Interaction methods, devices, equipment, and storage media based on virtual characters

Abstract

This application discloses an interaction method, apparatus, device, and storage medium based on a virtual character, relating to the field of computer technology. The method includes: displaying a photo generation interface showing first memory information, the first memory information being associated with historical dialogue records between a virtual character and a user account, the virtual character being a digital virtual image driven by artificial intelligence (AI); and, in response to an operation on the photo generation interface, displaying a first visual digital asset generated based on the first memory information, the first visual digital asset displaying a first photo image including the virtual character's image and the user account's image. This application, by creating a tangible reward for emotional investment, provides users with a substantial return on their emotional investment, greatly enhancing the long-term emotional connection and sense of belonging between the user account and the virtual character.

Description

Technical Field

[0001] This application relates to the field of computer technology, and in particular to an interaction method, apparatus, device and storage medium based on virtual characters. Background Technology

[0002] AI (Artificial Intelligence) characters refer to virtual characters in games that are driven by artificial intelligence and have the ability to engage in personalized dialogues with players, play games together, and dynamically generate memories based on interactions.

[0003] In this technology, players interact with AI characters through text, voice, and other means. The AI ​​characters' responses, emotions, and actions are generated in real time by artificial intelligence. The AI ​​characters have strong personalities, believe what the players say, and develop an emotional dependence on them. Their conversations with the players will affect the storyline and the characters' fates.

[0004] However, in order to ensure the independence of each dialogue session, the AI ​​character's memory is reset at the beginning of each dialogue session, resulting in a relatively short recall of the dialogue with the AI ​​character. Summary of the Invention

[0005] This application provides an interaction method, apparatus, device, and storage medium based on virtual characters. The technical solution provided by this application is as follows: According to one aspect of the embodiments of this application, an interaction method based on virtual characters is provided, the method comprising: The interface that displays the first memory information is a group photo generation interface. The first memory information is associated with the historical dialogue records between the virtual character and the user account. The virtual character is a digital virtual image driven by artificial intelligence (AI). In response to an operation on the group photo generation interface, a first visual digital asset generated based on the first memory information is displayed. The first visual digital asset displays a first group photo image containing the character image of the virtual character and the account image of the user account.

[0006] According to one aspect of the embodiments of this application, an interactive device based on a virtual character is provided, the device comprising: The interface display module is used to display the group photo generation interface of the first memory information, which is associated with the historical dialogue records between the virtual character and the user account. The virtual character is a digital virtual image driven by artificial intelligence (AI). The asset generation module is used to respond to the operation of the group photo generation interface and display a first visual digital asset generated based on the first memory information. The first visual digital asset displays a first group photo image containing the character image of the virtual character and the account image of the user account.

[0007] According to one aspect of the embodiments of this application, a computer device is provided, the computer device including a processor and a memory, the memory storing a computer program, the computer program being loaded and executed by the processor to implement the above-described interactive method based on virtual characters.

[0008] According to one aspect of the embodiments of this application, a computer-readable storage medium is provided, wherein a computer program is stored in the computer program, which is loaded and executed by a processor to implement the above-described interactive method based on virtual characters.

[0009] According to one aspect of the embodiments of this application, a computer program product is provided, the computer program product including a computer program, the computer program being loaded and executed by a processor to implement the above-described interactive method based on virtual characters.

[0010] The technical solution provided in this application can bring the following beneficial effects: By providing the function of generating visualized digital assets based on memory information, the historical dialogue records between virtual characters and user accounts are transformed into permanently existing visualized digital assets. Compared with related technologies where dialogue memories cannot be permanently stored, the technical solution provided in this application creates tangible rewards for users' emotional investment by creating enduring emotional assets, achieving deep emotional bonds and greatly enhancing the long-term emotional connection and sense of belonging between user accounts and virtual characters. Moreover, the visualized digital assets generated by user operation corresponding to memory information, integrating the text-to-image capabilities of AI large models, simplifies professional-level image creation to simple option selection. This allows ordinary users to generate high-quality group photos based on memory information without needing to master drawing or design skills, lowering the creative threshold for image generation, empowering non-professional users to engage in artistic creation, providing a highly personalized creative experience, greatly releasing users' creativity, and fully satisfying users' needs for self-expression. Attached Figure Description

[0011] Figure 1 This is a schematic diagram of a computer system provided in one embodiment of this application; Figure 2 This is a flowchart of an embodiment of the interaction method based on virtual characters provided in this application; Figure 3This is a schematic diagram of the display process of the group photo generation interface for the first memory information provided in one embodiment of this application; Figure 4 This is a schematic diagram of a dialogue interface between a virtual character and a user account provided in one embodiment of this application; Figure 5 This is a schematic diagram of the real image uploading process provided in one embodiment of this application; Figure 6 This is a schematic diagram illustrating the process of storing target visualized digital assets according to one embodiment of this application; Figure 7 This is a schematic diagram illustrating the replacement process of a visualized digital asset in an item library provided in one embodiment of this application; Figure 8 This is a schematic diagram of the memory details interface of the first memory information provided in one embodiment of this application; Figure 9 This is a schematic diagram of a process for adding a first visualized digital asset to a collection medium, provided in one embodiment of this application; Figure 10 This is a schematic diagram of the architecture of a memory keyword library provided in one embodiment of this application; Figure 11 This is a schematic diagram of a system architecture provided in one embodiment of this application; Figure 12 This is a block diagram of an interactive device based on a virtual character provided in one embodiment of this application; Figure 13 This is a structural block diagram of a computer device provided in one embodiment of this application. Detailed Implementation

[0012] To make the objectives, technical solutions, and advantages of this application clearer, the embodiments of this application will be described in further detail below with reference to the accompanying drawings.

[0013] Please refer to Figure 1 This illustration shows a schematic diagram of a computer system provided in one embodiment of this application. The computer system may include: a terminal device 10 and a server 20.

[0014] There may be one or more terminal devices 10. Terminal devices 10 may be electronic devices such as mobile phones, tablets, laptops, desktop computers, game consoles, e-book readers, multimedia playback devices, wearable devices, smart voice interaction devices, smart home appliances, vehicle terminals, aircraft, etc.

[0015] The terminal device 10 may have a client application for the target application installed. The target application has the function of communicating with the AI ​​system and can generate visualized digital assets based on the historical dialogue records between the user account and the AI-driven virtual character. Optionally, the target application can be an application that needs to be downloaded and installed, or it can be an application that can be used immediately. This application does not limit this.

[0016] Server 20 provides background services for clients of the target application installed and running on terminal device 10. For example, server 20 can be a background server for the aforementioned target application. Server 20 can be a standalone physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server providing basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, CDN (Content Delivery Network), and big data and artificial intelligence platforms, but is not limited to these. Optionally, server 20 can simultaneously provide background services for target applications on multiple terminal devices 10. Terminal devices 10 and server 20 can communicate with each other via a network.

[0017] The data storage system can store the data that the server 20 needs to process. The data storage system can be integrated on the server 20, or it can be placed in the cloud or on other servers.

[0018] In this embodiment, a photo generation interface for first memory information is displayed in the client's user interface. The first memory information is associated with historical dialogue records between a virtual character and a user account. The virtual character is an AI-driven digital virtual avatar. In response to an operation on the photo generation interface, a first visual digital asset generated based on the first memory information is displayed. The first visual digital asset displays a first photo image containing the virtual character's image and the user account's image. The first visual digital asset is added to a collection carrier, which aggregates and displays at least two visual digital assets.

[0019] Please refer to Figure 2 The diagram illustrates a flowchart of an interaction method based on a virtual character according to an embodiment of this application. The execution entity for each step of the method can be a terminal device. The method may include at least one of the following steps 210-220: Step 210: Display the group photo generation interface for the first memory information. The first memory information is associated with the historical dialogue records between the virtual character and the user account. The virtual character is a digital virtual image driven by artificial intelligence (AI).

[0020] A virtual character is a digital virtual avatar driven by an AI system provided by the target application. It has the ability to engage in personalized dialogue with a user account and generate recall information based on historical dialogue records. The user account is the account logged into the target application. Typically, when a virtual character engages in dialogue with a user account, the user account initiates the dialogue text. The virtual character generates corresponding dialogue text based on the dialogue text sent by the user account by calling the AI ​​model in the AI ​​system. The virtual character's dialogue text is used to answer questions from the user account or guide the user account to continue the dialogue.

[0021] The first memory information is generated based on the first dialogue text between the virtual character and the user account. The first dialogue text is the dialogue text contained in the historical dialogue records between the virtual character and the user account. Optionally, the first dialogue text may include one sentence or multiple sentences. If the first dialogue text includes one sentence, it can be either a dialogue text sent by the user account or a dialogue text sent by the virtual character. If the first dialogue text includes multiple sentences, it can include multiple consecutive dialogue texts sent by the user account, multiple consecutive dialogue texts sent by the virtual character, or dialogue text contained in at least one round of historical dialogue records between the virtual character and the user account, i.e., it includes at least one sentence sent by the user account and at least one sentence sent by the virtual character. The first memory information includes at least one of the following: the first dialogue text, the title of the first memory information, the generation time of the first memory information, the identification information of the user account, and the identification information of the virtual character. The title of the first memory information is a title text generated by an AI large model based on the first dialogue text, used to summarize the dialogue content in the first dialogue text. The generation time of the first memory information is the generation time of the first dialogue text.

[0022] The technical solution provided in this application is used to generate a first visual digital asset corresponding to the first memory information. After the first visual digital asset is generated, the first memory information also includes the first visual digital asset. At this time, the first memory information including the first visual digital asset is complete memory information.

