowchart of a method for generating a virtual character provided in an embodiment of the present application;

[0032] Figure 5 It is a scene schematic diagram of a method for generating a virtual character provided in an embodiment of the present application;

[0033] Figure 6 It is a scene schematic diagram of a method for generating a virtual character provided in an embodiment of the present application;

[0034] Figure 7 It is a structural schematic diagram of a device for generating a virtual character provided in an embodiment of the present application;

[0035] Figure 8 It is a structural schematic diagram of a device for generating a virtual character provided in an embodiment of the present application;

[0036] Fig. 9 It is a structural schematic diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0037] The technical solution in the present application will be described clearly and in detail below in conjunction with the accompanying drawings. In the description of the embodiments of the present application, unless otherwise specified, " / " means or, for example, A / B can mean A or B: "and / or" in the text is only a description of the association relationship of associated objects, indicating that there can be three relationships, for example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone. In addition, in the description of the embodiments of the present application, "multiple" means two or more than two.

[0038] In the following, the terms "first" and "second" are used for descriptive purposes only and are not to be understood as suggesting or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the features.

[0039] Figure 1 It is a scene diagram of a method for generating a virtual character provided in an embodiment of the present application.

[0040] In existing technical solutions, when an electronic device interacts with a user, a unified image is usually used for intelligent interaction with the user. This single image cannot meet the personalized needs of the user.

[0041] In an embodiment of the present application, when it is detected that a user has triggered an option to create a virtual character, a virtual character is generated based on the acquired feature description information of the virtual character, the image of the virtual character is used to display reply data corresponding to the user communication data, and the voice characteristics of the virtual character are used to output the reply data. Since the virtual character is created based on the feature description information of the virtual character input by the user, the created virtual character is related to the feature description information input by the user, thereby meeting the personalized needs of the user, and using the virtual character to reply to the reply data of the interaction with the user during the interaction process can improve the interactive experience of the user during the interaction process with the electronic device.

[0042] based on Figure 1 The scene shown is shown below. Figure 2-Figure 9 , a method for generating a virtual character provided in an embodiment of the present application is introduced in detail.

[0043] See also Figure 2, which is a flow chart of a method for generating a virtual character according to an embodiment of the present application. Figure 2 As shown, the method of the embodiment of the present application may include the following steps S101-S103.

[0044] S101, monitoring a user triggering an option to create a virtual character, and obtaining feature description information for the virtual character, the feature description information including image description information and sound description information of the virtual character;

[0045] In one embodiment, the virtual character is a virtual image used in an interactive interface when a user interacts with an electronic device; the feature description information may be the description information required to generate the virtual character, which includes description information of external features and description information of internal personality; the sound description information may be the characteristics of the sound emitted by the virtual character when interacting with the user, which may include volume, timbre, audio and other features.

[0046] Optionally, there is a virtual button “Create Virtual Character” in the interactive interface for interacting with the user. If a touch operation is detected on the virtual button, it can be determined that the user has triggered the option of creating a virtual character.

[0047] In another embodiment, the creation of a virtual character may be associated with preset gesture information. For example, the gesture information associated with the creation of a virtual character may be two-finger tapping on a display interface. If it is detected that the user taps on the display interface with two fingers, it can be determined that the user has triggered the option to create a virtual character.

[0048] Furthermore, when the user triggers the option of creating a virtual character, the feature description information input by the user for the virtual character to be created is obtained. In one embodiment, the feature description information input by the user through voice can be obtained through a microphone installed on the electronic device; in another embodiment, the feature description information input by the user can also be obtained through text input.

[0049] Optionally, in an embodiment of the present application, the user may also play audio of the sound characteristics of the virtual character that the user desires to create, and after the playback device acquires the audio, it may parse the audio to obtain sound description information of the audio.

[0050] S102, calling a character generation model and generating a virtual character based on feature description information;

[0051] In one embodiment, after the feature description information is acquired, the feature description information is input into a pre-trained character generation model, and then the character generation model generates a virtual character through the feature description information.

[0052] Optionally, in an embodiment of the present application, the character generation model may be Midjourney.

[0053] S103, obtaining input user communication data in the interactive interface for interacting with the user, displaying reply data corresponding to the user communication data based on the image of the virtual character, and outputting the reply data based on the voice characteristics of the virtual character.