[0023] Step 220, in response to an operation on the group photo generation interface, displays a first visual digital asset generated based on the first memory information. The first visual digital asset displays a first group photo image containing the character image of the virtual character and the account image of the user account.

[0024] The first visualized digital asset is a memory entity obtained by converting first memory information into a first group photo image and displaying it on an image carrier. The image carrier includes, but is not limited to, photos, badges, teacups, canvas bags, T-shirts, etc. If the first visualized digital asset is a badge, then the generated badge displays the first group photo image. The first group photo image is a group photo image containing the character image of a virtual character and the account image of a user account. The character image of the virtual character is a digital virtual image configured by default by the AI ​​system for the virtual character, and the account image of the user account is the image contained in the account image set by the user. The account image of the user account can be a real person's image or a virtual character's image; this application does not limit this.

[0025] The group photo generation interface for the first group photo information is used to generate the first visual digital asset. Operations on this interface are performed by the user to set the configuration information for the first visual digital asset. The configuration information includes at least one of the following: image information of the first group photo and carrier information of the first group photo. In response to operations on the group photo generation interface, the AI ​​model first generates the first group photo based on the image information set by the user. Then, based on the carrier information of the first group photo and the first group photo itself, the first visual digital asset is generated and displayed on the user interface.

[0026] Optionally, operations on the group photo generation interface may include operations on the image information of the first group photo image and operations on the carrier information of the first group photo image. Operations on the image information of the first group photo image are used to set the image content of the first group photo image, including at least one of the following: the user account's profile picture, the image style of the first group photo image, the image background of the first group photo image, and the image resolution of the first group photo image. Operations on the carrier information of the first group photo image are used to set the image carrier of the first group photo image, that is, to set the carrier format of the first visual digital asset. Then, based on the image information and carrier information of the first group photo image set by the user, the first visual digital asset is generated.

[0027] Optionally, the operations on the group photo generation interface can also include only operations on the image information of the first group photo image. Then, based on the image information of the first group photo image set by the user and the default carrier information of the first group photo image, a first visual digital asset is generated. For example, if the carrier format of the first visual digital asset can be set to a photo by default, then a photo displaying the first group photo image is generated.

[0028] Optionally, the operations on the group photo generation interface can also include only operations on the carrier information of the first group photo image. Then, based on the carrier information of the first group photo image set by the user and the image information of the first group photo image set by default, a first visual digital asset is generated. For example, the user's account avatar can default to the image contained in the user's account profile picture, the image style of the first group photo image can default to a cute style, the image background of the first group photo image can default to an amusement park background, and the image resolution of the first group photo image can default to 1920×1080.

[0029] For specific instructions on how to generate the group photo, please refer to the following examples, which will not be described here.

[0030] The technical solution provided in this application, by offering the function of generating visualized digital assets based on memory information, transforms the historical dialogue records between virtual characters and user accounts into permanently existing visualized digital assets. Compared to related technologies where dialogue memories cannot be permanently stored, the technical solution provided in this application, by creating tangible rewards for users' emotional investment through the creation of enduring emotional assets, achieves deep emotional bonds and greatly enhances the long-term emotional connection and sense of belonging between user accounts and virtual characters. Moreover, the visualized digital assets generated by user operation corresponding to memory information, integrating the text-to-image generation capabilities of AI large models, simplifies professional-level image creation into simple option selection. This allows ordinary users to generate high-quality group photos based on memory information without needing to master drawing or design skills, lowering the creative threshold for image generation, empowering non-professional users to engage in artistic creation, providing a highly personalized creative experience, greatly releasing users' creativity, and fully satisfying users' needs for self-expression.

[0031] In some embodiments, step 210 includes at least one of sub-steps 211 to 212.

[0032] Sub-step 211: Display the virtual character's memory list, which includes at least one memory piece of information.

[0033] After generating corresponding memory information based on the historical dialogue records between the virtual character and the user account, the memory information is added to the memory list. The memory list includes all memory information generated based on the historical dialogue records between the virtual character and the user account. Optionally, at least one memory information in the memory list can all contain visual digital assets, that is, the at least one memory information is complete memory information; the at least one memory information can also all not contain visual digital assets, that is, the at least one memory information is incomplete memory information; the at least one memory information can also contain at least one memory information containing visual digital assets and at least one memory information not containing visual digital assets, that is, the at least one memory information contains both complete and incomplete memory information.

[0034] Sub-step 212, in response to an operation on the first memory information in at least one memory information, displays the group photo generation interface of the first memory information.

[0035] If the first memory information is a memory information that does not contain any visual digital assets, then in response to an operation on the first memory information, the group photo generation interface for the first memory information is displayed. If the second memory information is a memory information that contains at least one visual digital asset, then in response to an operation on the second memory information, the memory details interface for the second memory information is displayed. An operation on the first memory information can be an operation where the user clicks on the first memory information among at least one memory information.

[0036] Figure 3 A schematic diagram showing the display process of the group photo generation interface for the first memory information is provided. Figure 3 Figure (1) shows the homepage interface 310 of the user account. The homepage interface 310 of the user account displays a memory control 301. After the user clicks the memory control 301, if there is no memory data between the virtual character and the user account, the following will be displayed: Figure 3 The prompt interface 320 shown in Figure (2) is used to prompt the user that there are currently no memories between the virtual character and the user account. The user can then click the dialog control 302 in the prompt interface 320 to display a dialog interface between the virtual character and the user account, allowing the user account and the virtual character to interact and generate memories. If there is memory data between the virtual character and the user account, then the following will be displayed: Figure 3 The memory interface 330 shown in Figure (3) contains a memory list. Each memory information in the memory list includes the title of the dialogue text and the generation time of the memory information. Among them, the memory information 303 also includes a visual digital asset, while the memory information 304 does not include a visual digital asset. When the user clicks on the memory information 304, the group photo generation interface of the memory information 304 will be displayed.

[0037] In some embodiments, step 210 includes at least one of sub-steps 213-214, where sub-steps 213-214 are parallel steps to sub-steps 211-212.

[0038] Sub-step 213: Display the dialogue interface between the virtual character and the user account, which includes at least one dialogue text.

[0039] Figure 4 A schematic diagram of a dialogue interface between a virtual character and a user account is shown. The dialogue interface 400 displays the virtual character's image 401 and the user account's image 402. The user account can enter dialogue text in the dialogue input box to have a dialogue with the virtual character.

[0040] Sub-step 214, in response to an operation on a first dialogue text in at least one dialogue text, displays a photo generation interface for first memory information, the first memory information including the first dialogue text.

[0041] During a conversation between a user account and a virtual character, if the user deems the initial dialogue text in the dialogue interface worthy of being converted into a visual digital asset, the user can directly perform operations on the initial dialogue text within the dialogue interface, displaying a group photo generation interface for the initial memory information. For example, the user can click or long-press the initial dialogue text to display multiple operation controls for the initial dialogue text; clicking the group photo generation control among these controls will then display the group photo generation interface for the initial memory information.

[0042] By providing the above two solutions for displaying the first memory information group photo generation interface, users can access the first memory information group photo generation interface from the virtual character's memory list, or directly from the dialogue interface between the virtual character and the user's account. This enriches the triggering methods for generating visual digital assets and expands the interactive functions based on virtual characters.

[0043] In some embodiments, the group photo generation interface displays an image selection control and a generation control. Then step 220 includes at least one of sub-steps 221-222.

[0044] Sub-step 221, in response to an operation on the image selection control, determines the account image selected by the user account, the account image being used to indicate the user account's profile.

[0045] The image selection control is used to select an account image. Operations on the image selection control are performed by the user to select an account image. Specifically, these operations pertain to the image information of the first group photo image, used to determine the user's account image within that image.

[0046] In some embodiments, the image selection control includes at least one candidate image, which includes at least one of the following: a real image uploaded by a user account, and at least one virtual image; wherein, the real image is an image containing a real person's image, and the virtual image is an image containing a virtual character's image. In response to an operation targeting a target candidate image among the at least one candidate image, the account image selected by the user account is determined as the target candidate image.

[0047] At least one candidate image is an image additionally uploaded by the user account. If the user account has not uploaded any real images, then at least one candidate image does not include a real image. The real image uploaded by the user account is an image containing a real person's image in the device's photo album. It can be an image containing a public figure's image or an image containing the user's personal image; this application does not limit this.

[0048] At least one virtual image among the candidate images is an image inherent in the image selection control, and at least one virtual image is an image generated by the AI ​​system and configured by default in the image selection control. The virtual character image in each virtual image is a different character image generated by the AI ​​system. Optionally, the at least one virtual image corresponding to different user accounts can be the same or different. For example, at least one virtual image can be generated by an AI large model based on the user account information, so that the virtual character image in the at least one virtual image matches the user account information.

[0049] If a user selects a target candidate image from at least one candidate image, then the account image is determined as the target candidate image, and the image in the target candidate image can be determined as the account image of the user's account.

[0050] By providing a real image uploaded by the user account and at least one virtual image among at least one candidate image, the account image has multiple possible choices. It can realize the function of uploading a real person image and a virtual character to generate a group photo image, realizing a lightweight fusion of digital identity and physical identity, and enriching the possibilities of group photo images.

[0051] In some embodiments, the group photo generation interface displays an image upload control, and in response to an operation on the image upload control, the real image uploaded by the user account is displayed in the image selection control.

[0052] Figure 5 A schematic diagram illustrating the upload process of a real image is shown. Figure 5 Figure (1) shows the group photo generation interface 510 for the first memory information. The group photo generation interface 510 displays an image upload control 501 and a virtual image 502. If the user uploads a real image through the image upload control 501, the candidate images include both the real image and the virtual image 502. If the user does not upload a real image through the image upload control 501, the candidate images only include the virtual image 502. After the user clicks the image upload control 501, the following is displayed: Figure 5 The upload prompt interface 520 shown in Figure (2) displays upload prompt information 505 and upload control 506. The upload prompt information is used to indicate the image conditions that the real image uploaded by the user account must meet, including: the real image does not obscure the face of the person, the real image contains only one person, and the real image has sufficient light. The user clicks the upload control 506 to select a real image from the device's photo album for upload. If the real image selected by the user does not meet the upload prompt information 505, an error message is displayed. If the real image selected by the user meets the upload prompt information 505, the following message is displayed: Figure 5 The image preview interface 530 shown in Figure (3) is as follows. The image preview interface 530 displays the real image 507 uploaded by the user account. The user can choose to re-upload the real image, or click the confirmation control 508 to confirm the upload of the real image 507. After uploading the real image 507, the following will be displayed: Figure 5 The group photo generation interface 540 shown in Figure (4) has a real image 507 displayed at the image upload control 501 in the group photo generation interface 540.

[0053] Sub-step 222, in response to an operation on the generation control, displays the first visual digital asset generated based on the first memory information and the account image.

[0054] In response to an operation on the generation control, a first visual digital asset is generated based on the account image selected by the user account. The first visual digital asset is generated based on the first memory information and the account image. The image carrier of the first group photo image and other image information of the first group photo image in the first visual digital asset are configured according to the default settings. For example, the image carrier of the first group photo image is configured as a photo by default.

[0055] like Figure 5 As shown in Figure (4), the group photo generation interface 540 displays a generation control 509. When the user clicks the generation control 509, the first visual digital asset is generated.

[0056] By allowing users to determine their account images, the resulting first group photo image features user accounts that align with their self-expression needs, giving users creative freedom and enhancing the user experience during the generation of the first visual digital asset.

[0057] In some embodiments, the group photo generation interface also displays parameter configuration controls. Step 220 then further includes sub-step 223, which follows sub-step 221.

[0058] Sub-step 223, in response to an operation on the parameter configuration control, determines the image configuration information of the first group photo image, the image configuration information being used to indicate the image format of the first group photo image; wherein, the first visual digital asset is generated based on the first memory information, the account image and the image configuration information.

[0059] The parameter configuration control is used to configure the image configuration information of the first group photo image. The image configuration information of the first group photo image includes at least one of the following: image information of the first group photo image and carrier information of the first group photo image. The image information of the first group photo image is used to indicate the image content of the first group photo image, and the carrier information of the first group photo image is used to indicate the image carrier of the first group photo image.

[0060] The parameter configuration control can be used to determine some or all of the image configuration information of the first group photo image. The first visual digital carrier will be generated based on the first memory information, the account image, and the image configuration information determined by the parameter configuration control. If the parameter configuration control is only used to determine some of the image configuration information of the first group photo image, the other image configuration information of the first group photo image will be configured according to the default settings. For example, if the parameter configuration control is used to determine the image carrier and image style of the first group photo image, the image background of the first group photo image will be generated according to the default amusement park background.

[0061] By providing parameter configuration controls, users can further customize the image configuration information of the first group photo, giving them more creative freedom, fully satisfying their self-expression needs, and improving their creative experience.

[0062] In some embodiments, the parameter configuration control includes at least one of the following: a style selection control, a carrier selection control, and a background selection control. Then sub-step 223 includes at least one of sub-steps 2231 to 2233.

[0063] Sub-step 2231, in response to an operation on the style selection control, determines the image style of the first group photo image.

[0064] The style selection control includes at least one candidate style image. Each candidate style image is used to indicate an image style, which includes, but is not limited to, graffiti style, cyberpunk style, cute style, humorous style, etc. The presentation effect of the image style is intuitively displayed through the candidate style images.

[0065] In response to an operation on a target candidate style image among at least one candidate style image, the image style of the first group photo image is determined to be the image style indicated by the target candidate style image.

[0066] Sub-step 2232, in response to an operation on the carrier selection control, determines the image carrier of the first group photo image, the image carrier being used as a first visual digital asset displaying the first group photo image.

[0067] The carrier selection control includes at least one candidate carrier image. Each candidate carrier image is used to indicate an image carrier, which includes, but is not limited to, photos, badges, teacups, canvas bags, T-shirts, etc. The presentation effect of the image carrier is displayed intuitively through the candidate carrier images.

[0068] In response to an operation targeting a target candidate carrier image among at least one candidate carrier image, the image carrier of the first group photo image is determined to be the image carrier indicated by the target candidate carrier image.

[0069] like Figure 5 The group photo generation interface 510 shown in Figure (1) has a style selection control 503 and a carrier selection control 504. The style selection control 503 includes multiple candidate style images, and the carrier selection control 504 includes multiple candidate carrier images. The user clicks on one of the candidate style images to determine the image style of the first group photo image, and clicks on one of the candidate carrier images to determine the image carrier of the first group photo image.

[0070] Sub-step 2233, in response to the operation on the background selection control, determines the background image of the first group photo image.

[0071] The background selection control includes at least one candidate background image. Each candidate background image is used to indicate an image background, including but not limited to amusement park background, coffee shop background, beach background, grassland background, office background, etc. The candidate background images visually demonstrate the presentation effect of the image background.

[0072] In response to an operation targeting a target candidate background image among at least one candidate background image, the image background of the first group photo image is determined to be the image background indicated by the target candidate background image.

[0073] By providing a multi-layered customizable generation pipeline including "image, style, medium, and background," standardized AI services are transformed into personalized creations that are unique to each individual. This allows users to not only be consumers but also "directors" and "curators" of their own memories and stories, satisfying the current users' strong demand for self-expression and personalized display.

[0074] In some embodiments, in response to an operation on the generation control, if the number of virtual resources owned by the user account is greater than or equal to a first number, the first number of virtual resources of the user account are consumed, and a first visual digital asset generated based on first memory information and an account image is displayed.

[0075] For example, generating the first visual digital asset requires a second amount of virtual resources in response to an operation on the image selection control; a third amount of virtual resources in response to an operation on the style selection control; a fourth amount of virtual resources in response to an operation on the carrier selection control; and a fifth amount of virtual resources in response to an operation on the background selection control. Generating the first visual digital asset directly using the default configuration does not require consuming virtual resources.

[0076] Based on the user's actions on the group photo generation interface, a first quantity of virtual resources required to generate the first visual digital asset is determined. This first quantity is determined by the user's actions on the group photo generation interface. If the user only performs an action on the image selection control, the first quantity equals the second quantity; if the user performs actions on both the image selection control and the style selection control, the first quantity is the sum of the second and third quantities; if the user performs actions on the image selection control, the style selection control, and the carrier selection control, the first quantity is the sum of the second, third, and fourth quantities; and if the user performs actions on the image selection control, the style selection control, the carrier selection control, and the background selection control, the first quantity is the sum of the second, third, fourth, and fifth quantities.

[0077] Optionally, a first quantity can be displayed in the generation control, allowing the user to know the amount of virtual resources required to generate the first visual digital asset. Alternatively, after the user clicks the generation control, resource consumption information can be displayed, indicating the amount of virtual resources required to generate the first visual digital asset. In response to a confirmation operation regarding the resource consumption information, if the number of virtual resources owned by the user's account is greater than or equal to the first quantity, the first quantity of virtual resources from the user's account is consumed, and the first visual digital asset is displayed.

[0078] If the number of virtual resources owned by a user's account is less than the first limit, a message indicating that the generation failed will be displayed to prompt the user to recharge virtual resources or reduce operations on the group photo generation interface.

[0079] By consuming the first amount of virtual resources from a user's account to generate the first visual digital asset, a brand-new in-app purchase and consumption scenario is created. Furthermore, style selection, carrier selection, and background selection can all be paid options, transforming users' emotional investment into considerable commercial revenue and enriching interactive gameplay based on virtual characters.

[0080] In some embodiments, step 220 may be followed by step 230, which includes at least one of sub-steps 231 to 232.

[0081] Sub-step 231: In the case of generating multiple first visual digital assets based on the first memory information, in response to the switching operation for the multiple first visual digital assets, display the target visual digital asset among the multiple first visual digital assets.

[0082] The configuration information of multiple first visual digital assets generated based on the first memory information is the same. That is, the account image, image style, image carrier, and image background of the first group photo image displayed in the multiple first visual digital assets are the same, but the displayed first group photo images are different. In other words, multiple different first group photo images are generated by the AI ​​big model according to the same configuration information and displayed on the same image carrier, resulting in multiple different first visual digital assets.

[0083] The switching operation for multiple first visual digital assets is an operation performed by the user to switch the display of each first visual digital asset. Optionally, the switching operation for multiple first visual digital assets can be a swipe operation. One first visual digital asset is displayed in the display interface, and the user swipes the display area of ​​that first visual digital asset in the display interface to switch to another first visual digital asset. Optionally, the switching operation for multiple first visual digital assets can also be an operation on a switching control. One first visual digital asset and a switching control are displayed in the display interface, and the user clicks the switching control to switch to another first visual digital asset.

[0084] In response to a switching operation for multiple first-visual digital assets, the display of each first-visual digital asset is switched until the target first-visual digital asset is displayed, at which point the switching operation stops.