[0054] In one embodiment, the user communication data may be data input by the user and used to control the dialogue with the electronic device, which may include request instructions, such as "please play a piece of light music", statement information, such as "I am in a good mood today", doubt information, such as "are there any movies you can recommend", etc. The reply data may be reply information generated by the electronic device based on the communication data input by the received user. After obtaining the virtual character corresponding to the feature description information through the character generation model, in the interactive interface for interacting with the user, the reply data of the user communication data may be displayed using the character image of the virtual character, and the reply data may be output using the voice features of the character.

[0055] It can be understood that in the embodiment of the present application, the character image of the virtual character is determined by the character generation model based on the image description information input by the user, and the voice characteristics of the virtual character are determined by the character generation model based on the voice description information input by the user.

[0056] Furthermore, in the embodiment of the present application, the reply data can also be parsed to obtain semantic information of the reply data, thereby determining the action corresponding to the semantic information, and controlling the character image of the virtual character to perform the action.

[0057] In an embodiment of the present application, when it is detected that a user has triggered an option to create a virtual character, a virtual character is generated based on the acquired feature description information of the virtual character, the virtual character's image is used to display reply data corresponding to the user's communication data, and the reply data is output using the virtual character's voice features. Since the virtual character is created based on the feature description of the virtual character input by the user, the created virtual character is related to the feature description information input by the user, thereby meeting the user's personalized needs, and using the virtual character to reply to the reply data of the interaction with the user during the interaction process can improve the interactive experience of the user during the interaction process with the electronic device.

[0058] See also Figure 3 , which is a flow chart of a method for generating a virtual character according to an embodiment of the present application. Figure 3 As shown, the method of the embodiment of the present application may include the following steps S201-S203.

[0059] S201, monitoring the user triggering the option of creating a virtual character;

[0060] Specifically, the specific process of detecting that the user triggers the option to create a virtual character can be found in the description of step S101 in the above-mentioned embodiment of the specification, which will not be elaborated here.

[0061] S202, obtaining voice description information of the user, performing voice recognition on the voice description information to obtain text description information corresponding to the voice description information;

[0062] In one embodiment, the electronic device obtains the user's voice description information of the virtual task to be created by means of a microphone device, and then performs voice recognition on the voice description information to obtain text description information corresponding to the voice description information.

[0063] Optionally, in an embodiment of the present application, before performing speech recognition on the speech description information, the collected speech description information may be first subjected to denoising to improve signal quality. The denoising method may include filtering, pre-emphasis, etc. to remove background noise and increase the energy of the high-frequency part, thereby improving the accuracy of speech recognition of the speech description information.

[0064] S203, extracting keyword information contained in the text description information, and determining feature description information of the virtual character in the keyword information.

[0065] In one embodiment, after the voice description information is converted into text description information, keyword information contained in the text description information is further extracted.

[0066] In one implementation, tools such as jieba may be used to extract keyword information contained in the text description information.

[0067] In another embodiment, the keyword extraction model can be trained, and after the voice description information is converted into text description information, the text description information is input into the keyword extraction model, and the keyword information contained in the text description information is obtained based on the output result of the keyword extraction model.

[0068] Further, after obtaining the keyword information, the electronic device determines the feature description information in the keyword information. It is understandable that in the embodiment of the present application, the electronic device can identify the words in the keyword that describe the character image of the virtual character, and then can identify the feature description information from the keyword information.

[0069] Furthermore, in an embodiment of the present application, after obtaining the feature description information, it is determined whether a virtual character can be generated directly based on the feature description information. If so, the virtual character is generated accordingly. If it is determined that the scope described by the feature description information is too large and is not sufficient to generate a virtual character that meets the user's needs, the user's identity information is obtained, and the user's personal information is obtained based on the user's identity information, and then the image description information is generated based on the personal information.

[0070] In one embodiment, if the user inputs the feature description information of the virtual character through audio, when the electronic device parses the audio to obtain the feature description information of the virtual character, it can also obtain the user's identity information through voiceprint recognition, and then obtain the corresponding stored user's personal information through the identity information, and supplement the feature description information of the virtual character based on the personal information. Specifically, the user's identity information is identified by analyzing the frequency, pitch, speech speed, pronunciation method, etc. in the feature description information input by audio. In the process of voiceprint recognition of interactive data, a user's voiceprint model is first established, and the voiceprint model contains the user's voice features. Then, the user's interactive data is compared with the features in the model to verify the user's identity information.