[0085] Sub-step 232, in response to the operation on the target visual digital asset, stores the target visual digital asset in the user account's item library and deletes other visual digital assets from the multiple first visual digital assets, the target visual digital asset being used to add to the collection carrier.

[0086] An operation targeting a target visual digital asset is a user-executed operation to store the target visual digital asset into the user's account inventory. For example, if a storage control is displayed in the visual digital asset's interface, then the operation targeting the target visual digital asset is an operation targeting the storage control. When the target visual digital asset is displayed, clicking the storage control will store the target visual digital asset into the inventory. After the target visual digital asset is stored, other visual digital assets among the multiple first visual digital assets generated based on the first memory information will be automatically deleted.

[0087] Figure 6 This diagram illustrates the process of storing target visual digital assets, where the user clicks... Figure 5 After generating control 509 as shown in Figure (4), the following will be displayed: Figure 6 The visualization digital asset generation interface 610 shown in Figure (1) displays a looping animation of the generation status and prompt text 601. After the first visualization digital asset is generated, the following is displayed: Figure 6 The visualization interface 620 shown in Figure (2) is a display interface for the visualized digital assets. The display interface 620 displays a first visualized digital asset 602 and a switching control 603. The user clicks the switching control 603 to switch to display other first visualized digital assets. After the user determines the target visualized digital asset to be stored, he / she clicks the storage control 605 in the display interface 620 to store the currently displayed target visualized digital asset into the item library.

[0088] In the case of generating a first visual digital asset based on the first memory information, in response to an operation on the first visual digital asset, the first visual digital asset is stored in the item library.

[0089] By generating multiple first-visual digital assets based on first-memory information, users can choose from a variety of first-visual digital assets that meet their aesthetic and personalized needs for storage, providing users with the possibility of selection and storage, and enhancing the interactive experience based on virtual characters.

[0090] In some embodiments, step 230 may further include at least one of sub-steps 233 to 234.

[0091] Sub-step 233, in response to the regeneration operation for the first visual digital asset, redisplays the group photo generation interface for the first memory information.

[0092] The regeneration operation for the first visual digital asset is an operation performed by the user to regenerate the first visual digital asset based on the first memory information. For example, if a regeneration control is displayed in the display interface of the first visual digital asset, then the regeneration operation for the first visual digital asset is an operation on the regeneration control. After the user clicks the regeneration control, the group photo generation interface of the first memory information is displayed again, and the user re-enters the generation process of the first visual digital asset.

[0093] Sub-step 244: In the case of regenerating multiple new first visual digital assets based on the first memory information, in response to the operation of a new target visual digital asset among the multiple new first visual digital assets, the target visual digital asset in the item library is replaced with the new target visual digital asset, and the target visual digital asset and other visual digital assets among the multiple new first visual digital assets are deleted. The new target visual digital asset is used to add to the collection carrier.

[0094] When multiple new first visual digital assets are regenerated based on the initial memory information, in response to a switching operation for the multiple new first visual digital assets, a new target visual digital asset is displayed among the multiple new first visual digital assets; in response to an operation for the new target visual digital asset among the multiple new first visual digital assets, the target visual digital asset in the item library is replaced with the new target visual digital asset. Simultaneously, the replaced target visual digital asset and other visual digital assets among the multiple new first visual digital assets are deleted. The visual digital assets stored in the item library are used to add to the collection medium.

[0095] Figure 7 This diagram illustrates the process of replacing visual digital assets in the item library, where the user clicks... Figure 6 After regenerating control 604 as shown in Figure (2), it displays as follows: Figure 7 The new visual digital asset display interface 710 shown in Figure (1) displays a new first visual digital asset and a storage control 701. When the user clicks on the storage control 701, it displays... Figure 7The replacement prompt interface 720 shown in Figure (2) has a replacement prompt message 702 and a replacement confirmation control 703. The replacement prompt message 702 is used to confirm with the user whether to perform the replacement. After the user clicks the replacement confirmation control 703, the first visual digital asset that has been stored in the item library is replaced with the new first visual digital asset currently displayed in the display interface 710.

[0096] In the case of regenerating a first visual digital asset based on the first memory information, in response to the operation on the first visual digital asset, the target visual digital asset in the item library is replaced with the new target visual digital asset.

[0097] By providing the ability to regenerate the first visual digital asset, users are given more options, allowing them to choose the first visual digital asset that better suits their aesthetic and personalized needs for storage, which greatly enhances the interactive experience based on virtual characters.

[0098] In some embodiments, in response to an operation on the group photo generation interface, after displaying the first visual digital asset generated based on the first memory information, if the first visual digital asset generated based on the first memory information does not meet the user's storage needs, the operation of storing the first visual digital asset in the item library may not be performed. Instead, the operation of regenerating the first visual digital asset may be performed directly, and the generation process of the first visual digital asset may be re-entered. In response to an operation on a new first visual digital asset, the new first visual digital asset is stored in the item library. If multiple new first visual digital assets are regenerated based on the first memory information, in response to an operation on a new target visual digital asset among the multiple new first visual digital assets, the new target visual digital asset is stored in the item library, and the other visual digital assets among the multiple new first visual digital assets are deleted.

[0099] In some embodiments, step 230 may further include at least one of sub-steps 235-236.

[0100] Sub-step 235, in response to the cancellation operation for the first visual digital asset, temporarily stores the first visual digital asset.

[0101] The cancellation operation for the first visual digital asset is an operation performed by the user to exit the display interface of the first visual digital asset. When the user exits the display interface of the first visual digital asset and the user has not stored the first visual digital asset in the item library, one or more first visual digital assets generated based on the first memory information are temporarily stored.

[0102] Optionally, the display interface of the first visualized digital asset may include an exit control. In this case, the cancellation operation for the first visualized digital asset is an operation on the exit control; after the user clicks the exit control, they exit the display interface of the first visualized digital asset. Alternatively, the cancellation operation for the first visualized digital asset can also be a swipe operation on the display interface of the first visualized digital asset. In this case, the user can exit the display interface of the first visualized digital asset by swiping other display areas besides the display area of ​​the first visualized digital asset.

[0103] Sub-step 236: After the temporary storage period of the first visual digital asset reaches the temporary storage period, delete the first visual digital asset.

[0104] This application does not limit the temporary storage period. For example, the temporary storage period can be 7 days. Then, after the temporary storage time of the first visual digital asset reaches 7 days, the temporarily stored first visual digital asset is deleted. That is to say, if the first visual digital asset is not stored in the item library, only one or more first visual digital assets generated are temporarily stored for 7 days.

[0105] By designing an intelligent and efficient digital content lifecycle management mechanism, visualized digital assets that are not stored are temporarily stored, and visualized digital assets that have exceeded their storage period are cleaned up. This encourages user decision-making and enhances the perceived value of assets, while automatically cleaning up invalid data, optimizing server storage resources, and achieving a balance between user experience and system efficiency.

[0106] In some embodiments, a memory details interface for displaying first memory information is provided; wherein the memory details interface includes at least one of the following: a first visual digital asset, a title of the first memory information, a first dialogue text corresponding to the first memory information, and the generation time of the first memory information.

[0107] After the first visual digital asset is stored in the item library, the first memory information is the complete memory information, which includes the first visual digital asset. Figure 8 A schematic diagram of the memory details interface for the first memory information is shown. The memory details interface 800 displays the title 801 of the first memory information, the first dialogue text 803 corresponding to the first memory information, the generation time 802 of the first memory information, and the first visualized digital asset 804. The memory details interface 800 provides a regeneration control and a memory arrangement control. If the user clicks the regeneration control, the process of replacing the visualized digital asset corresponding to sub-steps 243-244 is initiated. If the user clicks the memory arrangement control, the process of arranging the collection medium corresponding to step 230 is initiated.

[0108] By displaying the memory details interface that shows the first memory information, users can review their conversations with the virtual character based on the information displayed on the memory details interface, which helps to enhance the emotional bond between the user and the virtual character.

[0109] Optionally, a sharing control can be displayed in the first visual digital asset's display interface, or it can be displayed in the memory details interface of the first memory information. In response to an action on the sharing control, the first visual digital asset can be shared with other user accounts.

[0110] In some embodiments, step 220 may be followed by step 240.

[0111] Step 240: Add the first visual digital asset to the collection carrier, which is used to aggregate and display at least two visual digital assets.

[0112] A collection platform is a virtual scene where a user account can freely arrange and aggregate at least two visual digital assets owned by the user account. The form of the collection platform includes, but is not limited to, display cabinets, photo albums, desktops, walls, rooms, etc. Optionally, a collection platform can aggregate and display all visual digital assets owned by the user account, or it can aggregate and display only a portion of the visual digital assets owned by the user account.

[0113] After generating the first visual digital asset, the AI ​​system can automatically add it to the collection container, or it can add it in response to a collection operation. Optionally, the first visual digital asset can be displayed in the collection container according to its default display position, such as being displayed in the next display position in the collection container according to the default position order of each visual digital asset. Alternatively, the first visual digital asset can be displayed in the collection container according to the display position set by the user account, such as being interpolated among at least two visual digital assets already aggregated and displayed in the collection container.

[0114] By generating visual digital assets and then adding them to a collection platform, this technology creatively and seamlessly integrates three major technologies: natural language processing (dialogue), text-to-image large-scale model (generation), and 3D display (layout) of a game engine. This constructs a complete technological closed loop from textual memory to visual assets and then to spatial arrangement. This provides a new comprehensive paradigm for AI applications and realizes the scenario-based closed-loop application of multimodal AI technology.

[0115] In some embodiments, step 240 includes at least one of sub-steps 241 to 244.

[0116] Sub-step 241: Display the memory arrangement interface, which shows the collection media.

[0117] The memory layout interface is used to arrange the display style of at least two visual digital assets that are aggregated and displayed in the collection medium.

[0118] In some embodiments, the memory arrangement interface displays the maximum number of collectibles that can be placed and the number that has already been placed. The maximum number of collectibles that can be placed refers to the maximum number of visual digital assets that can be added to a collectible, and the number of collectibles that has already been placed refers to the number of visual digital assets that have been added to the collectible.

[0119] In some embodiments, the number of collectible carriers that can be placed is positively correlated with the level of interaction between the virtual character and the user account.

[0120] The interaction level between a virtual character and a user account indicates the degree of connection between their conversations. This interaction level is related to the number and frequency of conversations between the virtual character and the user account. The more conversations between the virtual character and the user account, and the higher the frequency of conversations, the higher the interaction level between them. A user account can improve the interaction level between the virtual character and the user account by frequently engaging in conversations with the virtual character.

[0121] The number of collectible items that can be placed is positively correlated with the interaction level between the virtual character and the user account. The number of collectible items that can be placed is determined based on the preset mapping between the number of collectible items that can be placed and the interaction level between the virtual character and the user account. For example, when the interaction level between the virtual character and the user account is level 1, the number of collectible items that can be placed is 5; when the interaction level between the virtual character and the user account is level 2, the number of collectible items that can be placed is 10. For each level increase in the interaction level between the virtual character and the user account, the number of collectible items that can be placed increases by 5.

[0122] By making the number of collectibles that can be placed positively correlated with the interaction level between the virtual character and the user account, the higher the interaction level between the virtual character and the user account, the more collectibles can be placed. This provides more virtual space for displaying visual digital assets and avoids the inability to properly arrange the generated visual digital assets due to the accumulation of memory information.

[0123] Sub-step 242, in response to an operation on the collection carrier, displays at least one visual digital asset stored in the user account's item library, the at least one visual digital asset including a first visual digital asset.

[0124] The operation on the collection carrier is an operation performed by the user to trigger the display of at least one visual digital asset stored in the item library. For example, the memory arrangement interface displays an arrangement control. After the user clicks the arrangement control, at least one visual digital asset stored in the item library is displayed, so that the user can select the first visual digital asset from the item library and arrange it into the collection carrier.

[0125] In some embodiments, at least one visual digital asset includes at least one of the following: at least one unplaced visual digital asset and at least one placed visual digital asset; the first visual digital asset belongs to the unplaced visual digital assets. The display format of the unplaced visual digital asset differs from that of the placed visual digital asset.

[0126] An unplaced visual digital asset is a visual digital asset that has not yet been added to the collection medium, while a placed visual digital asset is a visual digital asset that has already been added to the collection medium. The first visual digital asset has not yet been added to the collection medium; therefore, the first visual digital asset belongs to the unplaced category. Each visual digital asset in the item library indicates whether it has been added to the collection medium by displaying it in different ways. For example, an unplaced visual digital asset can be displayed in a normal form, while a placed visual digital asset can be displayed in a blurred form. Alternatively, an unplaced indication can be displayed on an unplaced visual digital asset, and a placed indication can be displayed on a placed visual digital asset.

[0127] By displaying different forms of visual digital assets in the item library, users can intuitively see whether each visual digital asset has been added to the collection container, thus making it easier for users to select unplaced visual digital assets from the item library and add them to the collection container, ensuring the convenience of users when performing the collection process.

[0128] In some embodiments, in response to a placement operation on an unplaced visual digital asset in the item library, the unplaced visual digital carrier is added to the collection carrier. After adding the unplaced visual digital carrier to the collection carrier, the display format of the unplaced visual digital carrier in the item library is updated. For example, the unplaced visual digital carrier in the item library can be updated to a blurred format. In response to a deplacement operation on a placed visual digital asset in the collection carrier, the placed visual digital carrier added to the collection carrier is revoked. After revoking the placed visual digital carrier added to the collection carrier, the display format of the placed visual digital carrier in the item library is updated. For example, the placed visual digital carrier in the item library can be updated to a normal format.

[0129] Sub-step 243, in response to an operation on a first visual digital asset among at least one visual digital asset, displays the first visual digital asset in an editing state in the collection carrier.

[0130] If the operation on the first visual digital asset among at least one visual digital asset is performed by the user to add the first visual digital asset to the collection carrier, then when adding the first visual digital asset to the collection carrier, the first visual digital asset in the editing state will be displayed in the collection carrier first. After the editing of the first visual digital asset in the editing state is completed, the user confirms that the first visual digital asset has been added to the collection carrier.

[0131] In some embodiments, sub-step 243 includes at least one of sub-steps 2431 to 2432.

[0132] Sub-step 2431, in response to a selection operation for a first visual digital asset among at least one visual digital asset, distinguishably displays the first visual digital asset among at least one visual digital asset.

[0133] After a user clicks on a first visual digital asset among at least one visual digital asset, the first visual digital asset is displayed separately among the at least one visual digital assets. Optionally, the first visual digital asset can be displayed by selecting the first visual digital asset, or by displaying selection prompt information on the first visual digital asset, such as displaying selection prompt animation, selection prompt text, selection prompt pattern, etc.

[0134] Sub-step 2432: If the number of items already placed on the collection carrier is less than the number of items that can be placed on the collection carrier, in response to the placement operation for the first visual digital asset, the first visual digital asset in the editing state is displayed on the collection carrier.

[0135] The arrangement of the first visual digital asset can be done by the user dragging the first visual digital asset to the collection carrier, or by clicking the "Add Control" option in the memory arrangement interface.

[0136] If the number of items already placed on the collection carrier equals the number of items that can be placed on the collection carrier, an error message is displayed in response to the placement operation for the first visualized digital asset.

[0137] By highlighting the first visual digital asset, users can intuitively see the selected visual digital asset, avoiding the possibility of making the wrong selection.

[0138] Sub-step 244, in response to an editing operation on the first visual digital asset in the editing state, displays the edited first visual digital asset in the collection carrier.

[0139] The editing operation for the first visual digital asset in the editing state is an operation performed by the user to edit the display style of the first visual digital asset. After the editing of the first visual digital asset in the editing state is completed, the edited first visual digital asset is displayed in the collection carrier, and the user confirms that the first visual digital asset has been added to the collection carrier.

[0140] In some embodiments, the editing operation includes at least one of the following: rotation operation, scaling operation, drag operation, copy operation, and mirror operation.

[0141] The rotation operation is used to adjust the display angle of the first visual digital asset, the scaling operation is used to adjust the display size of the first visual digital asset, the drag operation is used to adjust the display position of the first visual digital asset, the copy operation is used to adjust the display quantity of the first visual digital asset, and the mirror operation is used to adjust the display orientation of the first visual digital asset.

[0142] In some embodiments, when a first visual digital asset in an editable state is displayed in the collection medium, the user may also choose not to perform an editing operation on the first visual digital asset in an editable state, but instead directly perform a confirmation operation on the first visual digital asset in an editable state, in which case the edited first visual digital asset will be displayed in the collection medium.

[0143] By adding the first visual digital asset to the collection, users are incentivized to continuously interact with their virtual characters to create more visual digital assets, strengthening the long-term emotional connection between user accounts and virtual characters. Furthermore, the collection arrangement feature has a long-term developmental aspect, effectively increasing user login frequency and single-session dwell time, significantly improving user stickiness and average daily interaction time. Moreover, the beautiful photos and creative space arrangements generated by user accounts easily spread spontaneously on social media, becoming the most vivid promotional material for the application. This not only attracts new users but also inspires existing users' enthusiasm for creation and sharing, forming a healthy content ecosystem and social media buzz.

[0144] In some embodiments, in response to an operation on a second visual digital medium within the collection medium, a memory details interface for the second memory information is displayed. The operation on the second visual digital medium could be a user clicking on the second visual digital medium.

[0145] Figure 9 The diagram illustrates the process of adding a first visual digital asset to a collection medium, such as... Figure 9 As shown in Figure (1), an arrangement control 901 is displayed in the memory arrangement interface 900. When the user clicks the arrangement control 901, as shown in Figure (1), the arrangement control 901 is displayed. Figure 9 As shown in Figure (2), the memory arrangement interface 900 displays the number of collectible carriers that can be placed and the number that have already been placed 902. Two more visual digital carriers can be added to the collectible carriers. In response to an operation on the photo control 905 in the memory arrangement interface 900, at least one visual digital carrier in photo form from the item library is displayed. In response to an operation on the smack control 906, as shown in Figure (2), the number of visual digital carriers in photo form from the item library is displayed. Figure 9 At least one visual digital carrier in the form of a slapstick, as shown in Figure (3). Figure 9 As shown in Figure (2), at least one photo-style visual digital carrier is displayed in three display formats. Visual digital carrier 907 is distinguished from other visual digital carriers and is the first visual digital carrier selected by the user that has not been arranged. The display style of visual digital carrier 908 is used to indicate that visual digital carrier 908 has not been added to the collection carrier. The display style of visual digital carrier 909 is used to indicate that visual digital carrier 909 has been added to the collection carrier. Visual digital carrier 907 in the editing state is displayed in the memory arrangement interface 900. The visual digital carrier 907 in the editing state has editing controls, including a delete control 903 and a rotate control 904. The user can adjust the display style of visual digital carrier 907 through the editing controls. After the user finishes editing, click the save control 911 to confirm that visual digital carrier 907 has been added to the collection carrier.

[0146] The technical aspects of the interaction method based on virtual characters will be introduced below.