[0071] Exemplarily, when the electronic device obtains feature description information input by the user via audio, where the feature description information is “animals with soft voices”, if it determines that the feature description information input by the current user fails to fully describe the features required to generate a virtual character, then voiceprint recognition is performed on the feature description information input by the user via audio, and the user's identity information is identified as “Little A”. The personal information stored corresponding to the user's identity information is further obtained as “likes cats, and favorite color is white”. The obtained personal information can then be supplemented into the image description information, and then the character generation model generates a virtual character based on the supplemented feature description information, that is, the generated virtual character's image is “a white rag doll”.

[0072] Furthermore, after the virtual character is generated based on the supplemented feature description information, when the user communication data input by the user in the user interaction interface is obtained, the user communication data is input into the interaction model, and the interaction model generates reply data corresponding to the user communication data based on the user communication data, and displays the reply data using the character image of the virtual character. The interaction model is a pre-trained model, which can generate corresponding reply data based on the input user communication data, and the reply data is data corresponding to the input user communication data.

[0073] It can be understood that in the embodiment of the present application, if the user communication data received from the user is input by voice, the user communication data in text form can be obtained by voice recognition and then input into the interaction model.

[0074] In another embodiment, if the user inputs the user communication data in text form, it is directly input into the interaction model.

[0075] In an embodiment of the present application, when user communication data input by a user is received, reply data corresponding to the user communication data is generated through an exchange model, thereby realizing interaction with the user based on generating reply data corresponding to the user communication data input by the user; and by extracting keyword information in the text description information when the text description information is obtained, and then determining the characteristic description information of the virtual character in the keyword information, thereby realizing that when the user inputs voice description information, the characteristic description information of the virtual character is obtained from the voice description information; and the user's personal information is obtained through the user's identity information, and then the image description information is supplemented based on the personal information. Since the image description information input by the user is supplemented by the personal information, the content of the image description information is expanded and the accuracy of the generated character image is improved.

[0076] See also Figure 4 , which is a flow chart of a method for generating a virtual character according to an embodiment of the present application. Figure 4 As shown, the method of the embodiment of the present application may include the following steps S301-S303.

[0077] S301, obtaining the triggering duration of the user triggering the option of creating a virtual character;

[0078] In one embodiment, when it is detected that the user triggers the option of creating a virtual character, a timer is started to count the triggering time of the option of creating a virtual character triggered by the user.

[0079] S302, if the triggering time reaches the preset time and the feature description information for the virtual character is not received, then the preset question is displayed in the interactive interface;

[0080] In one embodiment, when it is determined that the trigger duration reaches a preset duration and the feature description information input by the user for the virtual character is not received, it is determined that the user is currently unable to determine the specific image of the virtual character to be created, and thus, in this embodiment of the application, preset questions can be displayed in the interactive interface. The preset questions are questions designed for creating virtual characters.

[0081] Optionally, in the embodiment of the present application, the preset questions may be based on the user's interests and hobbies. For example, the preset questions may specifically be asking the user which sports, books, etc. the user likes.

[0082] S303, obtaining the user's answer information to the preset question, and obtaining feature description information for the virtual character based on the answer information.

[0083] In one embodiment, after obtaining the user's reply information to the preset questions, the feature description information for the virtual character is obtained through the reply information. It can be understood that in the embodiment of the present application, there can be multiple preset questions, so that the user's reply information to multiple preset questions can be obtained, and as much reply information as possible can be obtained, thereby obtaining more detailed feature description information, thereby improving the accuracy of creating the virtual character. Optionally, in the embodiment of the present application, after obtaining the reply information, if it is determined that the reply information is not specific enough, and thus the virtual character cannot be accurately constructed, the step of displaying the preset questions in the interactive interface can be performed again until the specific reply information is obtained and the virtual character is generated.