[0147] In some embodiments, during the dialogue between the virtual character and the user account, the dialogue text between the virtual character and the user account is obtained through an asynchronous keyword capture device; if the dialogue text matches the recall keyword library, structured data corresponding to the dialogue text is generated, and each piece of structured data corresponds to a piece of recall information; wherein, the structured data corresponding to the dialogue text includes at least one of the following: the identification information of the structured data, the identification information of the user account, the identification information of the virtual character, the generation time of the structured data, the dialogue text, and the title of the dialogue text.

[0148] The architecture of the recall keyword database can be referenced. Figure 10 As shown, the memory keyword library includes a life tag pool, a self-made tag pool, and a holiday tag pool. The life tag pool includes at least one life tag, which indicates life-related keywords, such as "together," "cooking," and "chatting." The self-made tag pool includes at least one self-made tag, which is a tag set by the user account. The keywords indicated by the self-made tag can be memory-related keywords, such as "remember," "that time," and "reminisce." The holiday tag pool includes at least one holiday tag, which indicates holiday-related keywords, such as "Valentine's Day," "Mid-Autumn Festival," and "Dragon Boat Festival."

[0149] During the dialogue between the virtual character and the user account, an asynchronous keyword catcher is deployed. When the dialogue text between the virtual character and the user account matches the memory keyword database, structured data corresponding to the dialogue text is automatically generated and stored in the memory database. The aforementioned memory information is generated based on the structured data in the memory database.

[0150] When a user account initiates the process of generating visual digital assets, the Asset Manager collects all front-end selections made by the user account and encapsulates them into a standard generation request parameter package. This parameter package is structured as follows: { "base_request_id": "The unique batch ID generated this time". “memory_id”: “The associated memory record ID”, “player_appearance”: { "type": "real" / "game_avatar", "image_url": "Temporary storage address of the uploaded real image" / "game_avatar_id": "User account ID" }, “ai_idol_appearance”: “Preset visual identifier for a virtual character” "style_prompt": "Cyberpunk, warm, cinematic" "carrier_type": "photo" / "badge", “output_config”: { “count”: 4, “aspect_ratio”: “3:4” } } The generation requests are sent to the AI-generated image service via the large model API (Application Programming Interface) gateway. To handle high concurrency, requests enter a generation queue, and the gateway needs to handle long polling or WebSocket connections to maintain state. After generating multiple visual digital assets, the system stores them in the digital asset library and generates multiple temporary asset records (in an unstored state), associated with the base_request_id (generation batch). The frontend obtains the network links of multiple visual digital assets through the interface provided by the asset manager for display.

[0151] In some embodiments, in response to an operation on the memory arrangement interface, at least one visual digital asset stored in the user account's inventory is obtained, as well as visual digital assets already placed in the collection carrier; based on the visual digital assets already placed in the collection carrier, at least one visual digital asset is determined to include unarranged visual digital assets and arranged visual digital assets.

[0152] If a visual digital asset in the item library has been added to a collection medium, the status information of that visual digital asset is recorded as "added". If a visual digital asset in the item library has not yet been added to a collection medium, the status information of that visual digital asset is recorded as "not added". Then, based on the status information corresponding to at least one visual digital asset stored in the item library, the unplaced visual digital assets and the placed visual digital assets are determined.

[0153] In some embodiments, in response to a startup operation for a memory layout interface, a scene state snapshot of a user account is loaded from a memory database. The scene state snapshot is a data structure indicating the layout positions of at least two visual digital assets in a collection carrier. In response to a save operation for an updated collection carrier, the transformation matrices of each visual digital asset in the updated collection carrier are serialized into a new scene state snapshot. The new scene state snapshot overwrites the scene state snapshot in the memory database.

[0154] The system's spatial layout engine manages a 3D or 2.5D virtual scene. The scene data (camera view, lighting, environment maps) is predefined and used to display the collection assets. When a user account enters the memory layout interface, the engine loads a snapshot of the user account's scene state (an array containing the layout position, rotation information, and scaling information of all visualized digital assets) from the memory database. An example of the scene state snapshot data structure can be found below: { "scene_id": "The user account's unique space ID", “objects”: [ { "asset_id": "The ID of the visualized digital asset", "position": {"x": 10, "y": 5, "z": 0}, "rotation": 45, “scale”: 1.2 } / / ... other items ] } After a user clicks the placement control, the space placement engine queries the memory asset manager for the status information of all visual digital assets and provides the front end with icon data for three statuses based on their carrier_type and whether they have been added to the virtual scene. When a user performs a placement operation, an operable copy of the visual digital asset is instantiated in the virtual scene. When a user performs a drag operation, the screen coordinates are converted to scene world coordinates, and the position coordinates of the visual digital asset are updated in real time. When a user performs a rotate / scale operation, the rotation and size information of the visual digital asset are updated in real time based on the user's gesture or front end operation. When a user cancels a placement operation, the instance in the virtual scene is destroyed. If the visual digital asset is being removed from the item library for the first time and has not been saved, it is removed from the current editing list. When the user clicks the save control, the space placement engine serializes the transformation matrix of all visual digital assets in the current virtual scene into a new scene state snapshot and saves it to the memory database through the memory asset manager, overwriting the old version of the scene state snapshot. If the user clicks the close control, the front end discards all unsaved editing operations and directly reloads the last saved scene state snapshot.

[0155] Through the structured definitions of "memory records," "asset records," and "scene state snapshots," a scalable emotional interaction data framework is constructed, forming a clear emotional data model. This framework is easily expandable and can incorporate more memory dimensions (such as voice clips and videos), asset types (dynamic photo frames), or interactive gameplay in the future, laying the foundation for long-term system iteration. This logic ensures a complete data loop from "memory generation" to "asset creation" and then to "spatial display," with each stage having a clear, traceable, and rollbackable state, exhibiting good robustness and scalability.

[0156] Figure 11The diagram illustrates the system architecture. The entire system can be abstracted into five collaborative technical layers, and its architecture and data flow relationships include the following steps: S1, the dialogue text between the virtual character and the user account displayed on the client interface triggers keywords. S2, through an asynchronous keyword catcher, when the dialogue text matches the memory keyword library, a memory record is created, and the memory asset manager is called to generate structured data corresponding to the dialogue text. S3, the structured data is stored in the memory database. S4, the memory records in the memory data are read, and a memory list is generated and displayed on the client interface. S5, the user initiates a request to generate a visual digital asset on the client interface. S6, the memory asset manager collects all the user's front-end selections and encapsulates them into a standard generation request parameter package. S7, the visual digital asset is generated through the large model API gateway and collected by the memory asset manager. S8, the generated visual digital asset is stored in the digital asset library. S9, the asset data in the digital asset library is loaded, and the visual digital asset is displayed on the client interface. S10, the user triggers the edit mode on the client interface, calling the space layout engine to display the virtual scene where the collection carrier is located. S11, The spatial layout engine reads the state information of the visualized digital assets in the digital asset library and arranges the visualized digital assets in the virtual scene. S12, The spatial layout engine saves a new snapshot of the scene state.

[0157] The technical solution provided in this application offers an evolutionary path for game AI from a functional tool to an emotional partner. The value of AI extends beyond optimizing game balance or providing companionship; it lies in becoming a deep partner offering emotional value and creative support. This will drive the industry to rethink the role of AI in games and lead the next generation of emotional AI design trends. Furthermore, by "uploading real-life images to generate virtual world photos," a lightweight fusion of digital and physical identities is achieved, successfully and simplifies the concepts of digital assets and identity within the "metaverse." By "creating exclusive digital spaces," users are given true control and display rights over virtual assets, providing a feasible and acceptable precedent for the implementation of more complex metaverse concepts in games in the future. In summary, the technical solution in this application is not a simple aggregation of existing technologies, but rather a systematic innovation that creates significant benefits across technology, experience, and business dimensions. It not only solves the core pain point of the inability to retain emotional interactions within games but also opens up a new game category that integrates AI creation, personalized expression, and digital asset collection, possessing extremely high industrial application value and broad commercial prospects.

[0158] The following are embodiments of the apparatus described in this application, which can be used to execute the embodiments of the method described in this application. For details not disclosed in the apparatus embodiments of this application, please refer to the embodiments of the method described in this application.

[0159] Please refer to Figure 12 This diagram illustrates a block diagram of an interactive device based on a virtual character, according to an embodiment of this application. The device has the functionality to implement the aforementioned interactive method based on virtual characters. This functionality can be implemented in hardware or by hardware executing corresponding software. The device can be a terminal device as described above, or it can be installed within a terminal device. Figure 12 As shown, the device 1200 may include an interface display module 1210 and an asset generation module 1220.

[0160] The interface display module 1210 is used to display the group photo generation interface of the first memory information. The first memory information is associated with the historical dialogue records between the virtual character and the user account. The virtual character is a digital virtual image driven by artificial intelligence (AI).

[0161] The asset generation module 1220 is used to respond to the operation of the group photo generation interface and display a first visual digital asset generated based on the first memory information. The first visual digital asset displays a first group photo image that includes the character image of the virtual character and the account image of the user account.

[0162] In some embodiments, the group photo generation interface displays an image selection control and a generation control; the asset generation module 1220 is used for: In response to an operation on the image selection control, the account image selected by the user account is determined, the account image being used to indicate the account image of the user account; In response to an operation on the generation control, the first visual digital asset generated based on the first memory information and the account image is displayed.