[0084] Furthermore, if it is determined that the creation type of the option for creating a virtual character triggered by the user is a template selection type, then each currently stored character template is obtained, and each character template, feature description information of each character template, and timbre selection information are displayed in a display interface, a target character template is determined in the character template based on the received trigger information, and target timbre selection information is determined in the timbre selection information, the target character template is determined based on the feature description information of each character template, and a virtual character is generated based on the target character template and the target timbre selection information

[0085] Optionally, in the embodiment of the present application, the user can trigger the option of creating a virtual character by clicking the virtual button "Get character template" displayed in the interactive interface, and the electronic device determines that the creation type of the option of creating a virtual character triggered by the user is a template selection type. Then, the electronic device displays each character template currently stored in the interactive interface, wherein each character template displayed can be as follows: Figure 5 As shown, the characteristic description information of each character template is displayed in the display interface, refer to Figure 6 As shown; and the timbre selection information is displayed, wherein the timbre selection information includes: "gentle girl", "sunny girl", "cute boy". If it is detected that the user clicks on the target character template based on the character template displayed in the display interface, and determines the trigger information of the target timbre selection information in the timbre selection information, a virtual character is generated according to the character template and the target timbre selection information.

[0086] It can be understood that in the embodiment of the present application, for each character template, any timbre selection information can be selected from the timbre selection information as the target timbre selection information to generate a virtual character.

[0087] Furthermore, in an embodiment of the present application, after constructing the virtual character, it is also possible to obtain modification information of the user on the virtual character, and modify the generated virtual character according to the modification information.

[0088] For example, in the generated virtual character, the user is not satisfied with the pupil color of the virtual character and needs to modify it, then sends a voice message of "change the pupil color to brown" to make the modification. It can be understood that in the embodiment of the present application, the user can also input the modification information through text input, which will not be repeated here.

[0089] Furthermore, in an embodiment of the present application, after obtaining reply data of the user communication data, the emotional characteristics of the reply data are obtained, and then the virtual character is controlled to perform actions corresponding to the emotional characteristics based on the character image of the virtual character.

[0090] Optionally, in an embodiment of the present application, a sentiment dictionary containing positive and negative words can be constructed, and then the words in the reply data are matched with the words in the sentiment dictionary, the total number or strength of positive or negative words is calculated, and then the sentiment characteristics of the reply data are determined.

[0091] In addition, in another embodiment, the obtained reply data may be input into the sentiment model through training the sentiment model, and the sentiment characteristics of the reply data may be determined based on the output result of the sentiment model.

[0092] Furthermore, in the embodiment of the present application, the emotional characteristics can also be associated with the actions that the virtual character needs to perform, and then after determining the emotional characteristics of the reply data, the virtual character can be controlled to perform actions corresponding to the emotional characteristics.

[0093] In an embodiment of the present application, when it is determined that the triggering time of the user triggering the option of creating a virtual character reaches a preset time and the user input of the feature description information of the virtual character is not received, a preset question can be displayed in the interactive interface for interacting with the user, and the feature description information of the virtual character can be determined through the user's reply information to the preset question. Therefore, when the user is not clear about how to describe the virtual character he needs to generate, the user can be guided by the preset question, and then the feature description information of the virtual character is generated, and the feature description information can be effectively input, thereby improving the accuracy of the generated virtual character; and when the creation type of the user triggering the option of creating a virtual character is a template selection type, the virtual character can be generated based on the target character template and target timbre selection information selected by the user, and the user can select a virtual character that meets his personalized needs through the character template, thereby improving the convenience of generating a virtual character; and the virtual character can be modified based on the received modification information without re-entering the feature description information, thereby improving the convenience of modifying the virtual character; and the virtual character can be controlled to perform actions corresponding to the emotional characteristics according to the emotional characteristics of the reply data, so that the actions of the virtual character are associated with the reply data, thereby improving the interactive experience between the user and the virtual character.

[0094] based on Figure 1 The following is a schematic diagram of the scene. Figure 7-Figure 8 , the virtual character generation device provided in the embodiment of the present application is introduced in detail. It should be noted that, Figure 7-Figure 8 A device for generating a virtual character in the present application Figure 2-Figure 6 For the convenience of explanation, only the part related to the embodiment of the present application is shown. For the specific technical details not disclosed, please refer to the present application. Figure 2-Figure 6 Specifically, the virtual character generation device 1 includes: a monitoring unit 11 , a calling unit 12 , and a display unit 13 .