[0163] In some embodiments, the image selection control includes at least one candidate image, which includes at least one of the following: a real image uploaded by the user account, and at least one virtual image; wherein the real image is an image containing a real person's image, and the virtual image is an image containing a virtual character's image; the asset generation module 1220 is used for: In response to an operation targeting a target candidate image among the at least one candidate images, the account image selected by the user account is determined to be the target candidate image.

[0164] In some embodiments, the group photo generation interface also displays parameter configuration controls; the asset generation module 1220 is used for: In response to an operation on the parameter configuration control, image configuration information of the first group photo image is determined, the image configuration information being used to indicate the image format of the first group photo image; The first visualized digital asset is generated based on the first memory information, the account image, and the image configuration information.

[0165] In some embodiments, the parameter configuration control includes at least one of the following: a style selection control, a carrier selection control, and a background selection control; the asset generation module 1220 is used for: In response to an operation on the style selection control, the image style of the first group photo image is determined; In response to an operation on the carrier selection control, an image carrier for the first group photo image is determined, the image carrier being used as the first visual digital asset displaying the first group photo image; In response to an operation on the background selection control, a background image for the first group photo is determined.

[0166] In some embodiments, the asset generation module 1220 is configured to: In response to an operation on the generated control, if the number of virtual resources owned by the user account is greater than or equal to a first number, the first number of virtual resources of the user account are consumed, and the first visual digital asset generated based on the first memory information and the account image is displayed.

[0167] In some embodiments, the interface display module 1210 is configured to: Display the virtual character's memory list, which includes at least one memory information; in response to an operation on the first memory information in the at least one memory information, display a group photo generation interface for the first memory information; or, The dialog interface between the virtual character and the user account is displayed, and the dialog interface includes at least one dialogue text; in response to an operation on a first dialogue text in the at least one dialogue text, a photo generation interface for the first memory information is displayed, and the first memory information includes the first dialogue text.

[0168] In some embodiments, the device 1200 further includes an asset storage module, the asset storage module being configured to: In the case of generating multiple first visual digital assets based on the first memory information, in response to a switching operation for the multiple first visual digital assets, the target visual digital asset among the multiple first visual digital assets is displayed; In response to an operation on the target visual digital asset, the target visual digital asset is stored in the user account's item library, and other visual digital assets among the plurality of first visual digital assets are deleted, the target visual digital asset being added to the collection carrier.

[0169] In some embodiments, the asset storage module is configured to: In response to the regeneration operation of the first visualized digital asset, the group photo generation interface of the first memory information is redisplayed; In the case of regenerating multiple new first visual digital assets based on the first memory information, in response to the operation of a new target visual digital asset among the multiple new first visual digital assets, the target visual digital asset in the item library is replaced with the new target visual digital asset, and the target visual digital asset and other visual digital assets among the multiple new first visual digital assets are deleted, the new target visual digital asset being added to the collection carrier.

[0170] In some embodiments, the asset storage module is configured to: In response to a cancellation operation on the first visualized digital asset, the first visualized digital asset is temporarily stored. After the temporary storage period of the first visualized digital asset reaches the temporary storage deadline, the first visualized digital asset is deleted.

[0171] In some embodiments, the interface display module 1210 is configured to: The memory details interface displays the first memory information; wherein the memory details interface includes at least one of the following: the first visualized digital asset, the title of the first memory information, the first dialogue text corresponding to the first memory information, and the generation time of the first memory information.

[0172] In some embodiments, the device 1200 further includes an asset collection module, the asset collection module being configured to: The first visualized digital asset is added to a collection carrier, which is used to aggregate and display at least two visualized digital assets.

[0173] In some embodiments, the asset collection module is used for: The memory arrangement interface is displayed, and the memory arrangement interface displays the collection medium; In response to an operation on the collection medium, at least one visual digital asset stored in the user account's item library is displayed, the at least one visual digital asset including the first visual digital asset; In response to an operation on the first visual digital asset among the at least one visual digital assets, the first visual digital asset in an editing state is displayed in the collection carrier; In response to an editing operation on the first visual digital asset that is in an editing state, the edited first visual digital asset is displayed in the collection carrier.

[0174] In some embodiments, the at least one visual digital asset includes at least one of the following: at least one unplaced visual digital asset and at least one placed visual digital asset; the first visual digital asset belongs to the unplaced visual digital asset. The display format of the unplaced visual digital assets differs from that of the placed visual digital assets.

[0175] In some embodiments, the memory arrangement interface displays the number of collectible carriers that can be placed and the number that have already been placed; the asset collection module is used for: In response to a selection operation for the first visual digital asset among the at least one visual digital assets, the first visual digital asset is displayed separately among the at least one visual digital assets; If the number of items already placed on the collection carrier is less than the number of items that can be placed on the collection carrier, in response to the placement operation for the first visual digital asset, the first visual digital asset in the editing state is displayed on the collection carrier.

[0176] In some embodiments, the number of collectible carriers that can be placed is positively correlated with the level of interaction between the virtual character and the user account.

[0177] In some embodiments, the editing operation includes at least one of the following: rotation operation, scaling operation, drag operation, copy operation, and mirror operation.

[0178] In some embodiments, the interface display module 1210 is configured to: During the dialogue between the virtual character and the user account, the dialogue text between the virtual character and the user account is obtained through an asynchronous keyword capture device; If the dialogue text matches the memory keyword library, structured data corresponding to the dialogue text is generated, and each structured data corresponds to a memory information. The structured data corresponding to the dialogue text includes at least one of the following: the identification information of the structured data, the identification information of the user account, the identification information of the virtual character, the generation time of the structured data, the dialogue text, and the title of the dialogue text.

[0179] In some embodiments, the asset collection module is used for: In response to an operation on the memory arrangement interface, at least one visual digital asset stored in the user account's item library is obtained, as well as the visual digital assets already placed in the collection carrier are obtained. Based on the visual digital assets already placed in the collection carrier, determine the unplaced and placed visual digital assets among the at least one visual digital assets.

[0180] In some embodiments, the asset collection module is used for: In response to a launch operation for the memory layout interface, a scene state snapshot of the user account is loaded from the memory database. The scene state snapshot is a data structure used to indicate the layout positions of at least two visual digital assets in the collection carrier. In response to the save operation for the updated collection medium, the transformation matrix of each visualized digital asset in the updated collection medium is serialized into a new scene state snapshot. The new scene state snapshot is used to overwrite the scene state snapshot in the memory database.

[0181] It should be noted that the apparatus provided in the above embodiments is only illustrated by the division of the above functional modules when implementing its functions. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the content structure of the device can be divided into different functional modules to complete all or part of the functions described above. In addition, the apparatus and method embodiments provided in the above embodiments belong to the same concept, and the specific implementation process can be found in the method embodiments, which will not be repeated here.

[0182] Please refer to Figure 13 This diagram illustrates a structural block diagram of a computer device 1300 provided in one embodiment of this application. The computer device 1300 can be any electronic device capable of data calculation, processing, and storage. The computer device 1300 can be used to implement the virtual character-based interaction method provided in the above embodiments.

[0183] Typically, computer device 1300 includes a processor 1301 and a memory 1302.

[0184] Processor 1301 may include one or more processing cores, such as a quad-core processor, an octa-core processor, etc. Processor 1301 may be implemented using at least one hardware form selected from DSP (Digital Signal Processing), FPGA (Field Programmable Gate Array), and PLA (Programmable Logic Array). Processor 1301 may also include a main processor and a coprocessor. The main processor, also known as a CPU (Central Processing Unit), is used to process data in the wake-up state; the coprocessor is a low-power processor used to process data in the standby state. In some embodiments, processor 1301 may integrate a GPU (Graphics Processing Unit), which is responsible for rendering and drawing the content to be displayed on the screen. In some embodiments, processor 1301 may also include an AI (Artificial Intelligence) processor, which is used to handle computational operations related to machine learning.

[0185] The memory 1302 may include one or more computer-readable storage media, which may be non-transitory. The memory 1302 may also include high-speed random access memory and non-volatile memory, such as one or more disk storage devices or flash memory devices. In some embodiments, the non-transitory computer-readable storage media in the memory 1302 are used to store a computer program configured to be executed by one or more processors to implement the above-described virtual character-based interaction method.

[0186] Those skilled in the art will understand that Figure 13 The structure shown does not constitute a limitation on the computer device 1300, and may include more or fewer components than shown, or combine certain components, or use different component arrangements.

[0187] In an illustrative embodiment, a computer-readable storage medium is also provided, wherein a computer program is stored therein, and the computer program, when executed by a processor of a computer device, implements the aforementioned interaction method based on virtual characters. Optionally, the aforementioned computer-readable storage medium may be ROM (Read-Only Memory), RAM (Random Access Memory), CD-ROM (Compact Disc Read-Only Memory), magnetic tape, floppy disk, and optical data storage device, etc.

[0188] In an exemplary embodiment, a computer program product is also provided, comprising a computer program stored in a computer-readable storage medium. A processor of a computer device reads the computer program from the computer-readable storage medium and executes the computer program, causing the computer device to perform the aforementioned virtual character-based interaction method.

[0189] It should be noted that this application may display prompt interfaces, pop-ups, or output voice prompts before and during the collection of user data. These prompt interfaces, pop-ups, or voice prompts are used to inform users that their data is being collected. This ensures that the application only begins the steps for collecting user data after receiving confirmation from the user regarding the prompt interface or pop-up; otherwise (i.e., without user confirmation), the steps for collecting user data end, meaning no user data is collected. In other words, all user data collected by this application is processed strictly in accordance with the requirements of relevant national laws and regulations. The informed consent or separate consent of the data subject is obtained only with the user's consent and authorization. Subsequent data use and processing are conducted within the scope of laws, regulations, and the data subject's authorization, and the collection, use, and processing of relevant user data must comply with the relevant laws, regulations, and standards of the relevant countries and regions.