[0095] A monitoring unit 11 is used to monitor the user triggering the option of creating a virtual character, and obtain feature description information for the virtual character, where the feature description information includes image description information and sound description information of the virtual character;

[0096] A calling unit 12, used to call a character generation model and generate a virtual character based on feature description information;

[0097] The display unit 13 is used to obtain the input user communication data in the interactive interface for interacting with the user, display the reply data corresponding to the user communication data based on the character image of the virtual character, and output the reply data based on the voice characteristics of the virtual character.

[0098] Optionally, the display unit 13 is further used for:

[0099] The call interaction model generates reply data based on user communication data.

[0100] Optionally, the monitoring unit 11 includes: an acquisition subunit 111 and an extraction subunit 112 .

[0101] An acquisition subunit 111 is used to acquire the user's voice description information, and perform voice recognition on the voice description information to acquire text description information corresponding to the voice description information;

[0102] The extraction subunit 112 is used to extract keyword information contained in the text description information, and determine the feature description information of the virtual character in the keyword information.

[0103] Optionally, the extraction subunit 112 is further configured to:

[0104] Obtain the user's identity information, and obtain the user's personal information based on the user's identity information;

[0105] Supplement image description information based on personal information.

[0106] Optionally, the monitoring unit 11 includes:

[0107] The duration acquisition subunit 113 is used to acquire the trigger duration of the user triggering the option of creating a virtual character;

[0108] The display subunit 114 is used to display a preset question in the interactive interface if the triggering time reaches a preset time and no feature description information for the virtual character is received;

[0109] The answer acquisition subunit 115 is used to obtain the user's answer information to the preset question, and obtain feature description information for the virtual character based on the answer information.

[0110] Optionally, the virtual character generating device further includes: a template selecting unit 14 , a determining unit 15 , and a generating unit 16 .

[0111] The template selection unit 14 is used to obtain the currently stored character templates if it is determined that the creation type of the virtual character creation option triggered by the user is the template selection type, and display the character templates, feature description information of each character template, and timbre selection information in the display interface;

[0112] A determination unit 15, configured to determine a target character template in the character template based on the received trigger information, and determine the target timbre selection information in the timbre selection information, wherein the target character template is determined based on the feature description information of each character template;

[0113] The generating unit 16 is used to generate a virtual character based on the target character template and the target timbre selection information.

[0114] Optionally, the display unit 13 is further used for:

[0115] Obtain the user's modification information of the virtual character;

[0116] The avatar is modified based on the modification information.

[0117] Optionally, the display unit 13 is further used for:

[0118] Determine the sentiment characteristics of the response data;

[0119] Based on the character image of the virtual character, the virtual character is controlled to perform actions corresponding to the emotional characteristics.

[0120] In an embodiment of the present application, when it is detected that a user has triggered an option to create a virtual character, a virtual character is generated based on the acquired feature description information of the virtual character, the virtual character's image is used to display reply data corresponding to the user's communication data, and the reply data is output using the virtual character's voice features. Since the virtual character is created based on the feature description of the virtual character input by the user, the created virtual character is related to the feature description information input by the user, thereby meeting the user's personalized needs, and using the virtual character to reply to the reply data of the interaction with the user during the interaction process can improve the interactive experience of the user during the interaction process with the electronic device.

[0121] See also Fig. 9 , is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application. Fig. 9 As shown, the electronic device 500 includes a processor 501 and a memory 502. The processor 501 is electrically connected to the memory 502.

[0122] The processor 501 is the control center of the electronic device 500 and may include one or more processing cores. The processor 501 uses various interfaces and lines to connect various parts of the entire electronic device 500, and executes various functions and processes data of the electronic device 500 by running or calling computer programs stored in the memory 502, and calling data stored in the memory 502, so as to control the electronic device 500 as a whole. Optionally, the processor 501 can be implemented in at least one hardware form of digital signal processing (DSP), field programmable gate array (FPGA), and programmable logic array (PLA). The processor 501 can integrate one or a combination of CPU, graphics processing unit (GPU), modem, etc. Among them, the CPU mainly processes the operating system, user pages, and applications; the GPU is responsible for rendering and drawing display content; and the modem is used to process wireless communications. It is understandable that the above-mentioned modem may not be integrated into the processor 501, but may be implemented separately through a communication chip.

[0123] The memory 502 can be used to store software programs and modules, and the processor 501 executes various functional applications and data processing by running the computer programs and modules stored in the memory 502. The memory 502 can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, a computer program required for at least one function, etc.; the data storage area can store data created according to the use of the electronic device 500, etc.

[0124] In addition, the memory 502 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. Accordingly, the memory 502 may also include a memory controller to provide the processor 501 with access to the memory 502.

[0125] In this embodiment, the processor 501 in the electronic device 500 loads instructions corresponding to the processes of one or more computer programs into the memory 502 according to the following steps, and the processor 501 runs the computer program stored in the memory 502 to implement various functions, as follows:

[0126] Monitoring the user triggering the option of creating a virtual character, and obtaining feature description information for the virtual character, the feature description information including image description information and sound description information of the virtual character;

[0127] Calling the character generation model and generating a virtual character based on the feature description information;

[0128] The input user communication data is obtained in the interactive interface for interacting with the user, and the reply data corresponding to the user communication data is displayed based on the character image of the virtual character, and the reply data is output based on the voice characteristics of the virtual character.

[0129] Optionally, before the processor 501 displays the reply data corresponding to the user communication data based on the character image of the virtual character, it further executes:

[0130] The call interaction model generates reply data based on user communication data.

[0131] Optionally, when the processor 501 obtains the feature description information for the virtual character, it specifically executes:

[0132] Acquire the user's voice description information, perform voice recognition on the voice description information to obtain text description information corresponding to the voice description information;

[0133] The keyword information contained in the text description information is extracted, and the feature description information of the virtual character is determined in the keyword information.

[0134] Optionally, after determining the feature description information of the virtual character in the keyword information, the processor 501 further executes:

[0135] Obtain the user's identity information, and obtain the user's personal information based on the user's identity information;

[0136] Supplement image description information based on personal information.

[0137] Optionally, when the processor 501 obtains the feature description information for the virtual character, it specifically performs:

[0138] Get the trigger duration for the user to trigger the option to create a virtual character;

[0139] If the triggering time reaches the preset time and no feature description information for the virtual character is received, the preset question is displayed in the interactive interface;

[0140] The user's answer information to the preset questions is obtained, and feature description information for the virtual character is obtained based on the answer information.

[0141] Optionally, before obtaining feature description information for the virtual character, the processor 501 may further execute:

[0142] If it is determined that the creation type of the virtual character creation option triggered by the user is a template selection type, then the currently stored character templates are obtained, and each character template, feature description information of each character template, and timbre selection information are displayed in the display interface;

[0143] Determine a target character template in the character template based on the received trigger information, determine the target timbre selection information in the timbre selection information, the target character template being determined based on the feature description information of each character template;

[0144] Generate a virtual character based on the target character template and target timbre selection information.

[0145] Optionally, after inputting the feature description information into the character generation model to generate a virtual character corresponding to the character feature information, the processor 501 may further execute:

[0146] Obtain the user's modification information of the virtual character;

[0147] The avatar is modified based on the modification information.

[0148] Optionally, when the processor 501 displays the reply data corresponding to the user communication data based on the character image of the virtual character, the processor 501 specifically performs:

[0149] Determine the sentiment characteristics of the response data;

[0150] Based on the character image of the virtual character, the virtual character is controlled to perform actions corresponding to the emotional characteristics.

[0151] It should be understood that the device provided in the embodiment of the present application is used to execute the above-mentioned method for generating a virtual character, and thus can achieve the same effect as the above-mentioned implementation method.

[0152] In the case of an integrated unit, the device may include a processing module and a storage module. When the device is applied to an electronic device, the processing module may be used to control and manage the actions of the electronic device. The storage module may be used to support the electronic device in executing related program codes, etc.

[0153] The processing module may be a processor or a controller, which may implement or execute various exemplary logic blocks, modules and circuits described in conjunction with the disclosure of this application. The processor may also be a combination that implements computing functions, such as a combination of one or more microprocessors, a combination of digital signal processing (DSP) and a microprocessor, etc. The storage module may be a memory.

[0154] In addition, the device provided in the embodiment of the present application can specifically be a chip, component or module, and the chip may include a connected processor and memory; wherein the memory is used to store instructions, and when the processor calls and executes the instructions, the chip can execute a method for generating a virtual character provided in the above embodiment.