[0190] It should be understood that "multiple" as used herein refers to two or more. "And / or" describes the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A alone, A and B simultaneously, or B alone. The character " / " generally indicates that the preceding and following related objects are in an "or" relationship. Furthermore, the step numbers described herein are merely illustrative of one possible execution order. In some other embodiments, the steps may not be executed in numerical order, such as two steps with different numbers being executed simultaneously, or two steps with different numbers being executed in the reverse order of the illustration. This application does not limit this.

[0191] The above description is merely an exemplary embodiment of this application and is not intended to limit this application. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the protection scope of this application.

Claims

1. An interaction method based on virtual characters, characterized in that, The method includes: The interface that displays the first memory information is a group photo generation interface. The first memory information is associated with the historical dialogue records between the virtual character and the user account. The virtual character is a digital virtual image driven by artificial intelligence (AI). In response to an operation on the group photo generation interface, a first visual digital asset generated based on the first memory information is displayed. The first visual digital asset displays a first group photo image containing the character image of the virtual character and the account image of the user account.

2. The method according to claim 1, characterized in that, The group photo generation interface displays an image selection control and a generation control; The response to an operation on the group photo generation interface, displaying a first visual digital asset generated based on the first memory information, includes: In response to an operation on the image selection control, the account image selected by the user account is determined, the account image being used to indicate the account image of the user account; In response to an operation on the generation control, the first visual digital asset generated based on the first memory information and the account image is displayed.

3. The method according to claim 2, characterized in that, The image selection control includes at least one candidate image, which includes at least one of the following: a real image uploaded by the user account, and at least one virtual image; wherein, the real image is an image containing a real person's image, and the virtual image is an image containing a virtual character's image; The step of determining the account image selected by the user account in response to an operation on the image selection control includes: In response to an operation targeting a target candidate image among the at least one candidate images, the account image selected by the user account is determined to be the target candidate image.

4. The method according to claim 2 or 3, characterized in that, The group photo generation interface also displays parameter configuration controls; the method further includes: In response to an operation on the parameter configuration control, image configuration information of the first group photo image is determined, the image configuration information being used to indicate the image format of the first group photo image; The first visualized digital asset is generated based on the first memory information, the account image, and the image configuration information.

5. The method according to claim 4, characterized in that, The parameter configuration control includes at least one of the following: style selection control, carrier selection control, and background selection control; The step of determining the image configuration information of the first group photo image in response to an operation on the parameter configuration control includes at least one of the following: In response to an operation on the style selection control, the image style of the first group photo image is determined; In response to an operation on the carrier selection control, an image carrier for the first group photo image is determined, the image carrier being used as the first visual digital asset displaying the first group photo image; In response to an operation on the background selection control, a background image for the first group photo is determined.

6. The method according to any one of claims 2 to 5, characterized in that, The step of displaying the first visual digital asset generated based on the first memory information and the account image in response to an operation on the generation control includes: In response to an operation on the generated control, if the number of virtual resources owned by the user account is greater than or equal to a first number, the first number of virtual resources of the user account are consumed, and the first visual digital asset generated based on the first memory information and the account image is displayed.

7. The method according to any one of claims 1 to 6, characterized in that, The group photo generation interface that displays the first memory information includes: Display the virtual character's memory list, which includes at least one memory information; in response to an operation on the first memory information in the at least one memory information, display a group photo generation interface for the first memory information; or, The dialog interface between the virtual character and the user account is displayed, and the dialog interface includes at least one dialogue text; in response to an operation on a first dialogue text in the at least one dialogue text, a photo generation interface for the first memory information is displayed, and the first memory information includes the first dialogue text.

8. The method according to any one of claims 1 to 7, characterized in that, After displaying the first visual digital asset generated based on the first memory information, the method further includes: In the case of generating multiple first visual digital assets based on the first memory information, in response to a switching operation for the multiple first visual digital assets, the target visual digital asset among the multiple first visual digital assets is displayed; In response to an operation on the target visual digital asset, the target visual digital asset is stored in the user account's item library, and other visual digital assets among the plurality of first visual digital assets are deleted, the target visual digital asset being added to the collection carrier.

9. The method according to claim 8, characterized in that, The method further includes: In response to the regeneration operation of the first visualized digital asset, the group photo generation interface of the first memory information is redisplayed; In the case of regenerating multiple new first visual digital assets based on the first memory information, in response to the operation of a new target visual digital asset among the multiple new first visual digital assets, the target visual digital asset in the item library is replaced with the new target visual digital asset, and the target visual digital asset and other visual digital assets among the multiple new first visual digital assets are deleted, the new target visual digital asset being added to the collection carrier.

10. The method according to claim 8 or 9, characterized in that, The method further includes: In response to a cancellation operation on the first visualized digital asset, the first visualized digital asset is temporarily stored. After the temporary storage period of the first visualized digital asset reaches the temporary storage deadline, the first visualized digital asset is deleted.

11. The method according to any one of claims 1 to 10, characterized in that, The method further includes: The memory details interface displays the first memory information; wherein the memory details interface includes at least one of the following: the first visualized digital asset, the title of the first memory information, the first dialogue text corresponding to the first memory information, and the generation time of the first memory information.

12. The method according to any one of claims 1 to 11, characterized in that, The method further includes: The first visualized digital asset is added to a collection carrier, which is used to aggregate and display at least two visualized digital assets.

13. The method according to claim 12, characterized in that, Adding the first visualized digital asset to the collection medium includes: The memory arrangement interface is displayed, and the memory arrangement interface displays the collection medium; In response to an operation on the collection medium, at least one visual digital asset stored in the user account's item library is displayed, the at least one visual digital asset including the first visual digital asset; In response to an operation on the first visual digital asset among the at least one visual digital assets, the first visual digital asset in an editing state is displayed in the collection carrier; In response to an editing operation on the first visual digital asset that is in an editing state, the edited first visual digital asset is displayed in the collection carrier.

14. The method according to claim 13, characterized in that, The at least one visual digital asset includes at least one of the following: at least one unplaced visual digital asset, at least one placed visual digital asset; the first visual digital asset belongs to the unplaced visual digital asset. The display format of the unplaced visual digital assets differs from that of the placed visual digital assets.

15. The method according to claim 13 or 14, characterized in that, The memory arrangement interface displays the number of collectibles that can be placed and the number that have already been placed. The step of displaying the first visual digital asset in an editing state in the collection carrier in response to an operation on the first visual digital asset among the at least one visual digital assets includes: In response to a selection operation for the first visual digital asset among the at least one visual digital assets, the first visual digital asset is displayed separately among the at least one visual digital assets; If the number of items already placed on the collection carrier is less than the number of items that can be placed on the collection carrier, in response to the placement operation for the first visual digital asset, the first visual digital asset in the editing state is displayed on the collection carrier.

16. The method according to claim 15, characterized in that, The number of collectibles that can be placed is positively correlated with the level of interaction between the virtual character and the user account.

17. The method according to any one of claims 13 to 16, characterized in that, The editing operations include at least one of the following: rotation, scaling, dragging, copying, and mirroring.

18. The method according to any one of claims 1 to 17, characterized in that, The method further includes: During the dialogue between the virtual character and the user account, the dialogue text between the virtual character and the user account is obtained through an asynchronous keyword capture device; If the dialogue text matches the memory keyword library, structured data corresponding to the dialogue text is generated, and each structured data corresponds to a memory information. The structured data corresponding to the dialogue text includes at least one of the following: the identification information of the structured data, the identification information of the user account, the identification information of the virtual character, the generation time of the structured data, the dialogue text, and the title of the dialogue text.

19. The method according to any one of claims 1 to 18, characterized in that, The method further includes: In response to an operation on the memory arrangement interface, at least one visual digital asset stored in the user account's item library is obtained, as well as the visual digital assets already placed in the collection carrier are obtained. Based on the visual digital assets already placed in the collection carrier, determine the unplaced and placed visual digital assets among the at least one visual digital assets.

20. The method according to any one of claims 1 to 19, characterized in that, The method further includes: In response to a launch operation for the memory layout interface, a scene state snapshot of the user account is loaded from the memory database. The scene state snapshot is a data structure used to indicate the layout positions of at least two visual digital assets in the collection carrier. In response to the save operation for the updated collection medium, the transformation matrix of each visualized digital asset in the updated collection medium is serialized into a new scene state snapshot. The new scene state snapshot is used to overwrite the scene state snapshot in the memory database.

21. An interactive device based on a virtual character, characterized in that, The device includes: The interface display module is used to display the group photo generation interface of the first memory information, which is associated with the historical dialogue records between the virtual character and the user account. The virtual character is a digital virtual image driven by artificial intelligence (AI). The asset generation module is used to respond to the operation of the group photo generation interface and display a first visual digital asset generated based on the first memory information. The first visual digital asset displays a first group photo image containing the character image of the virtual character and the account image of the user account.

22. A computer device, characterized in that, The computer device includes a processor and a memory, the memory storing a computer program that is loaded and executed by the processor to implement the virtual character-based interaction method as described in any one of claims 1 to 20.

23. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program, which is loaded and executed by a processor to implement the virtual character-based interaction method as described in any one of claims 1 to 20.

24. A computer program product, characterized in that, The computer program product includes a computer program that is loaded and executed by a processor to implement the virtual character-based interaction method as described in any one of claims 1 to 20.

Images