[0155] An embodiment of the present application also provides a computer-readable storage medium, in which a computer program code is stored. When the computer program code is executed on a computer, the computer executes the above-mentioned related method steps to implement a method for generating a virtual character provided in the above embodiment.

[0156] This embodiment also provides a computer program product. When the computer program product is run on a computer, the computer is caused to execute the above-mentioned related steps to implement a method for generating a virtual character provided in the above embodiment.

[0157] Among them, the device, computer-readable storage medium, computer program product or chip provided in this embodiment is used to execute the corresponding method provided above. Therefore, the beneficial effects that can be achieved can refer to the beneficial effects in the corresponding method provided above, and will not be repeated here.

[0158] Through the description of the above implementation methods, technical personnel in the relevant field can understand that for the convenience and simplicity of description, only the division of the above-mentioned functional modules is used as an example. In actual applications, the above-mentioned functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above.

[0159] In the embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic, for example, the division of modules or units is only a logical function division, and there may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another device, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0160] The above contents are only specific implementation methods of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A method for generating a virtual character, characterized in that: The method comprises: Monitoring a user triggering an option to create a virtual character, and obtaining feature description information for the virtual character, the feature description information including image description information and sound description information of the virtual character; Calling a character generation model and generating a virtual character based on the feature description information; The input user communication data is obtained in an interactive interface for interacting with the user, and reply data corresponding to the user communication data is displayed based on the character image of the virtual character, and the reply data is output based on the voice characteristics of the virtual character.

2. The method according to claim 1, characterized in that: Before displaying the reply data corresponding to the user communication data based on the character image of the virtual character, the method further includes: The interaction model is called to generate the reply data based on the user communication data.

3. The method according to claim 1, characterized in that The obtaining of feature description information for the virtual character includes: Acquire the voice description information of the user, and perform voice recognition on the voice description information to acquire text description information corresponding to the voice description information; The keyword information contained in the text description information is extracted, and the feature description information of the virtual character is determined in the keyword information.

4. The method according to claim 3, characterized in that After determining the feature description information of the virtual character in the keyword information, the method further includes: Acquire the identity information of the user, and acquire the personal information of the user based on the identity information of the user; The image description information is supplemented based on the personal information.

5. The method according to claim 1, characterized in that The obtaining of feature description information for the virtual character includes: Obtaining the triggering duration of the user triggering the option of creating a virtual character; If the triggering time reaches a preset time and no feature description information for the virtual character is received, a preset question is displayed in the interactive interface; The user's answer information to the preset question is obtained, and feature description information for the virtual character is obtained based on the answer information.

6. The method according to claim 1, characterized in that Before acquiring the feature description information for the virtual character, the method further includes: If it is determined that the creation type of the option for creating a virtual character triggered by the user is a template selection type, then obtaining each currently stored character template, and displaying each character template, feature description information of each character template, and timbre selection information in a display interface; Determining a target character template in the character templates based on the received trigger information, and determining target timbre selection information in the timbre selection information, wherein the target character template is determined based on feature description information of each of the character templates; The virtual character is generated based on the target character template and the target timbre selection information.

7. The method according to claim 1, characterized in that After inputting the feature description information into the character generation model to generate a virtual character corresponding to the character feature information, the method further includes: Obtaining modification information of the virtual character by the user; The virtual character is modified based on the modification information.

8. A device for generating a virtual character, characterized in that: The device comprises: A monitoring unit, configured to monitor a user triggering an option to create a virtual character, and obtain feature description information for the virtual character, wherein the feature description information includes image description information and sound description information of the virtual character; A calling unit, used for calling a character generation model and generating a virtual character based on the feature description information; The display unit is used to obtain the input user communication data in the interactive interface for interacting with the user, display the reply data corresponding to the user communication data based on the character image of the virtual character, and output the reply data based on the voice characteristics of the virtual character.

9. An electronic device, characterized in that: The electronic device comprises: A memory for storing executable program codes; A processor, configured to call and run the executable program code from the memory, so that the electronic device executes the method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program code, and when the computer program code is executed, the method according to any one of claims 1 to 7 is implemented.

Images